{"meta":{"query_hash":"0259130d8859","filters":{"venue":"BMC Medical Research Methodology"},"cohort_total":504,"direct_labels_cover":25,"predictions_cover":504,"exported":504,"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/0259130d8859","api":"https://metacan.xera.ac/api/v1/cohort?venue=BMC+Medical+Research+Methodology"},"results":[{"id":"W1501619595","doi":"10.1186/1471-2288-1-2","title":"The CONSORT statement: revised recommendations for improving the quality of reports of parallel group randomized trials","year":2001,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2754,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Wood Council; University of Ottawa","funders":"U.S. National Library of Medicine; Wellcome Trust; Abbott Laboratories","keywords":"Consolidated Standards of Reporting Trials; Checklist; Randomized controlled trial; Statement (logic); Transparency (behavior); Quality (philosophy); Reliability (semiconductor); Medicine; Computer science; Medical education; Family medicine; Psychology; Surgery","score_opus":0.9839379047069265,"score_gpt":0.769898861168967,"score_spread":0.21403904353795955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501619595","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":[0.0084553035,0.003787341,0.96419847,0.016669743,0.00044852053,0.0055451617,0.000016112946,0.0000030833203,0.00087626546],"genre_scores_gemma":[0.13957757,0.008250766,0.8325743,0.0007242201,0.0005403594,0.0049145925,0.000055092136,0.000038825343,0.013324265],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.035199802,0.9057769,0.042702135,0.001184715,0.014366069,0.0007703762],"domain_scores_gemma":[0.02177028,0.9534449,0.015830738,0.004206349,0.0044469307,0.00030079635],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.97824776,0.00018958728,0.0088864835,0.0003238675,0.0004600416,0.00016452762,0.0024745972,0.00018173848,0.008089536],"category_scores_gemma":[0.9880641,0.00005999133,0.003389474,0.0013242277,0.0017838624,0.00007769968,0.0003918142,0.00044404215,0.000024062321],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029791264,0.00028919606,0.0030822107,0.0008202022,0.0017427038,0.0000091947195,0.0013978039,0.000019778849,0.0009844962,0.205679,0.15917014,0.597014],"study_design_scores_gemma":[0.0367435,0.00029790378,0.00092193816,0.00017101095,0.00069689524,0.00004449593,0.007478937,0.010224961,0.00017733993,0.4736927,0.4693251,0.00022524674],"about_ca_topic_score_codex":0.00032502823,"about_ca_topic_score_gemma":0.00046505663,"teacher_disagreement_score":0.59678876,"about_ca_system_score_codex":0.00003073634,"about_ca_system_score_gemma":0.0009830255,"threshold_uncertainty_score":0.9928172},"labels":[],"label_agreement":null},{"id":"W1503655999","doi":"10.1186/1471-2288-6-24","title":"Interval estimation and optimal design for the within-subject coefficient of variation for continuous and binary variables","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; King Faisal Specialist Hospital and Research Centre","keywords":"Statistics; Sample size determination; Confidence interval; Mathematics; Variance (accounting); Coefficient of variation; Interval estimation; Transformation (genetics); Reliability (semiconductor); Binary number; Variable (mathematics); Random variable; Computer science","score_opus":0.42944468168766925,"score_gpt":0.5289955412166452,"score_spread":0.09955085952897591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503655999","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073249163,0.00019755904,0.9906676,0.00041576388,0.00012138303,0.0012028859,0.000025977864,0.000015138616,0.000028784392],"genre_scores_gemma":[0.029886823,0.000024499263,0.96961844,0.0000228422,0.000095113945,0.00029457183,0.000004518979,0.000014122618,0.00003905927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9931438,0.005203208,0.0005237442,0.00029514811,0.0004904575,0.00034364845],"domain_scores_gemma":[0.7233116,0.27597412,0.000131391,0.00015383592,0.0003344812,0.00009456815],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04235991,0.000106475025,0.00042751143,0.000112055866,0.0001588836,0.00003145623,0.00018396808,0.00019021063,0.000041158564],"category_scores_gemma":[0.21234787,0.00006731136,0.000040562565,0.00015048224,0.0007502072,0.000032128442,0.00011506353,0.0002240857,2.726841e-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":[0.00088668027,0.00011103963,0.000054246884,0.00063209014,0.00003222709,0.0000017620509,0.000478445,0.00014349064,0.0017224214,0.9270322,0.000707973,0.068197444],"study_design_scores_gemma":[0.00061157474,0.00069346343,0.00051483605,0.00007076116,0.000039383303,0.000013985402,0.00013169159,0.4755017,0.0009742908,0.5213584,0.00004137935,0.000048585778],"about_ca_topic_score_codex":0.00013825127,"about_ca_topic_score_gemma":0.000023519771,"teacher_disagreement_score":0.4753582,"about_ca_system_score_codex":0.00002181904,"about_ca_system_score_gemma":0.0003292051,"threshold_uncertainty_score":0.986092},"labels":[],"label_agreement":null},{"id":"W1514307747","doi":"10.1186/1471-2288-3-13","title":"Identifying null meta-analyses that are ripe for updating","year":2003,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; CHEO Research Institute","keywords":"Meta-analysis; Computer science; Commit; Systematic review; MEDLINE; Data science; Statistics; Data mining; Medicine; Mathematics; Pathology","score_opus":0.9965072427985022,"score_gpt":0.7976498263949172,"score_spread":0.198857416403585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514307747","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":[0.004812109,0.0068192715,0.97516453,0.0019059217,0.0005738535,0.0012142041,0.000015765016,0.000012312427,0.009482013],"genre_scores_gemma":[0.09152129,0.00016425633,0.8822855,0.0009768503,0.00032510844,0.0008142457,0.000012200445,0.000045363624,0.023855206],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.33965784,0.60324305,0.015396513,0.0036335802,0.035923254,0.0021457772],"domain_scores_gemma":[0.1200023,0.8559108,0.006879085,0.00844207,0.006865939,0.001899812],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8397874,0.00043806143,0.008875151,0.0014413461,0.0006496849,0.00090439804,0.004468641,0.00045378046,0.10941668],"category_scores_gemma":[0.9522339,0.0001956677,0.005854082,0.003059426,0.00059699576,0.0002600228,0.00050592964,0.0010055673,0.002768248],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016251065,0.0004234381,0.042015355,0.0013871879,0.016495157,0.00016915174,0.0016352804,0.000124489,0.0024840508,0.25460607,0.6113119,0.069185376],"study_design_scores_gemma":[0.0010388007,0.00018140415,0.0020056455,0.000095364245,0.0052391915,0.00013957037,0.018142227,0.013033645,0.0027716,0.38046917,0.5762779,0.00060548005],"about_ca_topic_score_codex":0.000066008324,"about_ca_topic_score_gemma":0.00058911426,"teacher_disagreement_score":0.25266775,"about_ca_system_score_codex":0.0000691829,"about_ca_system_score_gemma":0.0008992426,"threshold_uncertainty_score":0.9980082},"labels":[],"label_agreement":null},{"id":"W1517951603","doi":"10.1186/1471-2288-6-14","title":"Reviewer agreement trends from four years of electronic submissions of conference abstract","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hamilton Health Sciences; McMaster University; St. Paul's Hospital; Providence Health Care; Winnipeg Regional Health Authority; University of Alberta","funders":"Canadian Institutes of Health Research; China Academy of Engineering Physics; University of Alberta","keywords":"Blinding; Intraclass correlation; Medicine; Trial registration; Quality Score; Family medicine; Clinical trial; Clinical psychology; Psychometrics; Internal medicine","score_opus":0.9586731752727339,"score_gpt":0.6946784667617693,"score_spread":0.2639947085109646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517951603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5629222,0.015609163,0.38244087,0.0028341897,0.00075718743,0.0010602517,0.000076540564,0.000008313179,0.034291293],"genre_scores_gemma":[0.9119006,0.0009240026,0.07002809,0.000075796386,0.0003235994,0.00006155316,0.000024924959,0.000014310804,0.016647154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7725514,0.17528458,0.016940987,0.0018853775,0.031952236,0.0013854038],"domain_scores_gemma":[0.6775684,0.30017668,0.005439303,0.006167108,0.009793005,0.00085553195],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.48825783,0.00018907487,0.0040885448,0.00082496426,0.000060516697,0.00005563838,0.0029038817,0.0002706096,0.1562312],"category_scores_gemma":[0.6725697,0.000099212666,0.0012984526,0.0020145513,0.00060610916,0.000063580694,0.00036537764,0.0006871716,0.0007765949],"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":[0.00005786436,0.0002701044,0.013649176,0.0001934587,0.0002194865,0.000022265142,0.00018084169,0.000014878144,0.0030157813,0.025572278,0.17516546,0.7816384],"study_design_scores_gemma":[0.0008708362,0.00040353512,0.40976527,0.00046551364,0.00021317157,0.000010398039,0.00060657156,0.0031559188,0.0010929311,0.16455755,0.4185813,0.00027699166],"about_ca_topic_score_codex":0.0011950816,"about_ca_topic_score_gemma":0.0018747194,"teacher_disagreement_score":0.7813614,"about_ca_system_score_codex":0.0000467199,"about_ca_system_score_gemma":0.0013464058,"threshold_uncertainty_score":0.9981815},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"evaluation","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W1534789916","doi":"10.1186/1471-2288-7-7","title":"Researching complementary and alternative treatments – the gatekeepers are not at home","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Complementary and Alternative Medicine Studies","field":"Medicine","cited_by":289,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Context (archaeology); Modalities; Alternative medicine; Acknowledgement; Medicine; Clinical trial; Strengths and weaknesses; Evidence-based medicine; Randomized controlled trial; Psychology; Computer science; Pathology; Sociology; Social psychology","score_opus":0.6942752946247227,"score_gpt":0.6102542469850069,"score_spread":0.08402104763971585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534789916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9751755,0.0013093577,0.0063111647,0.013784826,0.00034683556,0.0009566834,0.000029078374,0.000032842403,0.0020537155],"genre_scores_gemma":[0.9815481,0.0018208051,0.010942192,0.002059328,0.0013329105,0.00009238285,0.000050972125,0.000033945704,0.0021193875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98858654,0.006037229,0.00057075016,0.000664119,0.0028867247,0.001254645],"domain_scores_gemma":[0.9424444,0.055800315,0.00011106385,0.0004556999,0.00031977164,0.0008687819],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033286143,0.0002403486,0.000692229,0.00044317765,0.0008869567,0.000015278625,0.000443392,0.000053866832,0.0021426256],"category_scores_gemma":[0.02192437,0.00013956187,0.00011369122,0.00041356232,0.0027159723,0.00005344528,0.0014711472,0.0012685086,0.000048223035],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00789312,0.00050064456,0.76250607,0.00041631755,0.0013966215,0.003131081,0.00664797,0.0000010335216,0.0067876005,0.005658385,0.0065309503,0.19853021],"study_design_scores_gemma":[0.008941995,0.0031330402,0.9279895,0.00048749716,0.0001342005,0.0006669192,0.024614755,0.00036960733,0.0061407285,0.0038288278,0.023442984,0.00024994666],"about_ca_topic_score_codex":0.0017735928,"about_ca_topic_score_gemma":0.004675636,"teacher_disagreement_score":0.19828026,"about_ca_system_score_codex":0.0003540866,"about_ca_system_score_gemma":0.00023783097,"threshold_uncertainty_score":0.9999981},"labels":[],"label_agreement":null},{"id":"W1538635628","doi":"10.1186/1471-2288-5-24","title":"Which resources should be used to identify RCT/CCTs for systematic reviews: a systematic review","year":2005,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"MEDLINE; Systematic review; Checklist; Randomized controlled trial; Medicine; Meta-analysis; Cochrane Library; Psychology; Internal medicine","score_opus":0.9881017917846451,"score_gpt":0.7866764926358516,"score_spread":0.20142529914879348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1538635628","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":[3.3780418e-7,0.8227125,0.09901942,0.0031471772,0.00071877195,0.07353802,0.0000863032,0.000034725097,0.00074274413],"genre_scores_gemma":[3.0317594e-7,0.8815026,0.05052672,0.0023008736,0.001034472,0.044988517,0.000079726626,0.00019030539,0.019376438],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.1192057,0.74866116,0.0735546,0.0063431733,0.04910282,0.0031325275],"domain_scores_gemma":[0.06212758,0.8670834,0.029343141,0.024890792,0.012009205,0.0045459284],"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":[0.93246,0.0024084344,0.10927493,0.0049915733,0.0007147309,0.0019170638,0.023457007,0.002375792,0.017177591],"category_scores_gemma":[0.9875491,0.0010297225,0.018544111,0.015282187,0.0005426555,0.00030697137,0.0027195045,0.0036399225,0.026080992],"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":[0.0000068898357,0.0000737225,6.4764015e-7,0.8001254,0.0008316184,0.000017644592,0.00024757517,3.1175787e-7,1.5271706e-7,0.0008851849,0.16065876,0.03715204],"study_design_scores_gemma":[0.000115168295,0.00010795445,1.9259122e-7,0.49387658,0.0057388158,0.0001910465,0.00018875809,0.00008717102,5.0635336e-8,0.00035120104,0.49889925,0.00044381357],"about_ca_topic_score_codex":0.0000375601,"about_ca_topic_score_gemma":0.0015099564,"teacher_disagreement_score":0.3382405,"about_ca_system_score_codex":0.00068297045,"about_ca_system_score_gemma":0.004139716,"threshold_uncertainty_score":0.9992153},"labels":[],"label_agreement":null},{"id":"W1540816673","doi":"10.1186/1471-2288-6-33","title":"An alternative to the hand searching gold standard: validating methodological search filters using relative recall","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa; Canadian Agency for Drugs and Technologies in Health; University of Alberta; University of Saskatchewan; McGill University; Children's Hospital of Eastern Ontario","funders":"","keywords":"Recall; Gold standard (test); MEDLINE; Systematic review; Information retrieval; Randomized controlled trial; Computer science; Medicine; Medical physics; Psychology; Cognitive psychology; Surgery","score_opus":0.9791445577134705,"score_gpt":0.7440587898908313,"score_spread":0.23508576782263924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1540816673","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":[0.25211313,0.0002596586,0.7389576,0.0041017737,0.00031172668,0.001244925,0.000028370985,0.0000117128275,0.00297113],"genre_scores_gemma":[0.19282185,0.000023984003,0.801646,0.00061234785,0.0010659682,0.00011847366,0.00001428235,0.000039886963,0.0036572057],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.2719673,0.6837581,0.008690671,0.003010397,0.030517722,0.0020558292],"domain_scores_gemma":[0.26404944,0.71721715,0.0023598918,0.007166168,0.0069054035,0.0023019486],"candidate_categories":["metaresearch","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8495484,0.00048354082,0.0044339243,0.0014359269,0.0012561481,0.0017021085,0.0071060043,0.0004675251,0.012034581],"category_scores_gemma":[0.7982743,0.00020993427,0.0012664725,0.004475316,0.00174242,0.00042902702,0.0017969218,0.0028751541,0.0010709316],"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":[0.0020166019,0.0005876626,0.03612406,0.00034911183,0.0011547016,0.00071196456,0.022257535,0.052583314,0.03397582,0.15574424,0.089594975,0.6049],"study_design_scores_gemma":[0.0017508209,0.002228586,0.011230446,0.00049557636,0.00025721983,0.00035105555,0.020984314,0.5428141,0.0069626565,0.3115436,0.100256294,0.0011253132],"about_ca_topic_score_codex":0.0021344922,"about_ca_topic_score_gemma":0.0017401229,"teacher_disagreement_score":0.6037747,"about_ca_system_score_codex":0.00030582456,"about_ca_system_score_gemma":0.0014230656,"threshold_uncertainty_score":0.99970686},"labels":[],"label_agreement":null},{"id":"W1541868835","doi":"10.1186/1471-2288-1-11","title":"Sample size requirements for case-control study designs","year":2001,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Confounding; Sample size determination; Odds ratio; Fortran; Statistics; Computer science; Control (management); Sample (material); Case-control study; Odds; Software; Medicine; Mathematics; Logistic regression; Programming language; Artificial intelligence","score_opus":0.9182700472002921,"score_gpt":0.6957823635411999,"score_spread":0.22248768365909222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541868835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048610568,0.000045555553,0.94709015,0.00044337404,0.00012794013,0.0029788502,0.000025945494,0.00025421087,0.0004233809],"genre_scores_gemma":[0.21679673,0.000043488963,0.7806558,0.00019488244,0.00027467,0.0015335869,0.0000014666354,0.000050150207,0.00044924903],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9775878,0.017810902,0.00083793636,0.000692502,0.0017227514,0.0013480986],"domain_scores_gemma":[0.58995014,0.40816414,0.000114977614,0.0006929873,0.00057693705,0.00050081365],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06890425,0.00023114041,0.00079479814,0.00025159106,0.000317011,0.00002921901,0.0007488878,0.0003787162,0.0030313283],"category_scores_gemma":[0.71275806,0.00018705562,0.00013070392,0.00047191395,0.0005263082,0.00011794976,0.00029332825,0.0008695167,0.00002326324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065126787,0.0056811254,0.037200242,0.0010309324,0.00082148286,0.007797044,0.0040878607,0.000008282384,0.008616548,0.46658164,0.025315993,0.43634617],"study_design_scores_gemma":[0.0027827937,0.0025715753,0.0003552846,0.00005399586,0.000054529464,0.00044986757,0.002075778,0.0010320065,0.0008386957,0.98792654,0.0016343305,0.00022462253],"about_ca_topic_score_codex":0.00035377298,"about_ca_topic_score_gemma":0.0018931803,"teacher_disagreement_score":0.64385384,"about_ca_system_score_codex":0.00019632324,"about_ca_system_score_gemma":0.0006844242,"threshold_uncertainty_score":0.99788004},"labels":[],"label_agreement":null},{"id":"W1577169562","doi":"10.1186/1471-2288-10-68","title":"A life-course and time perspective on the construct validity of psychological distress in women and men. Measurement invariance of the K6 across gender","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Mental Health Treatment and Access","field":"Psychology","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut universitaire en santé mentale de Montréal; Université du Québec à Montréal; Concordia University; Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Measurement invariance; Distress; Construct validity; Psychology; Population; Mental health; Clinical psychology; Confirmatory factor analysis; Psychological distress; Construct (python library); Psychiatric epidemiology; Structural equation modeling; Medicine; Psychometrics; Psychiatry","score_opus":0.6103650174567217,"score_gpt":0.6039843144804005,"score_spread":0.006380702976321206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577169562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98930484,0.00041664898,0.000101288744,0.005070345,0.00026661166,0.0008021268,0.000032237567,0.0000059997924,0.0039998787],"genre_scores_gemma":[0.99839807,0.00008267821,0.0006850959,0.00043622733,0.00007733774,0.00021827992,7.5437066e-7,0.000009051148,0.00009251712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9839386,0.013298744,0.0004431684,0.00050573045,0.0011511837,0.0006625752],"domain_scores_gemma":[0.98128754,0.017427325,0.00015334168,0.00052865583,0.00020474437,0.00039840778],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03064027,0.0001457453,0.0004692103,0.00006336629,0.0001955934,0.000011575976,0.0005656047,0.00032293762,0.0020076295],"category_scores_gemma":[0.026822684,0.00007417462,0.00004701046,0.0002954653,0.003647292,0.000027058444,0.00035070087,0.0012657378,0.000010171697],"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":[0.011548878,0.0064559793,0.3566804,0.00063625013,0.00051433704,0.00011391135,0.051800665,6.725637e-7,0.010200874,0.4449292,0.007221793,0.10989703],"study_design_scores_gemma":[0.0029051069,0.00085786666,0.9447448,0.000085640706,0.000012841867,0.000046654273,0.011491691,0.00004953047,0.0006041516,0.03897411,0.000119115044,0.000108478],"about_ca_topic_score_codex":0.00060689915,"about_ca_topic_score_gemma":0.00041453898,"teacher_disagreement_score":0.58806443,"about_ca_system_score_codex":0.00007673195,"about_ca_system_score_gemma":0.0002253282,"threshold_uncertainty_score":0.9990642},"labels":[],"label_agreement":null},{"id":"W1597187916","doi":"10.1186/1471-2288-6-44","title":"Does a \"Level I Evidence\" rating imply high quality of reporting in orthopaedic randomised controlled trials?","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McMaster University; Hamilton General Hospital","funders":"","keywords":"Medicine; Evidence-based medicine; Randomized controlled trial; Cochrane Library; MEDLINE; Sample size determination; Rating scale; Meta-analysis; Rating system; Physical therapy; Family medicine; Alternative medicine; Surgery; Internal medicine; Psychology; Statistics","score_opus":0.9854238183784965,"score_gpt":0.7611828492904247,"score_spread":0.22424096908807178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597187916","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":[0.60211414,0.0026114592,0.38697395,0.0029502108,0.0005731709,0.0036715528,0.000007901626,0.000007984604,0.0010896521],"genre_scores_gemma":[0.8247706,0.00015963764,0.17008686,0.00013544217,0.00061406376,0.00070519577,0.0000063009547,0.00001751081,0.0035043554],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.014806665,0.86100733,0.091507345,0.0021089495,0.029333133,0.0012365672],"domain_scores_gemma":[0.0033482683,0.94733775,0.04008831,0.0036167435,0.005052282,0.00055667054],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9830996,0.0003788755,0.02458849,0.0017560257,0.00020614194,0.0002895737,0.0027713852,0.0005118148,0.019827154],"category_scores_gemma":[0.9979806,0.00013022043,0.005544266,0.0034488307,0.00081173045,0.00021950585,0.00054200715,0.0011998884,0.00013914207],"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":[0.027973784,0.0006943036,0.67545724,0.0022085484,0.0011657783,0.000392786,0.0013975354,0.0002055371,0.029884633,0.03775897,0.018860862,0.20400003],"study_design_scores_gemma":[0.1438886,0.0006116537,0.3947943,0.0028648719,0.0007911033,0.00009629681,0.009247273,0.023789268,0.0025756655,0.41799933,0.0023308115,0.0010108661],"about_ca_topic_score_codex":0.00468744,"about_ca_topic_score_gemma":0.0092883,"teacher_disagreement_score":0.38024035,"about_ca_system_score_codex":0.000092330345,"about_ca_system_score_gemma":0.0028223442,"threshold_uncertainty_score":0.98989254},"labels":[],"label_agreement":null},{"id":"W1602160603","doi":"10.1186/1471-2288-14-137","title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Traumatic Brain Injury and Neurovascular Disturbances","field":"Medicine","cited_by":796,"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":"Support vector machine; Logistic regression; Statistics; Random forest; Sample size determination; Artificial intelligence; Receiver operating characteristic; Regression; Machine learning; Computer science; Medicine; Mathematics","score_opus":0.7132462483034406,"score_gpt":0.5762959983442477,"score_spread":0.13695024995919292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1602160603","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":[0.16519451,0.00031821043,0.8311675,0.00041322535,0.00015155,0.0021803868,0.00001876243,0.00019006777,0.00036573905],"genre_scores_gemma":[0.83025897,0.00004966712,0.16805671,0.00025761954,0.0007598153,0.0003779563,0.00008288941,0.00004800345,0.00010839224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.986476,0.008905104,0.00072564674,0.001070129,0.002063147,0.00075995433],"domain_scores_gemma":[0.93600243,0.060870845,0.00019161649,0.0018503197,0.0004950863,0.0005896917],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050330345,0.00021177261,0.0008361284,0.0003191176,0.00031059879,0.000034749024,0.0008635205,0.0003412737,0.00009315325],"category_scores_gemma":[0.13152155,0.00016803676,0.0001290141,0.0003367706,0.00038342987,0.00014390852,0.00050828303,0.0010444258,0.000008594636],"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":[0.007146961,0.0039701913,0.050618935,0.0038972865,0.000752394,0.00016004627,0.005250841,0.004778277,0.0011961879,0.0017317239,0.0015876648,0.9189095],"study_design_scores_gemma":[0.0021947739,0.0015764764,0.002516148,0.0003666143,0.00012632589,0.000041284587,0.00090372626,0.9807326,0.00073944195,0.007844724,0.0028021643,0.00015570037],"about_ca_topic_score_codex":0.000093840754,"about_ca_topic_score_gemma":0.00021575693,"teacher_disagreement_score":0.97595435,"about_ca_system_score_codex":0.00005162588,"about_ca_system_score_gemma":0.0004131757,"threshold_uncertainty_score":0.97788477},"labels":[],"label_agreement":null},{"id":"W1603573412","doi":"10.1186/1471-2288-6-57","title":"Dealing with missing data in a multi-question depression scale: a comparison of imputation methods","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":655,"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 Calgary","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale; Government of Canada; Heart and Stroke Foundation of Canada","keywords":"Missing data; Statistics; Imputation (statistics); Statistic; Cohen's kappa; Standard deviation; Population; Mathematics; Kappa; Regression; Psychology; Medicine","score_opus":0.7482629066797014,"score_gpt":0.6934678501720167,"score_spread":0.05479505650768468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1603573412","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01445299,0.00032831458,0.98424304,0.00017993529,0.0000631984,0.00034856668,0.000010449142,0.000034861132,0.00033862633],"genre_scores_gemma":[0.051353864,0.000018074503,0.94845545,0.000011813886,0.00006781305,0.000029577071,0.000026233674,0.000024432235,0.000012749765],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96399504,0.03192572,0.0011754363,0.00072008715,0.0015153054,0.00066840596],"domain_scores_gemma":[0.86460733,0.13380001,0.0002662509,0.000711589,0.00036579088,0.00024900533],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.061452504,0.00016379317,0.0008105234,0.0003968479,0.00010927256,0.000025135652,0.00065240456,0.0003501677,0.00017445536],"category_scores_gemma":[0.18612792,0.000119502736,0.000034124485,0.0006304182,0.0006709506,0.00010250348,0.00042053204,0.0009452135,0.0000023162552],"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":[0.0004629173,0.00046964936,0.05056434,0.0006848171,0.000013418996,0.000030552394,0.00029921703,0.000020951811,0.006642275,0.1133977,0.00008435826,0.8273298],"study_design_scores_gemma":[0.0013178652,0.00022039299,0.025618922,0.0010333243,0.000031891846,0.000036394093,0.00037105696,0.3448774,0.008535251,0.6177282,0.000054714343,0.00017460303],"about_ca_topic_score_codex":0.001733915,"about_ca_topic_score_gemma":0.0027816885,"teacher_disagreement_score":0.8271552,"about_ca_system_score_codex":0.00006289201,"about_ca_system_score_gemma":0.0005451152,"threshold_uncertainty_score":0.96643215},"labels":[],"label_agreement":null},{"id":"W1654993868","doi":"10.1186/1471-2288-3-20","title":"Interdisciplinary research: putting the methods under the microscope","year":2003,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Interdisciplinary Research and Collaboration","field":"Decision Sciences","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":"","keywords":"Mantra; Silence; Engineering ethics; Relation (database); Sociology; Management science; Epistemology; Computer science; Engineering; Philosophy; Aesthetics","score_opus":0.8656772611912865,"score_gpt":0.7384364678476388,"score_spread":0.12724079334364768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1654993868","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":[0.046559107,0.0029289862,0.73298424,0.15188318,0.002019275,0.0016955987,0.000008149458,0.000060641592,0.061860807],"genre_scores_gemma":[0.5371273,0.00030565914,0.40187073,0.0023057747,0.002575647,0.0014068024,0.000010479843,0.00013005518,0.05426757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.55541056,0.4202341,0.0019953495,0.0018979758,0.01706148,0.0034005267],"domain_scores_gemma":[0.25490952,0.7316008,0.00032837744,0.004412793,0.0072609265,0.0014875475],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","insufficient_payload"],"category_scores_codex":[0.62829006,0.0002811622,0.00067717716,0.0011517887,0.0044461205,0.0011158584,0.0068585747,0.00050877564,0.0067437347],"category_scores_gemma":[0.51910657,0.00012432305,0.00030900468,0.00798434,0.0074896207,0.0003701776,0.006888118,0.005501517,0.0018176641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007321816,0.00027063032,0.00071092043,0.000039175942,0.00009587875,0.00012417285,0.0071081696,0.00008510725,0.012871793,0.4114633,0.32446083,0.24203785],"study_design_scores_gemma":[0.00047396403,0.000630924,0.0021305357,0.000060450602,0.000006085008,0.0001878723,0.09007993,0.0023567467,0.0044497866,0.7506115,0.14886864,0.00014356915],"about_ca_topic_score_codex":0.00010078885,"about_ca_topic_score_gemma":0.0041596545,"teacher_disagreement_score":0.4905682,"about_ca_system_score_codex":0.00029682624,"about_ca_system_score_gemma":0.005420517,"threshold_uncertainty_score":0.9999211},"labels":[],"label_agreement":null},{"id":"W1775522749","doi":"10.1186/1471-2288-5-5","title":"Comparison of nested case-control and survival analysis methodologies for analysis of time-dependent exposure","year":2005,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":235,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Nested case-control study; Covariate; Proportional hazards model; Statistics; Regression analysis; Cohort; Nested set model; Cohort study; Regression; Medicine; Survival analysis; Econometrics; Mathematics; Computer science; Data mining","score_opus":0.7964481715181267,"score_gpt":0.6724582142401484,"score_spread":0.12398995727797835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1775522749","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16807553,0.00049326045,0.83039665,0.00022996389,0.000022648854,0.0005329034,0.000074422656,0.00007387649,0.00010077585],"genre_scores_gemma":[0.4017955,0.00006916381,0.59786344,0.00001346464,0.000040092447,0.000103896666,0.00001057021,0.000015372543,0.00008848887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97346383,0.022330143,0.0015083487,0.0005846072,0.0014462629,0.00066682487],"domain_scores_gemma":[0.75514746,0.24272528,0.0004237086,0.0006047116,0.0008549841,0.00024385298],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.066856965,0.00022663835,0.0029600803,0.0019479515,0.00009645441,0.000011350901,0.0005493661,0.00055986573,0.0006436655],"category_scores_gemma":[0.24640135,0.0001796553,0.00048290807,0.0023794766,0.0011177763,0.00008355456,0.00029235022,0.0006170315,0.0000012699126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005934169,0.0021211088,0.28597763,0.002736607,0.04593874,0.00023982408,0.007089669,0.0071059074,0.07011959,0.1779649,0.0012213418,0.39355052],"study_design_scores_gemma":[0.0058723586,0.0044990713,0.022637408,0.00016829176,0.0326031,0.0001506328,0.011444956,0.49922225,0.09363995,0.32832605,0.00029744685,0.0011384677],"about_ca_topic_score_codex":0.00028981984,"about_ca_topic_score_gemma":0.0052478737,"teacher_disagreement_score":0.49211636,"about_ca_system_score_codex":0.000071276,"about_ca_system_score_gemma":0.00028920412,"threshold_uncertainty_score":0.9608671},"labels":[],"label_agreement":null},{"id":"W1791587479","doi":"10.1186/1471-2288-5-1","title":"Structural equation model testing and the quality of natural killer cell activity measurements","year":2005,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Immune Cell Function and Interaction","field":"Immunology and Microbiology","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":"University of Alberta","funders":"","keywords":"Covariance; Structural equation modeling; Econometrics; Natural killer cell; Natural (archaeology); Statistics; Cell; Immunology; Biology; Mathematics; Cytotoxic T cell; Genetics","score_opus":0.6722927013247167,"score_gpt":0.5234907777996085,"score_spread":0.14880192352510824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1791587479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95544994,0.0017362331,0.037108365,0.001430687,0.0016214666,0.00036815973,8.5880095e-7,0.000028747309,0.0022555655],"genre_scores_gemma":[0.9849671,0.000053949876,0.010780144,0.00016578026,0.000066521745,0.000024999097,0.000008102988,0.000008250101,0.003925117],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98185694,0.016615912,0.00047029898,0.00028831878,0.000365869,0.00040267868],"domain_scores_gemma":[0.9698097,0.029274048,0.00019498183,0.0002657713,0.0004076247,0.00004788554],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026647622,0.00011589776,0.00037974791,0.00013231786,0.00028866442,0.000009880466,0.00025641118,0.0002962893,0.00065998884],"category_scores_gemma":[0.069816954,0.00007176852,0.00008019385,0.00017866361,0.0011918884,0.00011784007,0.00021351298,0.0011861074,0.000051004892],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005345464,0.000114333736,0.0037844602,0.00012151531,0.00010244769,2.92956e-7,0.0009327443,0.00022144153,0.86750907,0.002889812,0.0019503795,0.11702807],"study_design_scores_gemma":[0.024498789,0.00069594925,0.07177069,0.00016652085,0.000094142306,0.00012837813,0.0014340162,0.34651405,0.5423534,0.007925832,0.0038079366,0.0006102984],"about_ca_topic_score_codex":0.00080698443,"about_ca_topic_score_gemma":0.00022124342,"teacher_disagreement_score":0.34629261,"about_ca_system_score_codex":0.000068450354,"about_ca_system_score_gemma":0.00032146793,"threshold_uncertainty_score":0.9380184},"labels":[],"label_agreement":null},{"id":"W1796940665","doi":"10.1186/1471-2288-6-23","title":"Optimizing search strategies to identify randomized controlled trials in MEDLINE","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; Western University; University of Saskatchewan","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Randomized controlled trial; Medicine; Surgery; Political science","score_opus":0.9682095325904341,"score_gpt":0.7601082411240092,"score_spread":0.20810129146642486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1796940665","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":[0.07433303,0.003944455,0.8929107,0.007824372,0.00050108373,0.0061481264,0.0000048124048,0.000011391753,0.014322023],"genre_scores_gemma":[0.29345682,0.0004637882,0.6798485,0.0005913319,0.0013435181,0.0025245338,0.000018604107,0.0000441361,0.021708759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.020446522,0.9091738,0.036975823,0.0020314257,0.029859269,0.0015131743],"domain_scores_gemma":[0.014149595,0.97385216,0.0036428263,0.003371973,0.003978782,0.0010046789],"candidate_categories":["metaresearch","metaepi_broad","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.98232424,0.00043158882,0.03721625,0.0041794344,0.00020964809,0.0014862895,0.0043981946,0.0005221152,0.045385804],"category_scores_gemma":[0.98345,0.00017620392,0.0061771306,0.004613493,0.0009140576,0.00022858524,0.00077789405,0.001369768,0.0028393208],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.23251186,0.0011286295,0.00417402,0.00079109595,0.0030607088,0.0008421486,0.0055326875,0.016535858,0.008966937,0.39591017,0.22971673,0.100829154],"study_design_scores_gemma":[0.37019113,0.00030871882,0.0027804559,0.00051699666,0.0006370758,0.0000649696,0.014382412,0.1565451,0.0004821438,0.43542483,0.017925149,0.00074102916],"about_ca_topic_score_codex":0.0012491042,"about_ca_topic_score_gemma":0.0028920395,"teacher_disagreement_score":0.21912381,"about_ca_system_score_codex":0.00010428905,"about_ca_system_score_gemma":0.00289051,"threshold_uncertainty_score":0.9995503},"labels":[],"label_agreement":null},{"id":"W1805646557","doi":"10.1186/1471-2288-5-8","title":"Evaluating the role of quality assessment of primary studies in systematic reviews of cancer practice guidelines","year":2005,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Hamilton Regional Laboratory Medicine Program; Cancer Care Ontario; University of Toronto; McMaster University","funders":"Ontario Ministry of Health and Long-Term Care; Cancer Care Ontario","keywords":"Systematic review; Quality (philosophy); Medicine; MEDLINE; Quality of evidence; Quality assessment; Primary care; Psychology; Family medicine; Meta-analysis; Political science; External quality assessment; Pathology","score_opus":0.9955758562608554,"score_gpt":0.8622804684686729,"score_spread":0.13329538779218253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1805646557","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":[0.17528674,0.656639,0.123752214,0.022325866,0.0006062633,0.01134645,0.000019246387,0.0000051468533,0.010019099],"genre_scores_gemma":[0.0399849,0.018454505,0.93850994,0.0007227692,0.00021867223,0.0010719019,0.0000013637623,0.000012873759,0.00102306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.044568133,0.8830902,0.041001614,0.0011299405,0.029599851,0.00061028777],"domain_scores_gemma":[0.04882344,0.9077089,0.017864114,0.0047652614,0.020609703,0.00022859525],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9408679,0.00020318094,0.009806137,0.00054528983,0.00007265255,0.000026801965,0.0028539384,0.00015721802,0.003137173],"category_scores_gemma":[0.9825619,0.00007503604,0.0010841287,0.0023425044,0.0008865054,0.00014188122,0.00073400233,0.000581286,0.000037139245],"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":[0.00022132987,0.00070695137,0.03513455,0.10023918,0.001665078,0.0000040655395,0.007995311,0.0013012406,0.008705991,0.03472387,0.011650289,0.7976521],"study_design_scores_gemma":[0.0044536768,0.0025955518,0.06059786,0.070171975,0.004228081,0.00010736998,0.23596363,0.36469057,0.0030665477,0.12722482,0.12570347,0.0011964523],"about_ca_topic_score_codex":0.00064085855,"about_ca_topic_score_gemma":0.001608489,"teacher_disagreement_score":0.81475776,"about_ca_system_score_codex":0.00014488774,"about_ca_system_score_gemma":0.00214566,"threshold_uncertainty_score":0.9977741},"labels":[],"label_agreement":null},{"id":"W1831738305","doi":"10.1186/1471-2288-2-7","title":"Publication bias in gastroenterological research – a retrospective cohort study based on abstracts submitted to a scientific meeting","year":2002,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"Deutscher Akademischer Austauschdienst","keywords":"Medicine; Publication bias; Logistic regression; Family medicine; Impact factor; MEDLINE; Cohort study; Publication; Internal medicine; Meta-analysis","score_opus":0.9767281836132805,"score_gpt":0.7064324347820012,"score_spread":0.27029574883127927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1831738305","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":[0.9545561,0.00006023644,0.015688542,0.010147294,0.00031912077,0.004482439,0.0000066344546,0.000016651595,0.014722981],"genre_scores_gemma":[0.97123176,0.000006940882,0.022529142,0.0004912244,0.00016059054,0.0010626515,0.000008121042,0.000019571116,0.0044899974],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.16508646,0.7326293,0.015822502,0.006214487,0.07697773,0.0032695055],"domain_scores_gemma":[0.29204023,0.6629203,0.003472721,0.01396761,0.023638407,0.003960745],"candidate_categories":["metaresearch","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9138358,0.000332418,0.003763098,0.0062972116,0.0006761865,0.0017335658,0.0051851952,0.0003805052,0.039561413],"category_scores_gemma":[0.96200114,0.00017716018,0.0006683406,0.013444791,0.0011161526,0.00017249904,0.0009447549,0.0027240713,0.009817017],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016241385,0.0012578809,0.9170504,0.00002270095,0.00004028739,0.00009283235,0.0007464045,0.00012992637,0.00008702344,0.00046116923,0.07032611,0.009622839],"study_design_scores_gemma":[0.0007009204,0.0012954295,0.93260616,0.00008612902,0.000014562091,0.00000882876,0.00173605,0.054693896,0.000020844202,0.0021063136,0.006602536,0.00012835609],"about_ca_topic_score_codex":0.00033776046,"about_ca_topic_score_gemma":0.0034120772,"teacher_disagreement_score":0.12695378,"about_ca_system_score_codex":0.0004938682,"about_ca_system_score_gemma":0.00054459827,"threshold_uncertainty_score":0.9995767},"labels":[],"label_agreement":null},{"id":"W1849959288","doi":"10.1186/s12874-015-0084-0","title":"An evaluation of harvest plots to display results of meta-analyses in overviews of reviews: a cross-sectional study","year":2015,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Alberta Health; Cochrane; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Quartile; Descriptive statistics; Statistics; Meta-analysis; Systematic review; Medicine; Psychology; MEDLINE; Mathematics; Confidence interval","score_opus":0.9960158154373674,"score_gpt":0.8204808956259304,"score_spread":0.17553491981143698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1849959288","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":[0.9360541,0.008138253,0.050420813,0.0002102656,0.00022721302,0.0037486197,0.000060238366,0.000002134135,0.0011383333],"genre_scores_gemma":[0.9304107,0.00009478579,0.067951985,0.000054367225,0.00009150986,0.00048337044,0.00001612323,0.000013568789,0.0008836287],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.08581806,0.8195509,0.034105252,0.002419947,0.05735581,0.0007500893],"domain_scores_gemma":[0.5153086,0.4087911,0.01769257,0.015326529,0.040269513,0.0026116832],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9268828,0.0002865825,0.009402717,0.0020946276,0.000051603394,0.00009940991,0.0036002265,0.0002568958,0.007449497],"category_scores_gemma":[0.9368964,0.00013034251,0.0019820787,0.005320131,0.0005714083,0.00026830428,0.0005235294,0.0004958673,0.00022001944],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023752109,0.00512875,0.8873724,0.00096910045,0.0044072084,0.000017575752,0.012339084,0.00761993,0.003923639,0.002845161,0.02446504,0.048536953],"study_design_scores_gemma":[0.0034671484,0.0026432986,0.9390123,0.00014423401,0.0027313135,0.000010858936,0.0040765884,0.025006922,0.0006461594,0.013707509,0.008296506,0.00025715525],"about_ca_topic_score_codex":0.0018112144,"about_ca_topic_score_gemma":0.010335107,"teacher_disagreement_score":0.42949057,"about_ca_system_score_codex":0.00010032584,"about_ca_system_score_gemma":0.0020475516,"threshold_uncertainty_score":0.99345785},"labels":[],"label_agreement":null},{"id":"W1896554341","doi":"10.1186/s12874-015-0058-2","title":"Efficiency of pragmatic search strategies to update clinical guidelines recommendations","year":2015,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Instituto de Salud Carlos III; Canadian Institutes of Health Research; Servicio Gallego de Salud; Red de Investigación en Servicios de Salud en Enfermedades Crónicas; Fundación Canaria de Investigación y Salud","keywords":"Computer science; SNOMED CT; Information retrieval; MEDLINE; Key (lock); Guideline; Systematized Nomenclature of Medicine; Matching (statistics); Data mining; Terminology; Medicine","score_opus":0.9511655897017278,"score_gpt":0.7770426722306951,"score_spread":0.1741229174710327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1896554341","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.167111,0.0002389538,0.70839745,0.120444916,0.0007892183,0.0012409945,0.000015592728,0.00006397913,0.0016979106],"genre_scores_gemma":[0.07881854,0.0006891802,0.91489047,0.0039076414,0.0010819496,0.000107504115,0.00012453715,0.000041980973,0.00033819108],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9620824,0.027952887,0.0042620846,0.0007720484,0.0039824294,0.00094813976],"domain_scores_gemma":[0.8441725,0.14406414,0.00039149367,0.0012112891,0.0074188598,0.0027417305],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20319282,0.00018175389,0.0010219603,0.0006366346,0.00010101804,0.00003245554,0.0006425563,0.00039778702,0.0023181255],"category_scores_gemma":[0.75112224,0.00014208799,0.00019447508,0.0014102729,0.0009205572,0.00018727078,0.0007163504,0.0015711219,0.0005742316],"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":[0.0049014715,0.0022284323,0.035094105,0.00075401715,0.00028198224,0.0001489842,0.0013571107,0.0002297987,0.0012166783,0.03653035,0.29633343,0.62092364],"study_design_scores_gemma":[0.038266383,0.029929034,0.03996371,0.0028085185,0.00083101855,0.0012224134,0.1423035,0.07555546,0.0036564688,0.09516401,0.5687391,0.0015603456],"about_ca_topic_score_codex":0.0009471607,"about_ca_topic_score_gemma":0.0010304609,"teacher_disagreement_score":0.6193633,"about_ca_system_score_codex":0.00012974681,"about_ca_system_score_gemma":0.012041668,"threshold_uncertainty_score":0.99859387},"labels":[],"label_agreement":null},{"id":"W1905212504","doi":"10.1186/1471-2288-1-8","title":"On the probability of cost-effectiveness using data from randomized clinical trials","year":2001,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Confidence interval; Sample size determination; Point estimation; Estimator; Coverage probability; Statistics; Parametric statistics; Bayesian probability; Interval estimation; Randomized controlled trial; Computer science; Credible interval; Econometrics; Mathematics; Medicine; Surgery","score_opus":0.9947389119596108,"score_gpt":0.8325544859025912,"score_spread":0.16218442605701966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1905212504","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":[0.09852708,0.00012820106,0.8919743,0.001264575,0.0012834143,0.005971899,0.00019711036,0.00004369359,0.0006097777],"genre_scores_gemma":[0.011403654,0.0004192266,0.9861605,0.00026224818,0.0012108014,0.0004507466,0.000012829434,0.00004840356,0.000031568798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.11786217,0.86907613,0.006464321,0.001570259,0.0040084673,0.0010186577],"domain_scores_gemma":[0.0036152673,0.9898975,0.0011722108,0.0037269064,0.0008552699,0.000732878],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.89741564,0.000313561,0.006587545,0.00017746317,0.00019072542,0.00003485767,0.0033496106,0.0011147006,0.008147381],"category_scores_gemma":[0.9987909,0.00016325958,0.0007986778,0.0007617782,0.0074333814,0.00005993066,0.0020272927,0.0030667214,0.00005939839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24788228,0.0017039736,0.0011676684,0.00038993935,0.00088064646,0.00006370359,0.00006622144,0.000005855379,0.0002644219,0.6219569,0.0028262904,0.12279213],"study_design_scores_gemma":[0.045886885,0.00025899164,0.00028748362,0.00043278598,0.0002627703,0.0000067239653,0.000061002676,0.017570488,0.00034086098,0.9345091,0.00024292854,0.00014000777],"about_ca_topic_score_codex":0.00049518014,"about_ca_topic_score_gemma":0.00013825997,"teacher_disagreement_score":0.3125522,"about_ca_system_score_codex":0.00010466159,"about_ca_system_score_gemma":0.002086758,"threshold_uncertainty_score":0.99923325},"labels":[],"label_agreement":null},{"id":"W1932363030","doi":"10.1186/s12874-015-0081-3","title":"Statistical power in parallel group point exposure studies with time-to-event outcomes: an empirical comparison of the performance of randomized controlled trials and the inverse probability of treatment weighting (IPTW) approach","year":2015,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; McGill University; Heart and Stroke Foundation of Canada","keywords":"Observational study; Statistical power; Inverse probability; Statistics; Marginal structural model; Randomized controlled trial; Weighting; Power analysis; Inverse probability weighting; Propensity score matching; Sample size determination; Computer science; Mathematics; Econometrics; Medicine; Algorithm; Posterior probability; Bayesian probability; Internal medicine","score_opus":0.7529466825685419,"score_gpt":0.6219541855890501,"score_spread":0.13099249697949178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1932363030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74675745,0.0003010321,0.24636,0.000648741,0.00002265942,0.0057611633,0.0000066932057,0.0000168477,0.00012540685],"genre_scores_gemma":[0.50847656,0.00006270793,0.4903165,0.000024262203,0.000011330941,0.0010636171,0.0000016311396,0.000011220858,0.000032171112],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8930015,0.100736074,0.003324664,0.00047095702,0.001951458,0.00051533204],"domain_scores_gemma":[0.7537316,0.24401972,0.0007908219,0.000583598,0.00063788943,0.00023636894],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18122926,0.00023870965,0.0066826516,0.00017276137,0.00005369314,0.0000058203755,0.00042957053,0.00019734992,0.000053646327],"category_scores_gemma":[0.4755994,0.00008531229,0.0002546557,0.00029547725,0.0042898073,0.00005275501,0.00035133684,0.00053942093,5.6540466e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.750981,0.0043374877,0.08313236,0.001487014,0.0020750265,0.0000059028507,0.042305052,0.00048906554,0.00032288767,0.110554874,0.0004730429,0.0038363314],"study_design_scores_gemma":[0.5005914,0.011965858,0.002999938,0.0007653569,0.00069432287,0.000017148153,0.017161299,0.06598046,0.0013619376,0.39811018,0.000018742583,0.00033334518],"about_ca_topic_score_codex":0.00009775284,"about_ca_topic_score_gemma":0.0002973432,"teacher_disagreement_score":0.29437014,"about_ca_system_score_codex":0.0001753271,"about_ca_system_score_gemma":0.0007642903,"threshold_uncertainty_score":0.99841994},"labels":[],"label_agreement":null},{"id":"W1935422282","doi":"10.1186/1471-2288-6-7","title":"Can electronic search engines optimize screening of search results in systematic reviews: an empirical study","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Alberta; Carleton University; University of Ottawa; McGill University; Children's Hospital of Eastern Ontario","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Cochrane Library; Systematic review; Medicine; Information retrieval; Computer science; Meta-analysis; Pathology","score_opus":0.9602321763929001,"score_gpt":0.7210932492357292,"score_spread":0.239138927157171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1935422282","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":[0.59716815,0.008173312,0.37947664,0.002846647,0.00018963002,0.010528069,0.000018953206,0.000020060575,0.001578528],"genre_scores_gemma":[0.87348586,0.00034077358,0.120739296,0.000100463156,0.00034749843,0.00071493373,0.000024724264,0.00004558241,0.0042008595],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.15289171,0.78281564,0.02617259,0.0030663535,0.032525845,0.0025278798],"domain_scores_gemma":[0.5525818,0.43135178,0.0027177052,0.007766983,0.004419139,0.0011626037],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8897012,0.00048042764,0.010532032,0.0030837795,0.00022555316,0.00031652977,0.005934031,0.000450763,0.003538878],"category_scores_gemma":[0.7825298,0.00023893257,0.0013204952,0.0076524075,0.0006915944,0.00019558179,0.00091398414,0.002250289,0.00037707493],"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":[0.0041350275,0.011977972,0.6590851,0.062112574,0.0019272735,0.0013648388,0.032506764,0.021668155,0.0014858514,0.023286533,0.058363583,0.12208633],"study_design_scores_gemma":[0.013218809,0.008963258,0.11926527,0.011943458,0.00082213554,0.00044928215,0.078949906,0.72816265,0.0005896911,0.02811764,0.007339738,0.0021781465],"about_ca_topic_score_codex":0.0028587582,"about_ca_topic_score_gemma":0.01321916,"teacher_disagreement_score":0.7064945,"about_ca_system_score_codex":0.00020444387,"about_ca_system_score_gemma":0.002162978,"threshold_uncertainty_score":0.99944437},"labels":[],"label_agreement":null},{"id":"W1945388302","doi":"10.1186/1471-2288-6-27","title":"Does updating improve the methodological and reporting quality of systematic reviews?","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Canadian Institute for Energy Training","funders":"","keywords":"Checklist; Confidence interval; Quality Score; Systematic review; Medicine; MEDLINE; Quality (philosophy); Cochrane Library; Meta-analysis; Statistics; Medical physics; Psychology; Mathematics; Internal medicine; Operations management","score_opus":0.9896759570325111,"score_gpt":0.7738181885184264,"score_spread":0.21585776851408467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1945388302","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":[0.17217062,0.011152802,0.8011588,0.004105818,0.00069857197,0.004872567,0.0000070327924,0.000013368096,0.005820411],"genre_scores_gemma":[0.24439836,0.0007301484,0.7437073,0.00048709387,0.00076321384,0.00087264524,0.0000055818946,0.000027409224,0.009008271],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.03945702,0.88522834,0.053400017,0.0020047363,0.018924281,0.0009856027],"domain_scores_gemma":[0.01374613,0.94098306,0.034968086,0.006296094,0.0035108766,0.0004957726],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.96723586,0.00032278532,0.0117653385,0.00042453,0.0003835794,0.00032148339,0.003233339,0.0003813792,0.0052521788],"category_scores_gemma":[0.9913879,0.000085550564,0.0019028224,0.0019306497,0.0014361192,0.00011493066,0.0011114782,0.0010930762,0.00021497827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021530782,0.00041640157,0.2120521,0.11466032,0.00071144657,0.000101311794,0.0021832413,0.000021817124,0.016233074,0.4458447,0.036525577,0.1710347],"study_design_scores_gemma":[0.0011072827,0.0004619714,0.103092104,0.0065406254,0.00068547495,0.00032050943,0.018521694,0.014537749,0.0018219176,0.82706475,0.024965573,0.00088034204],"about_ca_topic_score_codex":0.00049024995,"about_ca_topic_score_gemma":0.00062566134,"teacher_disagreement_score":0.38122004,"about_ca_system_score_codex":0.000037711343,"about_ca_system_score_gemma":0.0003800168,"threshold_uncertainty_score":0.99565715},"labels":[],"label_agreement":null},{"id":"W1950366691","doi":"10.1186/s12874-015-0045-7","title":"The use of the Godin-Shephard Leisure-Time Physical Activity Questionnaire in oncology research: a systematic review","year":2015,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":339,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Concordia University","funders":"Concordia University","keywords":"Medicine; MEDLINE; Scale (ratio); Physical activity; Alternative medicine; Family medicine; Clinical psychology; Physical therapy; Pathology","score_opus":0.8632981202567224,"score_gpt":0.6646766439473891,"score_spread":0.19862147630933324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1950366691","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":[0.00008585553,0.98720497,0.00017428937,0.0036119518,0.0006126011,0.0079665715,0.000022512502,0.000030296787,0.00029097366],"genre_scores_gemma":[0.000044925382,0.9940903,0.00023240084,0.00012980911,0.000617555,0.0028480138,0.000013291456,0.00008227483,0.0019414239],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.7634559,0.22609141,0.001622318,0.0009521808,0.0064111617,0.0014669762],"domain_scores_gemma":[0.79199487,0.20006593,0.00078230567,0.0032595647,0.0027207485,0.0011765858],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1736662,0.0005153818,0.008900436,0.0006226457,0.0002923929,0.00004118086,0.002208122,0.0013990158,0.000104583705],"category_scores_gemma":[0.44886884,0.0002369659,0.0013093337,0.0036544905,0.0041660983,0.00007963181,0.00174263,0.00881413,0.00020708273],"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":[0.00020266442,0.00030398078,0.00001068112,0.6094832,0.00017294215,0.00013493355,0.00021408782,6.2427425e-8,0.0000013113942,0.0005637639,0.005957132,0.38295522],"study_design_scores_gemma":[0.0003152767,0.0004289037,0.000015306096,0.4573495,0.0006357623,0.00031790574,0.00006604853,0.000047262776,0.0000012836209,0.0002457861,0.5404457,0.00013125673],"about_ca_topic_score_codex":0.0018534001,"about_ca_topic_score_gemma":0.0059167193,"teacher_disagreement_score":0.53448856,"about_ca_system_score_codex":0.0020457865,"about_ca_system_score_gemma":0.025745435,"threshold_uncertainty_score":0.99989736},"labels":[],"label_agreement":null},{"id":"W1962297384","doi":"10.1186/1471-2288-1-4","title":"Determinants of patient recruitment in a multicenter clinical trials group: trends, seasonality and the effect of large studies","year":2001,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":34,"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 Institutes of Health; General Secretariat for Research and Technology; National Institute of Allergy and Infectious Diseases; ACT Government","keywords":"Clinical trial; Demography; Medicine; Multivariate analysis; Multivariate statistics; Quarter (Canadian coin); Popularity; Seasonality; Observational study; Sample size determination; Gerontology; Internal medicine; Psychology; Statistics; Geography","score_opus":0.9568173224074039,"score_gpt":0.8038091370733084,"score_spread":0.15300818533409555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1962297384","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":[0.98686856,0.005864276,0.00045267216,0.0040678135,0.00025038113,0.0023016364,0.000011480043,0.000008613052,0.00017458593],"genre_scores_gemma":[0.96754676,0.02422493,0.0068844263,0.0003309593,0.0002149307,0.00054972357,0.0000041954104,0.000020799189,0.00022326266],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.4796303,0.4973934,0.008781133,0.0018228637,0.0101296,0.0022427267],"domain_scores_gemma":[0.10144774,0.89558756,0.0005505495,0.0008136443,0.00087376556,0.0007267457],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6473979,0.00020281531,0.0034983535,0.00032321678,0.00008253682,0.000006223432,0.0005055236,0.0008713787,0.00034768714],"category_scores_gemma":[0.925647,0.00010032071,0.00051087135,0.000728228,0.006729505,0.000031003412,0.0012965883,0.0040956894,0.000005693464],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.037802886,0.0007125222,0.6866291,0.0014968198,0.00023249268,0.00016454153,0.00072104676,1.2834982e-7,0.000059585112,0.0025793351,0.00014681164,0.26945472],"study_design_scores_gemma":[0.11494509,0.029623657,0.79747736,0.0067436956,0.0005098899,0.00015486685,0.0049252766,0.004542745,0.0034212098,0.033419322,0.0038909307,0.00034595054],"about_ca_topic_score_codex":0.0003431147,"about_ca_topic_score_gemma":0.0038777546,"teacher_disagreement_score":0.39819416,"about_ca_system_score_codex":0.000096075906,"about_ca_system_score_gemma":0.00068938435,"threshold_uncertainty_score":0.9982019},"labels":[],"label_agreement":null},{"id":"W1964304172","doi":"10.1186/1471-2288-8-1","title":"An administrative data merging solution for dealing with missing data in a clinical registry: adaptation from ICD-9 to ICD-10","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":503,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Provincial Health Services Authority; University of British Columbia; University of Alberta; University of Calgary","funders":"Canadian Institutes of Health Research; Eli Lilly Canada; Fondation pour la Recherche Médicale; W. Garfield Weston Foundation; Eli Lilly and Company; University of Alberta; Government of Canada; Boston Scientific Corporation","keywords":"Missing data; Statistic; Medicine; Data mining; ICD-10; Computer science; Statistics; Mathematics; Machine learning","score_opus":0.9723130920307268,"score_gpt":0.759938338111273,"score_spread":0.21237475391945382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964304172","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048881914,0.00019444387,0.9358237,0.012150641,0.00042757337,0.0015665608,0.00023117683,0.00007511709,0.00064886286],"genre_scores_gemma":[0.111596406,0.00042511648,0.87953156,0.0024132745,0.0017925915,0.00026656064,0.0037520158,0.00003747765,0.00018501692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96901196,0.024323469,0.0021407744,0.0011733418,0.0019787536,0.0013717139],"domain_scores_gemma":[0.8529254,0.14005657,0.0006356674,0.0031067699,0.0008730555,0.002402494],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0977209,0.00018524987,0.000752144,0.00029160222,0.0013757895,0.000016937012,0.0018820786,0.0007870065,0.00081143645],"category_scores_gemma":[0.31546447,0.00014888716,0.000030295238,0.00044973064,0.0005912038,0.0004941663,0.0008171002,0.0027283619,0.000088896195],"study_design_candidate":"simulation_or_modeling","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":[0.018843856,0.0006287436,0.03813229,0.0021877042,0.000114754715,0.00020487922,0.02728314,0.00010327981,0.0002652163,0.0069801672,0.06581361,0.8394424],"study_design_scores_gemma":[0.004616961,0.0017753814,0.033516526,0.0020742533,0.000032062435,0.000021085656,0.010189259,0.860641,0.00001139617,0.0020475625,0.08474501,0.0003295165],"about_ca_topic_score_codex":0.007311806,"about_ca_topic_score_gemma":0.026596176,"teacher_disagreement_score":0.8605377,"about_ca_system_score_codex":0.00020554711,"about_ca_system_score_gemma":0.0113610625,"threshold_uncertainty_score":0.9999243},"labels":[],"label_agreement":null},{"id":"W1967430978","doi":"10.1186/1471-2288-12-29","title":"Ongoing monitoring of data clustering in multicenter studies","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"McGill University","funders":"National Institutes of Health; Canadian Institutes of Health Research; European Commission; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute for Health and Care Research","keywords":"Multicenter study; Data science; Cluster analysis; MEDLINE; Computer science; Medicine; Data mining; Artificial intelligence; Internal medicine; Political science; Randomized controlled trial","score_opus":0.9953393046782701,"score_gpt":0.8079204800939596,"score_spread":0.18741882458431058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967430978","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":[0.6142167,0.019901834,0.36104548,0.00095353817,0.0015190215,0.00078231527,0.0000067767,0.000005489265,0.0015688507],"genre_scores_gemma":[0.55563974,0.0006093338,0.44224378,0.000040712053,0.00050824985,0.00004022182,0.000002082854,0.00001088389,0.0009049846],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.522374,0.42893943,0.017063957,0.002169729,0.027406342,0.0020465693],"domain_scores_gemma":[0.15086952,0.83072627,0.0029976263,0.011265418,0.0029505312,0.0011906484],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8009474,0.0001685426,0.0034763021,0.00094186625,0.000088621695,0.000072266295,0.004677799,0.00017507323,0.0038006683],"category_scores_gemma":[0.8842636,0.00008245065,0.00035596697,0.0016425207,0.00044262147,0.00042886115,0.0035424514,0.00068239274,0.0006399142],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003956811,0.000103338054,0.8153802,0.00036955683,0.00014691408,0.000010951796,0.0028817018,0.000016391112,0.0003569155,0.0004255954,0.0034746188,0.17679426],"study_design_scores_gemma":[0.0027123843,0.000257006,0.68012977,0.002418367,0.00023887873,0.00008456319,0.10008728,0.104792275,0.0011458822,0.0077713323,0.099654056,0.0007082176],"about_ca_topic_score_codex":0.000097974334,"about_ca_topic_score_gemma":0.0005123,"teacher_disagreement_score":0.40178683,"about_ca_system_score_codex":0.00005963238,"about_ca_system_score_gemma":0.00024663383,"threshold_uncertainty_score":0.99711},"labels":[],"label_agreement":null},{"id":"W1967747089","doi":"10.1186/s12874-015-0016-z","title":"Exploring physician specialist response rates to web-based surveys","year":2015,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":1003,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates; Alberta Innovates - Health Solutions","keywords":"Family medicine; Medicine; Health care; Specialty; Survey data collection; Descriptive statistics; Payment; Medical education; Business","score_opus":0.9375642504164767,"score_gpt":0.6565429842045365,"score_spread":0.28102126621194023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967747089","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":[0.8400149,0.00018312436,0.13256991,0.016652972,0.0025443188,0.00061793765,0.000014193201,0.00019357899,0.0072091045],"genre_scores_gemma":[0.6539276,0.00032167617,0.31867966,0.0071934485,0.008239619,0.0013511373,0.00003524436,0.00017141583,0.01008017],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.23867835,0.7545015,0.0005917035,0.00084951683,0.00353311,0.0018458087],"domain_scores_gemma":[0.5405221,0.45570523,0.000072109615,0.0005488195,0.0009627598,0.002188991],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.79800045,0.00024497017,0.00078478636,0.000968045,0.00084669585,0.00008077112,0.0015178918,0.0005417675,0.0012068881],"category_scores_gemma":[0.8998657,0.00021783661,0.00016727019,0.0026611348,0.002942242,0.00024362408,0.00039662336,0.0013174161,0.0011638404],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.26190042,0.0016016824,0.085625514,0.00016329119,0.00021476489,0.0017633892,0.06847332,0.00022248215,0.014027358,0.04173947,0.116044596,0.40822372],"study_design_scores_gemma":[0.0035426698,0.0015548622,0.31478125,0.00015838325,0.000019482026,0.000006135834,0.023782436,0.00024290217,0.0078124558,0.008577905,0.6387432,0.0007782923],"about_ca_topic_score_codex":0.003935582,"about_ca_topic_score_gemma":0.030161278,"teacher_disagreement_score":0.52269864,"about_ca_system_score_codex":0.00042282426,"about_ca_system_score_gemma":0.014492725,"threshold_uncertainty_score":0.9997712},"labels":[],"label_agreement":null},{"id":"W1967805982","doi":"10.1186/1471-2288-7-22","title":"Predictors of locating women six to eight years after contact: internet resources at recruitment may help to improve response rates in longitudinal research","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social 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":true,"ca_institutions":"St. Michael's Hospital; Institute for Work & Health; University Health Network; University of Toronto; Women's College Hospital","funders":"Canadian Institutes of Health Research; University of Toronto; Women's College Hospital; Toronto Rehabilitation Institute; Ontario Ministry of Health and Long-Term Care","keywords":"The Internet; Logistic regression; Medicine; Demography; Telephone interview; Internet access; Sample (material); Telephone call; Post-hoc analysis; Family medicine; Computer science; World Wide Web; Telecommunications","score_opus":0.6520594335687301,"score_gpt":0.6129777709830496,"score_spread":0.039081662585680466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967805982","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":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98822576,0.00038305827,0.0048101502,0.003251381,0.0007415382,0.0018407393,0.000017123271,0.00003361154,0.0006966304],"genre_scores_gemma":[0.9688806,0.00007787158,0.02174744,0.0003559293,0.000545216,0.0010077202,0.000003375494,0.00004064268,0.0073412103],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.4374075,0.5454534,0.0022438087,0.0021735937,0.007201526,0.005520162],"domain_scores_gemma":[0.61717963,0.3798515,0.00010592608,0.00055374845,0.0006840984,0.0016250736],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.72074556,0.00025179016,0.00092078233,0.0025073674,0.00034277685,0.000044523465,0.0015612468,0.0008850578,0.003195575],"category_scores_gemma":[0.7035643,0.00022414564,0.00011946167,0.003190163,0.002600646,0.00010457676,0.0016712479,0.0019156847,0.00023850382],"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":[0.29681823,0.00038117988,0.48689386,0.0001157023,0.00010732774,0.00091874483,0.15607516,0.000004352403,0.017899485,0.0010287673,0.0028668065,0.036890384],"study_design_scores_gemma":[0.0009590169,0.0025211356,0.8995686,0.00025817277,0.0000049887194,0.0000072951584,0.025045933,0.0000075701105,0.010326851,0.00051140995,0.06055362,0.00023541083],"about_ca_topic_score_codex":0.007395943,"about_ca_topic_score_gemma":0.065418445,"teacher_disagreement_score":0.41267473,"about_ca_system_score_codex":0.0017635284,"about_ca_system_score_gemma":0.0025111164,"threshold_uncertainty_score":0.9992139},"labels":[],"label_agreement":null},{"id":"W1968400162","doi":"10.1186/1471-2288-11-65","title":"Evaluating treatments in health care: The instability of a one-legged stool","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"South Health Campus; University of Calgary; Alberta Health Services","funders":"Alberta Children's Hospital Foundation; Alberta Children's Hospital Research Institute; Children's Hospital Foundation","keywords":"Randomized controlled trial; Context (archaeology); Health care; External validity; Medicine; Population; Alternative medicine; Scientific evidence; Mental health; Evidence-based medicine; Psychology; Psychiatry; Social psychology; Political science; Surgery; Environmental health","score_opus":0.9948415126318051,"score_gpt":0.7974380738501854,"score_spread":0.1974034387816197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968400162","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":[0.89197713,0.0049338825,0.08752857,0.0027528536,0.00028336488,0.0030757466,0.000010512966,0.000005403769,0.009432525],"genre_scores_gemma":[0.7045003,0.00013400616,0.29382637,0.00029677726,0.00006320017,0.00029112792,0.0000029763937,0.0000112775615,0.00087397656],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.16840608,0.7889206,0.0147216,0.001713325,0.025106322,0.0011320774],"domain_scores_gemma":[0.4038076,0.5756023,0.0052895555,0.009462711,0.0047140475,0.0011238174],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8352882,0.000185738,0.003777237,0.00062036264,0.00019877264,0.000051629326,0.0032319655,0.00019696573,0.022736207],"category_scores_gemma":[0.8552974,0.00007461449,0.00079465593,0.002603351,0.00087177404,0.00007577613,0.0006041936,0.0008046923,0.00039931497],"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":[0.0002947481,0.00055252685,0.14201945,0.0005483142,0.0002213416,0.000010033832,0.029768378,0.0000121808625,0.000119115175,0.012214533,0.0019790262,0.8122603],"study_design_scores_gemma":[0.0032174077,0.0029496122,0.797921,0.00045425064,0.00015273906,0.000028102078,0.051682696,0.010689543,0.00040639518,0.121891014,0.010256545,0.00035070904],"about_ca_topic_score_codex":0.002731909,"about_ca_topic_score_gemma":0.0063574053,"teacher_disagreement_score":0.8119096,"about_ca_system_score_codex":0.00018295097,"about_ca_system_score_gemma":0.003083669,"threshold_uncertainty_score":0.97815716},"labels":[],"label_agreement":null},{"id":"W1968444381","doi":"10.1186/1471-2288-14-4","title":"Modeling trajectories of perceived leg exertion during maximal cycle ergometer exercise in children and adolescents","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Perceived exertion; Rating of perceived exertion; Exertion; Physical therapy; Cycle ergometer; Work (physics); Interquartile range; Mathematics; Statistics; Physical medicine and rehabilitation; Psychology; Medicine; Heart rate","score_opus":0.10226941368275179,"score_gpt":0.4261101832676196,"score_spread":0.32384076958486785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968444381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836369,0.000263925,0.015102903,0.00021958076,0.000049389397,0.00064163964,8.013637e-7,0.000019136345,0.000065691136],"genre_scores_gemma":[0.9805028,0.00039249368,0.018873652,0.000017499979,0.00010623129,0.000046028603,0.0000073265924,0.000017364493,0.000036595447],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943739,0.0034577423,0.0004599484,0.00037776443,0.00091142056,0.00041922962],"domain_scores_gemma":[0.99697584,0.0022543082,0.00003529985,0.00024150837,0.00016387968,0.00032917794],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011095831,0.00011542718,0.0005123885,0.00047613026,0.00006224446,0.0000056607,0.00011855995,0.0002779248,0.00013697645],"category_scores_gemma":[0.025527446,0.000090026406,0.00008598847,0.00024656687,0.00051077444,0.00006121355,0.00011057584,0.0006102745,0.0000052353653],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041395286,0.0005654043,0.76393306,0.006686794,0.000044045937,0.0000070296255,0.0022146825,0.00029082576,0.12627271,0.0007577401,0.000007886718,0.09508027],"study_design_scores_gemma":[0.0022529194,0.000286399,0.9660589,0.0016829057,0.000011372607,0.000013865656,0.00031377465,0.027711611,0.0004562532,0.0011324763,0.0000011328217,0.00007836129],"about_ca_topic_score_codex":0.0005542952,"about_ca_topic_score_gemma":0.00011128502,"teacher_disagreement_score":0.20212585,"about_ca_system_score_codex":0.000046222118,"about_ca_system_score_gemma":0.00013539221,"threshold_uncertainty_score":0.982681},"labels":[],"label_agreement":null},{"id":"W1969814135","doi":"10.1186/1471-2288-12-97","title":"Validation of colorectal cancer surgery data from administrative data sources","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Environment and Protected Areas; University of Alberta; Health Sciences Centre; Alberta Health Services","funders":"","keywords":"Medicine; Colorectal cancer; Cancer registry; Stage (stratigraphy); Cancer; Disease; Emergency medicine; Internal medicine","score_opus":0.9320956486445319,"score_gpt":0.6699269667370584,"score_spread":0.26216868190747344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969814135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97198015,0.005844778,0.01862926,0.001584517,0.0004739746,0.00029733128,0.00053603086,0.000024909195,0.0006290446],"genre_scores_gemma":[0.93663293,0.0011737765,0.05831427,0.00025547095,0.0014577045,0.00003958313,0.0020207413,0.000018384138,0.00008712429],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9889519,0.006822932,0.00057840545,0.00058710243,0.0023177539,0.0007419098],"domain_scores_gemma":[0.9268304,0.06972257,0.00021288141,0.0017617036,0.00046527016,0.001007195],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038891185,0.00012964585,0.00070989504,0.00017836102,0.00009040847,0.000012014682,0.0012179811,0.0003079822,0.0049570818],"category_scores_gemma":[0.15912504,0.000100492936,0.000056003075,0.00047138313,0.00090516557,0.00036222962,0.0015164347,0.0007495899,0.000048162427],"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":[0.0024704428,0.00021999021,0.9100812,0.00019401735,0.00022595953,0.000055312692,0.00062649976,0.0000010412552,0.005826794,0.00024205317,0.041656226,0.038400427],"study_design_scores_gemma":[0.0024917836,0.0007873565,0.826207,0.0017364628,0.00047713052,0.00023936956,0.008614244,0.004575023,0.1119528,0.0013506149,0.041031916,0.000536328],"about_ca_topic_score_codex":0.0075809597,"about_ca_topic_score_gemma":0.0020020916,"teacher_disagreement_score":0.12023386,"about_ca_system_score_codex":0.00007853325,"about_ca_system_score_gemma":0.0041813054,"threshold_uncertainty_score":0.99902767},"labels":[],"label_agreement":null},{"id":"W1971181039","doi":"10.1186/1471-2288-13-147","title":"Quantitative summaries of treatment effect estimates obtained with network meta-analysis of survival curves to inform decision-making","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBI Group (Canada); Toronto East General Hospital","funders":"","keywords":"Meta-analysis; MEDLINE; Computer science; Data science; Medicine; Psychology; Management science; Political science; Internal medicine","score_opus":0.46761595238485654,"score_gpt":0.5472156030388824,"score_spread":0.07959965065402586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971181039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36617157,0.0039370395,0.61891836,0.0029791407,0.00022410043,0.004054751,0.000023755489,0.00007776839,0.003613554],"genre_scores_gemma":[0.47955477,0.00048297478,0.51796216,0.00035248217,0.00006540096,0.0007004035,0.00003661662,0.000033193057,0.00081198174],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9925773,0.0040411884,0.00073420745,0.0003905774,0.0017071787,0.0005495259],"domain_scores_gemma":[0.8708932,0.12688485,0.00020927428,0.0006142586,0.0009194378,0.0004789839],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014696993,0.00022364309,0.00271819,0.0009386181,0.00010129102,0.000013658952,0.00023947623,0.00013912274,0.0050168475],"category_scores_gemma":[0.07252658,0.00011910566,0.00058840774,0.00252079,0.0005750331,0.000043979286,0.00021865472,0.00026060126,0.0000313895],"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":[0.038325064,0.0013394882,0.0646514,0.0050911284,0.5169472,0.00055363483,0.003344386,0.012298289,0.0019641872,0.026811596,0.009210473,0.31946316],"study_design_scores_gemma":[0.012651004,0.16987953,0.14658743,0.0035839328,0.49204436,0.00039142062,0.010051892,0.124740645,0.010724082,0.012040307,0.01548384,0.0018215672],"about_ca_topic_score_codex":0.001692759,"about_ca_topic_score_gemma":0.004256031,"teacher_disagreement_score":0.3176416,"about_ca_system_score_codex":0.00011936962,"about_ca_system_score_gemma":0.00050551246,"threshold_uncertainty_score":0.9958927},"labels":[],"label_agreement":null},{"id":"W1972930488","doi":"10.1186/1471-2288-13-106","title":"Consensus-based recommendations for investigating clinical heterogeneity in systematic reviews","year":2013,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","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":"Ottawa Hospital; University of Ottawa","funders":"U.S. National Library of Medicine","keywords":"Systematic review; Study heterogeneity; MEDLINE; Delphi method; Meta-analysis; Psychology; Intervention (counseling); Delphi; Medicine; Computer science; Artificial intelligence; Pathology; Nursing","score_opus":0.9964621329312239,"score_gpt":0.8222049195440932,"score_spread":0.17425721338713063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972930488","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":[0.000010049496,0.8375575,0.14036529,0.001316647,0.0009672926,0.019496959,0.00004402715,0.000010099665,0.00023212697],"genre_scores_gemma":[3.9385407e-7,0.6436638,0.344404,0.00044147673,0.00035408596,0.0095376065,0.000077253644,0.00004922336,0.0014721488],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.09754024,0.8216319,0.06320985,0.0035728565,0.012512464,0.0015327061],"domain_scores_gemma":[0.019102877,0.9461414,0.019738078,0.009096866,0.003959722,0.0019610133],"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":[0.9369053,0.001008978,0.04687861,0.0028275757,0.00035153277,0.00068262476,0.007969256,0.0020202654,0.011488153],"category_scores_gemma":[0.9874949,0.00045269568,0.01141733,0.0049417973,0.0013425509,0.00008988258,0.00093134015,0.003497547,0.008678887],"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":[0.0000033645883,0.00009489266,0.00016516462,0.22324502,0.00019324177,0.000006734055,0.00002652966,6.6221463e-7,6.6653236e-8,0.0009864329,0.111672476,0.6636054],"study_design_scores_gemma":[0.00032280665,0.00012824804,0.000005180962,0.07962124,0.00065398036,0.00003891254,0.00011537066,0.0047390307,1.4453789e-7,0.0040639043,0.90997803,0.0003331289],"about_ca_topic_score_codex":0.000070014205,"about_ca_topic_score_gemma":0.0010416548,"teacher_disagreement_score":0.7983056,"about_ca_system_score_codex":0.0002797941,"about_ca_system_score_gemma":0.0067614075,"threshold_uncertainty_score":0.99979246},"labels":[],"label_agreement":null},{"id":"W1973165502","doi":"10.1186/1471-2288-10-97","title":"Methods of competing risks analysis of end-stage renal disease and mortality among people with diabetes","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Ministry of Health, Saskatchewan","keywords":"Diabetes mellitus; End stage renal disease; Medicine; Disease; Intensive care medicine; MEDLINE; Stage (stratigraphy); Gerontology; Environmental health; Internal medicine; Political science; Endocrinology","score_opus":0.4136505964496597,"score_gpt":0.5792338091429774,"score_spread":0.16558321269331772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973165502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9535914,0.0003115402,0.043885242,0.0002611617,0.00005484185,0.00046896844,0.000038139202,0.000027916542,0.0013607867],"genre_scores_gemma":[0.87518847,0.00008735594,0.12435885,0.000031957643,0.00007852222,0.00006416637,0.00006747281,0.000018178427,0.00010503612],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98826724,0.008017572,0.0006621877,0.0005744705,0.0018478117,0.000630729],"domain_scores_gemma":[0.9678421,0.02959039,0.00024988278,0.00085242314,0.0004176593,0.0010475608],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03454442,0.0001841348,0.0012686793,0.0008856884,0.00008437994,0.000014986097,0.0003367044,0.00017989647,0.0038775713],"category_scores_gemma":[0.056235466,0.0001337905,0.00021360836,0.0015855598,0.0033248991,0.000069231915,0.00047358454,0.00097083976,9.335372e-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":[0.0005196898,0.00024410496,0.97731483,0.0016162662,0.0019508008,0.00005319108,0.00022803382,0.000041021034,0.005017019,0.0064339004,0.000033345717,0.006547781],"study_design_scores_gemma":[0.001101891,0.0002646883,0.9733503,0.00013541654,0.0022690208,9.646354e-7,0.00088489073,0.019613493,0.0014479341,0.0007292378,0.00009440625,0.00010776409],"about_ca_topic_score_codex":0.001760334,"about_ca_topic_score_gemma":0.006357756,"teacher_disagreement_score":0.08047361,"about_ca_system_score_codex":0.000028395489,"about_ca_system_score_gemma":0.0012643927,"threshold_uncertainty_score":0.9993875},"labels":[],"label_agreement":null},{"id":"W1980766142","doi":"10.1186/1471-2288-8-36","title":"The changing causal foundations of cancer-related symptom clustering during the final month of palliative care: A longitudinal study","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Capital District Health Authority; Alberta Cancer Foundation; University of Alberta","funders":"","keywords":"Palliative care; Anxiety; Quality of life (healthcare); Depression (economics); Medicine; Nausea; Clinical psychology; Cancer; Psychology; Psychiatry; Internal medicine","score_opus":0.4789386243767834,"score_gpt":0.544799737576911,"score_spread":0.06586111320012761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980766142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9876188,0.0034163725,0.006295812,0.0010647348,0.00044117577,0.00088670105,0.0000100264415,0.00002442429,0.00024196359],"genre_scores_gemma":[0.9968519,0.001309632,0.0007930584,0.000019780085,0.00024037228,0.00029000454,0.0000052531677,0.000019777042,0.00047021746],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9917177,0.004836925,0.00059318193,0.000342363,0.0018525181,0.0006573154],"domain_scores_gemma":[0.98116684,0.017157545,0.00016140555,0.00050911325,0.0007836998,0.00022141302],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008714687,0.00014149497,0.00053259113,0.00026088586,0.00069233496,0.0000079394,0.0004448171,0.00015396353,0.0002701096],"category_scores_gemma":[0.012814593,0.00008167146,0.00014642677,0.0010342548,0.0012515449,0.000029773926,0.0004297541,0.0009752236,0.0000022461704],"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":[0.0021498087,0.00033003883,0.8852454,0.00077457033,0.0006969765,0.00021149329,0.09648227,0.00010317394,0.00047344973,0.0007349613,0.000076396915,0.012721469],"study_design_scores_gemma":[0.0030742895,0.001225694,0.93745214,0.00041179234,0.00014880486,0.00006607424,0.05413594,0.0018421817,0.0010012377,0.00012351784,0.0003964353,0.000121895464],"about_ca_topic_score_codex":0.011599438,"about_ca_topic_score_gemma":0.0733147,"teacher_disagreement_score":0.06171526,"about_ca_system_score_codex":0.00025866606,"about_ca_system_score_gemma":0.0019552587,"threshold_uncertainty_score":0.99550086},"labels":[],"label_agreement":null},{"id":"W1981125723","doi":"10.1186/1471-2288-12-39","title":"Measuring sidewalk distances using Google Earth","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"Canadian Institutes of Health Research; Ontario Ministry of Research and Innovation; Heart and Stroke Foundation of Canada","keywords":"Computer science; MEDLINE; Data science; Information retrieval; Biology","score_opus":0.8103782826320634,"score_gpt":0.597717910371374,"score_spread":0.21266037226068935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981125723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88966227,0.0029304908,0.08075955,0.0006992284,0.00089289335,0.000279412,0.000002948467,0.000081423575,0.024691805],"genre_scores_gemma":[0.9438635,0.00015136211,0.052832104,0.00008699282,0.0017513938,0.000020190257,0.0000023149357,0.000013836384,0.0012782819],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9786038,0.016264798,0.000392221,0.00036610165,0.0028010171,0.0015720524],"domain_scores_gemma":[0.9794839,0.018727845,0.00006738222,0.0003068945,0.00025004477,0.0011639358],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07411317,0.000112430025,0.00036440938,0.00016204883,0.0008864019,0.00004865184,0.000731638,0.00033105662,0.0043136966],"category_scores_gemma":[0.061930463,0.00009261943,0.000113418384,0.00072510564,0.0022894333,0.00039060984,0.0001374212,0.00080230454,0.000087148874],"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":[0.0001243731,0.00020509164,0.9245969,0.00011897059,0.000024055846,0.000020443542,0.007311796,0.0000018643824,0.0010850672,0.027204493,0.000307349,0.038999617],"study_design_scores_gemma":[0.0015938159,0.00017448096,0.5542477,0.00036880243,0.00006776062,0.000010749575,0.02631232,0.00056321296,0.005927827,0.0500924,0.35968605,0.0009549173],"about_ca_topic_score_codex":0.008216245,"about_ca_topic_score_gemma":0.029338153,"teacher_disagreement_score":0.37034923,"about_ca_system_score_codex":0.00011936451,"about_ca_system_score_gemma":0.0018167978,"threshold_uncertainty_score":0.9983881},"labels":[],"label_agreement":null},{"id":"W1982631664","doi":"10.1186/1471-2288-8-35","title":"On reporting results from randomized controlled trials with recurrent events","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Vancouver Coastal Health Research Institute; Vancouver Coastal Health","funders":"","keywords":"Randomized controlled trial; Poisson regression; Event (particle physics); Medicine; Outcome (game theory); Statistics; Sample size determination; Mathematics; Surgery; Population","score_opus":0.9821096590764797,"score_gpt":0.7397940935575624,"score_spread":0.2423155655189173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982631664","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":[0.3660893,0.0027750107,0.59656763,0.006464582,0.0013953308,0.008330128,0.000037699137,0.000022517623,0.018317817],"genre_scores_gemma":[0.49913943,0.0017615324,0.4538889,0.0011277366,0.0019452195,0.002619535,0.00009649838,0.000070210845,0.039350953],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.027793113,0.869072,0.06061316,0.0025757323,0.03892314,0.0010228379],"domain_scores_gemma":[0.0024431176,0.9551264,0.03248863,0.004846131,0.0039757714,0.001119958],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.97344005,0.00045126193,0.039565954,0.0012519174,0.00047806976,0.00018537685,0.0028752733,0.000438815,0.026816342],"category_scores_gemma":[0.99858624,0.00014857945,0.0065247254,0.0018829469,0.001018073,0.00008969565,0.00036047978,0.0014127914,0.002221551],"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":[0.7644461,0.0004791896,0.0019303251,0.000056128214,0.003724677,0.00077745237,0.0018320809,0.00008480643,0.000080427555,0.008935691,0.14514796,0.072505176],"study_design_scores_gemma":[0.7180854,0.0011040387,0.0028896788,0.0009768445,0.0012164391,0.00025870773,0.0012046375,0.02867327,0.00012525049,0.22365192,0.021197923,0.000615901],"about_ca_topic_score_codex":0.0002746647,"about_ca_topic_score_gemma":0.0002580357,"teacher_disagreement_score":0.21471623,"about_ca_system_score_codex":0.00007503065,"about_ca_system_score_gemma":0.0021975988,"threshold_uncertainty_score":0.99855536},"labels":[],"label_agreement":null},{"id":"W1982740710","doi":"10.1186/1471-2288-12-3","title":"Comparing multiple competing interventions in the absence of randomized trials using clinical risk-benefit analysis","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa; Health Canada; Western University","funders":"University of Ottawa; Consejo Nacional de Ciencia y Tecnología; Canada Research Chairs; Heart and Stroke Foundation of Canada","keywords":"Medicine; Ximelagatran; Fondaparinux; Randomized controlled trial; Orthopedic surgery; Psychological intervention; Placebo; Clinical trial; Warfarin; Physical therapy; Thrombosis; Surgery; Internal medicine; Dabigatran; Venous thromboembolism","score_opus":0.8530265573624219,"score_gpt":0.656739807391179,"score_spread":0.19628674997124296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982740710","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":[0.7737567,0.00228692,0.22154765,0.00046566705,0.0002479196,0.0012372313,0.0000031654558,0.000012107538,0.0004426863],"genre_scores_gemma":[0.90808,0.001825667,0.0893509,0.00016799725,0.00041802877,0.0001182912,0.000013378545,0.000011272511,0.000014503852],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.87138313,0.12142633,0.0037145526,0.00045254998,0.002055632,0.0009677878],"domain_scores_gemma":[0.38790268,0.6087427,0.0012034967,0.0010000353,0.0004978248,0.0006532381],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4651789,0.00014349708,0.0044566654,0.00070904277,0.00014446635,0.000016861946,0.00050259987,0.0002319267,0.00078726915],"category_scores_gemma":[0.5886618,0.00008552627,0.0017624063,0.0013645012,0.0010421908,0.00005492954,0.00041547982,0.0012133424,0.000013336286],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005739121,0.0016332809,0.97593147,0.00033734113,0.0017574315,0.000011484713,0.0014461739,0.0002053314,0.000044444994,0.0053043505,0.00018888932,0.0074006887],"study_design_scores_gemma":[0.0515497,0.00019702624,0.88946795,0.00090725283,0.0028901251,0.000011623115,0.0041413,0.049591154,0.000048793252,0.0008498433,0.00022587126,0.000119374],"about_ca_topic_score_codex":0.005967921,"about_ca_topic_score_gemma":0.0038919384,"teacher_disagreement_score":0.4873164,"about_ca_system_score_codex":0.00006245425,"about_ca_system_score_gemma":0.00023620923,"threshold_uncertainty_score":0.9021751},"labels":[],"label_agreement":null},{"id":"W1985969598","doi":"10.1186/1471-2288-11-21","title":"Comparing methods to estimate treatment effects on a continuous outcome in multicentre randomized controlled trials: A simulation study","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":70,"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; Health Sciences Centre; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Intraclass correlation; Estimator; Randomized controlled trial; Type I and type II errors; Context (archaeology); Confidence interval; Statistical power; Generalized estimating equation; Random effects model; Medicine; Gee; Sample size determination; Point estimation; Observational study; Standard error; Mathematics; Outcome (game theory); Meta-analysis; Surgery; Internal medicine","score_opus":0.8018225963297307,"score_gpt":0.692509018615857,"score_spread":0.10931357771387373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985969598","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":[0.079454444,0.00007718521,0.90772223,0.000121569945,0.0003974609,0.011134475,0.0000022123725,0.000079089405,0.001011333],"genre_scores_gemma":[0.23414478,0.000008633836,0.7630287,0.00006404176,0.000109330285,0.0025242823,0.0000010391906,0.000032884465,0.00008630854],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.65842754,0.3341678,0.003563189,0.00094181515,0.0016972995,0.0012023576],"domain_scores_gemma":[0.21859674,0.7792173,0.00045258357,0.0006316925,0.00033203105,0.0007696495],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30883852,0.0004459922,0.009668497,0.00091050565,0.00013484305,0.000050239505,0.0005227557,0.00035370543,0.0007166909],"category_scores_gemma":[0.9124405,0.00025470712,0.00059907016,0.0005765499,0.00032677405,0.0000402219,0.00024482934,0.0008790448,0.000048308368],"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":[0.39683133,0.0042139464,0.014476161,0.00035976135,0.0008173555,0.000486405,0.009397991,0.000061924686,0.000113842514,0.12748225,0.00001898414,0.44574004],"study_design_scores_gemma":[0.4441514,0.003407827,0.0049521243,0.00044354235,0.0005789171,0.0000057599445,0.0011393232,0.19852148,0.0005423502,0.34588066,0.000015996726,0.0003606115],"about_ca_topic_score_codex":0.00083199266,"about_ca_topic_score_gemma":0.0009040222,"teacher_disagreement_score":0.60360193,"about_ca_system_score_codex":0.00026978904,"about_ca_system_score_gemma":0.00036755978,"threshold_uncertainty_score":0.9999905},"labels":[],"label_agreement":null},{"id":"W1988453884","doi":"10.1186/1471-2288-12-51","title":"An optimal search filter for retrieving systematic reviews and meta-analyses","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":152,"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; Western University","funders":"McMaster University","keywords":"CINAHL; Systematic review; Filter (signal processing); Computer science; MEDLINE; Information retrieval; Data mining; Set (abstract data type); Sensitivity (control systems); Medicine; Psychological intervention; Engineering; Nursing","score_opus":0.9946120414367352,"score_gpt":0.7891043170409874,"score_spread":0.20550772439574783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988453884","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":[0.010009097,0.053433172,0.9290701,0.0012764788,0.00026686784,0.0051253745,0.00001697324,0.0000104876035,0.00079145754],"genre_scores_gemma":[0.07913811,0.0010281169,0.90362376,0.0009993677,0.0009352872,0.002645931,0.000018762152,0.000058363836,0.011552319],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.31260628,0.6453647,0.016939916,0.0022398105,0.020783924,0.0020653885],"domain_scores_gemma":[0.17691404,0.8012752,0.004041494,0.009081469,0.005097985,0.0035898262],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9063718,0.000489668,0.014014972,0.0012983211,0.00047251015,0.0007424314,0.0039353645,0.00046249968,0.040991914],"category_scores_gemma":[0.9152483,0.00019414423,0.003576945,0.0024163784,0.0006950265,0.0005754433,0.0006883946,0.0009346783,0.0016782728],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001141475,0.0021316556,0.022662207,0.18090233,0.03612942,0.00009303441,0.018366732,0.0001919381,0.006548239,0.09066202,0.48153234,0.15963861],"study_design_scores_gemma":[0.0037817266,0.003653973,0.006799529,0.0030089982,0.07799674,0.0013919743,0.030368343,0.24634698,0.0034965705,0.03094785,0.5885427,0.0036645874],"about_ca_topic_score_codex":0.0000380606,"about_ca_topic_score_gemma":0.000059789705,"teacher_disagreement_score":0.24615505,"about_ca_system_score_codex":0.00006135529,"about_ca_system_score_gemma":0.00043496583,"threshold_uncertainty_score":0.999099},"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":"W1989853314","doi":"10.1186/1471-2288-9-5","title":"Measuring agreement of administrative data with chart data using prevalence unadjusted and adjusted kappa","year":2009,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":177,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Calgary General Hospital; Alberta Bone and Joint Health Institute; University of Calgary","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale","keywords":"Kappa; Cohen's kappa; Statistics; Medicine; Sampling (signal processing); Sample size determination; Sample (material); Mathematics; Computer science","score_opus":0.9684346225908497,"score_gpt":0.6570201568897845,"score_spread":0.3114144657010651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989853314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5973017,0.002872126,0.3907014,0.0053936136,0.00027112686,0.001746694,0.0002083691,0.000032118918,0.0014728119],"genre_scores_gemma":[0.73024946,0.00073992024,0.2682155,0.00023268219,0.00021544792,0.0000145444865,0.000053886717,0.000012697442,0.0002658691],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9596533,0.023688285,0.0015916175,0.002099676,0.012024033,0.00094307074],"domain_scores_gemma":[0.9358465,0.05494029,0.00050868525,0.0059418636,0.0018305515,0.00093208445],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18285584,0.00022656185,0.00080535054,0.000405469,0.00026327002,0.000096260424,0.0057533225,0.00022798835,0.0011884006],"category_scores_gemma":[0.24845958,0.00014285053,0.000038199338,0.001287191,0.0016291391,0.00050303305,0.0025977402,0.00082962844,0.000019816522],"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":[0.0055043017,0.0022120813,0.13044031,0.0014943552,0.000405046,0.00030232256,0.0029590833,0.0002245794,0.02797928,0.0070339725,0.01093176,0.8105129],"study_design_scores_gemma":[0.0092830425,0.009673474,0.6395493,0.0043789656,0.00041933043,0.000432117,0.022421196,0.24415717,0.011662184,0.040653888,0.01580456,0.0015647456],"about_ca_topic_score_codex":0.0002220004,"about_ca_topic_score_gemma":0.0011910191,"teacher_disagreement_score":0.80894816,"about_ca_system_score_codex":0.00007229082,"about_ca_system_score_gemma":0.0023064837,"threshold_uncertainty_score":0.9997246},"labels":[],"label_agreement":null},{"id":"W1990368073","doi":"10.1186/1471-2288-12-111","title":"Investigating clinical heterogeneity in systematic reviews: a methodologic review of guidance in the literature","year":2012,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":226,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; University of Toronto; Hospital for Sick Children; University of Ottawa","funders":"","keywords":"Systematic review; MEDLINE; CINAHL; Study heterogeneity; Protocol (science); Clinical trial; Medicine; Meta-analysis; Psychology; Alternative medicine; Psychological intervention; Pathology; Nursing; Political science","score_opus":0.9933136472504177,"score_gpt":0.804038130845693,"score_spread":0.18927551640472473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990368073","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":[0.000008515306,0.97250533,0.013141722,0.00047453467,0.00057641946,0.012710781,0.000017272287,0.000004462138,0.0005609646],"genre_scores_gemma":[0.0000014933923,0.8602348,0.13458647,0.0011854558,0.00041385484,0.0032416899,0.00002675012,0.000035262114,0.0002742149],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.018876191,0.8924771,0.06483344,0.0027531309,0.019534662,0.0015255098],"domain_scores_gemma":[0.016095676,0.939724,0.026731955,0.0135806035,0.0028295754,0.0010381801],"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":[0.98055434,0.0011375365,0.058565322,0.0024290793,0.00012974316,0.0002896066,0.01611515,0.0021047064,0.0032556062],"category_scores_gemma":[0.98727274,0.00039828185,0.0106032295,0.014508544,0.0014827158,0.00021104442,0.0017424093,0.00710677,0.0015456803],"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":[0.0000020652114,0.00009646996,0.0005615427,0.64259565,0.00009825917,0.000031360127,0.0002232492,6.192201e-8,5.3027883e-8,0.0011398431,0.0041415044,0.35110995],"study_design_scores_gemma":[0.000101883365,0.00006492716,0.00009341751,0.5393328,0.00067237846,0.00020858595,0.000113822134,0.00003363115,4.8897167e-8,0.0028195458,0.45633987,0.00021910884],"about_ca_topic_score_codex":0.000039173512,"about_ca_topic_score_gemma":0.00038095782,"teacher_disagreement_score":0.45219836,"about_ca_system_score_codex":0.0001832127,"about_ca_system_score_gemma":0.0026973903,"threshold_uncertainty_score":0.99984694},"labels":[],"label_agreement":null},{"id":"W1990758640","doi":"10.1186/1471-2288-12-115","title":"Predicting waist circumference from body mass index","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Diabetes, Cardiovascular Risks, and Lipoproteins","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Purdue Pharma (Canada)","funders":"Sanofi","keywords":"Waist; Medicine; National Health and Nutrition Examination Survey; Body mass index; Overweight; Abdominal obesity; Circumference; Demography; Obesity; Population; Gerontology; Internal medicine; Environmental health; Mathematics","score_opus":0.4017367060840137,"score_gpt":0.4981967469124098,"score_spread":0.0964600408283961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990758640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72219324,0.007307744,0.25476182,0.0009700682,0.0013379867,0.00090252905,0.000016969654,0.00020060457,0.012309051],"genre_scores_gemma":[0.9438301,0.0005497894,0.049540587,0.00042732345,0.0046767453,0.0002052413,0.000056200766,0.00006150326,0.0006525564],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9812784,0.011804862,0.0006264707,0.0006849961,0.003758136,0.0018471229],"domain_scores_gemma":[0.9732384,0.022917211,0.00009197227,0.0011449802,0.00041506722,0.0021923413],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04216391,0.0002572892,0.0011498036,0.00038505095,0.00022446408,0.000032165703,0.0005862809,0.0007739453,0.0038970488],"category_scores_gemma":[0.13691379,0.00020669376,0.00038645012,0.00059659174,0.0008488622,0.00014921362,0.00041252872,0.0023926292,0.0005064406],"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":[0.00046881885,0.00028460746,0.5616882,0.0003144901,0.00048249628,0.00016452516,0.00044478275,0.0000010953003,0.002636441,0.0008715234,0.0019209385,0.4307221],"study_design_scores_gemma":[0.0035392286,0.000499739,0.92841125,0.0004753492,0.00019748743,0.00015923948,0.0011673538,0.0019043534,0.005444204,0.004534189,0.053318646,0.0003489556],"about_ca_topic_score_codex":0.018909683,"about_ca_topic_score_gemma":0.001006296,"teacher_disagreement_score":0.43037313,"about_ca_system_score_codex":0.00017445262,"about_ca_system_score_gemma":0.0014487589,"threshold_uncertainty_score":0.99990886},"labels":[],"label_agreement":null},{"id":"W1992131051","doi":"10.1186/1471-2288-9-37","title":"Comparison of Bayesian and classical methods in the analysis of cluster randomized controlled trials with a binary outcome: The Community Hypertension Assessment Trial (CHAT)","year":2009,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Centre for Advancing Health Outcomes; University of British Columbia; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Logistic regression; Statistics; Cluster randomised controlled trial; Random effects model; Medicine; Multilevel model; Meta-analysis; Mathematics; Internal medicine","score_opus":0.967801836731588,"score_gpt":0.7748591866462718,"score_spread":0.1929426500853162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992131051","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":[0.24659604,0.0012392201,0.73300475,0.012466377,0.00010348587,0.005855284,0.0000034596344,0.0000021367357,0.0007292329],"genre_scores_gemma":[0.7601023,0.000100785044,0.23873653,0.00052781735,0.000055877204,0.00032362933,0.0000052597097,0.00000581606,0.0001420396],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.033611193,0.9313528,0.021146541,0.0006911675,0.012715811,0.00048249387],"domain_scores_gemma":[0.02936026,0.95743346,0.0073821605,0.0037926084,0.0017446862,0.00028683132],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.96281296,0.0003191349,0.034091298,0.0019332175,0.00029489864,0.00018039288,0.003217423,0.0003593876,0.0018219312],"category_scores_gemma":[0.91898525,0.0000833349,0.004703127,0.0049427557,0.0020791213,0.00006540368,0.00036891914,0.001990566,0.0000032997063],"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":[0.8222281,0.002450661,0.017419722,0.00014992182,0.008393958,0.000019171961,0.005337253,0.00039252723,0.000482508,0.017052595,0.004356335,0.12171725],"study_design_scores_gemma":[0.42877275,0.0017081307,0.02943221,0.00009063731,0.008267479,0.000013229505,0.013209238,0.50154865,0.00001815247,0.016379349,0.00040584468,0.00015434899],"about_ca_topic_score_codex":0.00023739808,"about_ca_topic_score_gemma":0.0008526074,"teacher_disagreement_score":0.51350623,"about_ca_system_score_codex":0.000033005563,"about_ca_system_score_gemma":0.0006345579,"threshold_uncertainty_score":0.99909055},"labels":[],"label_agreement":null},{"id":"W1994338462","doi":"10.1186/1471-2288-13-2","title":"Modelling heterogeneity variances in multiple treatment comparison meta-analysis – Are informative priors the better solution?","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; St. Joseph’s Healthcare Hamilton; McMaster University","funders":"","keywords":"Prior probability; Variance (accounting); Statistics; Bayesian probability; Econometrics; Frequentist inference; Consistency (knowledge bases); Random effects model; Mathematics; Meta-analysis; Bayesian inference","score_opus":0.9815222390306786,"score_gpt":0.6931862774708827,"score_spread":0.2883359615597959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994338462","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":[0.1724359,0.0024660453,0.8163033,0.006681392,0.0000928321,0.0015003987,0.000009579168,0.0000059696767,0.0005045804],"genre_scores_gemma":[0.81355375,0.00011764231,0.18325138,0.0005425357,0.0000910845,0.0012360017,0.000011122423,0.000011006622,0.0011854656],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.68262863,0.28865942,0.011149973,0.0015811531,0.014788988,0.0011918537],"domain_scores_gemma":[0.48731604,0.49498397,0.005414965,0.007299311,0.0038695312,0.0011161889],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.4580802,0.00038875334,0.008212879,0.0013911249,0.00046572508,0.00059315277,0.0032970584,0.00031801336,0.026713489],"category_scores_gemma":[0.26090136,0.00013892628,0.0047211996,0.0045388713,0.00074827584,0.00035364705,0.00054390315,0.00084843294,0.0029314456],"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":[0.00014840065,0.001003012,0.54927987,0.00016900145,0.1256707,0.00003353499,0.014559658,0.22080949,0.00003209538,0.0032527896,0.02491779,0.060123637],"study_design_scores_gemma":[0.00029147134,0.000081825616,0.014949413,0.000005484162,0.0073843035,0.000003992296,0.0035039238,0.9609329,0.000044671793,0.0063763466,0.0062780324,0.00014764101],"about_ca_topic_score_codex":0.003968349,"about_ca_topic_score_gemma":0.017181553,"teacher_disagreement_score":0.7401234,"about_ca_system_score_codex":0.00014965965,"about_ca_system_score_gemma":0.0003971314,"threshold_uncertainty_score":0.9978449},"labels":[],"label_agreement":null},{"id":"W1996251131","doi":"10.1186/1471-2288-11-108","title":"Comparison of indicators of material circumstances in the context of an epidemiological study","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Institut National de la Recherche Scientifique","funders":"National Cancer Institute; Canadian Institutes of Health Research; Health Canada; Cancer Research Society","keywords":"Census; Census tract; Concordance; Index (typography); Proxy (statistics); Context (archaeology); Household income; Residential property; Cohen's kappa; Demography; Medicine; Geography; Socioeconomics; Environmental health; Statistics; Population; Economics; Mathematics; Sociology","score_opus":0.8083187798890671,"score_gpt":0.6709731600842157,"score_spread":0.13734561980485138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996251131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957781,0.00021111347,0.0005383697,0.000633655,0.0002374289,0.00056944357,0.000007269578,0.0000054011907,0.0020192468],"genre_scores_gemma":[0.99527466,0.00013585569,0.004268479,0.00017282016,0.000093307084,0.000042140156,0.000001435975,0.000003621115,0.000007675527],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9144958,0.081658594,0.0012044695,0.00025209304,0.0017257724,0.00066324585],"domain_scores_gemma":[0.9390246,0.05997253,0.00028128302,0.0002861694,0.00015853444,0.0002768299],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12657188,0.000075858334,0.000954093,0.00024292593,0.00012186743,0.000003315273,0.0011768898,0.00029494418,0.0015396237],"category_scores_gemma":[0.12584193,0.000044746397,0.000069597205,0.0005904044,0.0034885241,0.000049658116,0.00013051285,0.0005069629,0.0000013437875],"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":[0.00035912046,0.00078151235,0.83037084,0.00013672072,0.000010073843,0.000005717728,0.07224884,1.1031901e-7,0.00001265755,0.08255352,0.0001142731,0.013406585],"study_design_scores_gemma":[0.000386718,0.0009748915,0.6774235,0.000041564454,0.000005004156,3.8510217e-7,0.31376138,0.000012215985,0.00035070456,0.006608546,0.0003944119,0.000040704643],"about_ca_topic_score_codex":0.05262421,"about_ca_topic_score_gemma":0.055608213,"teacher_disagreement_score":0.24151255,"about_ca_system_score_codex":0.00003085407,"about_ca_system_score_gemma":0.0012129165,"threshold_uncertainty_score":0.9993731},"labels":[],"label_agreement":null},{"id":"W1997947326","doi":"10.1186/1471-2288-11-18","title":"Imputation strategies for missing binary outcomes in cluster randomized trials","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Population Health Research Institute; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"McMaster University; Canadian Institutes of Health Research; Government of Ontario; Saint Paul University; University of Ottawa","keywords":"Imputation (statistics); Missing data; Randomized controlled trial; MEDLINE; Computer science; Statistics; Medicine; Psychology; Mathematics; Internal medicine; Biology","score_opus":0.8477093270696267,"score_gpt":0.6595906078465309,"score_spread":0.18811871922309575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997947326","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":[0.005797567,0.00009848039,0.98949337,0.00088624534,0.00030259634,0.001746777,0.000009559282,0.000039386035,0.0016260103],"genre_scores_gemma":[0.008350166,0.000045180164,0.99054384,0.00015976239,0.00012559706,0.00065643556,0.000003902131,0.000025406747,0.000089733796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89704186,0.09862755,0.0018761005,0.0005097372,0.0010761345,0.00086859806],"domain_scores_gemma":[0.3470462,0.6518051,0.00023552358,0.00028461384,0.00031587537,0.0003126736],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24226528,0.00018671328,0.0023470898,0.00045942632,0.00010660699,0.00004456791,0.00040869988,0.00042560475,0.0014859225],"category_scores_gemma":[0.82380354,0.00011872741,0.00030731852,0.00029330247,0.000952666,0.00010297655,0.00015331611,0.000642136,0.000011769627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026137594,0.00018223142,0.0001744958,0.0004392528,0.00006267474,0.000029843744,0.0013570219,2.4445671e-7,0.00013366123,0.8529637,0.0005392535,0.11798004],"study_design_scores_gemma":[0.035725653,0.00022169697,0.00040293267,0.00012875219,0.000041969095,0.0000072026573,0.0009883861,0.007723248,0.00018175544,0.95442855,0.000027909531,0.000121917525],"about_ca_topic_score_codex":0.00027999177,"about_ca_topic_score_gemma":0.00020643078,"teacher_disagreement_score":0.58153826,"about_ca_system_score_codex":0.000052708383,"about_ca_system_score_gemma":0.0012175627,"threshold_uncertainty_score":0.99942684},"labels":[],"label_agreement":null},{"id":"W1997967369","doi":"10.1186/1471-2288-11-67","title":"Bayesian adjustment for measurement error in continuous exposures in an individually matched case-control study","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Pregnancy and Medication Impact","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; University of Alberta","keywords":"Observational error; Statistics; Bayesian probability; Errors-in-variables models; Computer science; Logistic regression; Econometrics; Mathematics","score_opus":0.6719192017087979,"score_gpt":0.547367602444694,"score_spread":0.12455159926410397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997967369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81139463,0.0019864566,0.17652394,0.0011542559,0.00041847883,0.007865997,0.00002189448,0.00007314959,0.00056122453],"genre_scores_gemma":[0.9580529,0.00005078776,0.038867638,0.0005726977,0.00021308607,0.002126491,0.000009353935,0.000035341553,0.000071737304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97843164,0.0160116,0.0011128642,0.0007491235,0.0024550965,0.0012396749],"domain_scores_gemma":[0.988301,0.009073336,0.00013339055,0.00073637825,0.0005218995,0.0012339891],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07665415,0.00023661657,0.001071131,0.00093106425,0.00008094208,0.000009958863,0.00045343617,0.00044229103,0.0010858239],"category_scores_gemma":[0.07981592,0.00018488168,0.00010603136,0.00049876166,0.00039052425,0.00010108529,0.00011011818,0.0011371128,0.000010985529],"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":[0.008860898,0.008008069,0.7180974,0.00065545045,0.00025815135,0.0065410715,0.030185102,0.0000027513358,0.0011729407,0.0006260303,0.0004640128,0.22512813],"study_design_scores_gemma":[0.026584659,0.009708331,0.93466914,0.0007855473,0.00012434764,0.0008120169,0.02324969,0.0011394317,0.000560781,0.0019906452,0.0001249027,0.0002505241],"about_ca_topic_score_codex":0.0015553456,"about_ca_topic_score_gemma":0.026027616,"teacher_disagreement_score":0.22487761,"about_ca_system_score_codex":0.0003323557,"about_ca_system_score_gemma":0.0028167386,"threshold_uncertainty_score":0.9998273},"labels":[],"label_agreement":null},{"id":"W1998162533","doi":"10.1186/1471-2288-8-53","title":"The efficiency and effectiveness of utilizing diagrams in interviews: an assessment of participatory diagramming and graphic elicitation","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Focus Groups and Qualitative Methods","field":"Social Sciences","cited_by":51,"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 Rehabilitation Institute; Institute for Clinical Evaluative Sciences; University of Toronto; University Health Network; York University; Ontario Institute for Cancer Research; Cancer Care Ontario","funders":"Canadian Institutes of Health Research; University Health Network","keywords":"Respondent; Citizen journalism; Data collection; Computer science; Photo elicitation; Infographic; Qualitative research; Qualitative property; Preference elicitation; Psychology; Applied psychology; Thematic analysis; Management science; Knowledge management; Data science; Data mining; Preference; Engineering","score_opus":0.7473274238471572,"score_gpt":0.6773810916793676,"score_spread":0.06994633216778967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998162533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86814773,0.002186014,0.1288408,0.00013590991,0.00008078538,0.0003254968,6.262155e-7,0.0000056039885,0.00027701684],"genre_scores_gemma":[0.9719847,0.0030670427,0.02481049,0.000009385954,0.00002736718,0.000090693844,6.3589357e-7,0.0000057871907,0.0000039090028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.85840905,0.1389505,0.00056248764,0.0003291029,0.0012100735,0.00053875556],"domain_scores_gemma":[0.856562,0.14273246,0.00010519598,0.00014790715,0.00023013017,0.00022230422],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19632758,0.00007976833,0.00041447303,0.00023601447,0.00042628226,0.000011057355,0.00026415792,0.0001469077,0.000012641143],"category_scores_gemma":[0.101963274,0.00005395707,0.00004397312,0.00071768835,0.005770031,0.000090453264,0.00013750928,0.00042984556,1.4171083e-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":[0.0001676052,0.00021873166,0.32806423,0.0004806191,0.000019335444,0.000009521923,0.054386966,0.0000030839497,0.0025101511,0.3559996,0.0000023649368,0.25813782],"study_design_scores_gemma":[0.0007636564,0.0009243025,0.8918201,0.0003145031,0.0000088472025,0.000003133526,0.05970454,0.002715467,0.0007818592,0.04260113,0.00025159804,0.00011087371],"about_ca_topic_score_codex":0.0035494762,"about_ca_topic_score_gemma":0.009044226,"teacher_disagreement_score":0.56375587,"about_ca_system_score_codex":0.0000415864,"about_ca_system_score_gemma":0.00056510716,"threshold_uncertainty_score":0.99693567},"labels":[],"label_agreement":null},{"id":"W1999352987","doi":"10.1186/1471-2288-14-124","title":"Shame for disrespecting evidence: the personal consequences of insufficient respect for structural equation model testing","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","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":"University of Alberta","funders":"","keywords":"Shame; Structural equation modeling; Psychology; MEDLINE; Social psychology; Statistics; Mathematics; Political science","score_opus":0.9656740959597252,"score_gpt":0.6924039766608265,"score_spread":0.27327011929889866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999352987","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":[0.31263816,0.00050778105,0.68298703,0.002406166,0.0004177199,0.00071245973,0.000012544228,0.00002577847,0.00029231378],"genre_scores_gemma":[0.492082,0.000014171218,0.5071292,0.00014016808,0.00036361805,0.00015196469,0.0000012692985,0.000011242488,0.00010640894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9661232,0.024330387,0.0017362717,0.001149969,0.005475449,0.001184724],"domain_scores_gemma":[0.0379243,0.95708275,0.0007434763,0.0007381367,0.0031686786,0.0003426802],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34386772,0.00019466222,0.00079545233,0.0007969818,0.00092224526,0.00015178764,0.002326498,0.00027593202,0.0001374691],"category_scores_gemma":[0.98757493,0.00010649357,0.0002704137,0.0027444635,0.0022384017,0.00015955494,0.0005324286,0.0007292161,0.0000041665376],"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":[0.0019671535,0.0000759493,0.055076808,0.00031835938,0.000054597196,0.0000024531964,0.0044142003,0.007580233,0.0182183,0.11398549,0.0029522695,0.7953542],"study_design_scores_gemma":[0.0004015865,0.00064063363,0.0033068038,0.000114978306,0.000008993927,0.0000174275,0.0021710743,0.6739253,0.0007717029,0.3182881,0.0002629075,0.00009056445],"about_ca_topic_score_codex":0.00018688617,"about_ca_topic_score_gemma":0.00011394121,"teacher_disagreement_score":0.9327523,"about_ca_system_score_codex":0.00009650272,"about_ca_system_score_gemma":0.001730105,"threshold_uncertainty_score":0.82474846},"labels":[],"label_agreement":null},{"id":"W1999761369","doi":"10.1186/1471-2288-10-109","title":"Barriers and facilitators to recruitment of physicians and practices for primary care health services research at one centre","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":115,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute of Population and Public Health; Élisabeth Bruyère Hospital; Bruyère; University of Ottawa","funders":"","keywords":"Sampling frame; Qualitative research; Primary care; Health care; Medical education; Descriptive statistics; Best practice; Nursing; Medicine; Psychology; Public relations; Family medicine; Political science; Population; Sociology","score_opus":0.8628859333609432,"score_gpt":0.7324734413163235,"score_spread":0.1304124920446197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999761369","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":[0.9380021,0.0033303865,0.0016741881,0.0498615,0.00026316117,0.0053436765,0.00012670021,0.000034818466,0.0013634466],"genre_scores_gemma":[0.2839617,0.016383175,0.6823961,0.0068546254,0.0013725027,0.0017538985,0.00015753128,0.00016535375,0.0069550835],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97361887,0.015861567,0.001013362,0.0013819038,0.0062747067,0.0018496196],"domain_scores_gemma":[0.71741724,0.2758256,0.00022247298,0.00088450115,0.003052923,0.0025972917],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14072849,0.00019753783,0.0010865259,0.000633599,0.00057589065,0.0000333502,0.0006317718,0.00092521735,0.00034314935],"category_scores_gemma":[0.35969815,0.00016465042,0.00010445278,0.0007368477,0.003747513,0.00008057701,0.0017630494,0.005574439,0.000021076652],"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":[0.009767567,0.00052851316,0.09273614,0.04341539,0.00033133212,0.00006224927,0.0315415,4.0813802e-7,0.04528129,0.024954636,0.0024161842,0.7489648],"study_design_scores_gemma":[0.01993691,0.036850642,0.198075,0.014427979,0.0002172753,0.0001829689,0.24652523,0.00081275555,0.04181473,0.05634646,0.3835681,0.0012419558],"about_ca_topic_score_codex":0.0021078307,"about_ca_topic_score_gemma":0.029211937,"teacher_disagreement_score":0.74772286,"about_ca_system_score_codex":0.00035515474,"about_ca_system_score_gemma":0.0067928904,"threshold_uncertainty_score":0.9989637},"labels":[],"label_agreement":null},{"id":"W1999826862","doi":"10.1186/1471-2288-11-2","title":"Autism spectrum disorders and fetal hypoxia in a population-based cohort: Accounting for missing exposures via Estimation-Maximization algorithm","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":69,"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 Alberta","funders":"Assistance publique-Hôpitaux de Paris; Fondation pour la Recherche Médicale; Government of Alberta","keywords":"Autism; Cohort; Expectation–maximization algorithm; Population; Medicine; Hypoxia (environmental); Fetal alcohol; Algorithm; Computer science; Psychiatry; Maximum likelihood; Pregnancy; Statistics; Biology; Pathology; Mathematics; Environmental health; Genetics; Chemistry","score_opus":0.16320095621973701,"score_gpt":0.4278796753821798,"score_spread":0.2646787191624428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999826862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08848092,0.0003741424,0.9066998,0.0030190467,0.00017810588,0.00095673057,0.0000056094773,0.000046505156,0.00023916361],"genre_scores_gemma":[0.43997213,0.00004213411,0.55935377,0.00023498041,0.000083483814,0.00013758252,0.000094591975,0.000024916259,0.00005638065],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99558294,0.0020484917,0.000526684,0.0005287286,0.00068097457,0.0006321655],"domain_scores_gemma":[0.98674536,0.012536365,0.00009873123,0.00022572246,0.00006203426,0.00033179834],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010215347,0.00016206091,0.0005142087,0.0005686211,0.00018292578,0.000014030188,0.00015086947,0.0003770759,0.0003197165],"category_scores_gemma":[0.030698055,0.00014079586,0.00007580229,0.0004092236,0.00048781815,0.000101642574,0.00009875886,0.00055852724,0.000006950883],"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":[0.00071528554,0.00020677035,0.25720924,0.0003956378,0.000030704978,0.00008643938,0.00043513547,0.000032024673,0.00027298002,0.0033548998,0.000022594582,0.7372383],"study_design_scores_gemma":[0.0019110352,0.00041068744,0.59867495,0.00011563427,0.000023142908,0.00010942743,0.00006451438,0.3129659,0.00018004524,0.0853529,0.00006868288,0.00012306866],"about_ca_topic_score_codex":0.0015328678,"about_ca_topic_score_gemma":0.0010471698,"teacher_disagreement_score":0.7371152,"about_ca_system_score_codex":0.00009033292,"about_ca_system_score_gemma":0.0005173146,"threshold_uncertainty_score":0.97746676},"labels":[],"label_agreement":null},{"id":"W2003143266","doi":"10.1186/1471-2288-14-14","title":"A Monte Carlo simulation study comparing linear regression, beta regression, variable-dispersion beta regression and fractional logit regression at recovering average difference measures in a two sample design","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Fractional Differential Equations Solutions","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Logistic regression; Statistics; Regression analysis; Linear regression; BETA (programming language); Regression dilution; Monte Carlo method; Regression diagnostic; Mathematics; Cross-sectional regression; Regression; Logit; Factor regression model; Econometrics; Proper linear model; Bayesian multivariate linear regression; Computer science","score_opus":0.6280790340852682,"score_gpt":0.5473857233646657,"score_spread":0.08069331072060248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003143266","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":[0.38448355,0.00030081772,0.61301,0.00047001868,0.00039842929,0.0010923764,0.000012339076,0.00011198114,0.00012052484],"genre_scores_gemma":[0.8162979,0.00022212582,0.18227737,0.0000418427,0.00037152143,0.0002447527,0.000038531427,0.00007292912,0.00043306308],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96212095,0.02942217,0.0016134392,0.0015242408,0.004003592,0.0013156226],"domain_scores_gemma":[0.8669647,0.1292459,0.0006579062,0.0012062063,0.0009899631,0.00093533966],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031373095,0.00059844705,0.0014014691,0.0011406093,0.0014550025,0.00010050311,0.0007846934,0.000660378,0.00065974065],"category_scores_gemma":[0.17596737,0.00042714606,0.00016842653,0.0010858068,0.00058571616,0.00039253398,0.0014220969,0.00237415,0.000029835996],"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":[0.017476324,0.00853315,0.517416,0.0017866907,0.0006557238,0.00022876113,0.008008688,0.27224496,0.019186946,0.033990894,0.006596261,0.11387562],"study_design_scores_gemma":[0.0040978184,0.00051442266,0.04306102,0.0025909753,0.00008199654,0.000043484542,0.00054254854,0.91289574,0.00043908635,0.0343578,0.0008616848,0.0005134249],"about_ca_topic_score_codex":0.0049242047,"about_ca_topic_score_gemma":0.00786681,"teacher_disagreement_score":0.64065075,"about_ca_system_score_codex":0.0008776437,"about_ca_system_score_gemma":0.0008031888,"threshold_uncertainty_score":0.9999274},"labels":[],"label_agreement":null},{"id":"W2006031679","doi":"10.1186/1471-2288-7-34","title":"A simulation study of sample size for multilevel logistic regression models","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":400,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; St. Michael's Hospital; University of Toronto","funders":"Ontario Ministry of Health and Long-Term Care","keywords":"Statistics; Sample size determination; Multilevel model; Logistic regression; Random effects model; Variance (accounting); Covariance; Mathematics; Hierarchical database model; Sample (material); Econometrics; Regression; Medicine; Computer science; Meta-analysis; Data mining","score_opus":0.8745461031859402,"score_gpt":0.6879301196957895,"score_spread":0.18661598349015063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006031679","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":[0.030422483,0.000025757583,0.96788126,0.000051890936,0.00015584377,0.0012227945,0.000028375554,0.000034115183,0.00017745416],"genre_scores_gemma":[0.34744367,0.0000046209366,0.65229523,0.000019021118,0.0001078447,0.00007018898,0.0000016017073,0.000017823219,0.00004000866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98602843,0.009764019,0.0010562779,0.00053055334,0.0018064348,0.0008143009],"domain_scores_gemma":[0.24889825,0.74919707,0.00018858489,0.0004714881,0.00084309455,0.00040151612],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06386741,0.00016542418,0.0007595498,0.00024052846,0.000158251,0.000011087606,0.00047629274,0.00036028688,0.00053995237],"category_scores_gemma":[0.8397517,0.00011694792,0.00009135276,0.00034992993,0.00051032624,0.00004634779,0.00024426196,0.0005821232,0.000002250609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022058638,0.0018065725,0.0011445602,0.00088377006,0.00005611546,0.000029779903,0.0019365319,0.00027824618,0.00037653334,0.59511614,0.00023357288,0.3959323],"study_design_scores_gemma":[0.0012766068,0.00094949506,0.0012013626,0.000102523125,0.000021550915,0.0000017826019,0.0009770017,0.24490961,0.00019456804,0.7502479,0.000028804894,0.00008880534],"about_ca_topic_score_codex":0.00034634263,"about_ca_topic_score_gemma":0.0004366847,"teacher_disagreement_score":0.77588433,"about_ca_system_score_codex":0.00006427249,"about_ca_system_score_gemma":0.00040712464,"threshold_uncertainty_score":0.9639455},"labels":[],"label_agreement":null},{"id":"W2008678163","doi":"10.1186/1471-2288-11-101","title":"Additive and multiplicative hazards modeling for recurrent event data analysis","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Saskatchewan Health Authority","funders":"University of Saskatchewan","keywords":"Censoring (clinical trials); Proportional hazards model; Multiplicative function; Covariate; Statistics; Confidence interval; Multivariate statistics; Additive model; Event (particle physics); Hazard ratio; Econometrics; Hazard; Regression analysis; Accelerated failure time model; Regression; Computer science; Mathematics","score_opus":0.9227710037629375,"score_gpt":0.6747474968653392,"score_spread":0.24802350689759833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008678163","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006346227,0.00025305245,0.9914505,0.00019479136,0.000092967115,0.000598774,0.00039442192,0.000029577006,0.00063970796],"genre_scores_gemma":[0.027846845,0.0003345654,0.97116774,0.000053542128,0.00013113547,0.00032746646,0.00006143425,0.00001968283,0.000057609766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98612,0.010642823,0.00063090294,0.0009079837,0.0010026115,0.0006957118],"domain_scores_gemma":[0.84951633,0.14800681,0.000113523645,0.0010317761,0.0006898775,0.0006416626],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046755657,0.00016882742,0.00077617407,0.00033097938,0.00017673905,0.000016250788,0.0009359378,0.00026623075,0.0015269982],"category_scores_gemma":[0.48059553,0.00012596374,0.00010805104,0.00056688685,0.0007117138,0.000058263417,0.001089054,0.00068760203,0.000008548652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006172,0.00023438482,0.00022128745,0.00019511677,0.00045225144,0.0000079075735,0.001234887,0.0000011723458,0.000023239658,0.38223347,0.0011603372,0.61361873],"study_design_scores_gemma":[0.00034742733,0.0003088099,0.00035353858,0.000046226414,0.00017864503,0.0000032766184,0.0006523202,0.52069193,0.0000977233,0.4769742,0.00024229239,0.00010364059],"about_ca_topic_score_codex":0.00031071628,"about_ca_topic_score_gemma":0.0009025539,"teacher_disagreement_score":0.6135151,"about_ca_system_score_codex":0.000045521785,"about_ca_system_score_gemma":0.0005669276,"threshold_uncertainty_score":0.9993857},"labels":[],"label_agreement":null},{"id":"W2012885820","doi":"10.1186/1471-2288-7-39","title":"Comparison of Bayesian and frequentist approaches in modelling risk of preterm birth near the Sydney Tar Ponds, Nova Scotia, Canada","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Nova scotia; Frequentist inference; Bayesian probability; Bayes' theorem; Bayesian inference; Medicine; tar (computing); Environmental science; Demography; Statistics; Geography; Computer science; Mathematics; Sociology","score_opus":0.5642763964582974,"score_gpt":0.5106269648923341,"score_spread":0.05364943156596336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012885820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6939118,0.0003722246,0.3036765,0.0010547844,0.000059617058,0.00027369556,0.000010669922,0.000003052711,0.0006376747],"genre_scores_gemma":[0.88775426,0.00006978791,0.111933954,0.00017182213,0.000027804244,0.000002903152,0.0000026674659,0.000008396619,0.000028387902],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890527,0.0075212764,0.000760389,0.0003275499,0.0015720631,0.00076603284],"domain_scores_gemma":[0.9785187,0.020388195,0.0001919801,0.0003296462,0.000023530958,0.00054789695],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04999676,0.00010458207,0.00047252356,0.00008290771,0.00016956837,0.0000093967255,0.0004824791,0.00021402925,0.0006866434],"category_scores_gemma":[0.0172397,0.000073754796,0.00003134511,0.00045001035,0.0027138856,0.000053097614,0.00030386238,0.0010202656,0.0000037931554],"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":[0.00042436324,0.00015057136,0.9528711,0.0005004455,0.00001836725,0.000016560847,0.005633413,0.0061000804,0.00013950921,0.00162208,0.0010676343,0.03145587],"study_design_scores_gemma":[0.0010007033,0.00050523516,0.4328999,0.00017995446,0.000015157519,0.000019142613,0.004656102,0.5506586,0.0021627485,0.0059530903,0.0017477206,0.00020165267],"about_ca_topic_score_codex":0.8694503,"about_ca_topic_score_gemma":0.96135825,"teacher_disagreement_score":0.5445585,"about_ca_system_score_codex":0.00020055175,"about_ca_system_score_gemma":0.0011904419,"threshold_uncertainty_score":0.9999425},"labels":[],"label_agreement":null},{"id":"W2014411687","doi":"10.1186/1471-2288-8-32","title":"The ratio of means method as an alternative to mean differences for analyzing continuous outcome variables in meta-analysis: A simulation study","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":339,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Health Sciences Centre; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre; SickKids Foundation; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Confidence interval; Meta-analysis; Strictly standardized mean difference; Publication bias; Pooling; Standard deviation; Study heterogeneity; Sample size determination; Pooled variance; Weighting; Mean difference; Type I and type II errors; Statistical power; Mathematics; Medicine; Econometrics; Computer science; Internal medicine","score_opus":0.974214244217264,"score_gpt":0.7376015835997741,"score_spread":0.23661266061748987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014411687","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":[0.14277253,0.0004867298,0.8529857,0.000812789,0.00009912213,0.0026146236,0.000013830481,0.0000045311194,0.00021018123],"genre_scores_gemma":[0.7705151,0.000019700363,0.22677146,0.00011941164,0.00007673687,0.0006556588,0.0000041186413,0.000012633353,0.0018251754],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.42772534,0.53102106,0.016950052,0.0026954059,0.020432506,0.0011756428],"domain_scores_gemma":[0.21444178,0.7687662,0.0040655825,0.0051338477,0.006678965,0.0009135803],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7407974,0.00036786354,0.010072881,0.0023993,0.0005326459,0.00028792254,0.0044506383,0.0002134198,0.0040084356],"category_scores_gemma":[0.7792231,0.0001485715,0.0034146877,0.006552769,0.00044180083,0.00020143534,0.00047192446,0.0005920812,0.000062123996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00127766,0.0020449504,0.6253496,0.00014632326,0.12530386,0.000092422866,0.04958177,0.09963482,0.00018370253,0.06144586,0.0008180459,0.03412099],"study_design_scores_gemma":[0.0011673622,0.0016678884,0.04606834,0.000011149766,0.027924875,0.000009995226,0.02609448,0.81830984,0.00008501181,0.07712758,0.0011686307,0.00036483415],"about_ca_topic_score_codex":0.0018058103,"about_ca_topic_score_gemma":0.020086365,"teacher_disagreement_score":0.718675,"about_ca_system_score_codex":0.00006288167,"about_ca_system_score_gemma":0.0006275284,"threshold_uncertainty_score":0.9977945},"labels":[],"label_agreement":null},{"id":"W2015141376","doi":"10.1186/1471-2288-8-30","title":"Bayes rules for optimally using Bayesian hierarchical regression models in provider profiling to identify high-mortality hospitals","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Medical Coding and Health Information","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":"Institute for Clinical Evaluative Sciences","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Bayes' theorem; Bayesian probability; Medicine; Statistics; Bayes error rate; Mean squared error; Sample size determination; Computer science; Econometrics; Mathematics; Bayes classifier","score_opus":0.8324878767448155,"score_gpt":0.677557636550425,"score_spread":0.1549302401943905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015141376","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45802245,0.00012118517,0.5347597,0.0036811542,0.0005360158,0.002339571,0.00002314029,0.000068321286,0.0004484923],"genre_scores_gemma":[0.28855115,0.000222411,0.7060269,0.0021041252,0.0010549203,0.0014966016,0.00010448688,0.000053421525,0.00038595617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9703323,0.021483788,0.0022197077,0.00083345,0.002841433,0.0022892763],"domain_scores_gemma":[0.94159186,0.054383855,0.0003284763,0.0006844946,0.00095905724,0.0020522526],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07665848,0.00027345095,0.0010543957,0.0008827731,0.0016424836,0.00001646683,0.00075678615,0.0012589528,0.0006149327],"category_scores_gemma":[0.1729861,0.00020759259,0.00012876357,0.00071714394,0.0006790566,0.00032554645,0.0006323037,0.0035874264,0.00007384577],"study_design_candidate":"simulation_or_modeling","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":[0.014721471,0.001575133,0.3239697,0.04279458,0.00025794157,0.0007915126,0.07197337,0.0058680973,0.006168518,0.35381016,0.039783668,0.13828585],"study_design_scores_gemma":[0.007389576,0.0016000135,0.116799444,0.0070965034,0.000037457212,0.00006094723,0.0055821063,0.6775446,0.0006178605,0.17881668,0.003510816,0.0009440249],"about_ca_topic_score_codex":0.0025411537,"about_ca_topic_score_gemma":0.0010240608,"teacher_disagreement_score":0.67167646,"about_ca_system_score_codex":0.0007015876,"about_ca_system_score_gemma":0.011682021,"threshold_uncertainty_score":0.9996572},"labels":[],"label_agreement":null},{"id":"W2019065492","doi":"10.1186/1471-2288-10-8","title":"Harnessing Social Networks along with Consumer-Driven Electronic Communication Technologies to Identify and Engage Members of 'Hard-to-Reach' Populations: A Methodological Case Report","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"Social Sciences and Humanities Research Council of Canada; Canadian Institutes of Health Research; Alberta Heritage Foundation for Medical Research; Fondation pour la Recherche Médicale","keywords":"Popularity; Population; Referral; Social media; Sample (material); Internet privacy; Sampling (signal processing); Public relations; Set (abstract data type); Psychology; Business; Marketing; Medicine; Family medicine; Computer science; Social psychology; World Wide Web; Political science; Environmental health; Telecommunications","score_opus":0.7336373005663528,"score_gpt":0.6383844795544736,"score_spread":0.09525282101187915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019065492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7356912,0.0003892874,0.2569708,0.005706003,0.00021788124,0.0006932101,0.000003517979,0.00013996681,0.00018818845],"genre_scores_gemma":[0.60308427,0.00012082542,0.39632067,0.00009860607,0.00009937666,0.0001746944,0.000008932633,0.000017309341,0.00007529162],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7470665,0.24793765,0.0009887946,0.0009457088,0.0015518818,0.0015094917],"domain_scores_gemma":[0.7611262,0.2367035,0.00026472448,0.0007010718,0.0007066057,0.0004979128],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.37839538,0.00022596437,0.0009048691,0.0007178839,0.0018758917,0.00006255148,0.0009648218,0.0012654832,0.00027461292],"category_scores_gemma":[0.6512785,0.00018267229,0.000093104216,0.0017089574,0.005511071,0.00014905958,0.00072105567,0.0035153285,0.000005677884],"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":[0.020006888,0.0006716553,0.24621226,0.00023480009,0.00061481696,0.011257996,0.04656487,0.00019706305,0.02286251,0.23377322,0.0023783795,0.41522554],"study_design_scores_gemma":[0.0043639936,0.0025180639,0.7400175,0.00051292294,0.00046026247,0.018947214,0.12033646,0.0022619793,0.0037015409,0.0818158,0.02295577,0.002108542],"about_ca_topic_score_codex":0.006705389,"about_ca_topic_score_gemma":0.10254522,"teacher_disagreement_score":0.4938052,"about_ca_system_score_codex":0.00011317136,"about_ca_system_score_gemma":0.0018236917,"threshold_uncertainty_score":0.99990904},"labels":[],"label_agreement":null},{"id":"W2019743290","doi":"10.1186/1471-2288-12-126","title":"Bias-corrected estimator for intraclass correlation coefficient in the balanced one-way random effects model","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; McMaster University; Hospital for Sick Children; Public Health Ontario; SickKids Foundation; University of Toronto; Princess Margaret Cancer Centre","funders":"Hospital for Sick Children","keywords":"Estimator; Intraclass correlation; Statistics; Mean squared error; Bias of an estimator; Context (archaeology); Mathematics; Minimum-variance unbiased estimator; Variance (accounting); Random effects model; Efficient estimator; Consistent estimator; Econometrics; Meta-analysis; Medicine; Psychometrics","score_opus":0.7019645147797443,"score_gpt":0.5870564450990389,"score_spread":0.11490806968070544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019743290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033305325,0.00014615495,0.96281993,0.0007393783,0.000538659,0.001657209,0.000011480775,0.000044042285,0.0007378061],"genre_scores_gemma":[0.15043367,0.000028461733,0.84806746,0.00024476124,0.00023856957,0.0008621036,0.000012508164,0.000025926709,0.000086548775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9722045,0.023854049,0.00072169176,0.00039084195,0.001625795,0.0012031244],"domain_scores_gemma":[0.5760913,0.42271793,0.00011287434,0.0004010207,0.0003021613,0.00037475288],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08172122,0.00018994875,0.0007310963,0.00023288741,0.00019567886,0.000030621624,0.00059634034,0.00042569314,0.00017454087],"category_scores_gemma":[0.6791518,0.00012022107,0.00010530142,0.0005827063,0.00055905,0.00006039781,0.00015796539,0.0011795907,0.000026541196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013099576,0.0007709757,0.0014312855,0.0007325651,0.000027711856,0.0000065697545,0.0017472351,0.00031010775,0.0008069469,0.8993877,0.0038344883,0.08963442],"study_design_scores_gemma":[0.0024451914,0.0002262385,0.0021057792,0.00016758287,0.000026672142,0.000012101053,0.00021214737,0.6816895,0.00046419897,0.312412,0.00011290468,0.0001257046],"about_ca_topic_score_codex":0.00004464824,"about_ca_topic_score_gemma":0.00007839349,"teacher_disagreement_score":0.6813794,"about_ca_system_score_codex":0.000104288825,"about_ca_system_score_gemma":0.0004986985,"threshold_uncertainty_score":0.94556123},"labels":[],"label_agreement":null},{"id":"W2021966610","doi":"10.1186/1471-2288-7-47","title":"Program design features that can improve participation in health education interventions","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto; Toronto Metropolitan University; University Health Network","funders":"","keywords":"Psychological intervention; Medicine; Population; Intervention (counseling); Family medicine; Health education; Program evaluation; Medical education; Nursing; Gerontology; Public health; Environmental health","score_opus":0.9744480114400934,"score_gpt":0.8642184583148269,"score_spread":0.1102295531252665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021966610","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08179443,0.0004354601,0.8202623,0.084873006,0.002251034,0.008097284,0.000014899135,0.00018039913,0.0020911796],"genre_scores_gemma":[0.42316255,0.00039464308,0.5437798,0.021463493,0.0010444357,0.006391824,0.00004745295,0.000047882462,0.0036679127],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.89837325,0.0932256,0.0022369823,0.0007203265,0.0023853476,0.003058529],"domain_scores_gemma":[0.87941986,0.11711888,0.0004928437,0.0005195811,0.0006597495,0.0017890857],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23351644,0.00013775381,0.0004423245,0.0010599489,0.00080653693,0.000016467768,0.00054136635,0.00039087984,0.0014259825],"category_scores_gemma":[0.2202995,0.00011798786,0.00007360718,0.0015194818,0.00049993774,0.00012807651,0.00024799627,0.002283488,0.00013311645],"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":[0.00026044375,0.0004989799,0.041929193,0.0019505289,0.000008024339,0.0000061757223,0.016770124,0.000003632313,0.00014128684,0.014648431,0.029174812,0.8946084],"study_design_scores_gemma":[0.0030192598,0.002202909,0.83456475,0.0020787984,0.000007850481,0.000012798171,0.042747304,0.00065345323,0.00056048384,0.019288898,0.094528176,0.00033530005],"about_ca_topic_score_codex":0.01361298,"about_ca_topic_score_gemma":0.11943456,"teacher_disagreement_score":0.89427304,"about_ca_system_score_codex":0.0011490101,"about_ca_system_score_gemma":0.021582745,"threshold_uncertainty_score":0.99948686},"labels":[],"label_agreement":null},{"id":"W2022170760","doi":"10.1186/1471-2288-13-90","title":"The impact of deployment experience and prior healthcare utilization on enrollment in a large military cohort study","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Fibromyalgia and Chronic Fatigue Syndrome Research","field":"Medicine","cited_by":6,"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 and Materiel Command; McMaster University","keywords":"Medicine; Generalizability theory; Logistic regression; Cohort; Confounding; Military deployment; Cohort study; Health care; Prospective cohort study; Software deployment; Odds; Gerontology; Population; Demography; Family medicine; Environmental health; Psychology; Surgery","score_opus":0.37148557539398935,"score_gpt":0.5686661792552166,"score_spread":0.1971806038612272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022170760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917124,0.0024652532,0.0005370661,0.0018283365,0.000044624787,0.0033312049,0.0000022008965,0.00001257044,0.00006636114],"genre_scores_gemma":[0.99592596,0.0020181092,0.00094973354,0.0000183358,0.000021784885,0.00088878017,0.000006554161,0.0000174594,0.0001532692],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9849298,0.010570904,0.00060479966,0.00050572125,0.0024159313,0.00097281963],"domain_scores_gemma":[0.98558295,0.012756718,0.000046386293,0.0006026598,0.0003571772,0.00065413315],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022424642,0.00014592255,0.0005573138,0.00031959472,0.00018486801,0.000009975634,0.00029753713,0.00019167457,0.0008910495],"category_scores_gemma":[0.027925583,0.000081779326,0.000080720434,0.0005566005,0.00070487394,0.00004430234,0.0003139436,0.000928239,0.000018022167],"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":[0.00090176257,0.0010163421,0.9725628,0.00061813905,0.000078067525,0.000061317696,0.0028381855,0.0000025149611,0.00035133533,0.00025013497,0.0004865503,0.020832881],"study_design_scores_gemma":[0.0024168068,0.0059889476,0.98094136,0.00033622142,0.0000047127123,0.00003547631,0.005818995,0.0039036395,0.00016856706,0.00030301325,0.000021837594,0.000060411105],"about_ca_topic_score_codex":0.010802726,"about_ca_topic_score_gemma":0.00062463514,"teacher_disagreement_score":0.02077247,"about_ca_system_score_codex":0.00041613617,"about_ca_system_score_gemma":0.002042111,"threshold_uncertainty_score":0.9957844},"labels":[],"label_agreement":null},{"id":"W2022178611","doi":"10.1186/1471-2288-10-29","title":"The Jamaica asthma and allergies national prevalence survey: rationale and methods","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Asthma and respiratory diseases","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":"University of Ottawa","funders":"","keywords":"Asthma; Medicine; Environmental health; Stratified sampling; Public health; Allergy; Cluster sampling; Cross-sectional study; Population; Family medicine; Pediatrics; Demography; Immunology; Pathology","score_opus":0.3540239106052387,"score_gpt":0.5689969500289297,"score_spread":0.214973039423691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022178611","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":[0.8859686,0.0156039065,0.07732301,0.016156642,0.0007313543,0.0013714161,0.000049622297,0.00008179833,0.0027136456],"genre_scores_gemma":[0.23717001,0.012625881,0.73143435,0.0034314152,0.002636245,0.00068526255,0.00007690689,0.00009078478,0.011849134],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98123115,0.015815,0.00034079672,0.00044399206,0.0016975339,0.00047150042],"domain_scores_gemma":[0.86964476,0.1282167,0.00006298921,0.00031953346,0.0009152354,0.00084080274],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059309006,0.00012005588,0.00030075727,0.00014510949,0.0004904679,0.000043890548,0.00023334676,0.00027816405,0.00078521896],"category_scores_gemma":[0.2916407,0.00007056671,0.00004945396,0.00022635667,0.0030653204,0.00005599958,0.0003257234,0.0011086693,0.000012706345],"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":[0.0030421163,0.0003482262,0.14753583,0.000994571,0.00018904194,0.000090973124,0.00059112906,0.000002216385,0.021805989,0.051679906,0.026829159,0.74689084],"study_design_scores_gemma":[0.0011410308,0.00036480365,0.7992821,0.00005646601,0.000012105054,0.00028313877,0.000326658,0.0021667385,0.00051745324,0.007883463,0.1878465,0.00011954751],"about_ca_topic_score_codex":0.000049342165,"about_ca_topic_score_gemma":0.00071155495,"teacher_disagreement_score":0.7467713,"about_ca_system_score_codex":0.000017466922,"about_ca_system_score_gemma":0.0022417689,"threshold_uncertainty_score":0.99964774},"labels":[],"label_agreement":null},{"id":"W2022418062","doi":"10.1186/1471-2288-14-127","title":"Methodological and ethical issues in research using social media: a metamethod of Human Papillomavirus vaccine studies","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Social media; Credibility; Research ethics; Transparency (behavior); Generalizability theory; CLARITY; Psychology; Internet privacy; Informed consent; Public relations; Medicine; Computer science; World Wide Web; Political science; Alternative medicine","score_opus":0.9767535309614988,"score_gpt":0.79382938185026,"score_spread":0.18292414911123878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022418062","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":[0.9436165,0.007402748,0.006665877,0.038154993,0.0018718956,0.0015720982,0.0000025786821,0.00006593098,0.00064737006],"genre_scores_gemma":[0.48046312,0.009616658,0.50154525,0.00047377733,0.006709131,0.001073583,0.000005361878,0.00006191145,0.00005120682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.621241,0.36914933,0.0014224274,0.0009548473,0.005272823,0.00195958],"domain_scores_gemma":[0.12963955,0.86573625,0.0003272894,0.00049817865,0.0026363546,0.0011623771],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","sts","research_integrity"],"category_scores_codex":[0.5161341,0.0002277571,0.002084801,0.0013574495,0.0015658484,0.000038854294,0.0010181735,0.0022052855,0.0004886158],"category_scores_gemma":[0.9159092,0.00019557198,0.00013005677,0.0029401642,0.009052991,0.00009632319,0.000831946,0.0055443756,0.000010637621],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049843173,0.00028162118,0.02466813,0.0008862897,0.00008374181,0.000030144534,0.19837204,0.0000010169535,0.0046905396,0.57319635,0.0010606545,0.19623104],"study_design_scores_gemma":[0.0023376308,0.0009198562,0.07340495,0.00058869104,0.00005690474,0.00001158009,0.1527998,0.0002502733,0.0015042037,0.7537033,0.013953406,0.00046939374],"about_ca_topic_score_codex":0.019138053,"about_ca_topic_score_gemma":0.039740916,"teacher_disagreement_score":0.49658692,"about_ca_system_score_codex":0.00053886673,"about_ca_system_score_gemma":0.002754661,"threshold_uncertainty_score":0.999734},"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":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2023529456","doi":"10.1186/1471-2288-14-67","title":"A Bayesian framework for estimating the incremental value of a diagnostic test in the absence of a gold standard","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Gold standard (test); Context (archaeology); Bayesian probability; Bayes' theorem; Statistics; Sensitivity (control systems); Latent tuberculosis; Medicine; Computer science; Mathematics; Tuberculosis","score_opus":0.29745886683012795,"score_gpt":0.5498200957600959,"score_spread":0.252361228929968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023529456","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":[0.16742735,0.00043303357,0.81097907,0.019224478,0.00009330946,0.0013798098,0.000018712835,0.000009407332,0.000434828],"genre_scores_gemma":[0.5975898,0.00012989146,0.40086803,0.00079229457,0.00027127514,0.0003193214,0.0000059299255,0.000012897471,0.000010544115],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9736096,0.021951793,0.0009590641,0.00041362923,0.0020386835,0.0010272317],"domain_scores_gemma":[0.14418465,0.8539039,0.00019604871,0.00085592025,0.00044695623,0.00041252252],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1112983,0.0001350516,0.0008466061,0.0002534356,0.00010155459,0.0000072288913,0.00085485424,0.0003306614,0.0001795755],"category_scores_gemma":[0.9135197,0.00006905176,0.00016349128,0.00069154025,0.002083578,0.000025025807,0.00028523698,0.0015739175,0.000005027944],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0055006994,0.0013336799,0.43293065,0.004795125,0.00025343805,0.00013066096,0.0053302823,0.00026257077,0.0073255226,0.3044624,0.014430157,0.22324483],"study_design_scores_gemma":[0.00704848,0.016174683,0.19072121,0.0044729994,0.00010842212,0.0004918478,0.006019735,0.3643135,0.0035757143,0.40265712,0.0040774923,0.00033878232],"about_ca_topic_score_codex":0.0011704777,"about_ca_topic_score_gemma":0.00059607957,"teacher_disagreement_score":0.8319521,"about_ca_system_score_codex":0.000072420444,"about_ca_system_score_gemma":0.0010650735,"threshold_uncertainty_score":0.9151054},"labels":[],"label_agreement":null},{"id":"W2024222715","doi":"10.1186/1471-2288-13-51","title":"Magnitude of discordance between registry data and death certificate when evaluating leading causes of death in dialysis patients","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Autopsy Techniques and Outcomes","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":"McGill University; Université de Montréal; McGill University Health Centre; Hôpital Maisonneuve-Rosemont","funders":"","keywords":"Death certificate; Medicine; Dialysis; Cause of death; Population; Disease registry; Intensive care medicine; Internal medicine; Emergency medicine; Disease; Environmental health","score_opus":0.8016312647466157,"score_gpt":0.6071493937116736,"score_spread":0.19448187103494208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024222715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97215456,0.00041467496,0.025715642,0.0008158894,0.00002865188,0.0006048261,0.000022236149,0.000017731223,0.0002257964],"genre_scores_gemma":[0.7762596,0.00028110735,0.22300725,0.0000421015,0.00006313528,0.00004982434,0.00006245082,0.000017492202,0.00021702822],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9924867,0.0041738963,0.0008815264,0.00053784857,0.0013984755,0.00052154425],"domain_scores_gemma":[0.977619,0.020257048,0.00025487944,0.0010852929,0.00042475775,0.00035903047],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01756897,0.00013885427,0.000996801,0.00035905078,0.00004698506,0.000009140477,0.0006457428,0.00024043953,0.00035551167],"category_scores_gemma":[0.12046103,0.00010170756,0.00005752533,0.00030951385,0.00053902785,0.00011127781,0.000987904,0.00069282646,0.0000049537744],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009973708,0.00008671541,0.94242585,0.0005500357,0.000043928587,0.0000083171535,0.00026795198,2.2067054e-7,0.0021927503,0.00023270074,0.0001967615,0.05389502],"study_design_scores_gemma":[0.0010452664,0.00046787938,0.987817,0.0005340923,0.000077534394,0.0000056973486,0.0002055248,0.001241515,0.0039182063,0.004506337,0.00009060294,0.00009034901],"about_ca_topic_score_codex":0.0036113586,"about_ca_topic_score_gemma":0.00035724475,"teacher_disagreement_score":0.1972916,"about_ca_system_score_codex":0.0000602923,"about_ca_system_score_gemma":0.00050904835,"threshold_uncertainty_score":0.8869477},"labels":[],"label_agreement":null},{"id":"W2028238637","doi":"10.1186/1471-2288-11-95","title":"A comparison of a new multinomial stopping rule with stopping rules of fleming and gehan in single arm phase II cancer clinical trials","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Ontario Clinical Oncology Group; McMaster University; Juravinski Hospital; Juravinski Cancer Centre","funders":"","keywords":"Early stopping; Clinical trial; Medicine; Statistics; Internal medicine; Mathematics; Computer science; Artificial intelligence","score_opus":0.9873198587340849,"score_gpt":0.8050490733946936,"score_spread":0.18227078533939134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028238637","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":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5894919,0.00039652706,0.40857166,0.00015769244,0.00028892167,0.0007670432,0.000024820272,0.000020164112,0.0002812615],"genre_scores_gemma":[0.12675728,0.00018100966,0.8723948,0.00003702178,0.00046391555,0.000073450916,0.0000011977125,0.000038171074,0.0000531508],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.893865,0.09427879,0.00719501,0.0011355255,0.0022848663,0.0012408274],"domain_scores_gemma":[0.22763677,0.76835597,0.0016865929,0.00071442453,0.000532055,0.0010741878],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23238027,0.0002731299,0.0042969524,0.0004853364,0.00010432164,0.00001118003,0.0006776627,0.0007735499,0.0014366535],"category_scores_gemma":[0.8835946,0.00020080364,0.00024889142,0.0004610848,0.0024700298,0.000063381696,0.00072141545,0.0018338797,0.0000019438291],"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":[0.014180636,0.007214798,0.02485406,0.0014392401,0.00032986785,0.000057523797,0.007049658,0.0000020484538,0.0072501223,0.030073509,0.00043504368,0.9071135],"study_design_scores_gemma":[0.041279722,0.01939569,0.0076124542,0.0056630163,0.00050856586,0.000029949375,0.00505005,0.0068178247,0.041299764,0.87120074,0.00040568528,0.000736541],"about_ca_topic_score_codex":0.0015176802,"about_ca_topic_score_gemma":0.0009899318,"teacher_disagreement_score":0.90637696,"about_ca_system_score_codex":0.000081575046,"about_ca_system_score_gemma":0.0018829255,"threshold_uncertainty_score":0.9994762},"labels":[],"label_agreement":null},{"id":"W2028361935","doi":"10.1186/1471-2288-7-20","title":"Developing algorithms for healthcare insurers to systematically monitor surgical site infection rates","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Surgical site infection prevention","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"GlaxoSmithKline (Canada)","funders":"U.S. Public Health Service; Centers for Disease Control and Prevention; UnitedHealth Group; Sanofi; GlaxoSmithKline; Pfizer","keywords":"Operationalization; Descriptive statistics; Quartile; Health care; Medicine; Computer science; Actuarial science; Database; Data mining; Confidence interval; Statistics; Business","score_opus":0.5889505602967168,"score_gpt":0.6257357425118332,"score_spread":0.036785182215116397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028361935","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31357726,0.00020120261,0.6780006,0.0053008255,0.0006854758,0.0018180704,0.000003734422,0.0001296894,0.00028310748],"genre_scores_gemma":[0.36355317,0.00028796084,0.62939024,0.0013781966,0.0030820724,0.00093044544,0.000099110126,0.000095767624,0.0011830485],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98672444,0.007818289,0.0012203843,0.0007217875,0.0022093826,0.0013057318],"domain_scores_gemma":[0.93874997,0.057419203,0.00012065189,0.00036580503,0.0015856314,0.0017587226],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07651277,0.0002261251,0.0009261367,0.0008911187,0.0003079656,0.000033714514,0.0001815493,0.0007807526,0.00084492954],"category_scores_gemma":[0.09754344,0.00017999295,0.00027601412,0.0014635489,0.0002973175,0.00007873907,0.00020296407,0.0010950919,0.00025922665],"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":[0.008711003,0.0007067674,0.18565805,0.009397818,0.00032797383,0.00081871933,0.00067661284,0.000013538395,0.0039877286,0.037490185,0.0010060678,0.75120556],"study_design_scores_gemma":[0.022375515,0.012252078,0.5722572,0.009072462,0.00026866203,0.006414374,0.001735808,0.004959234,0.03990895,0.01993024,0.30909252,0.0017329422],"about_ca_topic_score_codex":0.0007764236,"about_ca_topic_score_gemma":0.0008764667,"teacher_disagreement_score":0.7494726,"about_ca_system_score_codex":0.0007392425,"about_ca_system_score_gemma":0.0012578616,"threshold_uncertainty_score":0.95092446},"labels":[],"label_agreement":null},{"id":"W2033640301","doi":"10.1186/1471-2288-13-114","title":"Heterogeneity and event dependence in the analysis of sickness absence","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Frailty in Older Adults","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Duration (music); Context (archaeology); Event (particle physics); Poisson distribution; Set (abstract data type); Econometrics; Poisson regression; Survival analysis; Conditional probability; Psychology; Public health; Medicine; Computer science; Statistics; Population; Environmental health; Geography; Economics; Mathematics; Internal medicine","score_opus":0.4047481177464166,"score_gpt":0.5467519255641723,"score_spread":0.14200380781775568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033640301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9630099,0.00066738063,0.031359196,0.004114982,0.000046686717,0.0005264102,0.0000021920412,0.000008384206,0.00026487652],"genre_scores_gemma":[0.9767959,0.00038084053,0.022098547,0.00043228854,0.000048386617,0.00013092741,0.000005570919,0.000006870684,0.000100686215],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98673415,0.009942625,0.0004831171,0.0003934085,0.0019278476,0.0005188218],"domain_scores_gemma":[0.96087,0.037710726,0.00006718815,0.00064084254,0.00034817256,0.0003630715],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02634859,0.0001013179,0.0006156319,0.0005512612,0.000047325662,0.00001023987,0.00048598164,0.00022058202,0.0010296819],"category_scores_gemma":[0.08116497,0.000061216255,0.000106272426,0.0015306933,0.0011641303,0.000049894676,0.00026073412,0.000823444,0.00002897897],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033447807,0.00050907675,0.817313,0.00060475565,0.000511087,0.00024311547,0.0027264217,0.00004535538,0.0067229476,0.002250994,0.000852215,0.16788651],"study_design_scores_gemma":[0.0006680257,0.00023923992,0.9843337,0.00009920801,0.00009673856,0.00010019297,0.0010553155,0.010714654,0.0011557541,0.0013076967,0.0001680271,0.000061454135],"about_ca_topic_score_codex":0.0043342933,"about_ca_topic_score_gemma":0.01124143,"teacher_disagreement_score":0.16782506,"about_ca_system_score_codex":0.000042023345,"about_ca_system_score_gemma":0.00045139962,"threshold_uncertainty_score":0.99988353},"labels":[],"label_agreement":null},{"id":"W2036060563","doi":"10.1186/1471-2288-10-82","title":"Inter-rater agreement and reliability of the COSMIN (COnsensus-based Standards for the selection of health status Measurement Instruments) Checklist","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":289,"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":"Vrije Universiteit Amsterdam; University of Oxford; McMaster University; Goddard Space Flight Center; University of Washington","keywords":"Checklist; Kappa; Inter-rater reliability; Intraclass correlation; Cohen's kappa; Reliability (semiconductor); Medicine; Quality (philosophy); Agreement; Terminology; Psychology; Applied psychology; Physical therapy; Medical physics; Clinical psychology; Statistics; Psychometrics; Rating scale; Mathematics","score_opus":0.5948043968788056,"score_gpt":0.5666070490965269,"score_spread":0.02819734778227867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036060563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7360402,0.00026790256,0.23604037,0.023667121,0.0011681955,0.0025354896,0.00008794098,0.000008788287,0.00018402388],"genre_scores_gemma":[0.9704114,0.00007649354,0.028815242,0.0003273527,0.00007062288,0.00017400643,0.0000013686418,0.000008853127,0.00011463904],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9401533,0.03720393,0.0030697882,0.0011458405,0.01720643,0.0012206894],"domain_scores_gemma":[0.93022543,0.06034505,0.00081088947,0.0016480009,0.006530828,0.00043981196],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39401495,0.00016993107,0.0006664849,0.00020724724,0.00048070043,0.000051671,0.001216097,0.00020023438,0.0010586313],"category_scores_gemma":[0.38449427,0.000079416146,0.00021222742,0.0007389415,0.0028427758,0.000042088726,0.00044543628,0.00094143,0.0000024414717],"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":[0.002453449,0.00089207065,0.36769968,0.00085631653,0.00009789977,3.107363e-7,0.0010337174,0.00013585147,0.01665502,0.0025695155,0.018010149,0.58959603],"study_design_scores_gemma":[0.007085396,0.0044682357,0.56682533,0.0006157815,0.000078459896,0.000008793487,0.0054242373,0.026630612,0.07637274,0.07185221,0.2402325,0.00040569247],"about_ca_topic_score_codex":0.001463431,"about_ca_topic_score_gemma":0.009785491,"teacher_disagreement_score":0.5891903,"about_ca_system_score_codex":0.00033257526,"about_ca_system_score_gemma":0.00629961,"threshold_uncertainty_score":0.9998709},"labels":[],"label_agreement":null},{"id":"W2037821323","doi":"10.1186/1471-2288-7-17","title":"Relation between body mass index and depression: a structural equation modeling approach","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Bariatric Surgery and Outcomes","field":"Medicine","cited_by":89,"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","funders":"","keywords":"Body mass index; Depression (economics); Obesity; Structural equation modeling; Dyslipidemia; Medicine; Diabetes mellitus; Internal medicine; Endocrinology","score_opus":0.544310040841943,"score_gpt":0.5323540743398104,"score_spread":0.011955966502132598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037821323","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":[0.4260084,0.00035596083,0.5720439,0.0002825961,0.00015874002,0.00022769351,4.4279508e-7,0.000032134765,0.00089015753],"genre_scores_gemma":[0.8474575,0.0000607814,0.15114245,0.00010269484,0.0010012217,0.000013960538,0.00003774162,0.000016623575,0.00016702051],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99232465,0.004162288,0.00059717934,0.00048814827,0.0017329417,0.00069477776],"domain_scores_gemma":[0.9652886,0.033347793,0.00007353438,0.00029700476,0.00027575763,0.0007173189],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04132051,0.00013766195,0.00053296547,0.00052256987,0.00020669705,0.000015140316,0.00014572265,0.000674747,0.00021282748],"category_scores_gemma":[0.07844442,0.00010116867,0.00007987325,0.0005425145,0.00027280764,0.00010219834,0.000159207,0.0013855171,0.000008211642],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084115553,0.00001865999,0.92817265,0.00017034206,0.000045928176,0.000045577843,0.00025393843,0.000059587983,0.000281991,0.0017646649,0.00006413523,0.0682814],"study_design_scores_gemma":[0.001886291,0.000117939606,0.6313518,0.000076298325,0.000055850818,0.00013057562,0.00078599795,0.35324115,0.00021840849,0.011886087,0.0001112122,0.0001383573],"about_ca_topic_score_codex":0.00018625625,"about_ca_topic_score_gemma":0.000016552262,"teacher_disagreement_score":0.42144912,"about_ca_system_score_codex":0.000085725325,"about_ca_system_score_gemma":0.00054972793,"threshold_uncertainty_score":0.9871623},"labels":[],"label_agreement":null},{"id":"W2038221914","doi":"10.1186/1471-2288-12-15","title":"An empirical comparison of methods for analyzing correlated data from a discrete choice survey to elicit patient preference for colorectal cancer screening","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; St. Joseph’s Healthcare Hamilton; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Multinomial logistic regression; Statistics; Multivariate probit model; Multinomial probit; Econometrics; Logistic regression; Probit model; Bivariate analysis; Correlation; Probit; Mathematics","score_opus":0.9193839092889916,"score_gpt":0.628187695034638,"score_spread":0.2911962142543536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038221914","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":[0.46160498,0.0011072585,0.5354539,0.00011120849,0.00023212463,0.00052668015,0.00093687314,0.000007019165,0.000019902205],"genre_scores_gemma":[0.54049367,0.00007854465,0.45802918,0.00007957905,0.00015598077,0.00028953172,0.00083650975,0.000022481487,0.000014529083],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9933675,0.0038625305,0.0011246492,0.00075995084,0.00014183109,0.0007435499],"domain_scores_gemma":[0.95690095,0.041532338,0.0003520166,0.0005632457,0.00008885877,0.0005625806],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039473135,0.00015707457,0.0009044576,0.00025132715,0.00016720133,0.000022906406,0.00085927726,0.00032813824,0.00082989514],"category_scores_gemma":[0.059283335,0.00015862647,0.00008804153,0.0002841961,0.00023350563,0.00026075973,0.00049147714,0.00038562386,0.000026101927],"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":[0.00052812556,0.00016548384,0.9393342,0.00003236114,0.00009666905,2.8935343e-8,0.0008729699,0.00034879163,0.00037063184,0.00044137012,0.00095375354,0.05685561],"study_design_scores_gemma":[0.0007222088,0.0005199289,0.7138903,0.000029524954,0.000017904933,2.5539597e-7,0.0002529298,0.2790669,0.00077824836,0.0010232495,0.003528289,0.00017026071],"about_ca_topic_score_codex":0.007996823,"about_ca_topic_score_gemma":0.0036447672,"teacher_disagreement_score":0.27871808,"about_ca_system_score_codex":0.00016855965,"about_ca_system_score_gemma":0.0001436976,"threshold_uncertainty_score":0.998609},"labels":[],"label_agreement":null},{"id":"W2039269107","doi":"10.1186/1471-2288-10-11","title":"Association between framing of the research question using the PICOT format and reporting quality of randomized controlled trials","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Blinding; Consolidated Standards of Reporting Trials; Quality Score; Medicine; Research design; Randomized controlled trial; Population; Sample size determination; Family medicine; Clinical trial; MEDLINE; Statistics; Internal medicine; Environmental health; Mathematics","score_opus":0.9848394258729563,"score_gpt":0.7876964260500048,"score_spread":0.19714299982295147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039269107","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":[0.7712134,0.0007632155,0.22085337,0.0029377881,0.0003675525,0.003159721,0.0000041456233,0.0000020291977,0.0006987428],"genre_scores_gemma":[0.9480155,0.000120402045,0.05019671,0.00003536716,0.0003930356,0.00015649023,0.0000013615977,0.000008556505,0.0010725495],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.0084558735,0.92403454,0.039309286,0.0007003673,0.026874168,0.000625776],"domain_scores_gemma":[0.0013485128,0.9511934,0.03626013,0.00250011,0.008454738,0.00024313957],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.99283797,0.00016611401,0.016679298,0.0006777593,0.00050784304,0.00023649554,0.002066084,0.0005132755,0.0017366556],"category_scores_gemma":[0.99845016,0.000050691797,0.0032978568,0.001893297,0.0016712348,0.00011316842,0.00074614905,0.002035,0.000009926548],"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":[0.022059193,0.00019743518,0.6986077,0.0012973738,0.005510972,0.0000040603904,0.006774228,0.000035238947,0.045860235,0.1081776,0.005059711,0.10641626],"study_design_scores_gemma":[0.12623124,0.00021930724,0.11749078,0.0009723183,0.003012126,0.000043140175,0.012290354,0.08905983,0.0060880757,0.6409274,0.0032560364,0.00040942652],"about_ca_topic_score_codex":0.00089364377,"about_ca_topic_score_gemma":0.0006501692,"teacher_disagreement_score":0.5811169,"about_ca_system_score_codex":0.000056759614,"about_ca_system_score_gemma":0.0012548378,"threshold_uncertainty_score":0.9991759},"labels":[],"label_agreement":null},{"id":"W2041448343","doi":"10.1186/1471-2288-9-68","title":"A multidisciplinary systematic literature review on frailty: Overview of the methodology used by the Canadian Initiative on Frailty and Aging","year":2009,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Frailty in Older Adults","field":"Medicine","cited_by":99,"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 Calgary; McGill University Health Centre; Université de Montréal","funders":"Canadian Institutes of Health Research; Max Bell Foundation","keywords":"Systematic review; Multidisciplinary approach; Management science; Identification (biology); Variety (cybernetics); Flexibility (engineering); Set (abstract data type); Conceptual framework; Grey literature; Quality (philosophy); MEDLINE; Computer science; Psychology; Sociology; Political science; Social science; Engineering","score_opus":0.7288687374509886,"score_gpt":0.602523009904734,"score_spread":0.12634572754625462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041448343","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":[0.0000037144641,0.97292995,0.00034885915,0.014962813,0.00034407765,0.008163325,0.0001459232,0.000037766786,0.0030635907],"genre_scores_gemma":[0.0000060846473,0.98243576,0.0070425933,0.0053055743,0.00030345572,0.0009098769,0.00011283915,0.00014901922,0.003734785],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.87559074,0.11680595,0.0019878238,0.0012481931,0.0030419012,0.0013254123],"domain_scores_gemma":[0.83244133,0.16212599,0.00095096766,0.0026033863,0.0005338713,0.0013444723],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.062353306,0.00090387557,0.007156702,0.00096444465,0.00047341458,0.000044740784,0.0019095741,0.001975495,0.0006407745],"category_scores_gemma":[0.26882312,0.00042258945,0.00097045064,0.0024099622,0.0021107069,0.00004531419,0.00070474803,0.0075071435,0.00009774097],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050715407,0.00011631746,0.000008302931,0.62108845,0.00044125668,0.00027465093,0.0008454059,7.333586e-8,0.0000014999648,0.002267334,0.018531794,0.3563742],"study_design_scores_gemma":[0.00067084027,0.0007637839,0.00005706959,0.71431124,0.0010210874,0.0011011609,0.00013330785,0.000015757145,0.00000428501,0.0007383669,0.2809056,0.00027747732],"about_ca_topic_score_codex":0.0034575472,"about_ca_topic_score_gemma":0.03191265,"teacher_disagreement_score":0.3560967,"about_ca_system_score_codex":0.0006859783,"about_ca_system_score_gemma":0.007070002,"threshold_uncertainty_score":0.9998226},"labels":[],"label_agreement":null},{"id":"W2042253023","doi":"10.1186/1471-2288-9-43","title":"Timing of surgical antibiotic prophylaxis administration: Complexities of analysis","year":2009,"lang":"en","type":"letter","venue":"BMC Medical Research Methodology","topic":"Advanced Statistical Process Monitoring","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":"St. Michael's Hospital; Toronto Metropolitan University; University Health Network; University of Toronto; SickKids Foundation; The Wilson Centre; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; University Health Network","keywords":"Documentation; Data extraction; Protocol (science); Medicine; Intensive care medicine; Antibiotics; Antibiotic prophylaxis; Coding (social sciences); Data collection; Computer science; Risk analysis (engineering); MEDLINE; Alternative medicine; Pathology; Statistics","score_opus":0.8190355955151777,"score_gpt":0.6585639053996756,"score_spread":0.1604716901155021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042253023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018133032,0.0010845112,0.9008107,0.088979006,0.000521819,0.0005075465,0.00015633517,0.00003670632,0.00609008],"genre_scores_gemma":[0.21961129,0.0003514779,0.76183426,0.007408508,0.0056213904,0.00003481781,0.00022842645,0.00007880137,0.004831038],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95142037,0.028876623,0.003060099,0.0013651754,0.014156495,0.0011212291],"domain_scores_gemma":[0.7263522,0.26878405,0.0008276399,0.0011409121,0.0025209943,0.00037418015],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.05987178,0.0003455753,0.0030039435,0.0026483198,0.00017194275,0.0000661054,0.0028921096,0.0016783448,0.0036002754],"category_scores_gemma":[0.35212272,0.0002512382,0.00059089484,0.00486872,0.00460534,0.000115489085,0.00060501514,0.004487061,0.00004742643],"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":[0.002122504,0.00068373093,0.008470824,0.0043389834,0.0015797329,0.008354301,0.0008933297,0.0003348423,0.00024325753,0.024135802,0.46292615,0.48591655],"study_design_scores_gemma":[0.0021577454,0.007654492,0.007963073,0.0012203489,0.00081709673,0.000361632,0.002061758,0.013510025,0.005743485,0.67089254,0.28611892,0.0014988902],"about_ca_topic_score_codex":0.0001371847,"about_ca_topic_score_gemma":0.00014996505,"teacher_disagreement_score":0.6467567,"about_ca_system_score_codex":0.00009251585,"about_ca_system_score_gemma":0.0026905553,"threshold_uncertainty_score":0.999994},"labels":[],"label_agreement":null},{"id":"W2046203927","doi":"10.1186/1471-2288-8-29","title":"Examining intra-rater and inter-rater response agreement: A medical chart abstraction study of a community-based asthma care program","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Asthma and respiratory diseases","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"National Center for Advancing Translational Sciences; University of Toronto; Ontario Ministry of Health and Long-Term Care","keywords":"Asthma; Cohen's kappa; Kappa; Medicine; Spirometry; Referral; Concordance; Inter-rater reliability; Chart; Confidence interval; Medical record; Physical therapy; Family medicine; Statistics; Internal medicine; Mathematics","score_opus":0.5117448704984061,"score_gpt":0.5379487246087348,"score_spread":0.02620385411032866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046203927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99528325,0.00041868872,0.0017537847,0.0008077218,0.00013439496,0.0012952912,0.0000057189914,0.00006836722,0.00023279499],"genre_scores_gemma":[0.99464685,0.000059255926,0.0037585602,0.0007495611,0.00021769168,0.00035883242,0.000034395125,0.000033188244,0.00014168059],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96504575,0.030131837,0.0008407353,0.00045115882,0.0028028155,0.00072767725],"domain_scores_gemma":[0.979001,0.018293742,0.00012949304,0.0006782033,0.0006427407,0.0012548376],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02550752,0.0002415798,0.0008266768,0.0006528649,0.00040833416,0.000014991391,0.00038292794,0.0004966555,0.0017122643],"category_scores_gemma":[0.044221673,0.00017375026,0.00009738857,0.00045269678,0.0021221638,0.00006507249,0.00038351896,0.0023184754,0.000029957426],"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":[0.038827702,0.010504409,0.25959036,0.0027417752,0.00031098863,0.0049514063,0.03546151,0.0000032165508,0.0052504623,0.000017766186,0.0021919454,0.64014846],"study_design_scores_gemma":[0.015792202,0.042606726,0.81247467,0.0011806902,0.00009075677,0.00088746607,0.10023734,0.0004887658,0.0031173846,0.000029481682,0.02271552,0.00037899325],"about_ca_topic_score_codex":0.00038672844,"about_ca_topic_score_gemma":0.000677856,"teacher_disagreement_score":0.63976943,"about_ca_system_score_codex":0.00009802488,"about_ca_system_score_gemma":0.002566342,"threshold_uncertainty_score":0.9999832},"labels":[],"label_agreement":null},{"id":"W2046318951","doi":"10.1186/1471-2288-13-46","title":"‘Trying to pin down jelly’ - exploring intuitive processes in quality assessment for meta-ethnography","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":156,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institute for Health and Care Research","keywords":"Rigour; Qualitative research; Interpretation (philosophy); Context (archaeology); CLARITY; Quality (philosophy); Inclusion (mineral); Nursing research; Psychology; Health care; Engineering ethics; Management science; Epistemology; Applied psychology; Medical education; Medicine; Computer science; Sociology; Nursing; Social psychology; Social science; Political science; Engineering","score_opus":0.99372823810203,"score_gpt":0.7774698873370017,"score_spread":0.2162583507650283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046318951","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":[0.10326382,0.0011354729,0.8817758,0.007333046,0.00031181832,0.0036434499,0.000013170604,0.000012473529,0.0025109737],"genre_scores_gemma":[0.13181932,0.00022840447,0.8420345,0.0013064283,0.00030484423,0.022424435,0.000009745753,0.000033217017,0.0018390772],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6090611,0.34471065,0.01605265,0.003434687,0.02458398,0.002156874],"domain_scores_gemma":[0.11062527,0.8677865,0.0028468107,0.005523238,0.010924515,0.0022936226],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.74262285,0.0003897605,0.0065015955,0.0024081238,0.0002886581,0.00062678655,0.0038554035,0.00030305758,0.033003353],"category_scores_gemma":[0.88497853,0.00018902252,0.0018411024,0.0064893328,0.00046587476,0.0004808103,0.0009265756,0.0010365973,0.0011858986],"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":[0.00028329808,0.0008445462,0.0542303,0.0036791558,0.0030847015,0.000033001674,0.011479828,0.0002344388,0.0017823596,0.053896952,0.10024787,0.77020353],"study_design_scores_gemma":[0.0024291258,0.0014241332,0.08152368,0.0006170114,0.0008532476,0.000023206674,0.05184869,0.009689278,0.0019473493,0.5639636,0.28426734,0.001413341],"about_ca_topic_score_codex":0.0009986557,"about_ca_topic_score_gemma":0.0031295721,"teacher_disagreement_score":0.7687902,"about_ca_system_score_codex":0.00011388699,"about_ca_system_score_gemma":0.0015895054,"threshold_uncertainty_score":0.99959177},"labels":[],"label_agreement":null},{"id":"W2049234896","doi":"10.1186/1471-2288-11-173","title":"Comparison of ICD code-based diagnosis of obesity with measured obesity in children and the implications for health care cost estimates","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University; University of Alberta","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale; Heart and Stroke Foundation of Canada","keywords":"Medicine; Obesity; Diagnosis code; Health care; Population; Public health; Environmental health; Gerontology; Internal medicine","score_opus":0.8148504542725739,"score_gpt":0.6640189070090887,"score_spread":0.15083154726348513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049234896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6122469,0.0019682394,0.36531284,0.0130462125,0.00010356409,0.0067705535,0.0001799626,0.000038776965,0.00033297684],"genre_scores_gemma":[0.91530883,0.00030824757,0.08197064,0.00071327377,0.0000441952,0.0015691097,0.000069479414,0.000011602468,0.0000046396244],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98365796,0.013353568,0.0012378306,0.0002594805,0.00078904635,0.00070214743],"domain_scores_gemma":[0.93335193,0.06448122,0.00048013136,0.0003846098,0.0008234032,0.00047867463],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04496086,0.000114056034,0.0009231957,0.00024763143,0.000633494,0.000002158436,0.00040515352,0.00033523832,0.00012892374],"category_scores_gemma":[0.067693025,0.00006885079,0.000049726666,0.00040236767,0.0014310199,0.000037807826,0.00013027836,0.0011750574,0.000002710474],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013386125,0.0001765333,0.9656868,0.0020163099,0.00001522621,6.519616e-8,0.009101272,0.0000041710273,0.0000013163082,0.010385346,0.0012335832,0.010040774],"study_design_scores_gemma":[0.0044363183,0.00063712307,0.98747134,0.0006539282,0.000017662074,0.000001029589,0.002529251,0.0017349635,0.00014811083,0.0021462054,0.00016212728,0.00006194328],"about_ca_topic_score_codex":0.0064184107,"about_ca_topic_score_gemma":0.013370891,"teacher_disagreement_score":0.30306196,"about_ca_system_score_codex":0.0001426955,"about_ca_system_score_gemma":0.0044384073,"threshold_uncertainty_score":0.98341376},"labels":[],"label_agreement":null},{"id":"W2051000394","doi":"10.1186/1471-2288-10-51","title":"Pan-Canadian assessment of pandemic immunization data collection: study methodology","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Influenza Virus Research Studies","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":"Public Health Ontario; University Health Network; Ottawa Hospital; Public Health Agency of Canada; Institute for Clinical Evaluative Sciences; McGill University; University of British Columbia; University of Alberta; Toronto Public Health; Centre for Advancing Health Outcomes; Centre for Social Innovation; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Public Health Agency; Institute for Clinical Evaluative Sciences; Public Health Agency of Canada","keywords":"Data collection; Vaccination; Immunization; Usability; Medicine; Pandemic; Observational study; Family medicine; Medical emergency; Computer science; Coronavirus disease 2019 (COVID-19); Immunology; Disease; Statistics","score_opus":0.8556963831643124,"score_gpt":0.6870912643858116,"score_spread":0.16860511877850082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051000394","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":[0.8256803,0.0011881385,0.14799537,0.0054254555,0.0018535529,0.0051866127,0.00007007145,0.0001535754,0.012446932],"genre_scores_gemma":[0.45410526,0.0013722744,0.5413788,0.00047099774,0.0007213688,0.00037180833,0.00015077133,0.00006951801,0.0013591886],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9566107,0.036074273,0.0011557043,0.0010688503,0.0035710891,0.0015193778],"domain_scores_gemma":[0.90218204,0.09002426,0.00021376005,0.0032771053,0.0026621707,0.0016406422],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12315784,0.00024737124,0.001283056,0.0016843375,0.00052693306,0.000022721044,0.001664105,0.00071531784,0.0041138446],"category_scores_gemma":[0.37373692,0.00019818774,0.00010203123,0.0020230063,0.0021668866,0.00012662383,0.0018242358,0.0042827222,0.000062367544],"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":[0.0011023898,0.0010851152,0.86877424,0.0004078236,0.00071101164,0.0002432188,0.0012626695,0.0000031910083,0.02542265,0.0043526255,0.0071629602,0.08947209],"study_design_scores_gemma":[0.0064338986,0.0038135229,0.9398042,0.00011771218,0.00018325333,0.0003816661,0.0058407835,0.0065606562,0.0009392911,0.0019379429,0.033662736,0.0003243349],"about_ca_topic_score_codex":0.094794944,"about_ca_topic_score_gemma":0.38392812,"teacher_disagreement_score":0.39338344,"about_ca_system_score_codex":0.00031063854,"about_ca_system_score_gemma":0.018015843,"threshold_uncertainty_score":0.99801445},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":true,"about_ca_topic":true,"confidence":"medium"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2051284664","doi":"10.1186/1471-2288-10-15","title":"Electronic search strategies to identify reports of cluster randomized trials in MEDLINE: low precision will improve with adherence to reporting standards","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University; Institute of Population and Public Health; University of Ottawa; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Cluster (spacecraft); Medicine; Randomized controlled trial; Medical physics; Family medicine; Information retrieval; Computer science; Pathology; Political science","score_opus":0.8874814456484222,"score_gpt":0.7286403869770463,"score_spread":0.158841058671376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051284664","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":[0.50192505,0.00019783746,0.49208456,0.0011449244,0.00035945658,0.00367178,0.000005801388,0.000005060289,0.00060553645],"genre_scores_gemma":[0.7628393,0.00006851463,0.23410618,0.00014457658,0.00026042748,0.00074786256,0.0000046792393,0.000028468914,0.0017999619],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.053052727,0.7913287,0.07854138,0.0053092,0.06851107,0.0032568756],"domain_scores_gemma":[0.032745328,0.9193839,0.019507391,0.008706307,0.017453857,0.0022032391],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9702266,0.00039494224,0.0143922325,0.002264447,0.00013841307,0.0006084632,0.002784166,0.0005145971,0.013477149],"category_scores_gemma":[0.9893037,0.00017296136,0.0017618312,0.0044439794,0.0007677826,0.00033903305,0.0009682023,0.0022255578,0.00011362537],"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":[0.13536358,0.0007270377,0.01588389,0.0019531709,0.0014251296,0.0013663217,0.009612027,0.0016464058,0.13972919,0.015840583,0.031222126,0.64523053],"study_design_scores_gemma":[0.14994548,0.0129043115,0.018106358,0.0061103343,0.0013897105,0.0023214843,0.03303381,0.05296625,0.06421838,0.61308116,0.042570475,0.0033522407],"about_ca_topic_score_codex":0.0006422964,"about_ca_topic_score_gemma":0.009666349,"teacher_disagreement_score":0.6418783,"about_ca_system_score_codex":0.00013941799,"about_ca_system_score_gemma":0.009556212,"threshold_uncertainty_score":0.9960587},"labels":[],"label_agreement":null},{"id":"W2053658037","doi":"10.1186/1471-2288-9-62","title":"Optimal strategy to identify incidence of diagnostic of diabetes using administrative data","year":2009,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Medicine; Diabetes mellitus; Incidence (geometry); McNemar's test; Medical record; Emergency medicine; Retrospective cohort study; Disease; Cohort; Diagnosis code; Pediatrics; Medical emergency; Family medicine; Internal medicine; Environmental health; Statistics; Population","score_opus":0.9452251642253298,"score_gpt":0.7572481249518934,"score_spread":0.18797703927343634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053658037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8159818,0.0002776433,0.17969857,0.001874715,0.0002886751,0.00085134484,0.000051490882,0.000021614014,0.0009541657],"genre_scores_gemma":[0.868274,0.00017930311,0.13026266,0.00081488176,0.00031291504,0.00003953264,0.000046305493,0.000008938679,0.00006149007],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9754809,0.019033946,0.0017466288,0.0004060395,0.002249414,0.0010830528],"domain_scores_gemma":[0.79906523,0.19714697,0.00047816208,0.0009817336,0.0010779101,0.0012499735],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07056766,0.00012651185,0.0007313181,0.00039541692,0.0003330233,0.000005034157,0.00125597,0.0005050178,0.0015582092],"category_scores_gemma":[0.54515046,0.00010165276,0.00004149207,0.00074967166,0.00057612703,0.00018240951,0.0006591815,0.0017442525,0.000071204966],"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":[0.0031611854,0.0015322138,0.21902297,0.022396537,0.00022953762,0.00013280328,0.03213781,0.0013143641,0.028495837,0.08343391,0.059730373,0.54841244],"study_design_scores_gemma":[0.0056616385,0.015699383,0.7304552,0.016113888,0.00014960002,0.000021965556,0.032619257,0.15769337,0.0069511533,0.027557759,0.0061276783,0.0009490583],"about_ca_topic_score_codex":0.0005107707,"about_ca_topic_score_gemma":0.00032707595,"teacher_disagreement_score":0.5474634,"about_ca_system_score_codex":0.000098560806,"about_ca_system_score_gemma":0.0071294345,"threshold_uncertainty_score":0.9993545},"labels":[],"label_agreement":null},{"id":"W2055183665","doi":"10.1186/1471-2288-8-24","title":"Comparison of two dependent within subject coefficients of variation to evaluate the reproducibility of measurement devices","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; King Faisal Specialist Hospital and Research Centre","keywords":"Reproducibility; Variation (astronomy); Statistics; Coefficient of variation; Computer science; Mathematics; Physics","score_opus":0.9180959778308471,"score_gpt":0.6669296548463675,"score_spread":0.2511663229844796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055183665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71341825,0.00023545278,0.28374502,0.0006714931,0.0006923231,0.0008342314,0.0000040450404,0.000006204551,0.0003929873],"genre_scores_gemma":[0.98003894,0.0000065375643,0.019683894,0.000037710644,0.00006717459,0.000040084433,0.0000024003355,0.0000063735743,0.00011687916],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6569015,0.21296763,0.01114701,0.0056049326,0.11148844,0.0018905235],"domain_scores_gemma":[0.8797942,0.09164526,0.0015999819,0.0054104915,0.020961026,0.00058907346],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.66115654,0.0001390532,0.0009044636,0.00069828826,0.00026190435,0.000020692918,0.0020738675,0.0001391853,0.0011296321],"category_scores_gemma":[0.73367405,0.00007917111,0.00016459852,0.002659784,0.0012878099,0.00008306014,0.0004911315,0.00040923155,0.0000419555],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032935988,0.0018213334,0.5628785,0.00021430239,0.00016326839,0.0000028242093,0.035287414,0.01974046,0.29103017,0.0045860936,0.004990783,0.07599123],"study_design_scores_gemma":[0.0025182576,0.0013098012,0.46598008,0.00020320079,0.00007547477,0.000008733773,0.0047108387,0.069957584,0.4336515,0.021122826,0.000267819,0.00019389445],"about_ca_topic_score_codex":0.0012680487,"about_ca_topic_score_gemma":0.005052481,"teacher_disagreement_score":0.2666207,"about_ca_system_score_codex":0.00015332644,"about_ca_system_score_gemma":0.0032909184,"threshold_uncertainty_score":0.99978346},"labels":[],"label_agreement":null},{"id":"W2055830213","doi":"10.1186/1471-2288-13-134","title":"How confidence intervals become confusion intervals","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of British Columbia","funders":"","keywords":"Confidence interval; Harm; Confusion; MEDLINE; Medicine; Point estimation; Statistical significance; Psychology; Statistics; Social psychology; Mathematics","score_opus":0.9715599684711017,"score_gpt":0.7146335475274728,"score_spread":0.25692642094362894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055830213","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":[0.12702332,0.0015639181,0.82760376,0.033149898,0.0009645898,0.0016779683,0.000005608925,0.000017932647,0.007993005],"genre_scores_gemma":[0.62401545,0.00045836263,0.22581057,0.0030855543,0.0008260259,0.0008188924,0.000012988754,0.000050248196,0.14492193],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.53529704,0.42168066,0.011075712,0.0024930146,0.027907347,0.0015462085],"domain_scores_gemma":[0.121887945,0.842664,0.005284731,0.012087064,0.014424304,0.0036519798],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.717023,0.000380291,0.0055829585,0.0012473374,0.0002651778,0.0018910032,0.0074325325,0.0005313557,0.26082382],"category_scores_gemma":[0.91610354,0.00017519172,0.0018362768,0.0021464976,0.0013619079,0.00047953526,0.0019631274,0.0014060831,0.02783901],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003837542,0.000121619414,0.01081347,0.0002480993,0.00020294898,0.000054241627,0.0009746597,0.0000016506779,0.0030207515,0.041950274,0.5410313,0.4015426],"study_design_scores_gemma":[0.0009875626,0.0006976826,0.028011728,0.0005038665,0.000090510075,0.00023808802,0.009674029,0.025053885,0.0011962985,0.35455394,0.57839996,0.00059247966],"about_ca_topic_score_codex":0.00043143326,"about_ca_topic_score_gemma":0.00062303524,"teacher_disagreement_score":0.60179317,"about_ca_system_score_codex":0.000073366944,"about_ca_system_score_gemma":0.00077423186,"threshold_uncertainty_score":0.99914515},"labels":[],"label_agreement":null},{"id":"W2056264205","doi":"10.1186/1471-2288-11-126","title":"A randomised trial and economic evaluation of the effect of response mode on response rate, response bias, and item non-response in a survey of doctors","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":252,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Health and Medical Research Council; Medical Research Council; University of Melbourne; Monash University","keywords":"Non-response bias; Response bias; Medicine; Family medicine; Response time; Interactive voice response; Mode (computer interface); Computer-assisted web interviewing; Psychology; Statistics; Social psychology; Computer science","score_opus":0.7886407742558061,"score_gpt":0.6233967687334692,"score_spread":0.16524400552233698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056264205","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":[0.99533737,0.00027405765,0.00029625327,0.00044390894,0.00049722847,0.0030252773,0.00005409806,0.00001116183,0.00006064522],"genre_scores_gemma":[0.9981073,0.00014499966,0.00122166,0.000029611332,0.00003960355,0.00027433212,0.0000019543427,0.000025321317,0.00015517793],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.030253433,0.9646453,0.001563008,0.00076018396,0.0019755152,0.0008025475],"domain_scores_gemma":[0.24599782,0.7519389,0.0005079758,0.0006796115,0.000511557,0.00036413994],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.93238676,0.00028984595,0.001583203,0.0014505977,0.00026414197,0.000012643152,0.00088353833,0.0009388429,0.00041336243],"category_scores_gemma":[0.9640813,0.0002015506,0.00021568898,0.0012187569,0.005872172,0.0001086586,0.00036267412,0.0009679274,0.0000037485834],"study_design_candidate":"randomized_trial","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":[0.9391641,0.00013995035,0.0317282,0.000046019446,0.000069175505,0.00001084495,0.009527367,0.000017543078,0.016980711,0.00005540626,0.000055989334,0.0022047118],"study_design_scores_gemma":[0.084921405,0.00675922,0.88413143,0.00016506352,0.000049383925,0.000004349996,0.00095405657,0.0007105719,0.021756928,0.00036252924,0.000035296405,0.00014977784],"about_ca_topic_score_codex":0.01326669,"about_ca_topic_score_gemma":0.013319283,"teacher_disagreement_score":0.8542427,"about_ca_system_score_codex":0.00026853514,"about_ca_system_score_gemma":0.00968721,"threshold_uncertainty_score":0.99683326},"labels":[],"label_agreement":null},{"id":"W2058090893","doi":"10.1186/1471-2288-9-50","title":"Data enhancement for co-morbidity measurement among patients referred for sleep diagnostic testing: an observational study","year":2009,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Obstructive Sleep Apnea Research","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale","keywords":"Observational study; Medicine; Kappa; Emergency medicine; Cohen's kappa; Population; Retrospective cohort study; Pediatrics; Physical therapy; Intensive care medicine; Internal medicine; Statistics","score_opus":0.9228884049243719,"score_gpt":0.6355039764328965,"score_spread":0.2873844284914754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058090893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6664115,0.000094307354,0.3225283,0.0012563262,0.00039827733,0.008884618,0.0001951774,0.000061947736,0.00016955943],"genre_scores_gemma":[0.7832011,0.000013556886,0.21195744,0.0002731391,0.0009362175,0.0019475172,0.0015459751,0.00005169663,0.00007337808],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9807054,0.008333743,0.0010459266,0.001537142,0.006848682,0.0015291064],"domain_scores_gemma":[0.8509032,0.13599156,0.00027634026,0.0027302091,0.007981904,0.0021167651],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.071203314,0.0003014278,0.0008913314,0.0004367265,0.00045615394,0.00004968975,0.0014860677,0.00032805165,0.0003988375],"category_scores_gemma":[0.70898443,0.00025152817,0.000105887055,0.0006495479,0.00065478415,0.00025459894,0.00049986993,0.0010216896,0.000017219278],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005243672,0.01037315,0.6835503,0.0005068466,0.00034104893,0.000048580438,0.00030958166,0.000006232761,0.003758426,0.000593231,0.0065833265,0.2886856],"study_design_scores_gemma":[0.010656084,0.016041225,0.94559324,0.00011402297,0.00012484488,0.0000053110816,0.00047022145,0.021259481,0.0013076882,0.0020429932,0.0021405867,0.0002443255],"about_ca_topic_score_codex":0.00022180384,"about_ca_topic_score_gemma":0.000877253,"teacher_disagreement_score":0.63778114,"about_ca_system_score_codex":0.0006317436,"about_ca_system_score_gemma":0.0015736981,"threshold_uncertainty_score":0.9999937},"labels":[],"label_agreement":null},{"id":"W2058992501","doi":"10.1186/1471-2288-13-149","title":"Comparison of sample characteristics in two pregnancy cohorts: community-based versus population-based recruitment methods","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Alberta Children's Hospital Research Institute; Children's Hospital Foundation; Alberta Children's Hospital Foundation; Children's Health Research Institute; Women and Children's Health Research Institute; Alberta Innovates; University of Calgary; Alberta Health Services","keywords":"Sample (material); Population; Pregnancy; Statistics; Medicine; Demography; Psychology; Obstetrics; Environmental health; Mathematics; Biology; Sociology","score_opus":0.9014231203671458,"score_gpt":0.7190122250703737,"score_spread":0.18241089529677212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058992501","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":[0.5857662,0.00032736963,0.40909493,0.0014123175,0.0010414455,0.0016439463,0.000022257058,0.000058996407,0.0006325699],"genre_scores_gemma":[0.43132022,0.00004864218,0.5675142,0.00018694437,0.00010083742,0.00063462596,0.000119275006,0.000020919593,0.000054315988],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.441564,0.5543336,0.0011214172,0.00040050605,0.0015687646,0.0010117199],"domain_scores_gemma":[0.41870728,0.57949096,0.00025048942,0.00057861744,0.0005168778,0.00045576703],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3609004,0.00020944569,0.0012445677,0.0007238808,0.0006858066,0.000029286466,0.0011509567,0.00058741745,0.0039336137],"category_scores_gemma":[0.7213517,0.0001906059,0.0001528079,0.0012793847,0.0021323008,0.00009681489,0.00021396724,0.0022029271,0.000030451813],"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":[0.00470099,0.00075714884,0.82784677,0.00017460188,0.00003805249,0.0000063352663,0.0039005876,0.000044090822,0.0002774184,0.0044419193,0.0001524426,0.15765962],"study_design_scores_gemma":[0.0040859175,0.00087285135,0.96532285,0.00048241357,0.000030851184,4.2552495e-7,0.0061059236,0.0051821787,0.001920286,0.010960356,0.004692472,0.00034348178],"about_ca_topic_score_codex":0.089784235,"about_ca_topic_score_gemma":0.05843404,"teacher_disagreement_score":0.36045128,"about_ca_system_score_codex":0.00033282585,"about_ca_system_score_gemma":0.0033931532,"threshold_uncertainty_score":0.9969769},"labels":[],"label_agreement":null},{"id":"W2059305841","doi":"10.1186/1471-2288-13-31","title":"Representativeness of an HIV cohort of the sites from which it is recruiting: results from the Ontario HIV Treatment Network (OHTN) cohort study","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Windsor Regional Hospital; Ottawa Hospital; University of Ottawa; St. Michael's Hospital; Maple Leaf Medical Clinic; Women's College Hospital; Ontario HIV Treatment Network; Public Health Ontario; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; McMaster University; Ontario HIV Treatment Network; University of Ottawa; University of Toronto; Hamilton Health Sciences","keywords":"Generalizability theory; Medicine; Cohort; Demography; Cohort study; Human immunodeficiency virus (HIV); Logistic regression; Representativeness heuristic; Internal medicine; Immunology; Psychology; Social psychology","score_opus":0.4430357152999285,"score_gpt":0.5297740922967391,"score_spread":0.08673837699681058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059305841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97541064,0.00026971154,0.002298766,0.011001978,0.00011805573,0.004459649,0.0002626976,0.000021952834,0.0061565638],"genre_scores_gemma":[0.9305937,0.00047017212,0.022576943,0.00040812738,0.0011593482,0.0016951264,0.00082571915,0.00007116968,0.04219968],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9610643,0.031846114,0.0015076877,0.0010342606,0.0035503777,0.0009972566],"domain_scores_gemma":[0.9067028,0.08615537,0.00047327526,0.0032790366,0.0022826348,0.0011068968],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027058013,0.00028179804,0.0012839937,0.00016079943,0.00035020016,0.000041156854,0.0013671683,0.00033614857,0.015375006],"category_scores_gemma":[0.097716816,0.00014726222,0.00037449767,0.0009802108,0.0015522515,0.00012104426,0.0008280053,0.0015784184,0.000120846744],"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":[0.0019375405,0.001472965,0.8923574,0.000025356785,0.0011094032,0.00003139247,0.008448639,0.000009358609,0.0010224718,0.00004934786,0.08599673,0.0075393664],"study_design_scores_gemma":[0.004217842,0.0043005696,0.9694845,0.0004990776,0.0002426598,0.000010262603,0.009523925,0.0022171189,0.003000767,0.0016989484,0.004674315,0.00013002902],"about_ca_topic_score_codex":0.41164762,"about_ca_topic_score_gemma":0.4019389,"teacher_disagreement_score":0.08132242,"about_ca_system_score_codex":0.00034411484,"about_ca_system_score_gemma":0.0027416204,"threshold_uncertainty_score":0.9855251},"labels":[],"label_agreement":null},{"id":"W2059967722","doi":"10.1186/1471-2288-13-18","title":"On the proportional hazards model for occupational and environmental case-control analyses","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Occupational and environmental lung diseases","field":"Medicine","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":"Université de Montréal","funders":"Institut de Veille Sanitaire; Fondation de France","keywords":"Statistics; Logistic regression; Estimator; Covariate; Variance (accounting); Confidence interval; Regression analysis; Population; Econometrics; Mathematics; Medicine; Environmental health","score_opus":0.4769634720420879,"score_gpt":0.5363105312126966,"score_spread":0.059347059170608674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059967722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8403661,0.0002771482,0.15173058,0.0059296554,0.00003771937,0.0012910288,0.00018635388,0.000015201232,0.00016619216],"genre_scores_gemma":[0.9742331,0.000045978024,0.021700457,0.0020101846,0.00019724018,0.0008560427,0.00012594079,0.000014912046,0.0008161363],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963108,0.0013821803,0.0002830429,0.00034570633,0.0013110181,0.00036729677],"domain_scores_gemma":[0.97854835,0.020686349,0.00004471383,0.00020127698,0.00005656665,0.00046272753],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041123307,0.00012424975,0.00025723927,0.000120605844,0.0002844299,0.000015658023,0.00010722478,0.00014428303,0.004950212],"category_scores_gemma":[0.014671557,0.000070944785,0.00011576982,0.00007059994,0.0009795364,0.00005346147,0.00008106736,0.00033913465,0.00008115021],"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":[0.02207903,0.0053954255,0.51294875,0.0010420543,0.0017512066,0.000982676,0.000669944,0.0039160303,0.024543203,0.13242932,0.11863097,0.17561138],"study_design_scores_gemma":[0.0021787072,0.00072189025,0.29185495,0.000038204675,0.000097857985,0.00065031566,0.00034459657,0.67617977,0.0001881192,0.027387615,0.00023159178,0.00012637215],"about_ca_topic_score_codex":0.00009153284,"about_ca_topic_score_gemma":0.0000299171,"teacher_disagreement_score":0.67226374,"about_ca_system_score_codex":0.00008919738,"about_ca_system_score_gemma":0.0004912641,"threshold_uncertainty_score":0.9959594},"labels":[],"label_agreement":null},{"id":"W2060836284","doi":"10.1186/1471-2288-14-130","title":"Creating groups with similar expected behavioural response in randomized controlled trials: a fuzzy cognitive map approach","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Computer science; Randomized controlled trial; Baseline (sea); Cognition; Sample (material); Psychology; Cognitive psychology; Clinical psychology; Machine learning; Medicine; Psychiatry","score_opus":0.4424440650821484,"score_gpt":0.5011508264224273,"score_spread":0.05870676134027886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060836284","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":[0.111052394,0.0003169701,0.88066745,0.0020394968,0.00018114457,0.0025825722,0.0000015695135,0.000099784615,0.0030586356],"genre_scores_gemma":[0.68204236,0.00006675161,0.31487882,0.0004929547,0.0002215863,0.001999235,0.00000775118,0.000019836532,0.0002706924],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.72569376,0.26696694,0.0016756908,0.0012176933,0.0030483105,0.0013975946],"domain_scores_gemma":[0.21081041,0.7853267,0.000646273,0.00077503594,0.0014386334,0.001002916],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.46636242,0.0003251891,0.004487496,0.0014129515,0.00034166602,0.00020361006,0.0015143211,0.00034999652,0.00013451565],"category_scores_gemma":[0.7333521,0.00019440311,0.00050119136,0.0017152943,0.0019976513,0.00034631978,0.0005977481,0.0014050805,0.000026892836],"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":[0.8521364,0.00068676076,0.0016785833,0.00012786312,0.00029780812,0.00037590886,0.012647365,0.000022425393,0.001485046,0.07454834,0.00012613893,0.0558674],"study_design_scores_gemma":[0.7023327,0.0020487537,0.0045298226,0.0010931791,0.0001480148,0.00016710983,0.008346486,0.25337687,0.00054083124,0.02660476,0.000098360404,0.00071311725],"about_ca_topic_score_codex":0.00035384402,"about_ca_topic_score_gemma":0.00026643346,"teacher_disagreement_score":0.57098997,"about_ca_system_score_codex":0.000103158105,"about_ca_system_score_gemma":0.0022710748,"threshold_uncertainty_score":0.79275286},"labels":[],"label_agreement":null},{"id":"W2060971566","doi":"10.1186/1471-2288-13-116","title":"Inconsistency in the items included in tools used in general health research and physical therapy to evaluate the methodological quality of randomized controlled trials: a descriptive analysis","year":2013,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics; University of Alberta","funders":"Alberta Innovates; Killam Trusts; University of Alberta; Canadian Institutes of Health Research; Physiotherapy Foundation of Canada; Alberta Innovates - Health Solutions; Women and Children's Health Research Institute; Children's Health Research Institute","keywords":"Blinding; Comparability; Randomized controlled trial; Quality (philosophy); Medicine; Descriptive statistics; Research design; Inclusion and exclusion criteria; Medical physics; Statistics; Alternative medicine; Mathematics; Surgery","score_opus":0.9962394484585844,"score_gpt":0.8198154726783908,"score_spread":0.17642397578019353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060971566","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":[0.022784678,0.9076906,0.026370294,0.005700271,0.00016706224,0.03694959,0.00003232675,0.0000039135693,0.00030126382],"genre_scores_gemma":[0.0025804332,0.946214,0.030853035,0.00033133547,0.00031914993,0.019265946,0.000025572832,0.0000339119,0.00037658753],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.013720521,0.90873617,0.044551633,0.0029040566,0.0283029,0.0017846999],"domain_scores_gemma":[0.0059882915,0.9736418,0.009602441,0.0057829316,0.00413949,0.0008450395],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","bibliometrics","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9914954,0.0009933463,0.11283014,0.009401452,0.00030801634,0.0008755353,0.008958339,0.0011387179,0.002574806],"category_scores_gemma":[0.98602754,0.00028670082,0.01337856,0.02446816,0.003672722,0.00015716428,0.0017905988,0.0058228495,0.00011898745],"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":[0.020377839,0.0009293134,0.0007047273,0.0019210059,0.005010441,0.000030139963,0.014314923,0.000022855824,0.000011553943,0.018103495,0.0014628813,0.93711084],"study_design_scores_gemma":[0.30331627,0.003450902,0.007063833,0.010463609,0.006916312,0.000068199115,0.05328022,0.031134846,0.000004271171,0.5010353,0.081210524,0.0020557572],"about_ca_topic_score_codex":0.0076577803,"about_ca_topic_score_gemma":0.014633808,"teacher_disagreement_score":0.9350551,"about_ca_system_score_codex":0.00044969632,"about_ca_system_score_gemma":0.006378876,"threshold_uncertainty_score":0.9999585},"labels":[],"label_agreement":null},{"id":"W2061351229","doi":"10.1186/1471-2288-12-101","title":"How pragmatic or explanatory is the randomized, controlled trial? The application and enhancement of the PRECIS tool to the evaluation of a smoking cessation trial","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pfizer (Canada); Dalhousie University; Toronto Rehabilitation Institute; University of Toronto; Centre for Addiction and Mental Health","funders":"University of Toronto; Pfizer","keywords":"Randomized controlled trial; Generalizability theory; External validity; Psychological intervention; Medicine; Research design; Smoking cessation; Explanatory power; Family medicine; Psychology; Nursing; Social psychology; Surgery","score_opus":0.8870880369461873,"score_gpt":0.7550064663428986,"score_spread":0.13208157060328873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061351229","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":[0.5350162,0.00034664094,0.22363384,0.1812041,0.001428373,0.057962805,0.000012659702,0.000009029143,0.00038636138],"genre_scores_gemma":[0.9471745,0.00020911884,0.0026884659,0.007057385,0.0009799704,0.041409962,0.000002500372,0.000012458176,0.00046562703],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.673115,0.31562287,0.0026951206,0.00038928387,0.0071420283,0.0010356863],"domain_scores_gemma":[0.4932324,0.5021619,0.0016684256,0.0011198656,0.001545351,0.00027199666],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.51293355,0.00011642642,0.0008390896,0.0001499539,0.00104417,0.000017591641,0.00086637505,0.0001918881,0.00089973415],"category_scores_gemma":[0.5977389,0.00003853066,0.00012579412,0.0007747139,0.0009377959,0.00010929754,0.0003635474,0.0007924559,0.000008993967],"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":[0.85646856,0.00009342757,0.00022759888,0.0003079044,0.00011504485,2.566501e-8,0.06076342,0.000004057454,0.0003341108,0.012595175,0.008820458,0.060270213],"study_design_scores_gemma":[0.9597502,0.00030459274,0.00082442793,0.00014388416,0.00019595135,0.0000010955702,0.015785761,0.0038261984,0.0004565112,0.004600891,0.014043009,0.000067530455],"about_ca_topic_score_codex":0.0004572347,"about_ca_topic_score_gemma":0.000852498,"teacher_disagreement_score":0.4121583,"about_ca_system_score_codex":0.0001912932,"about_ca_system_score_gemma":0.004981845,"threshold_uncertainty_score":0.9851458},"labels":[],"label_agreement":null},{"id":"W2063585734","doi":"10.1186/1471-2288-8-28","title":"Comparison of generalized estimating equations and quadratic inference functions using data from the National Longitudinal Survey of Children and Youth (NLSCY) database","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; University of Guelph; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Gee; Generalized estimating equation; Confidence interval; Covariate; Structural equation modeling; Statistics; Population; Estimating equations; Longitudinal study; Psychology; Demography; Medicine; Mathematics","score_opus":0.9273639114767059,"score_gpt":0.6624919635322225,"score_spread":0.26487194794448343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063585734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29140496,0.00020662132,0.7066236,0.000059348564,0.000043138058,0.00017108218,0.0014688468,0.0000061367614,0.000016227235],"genre_scores_gemma":[0.3573088,0.00003311916,0.6422898,0.000010203891,0.000056823596,0.0000048801917,0.0002875348,0.0000067959627,0.0000020144964],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9826892,0.014360413,0.0008325753,0.00044294164,0.0013774663,0.00029742092],"domain_scores_gemma":[0.7518448,0.24654523,0.00025647937,0.0005056636,0.000645569,0.00020224029],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025254233,0.00012292452,0.0006146127,0.00012435364,0.00032284373,0.000017905802,0.0005312879,0.00013072061,0.00027870547],"category_scores_gemma":[0.53189653,0.0000850425,0.000021736396,0.0004191868,0.0019340646,0.00009844114,0.0008116869,0.00054377416,0.0000011609726],"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":[0.00026038243,0.00036276662,0.803048,0.00021037819,0.00020957492,0.0000029473524,0.002534724,0.000030154213,0.0009526531,0.18233378,0.0006631041,0.009391528],"study_design_scores_gemma":[0.00069101603,0.00011415418,0.46329802,0.00020582556,0.0000845851,0.000020041656,0.00035628633,0.42923084,0.000109288965,0.10576951,6.11418e-7,0.00011980513],"about_ca_topic_score_codex":0.012395258,"about_ca_topic_score_gemma":0.0033500781,"teacher_disagreement_score":0.5066423,"about_ca_system_score_codex":0.000017513426,"about_ca_system_score_gemma":0.001048454,"threshold_uncertainty_score":0.9941813},"labels":[],"label_agreement":null},{"id":"W2064924394","doi":"10.1186/1471-2288-14-111","title":"You are how you recruit: a cohort and randomized controlled trial of recruitment strategies","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Alberta Hospital; University of Alberta","funders":"Canadian Institutes of Health Research; University of Alberta; Alberta Innovates; Alberta Innovates - Health Solutions; Women and Children's Health Research Institute; Children's Health Research Institute","keywords":"Medicine; Attendance; Population; Family medicine; Cohort; Demography; Randomized controlled trial; Internal medicine; Environmental health","score_opus":0.857900825114129,"score_gpt":0.6793127888128082,"score_spread":0.1785880363013208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064924394","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":[0.61885935,0.0048527457,0.17538482,0.10579945,0.0022860277,0.05097526,0.000017632852,0.00020414084,0.04162055],"genre_scores_gemma":[0.76971316,0.035454396,0.15409325,0.0013990445,0.0033928659,0.0141902,0.000040035095,0.00016246231,0.02155457],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.85700333,0.12620737,0.0028644686,0.001581791,0.010557644,0.001785381],"domain_scores_gemma":[0.18282056,0.80964977,0.0006814753,0.0016146859,0.0031804803,0.0020530492],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4573835,0.00033149187,0.0057678777,0.0007027661,0.00018666344,0.00007425435,0.0007500048,0.0017851796,0.0011144114],"category_scores_gemma":[0.91335684,0.0002089665,0.00072441663,0.0005703293,0.0076419637,0.00007870196,0.00074280595,0.0057134596,0.000024465766],"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":[0.89464396,0.00048059883,0.0010277283,0.0009320287,0.00057580654,0.00006289338,0.00022049283,5.1853317e-7,0.00044801936,0.087616585,0.0005157743,0.013475604],"study_design_scores_gemma":[0.87597626,0.003721972,0.00062877696,0.000730284,0.00025088535,0.000041261737,0.0013890696,0.0014271043,0.00032624396,0.113037415,0.0023102092,0.00016049214],"about_ca_topic_score_codex":0.00026002218,"about_ca_topic_score_gemma":0.00057912205,"teacher_disagreement_score":0.6834424,"about_ca_system_score_codex":0.00012056952,"about_ca_system_score_gemma":0.0056693405,"threshold_uncertainty_score":0.9999676},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"randomized_trial","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"randomized_trial","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2065772279","doi":"10.1186/1471-2288-12-133","title":"Constructing episodes of inpatient care: data infrastructure for population-based research","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Trauma and Emergency Care Studies","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Medicine; Intensive care; Emergency medicine; Hospital care; Population; Intensive care unit; Pediatrics; Intensive care medicine; Health care","score_opus":0.7846981599681311,"score_gpt":0.6307647250226533,"score_spread":0.15393343494547773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065772279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.879211,0.009027188,0.09841448,0.0029025814,0.0020323242,0.002379152,0.00029295744,0.00007722823,0.0056630555],"genre_scores_gemma":[0.7651401,0.00014047736,0.23315851,0.000064580425,0.0008316731,0.000112839465,0.00046950224,0.00002531689,0.000056988716],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98915136,0.005911399,0.00069441507,0.00050630915,0.002513869,0.0012226216],"domain_scores_gemma":[0.9472155,0.048437566,0.00010717006,0.0010905721,0.0024530252,0.00069614744],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030853659,0.00014970623,0.0007055877,0.00056953257,0.00029706807,0.000006207584,0.00060316717,0.00037237507,0.00071456213],"category_scores_gemma":[0.23966305,0.00011379293,0.00009751002,0.0008982489,0.0012520528,0.00008515573,0.00065407594,0.001134903,0.000006196032],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007922906,0.00010638232,0.75199205,0.001825957,0.00008952432,0.0000040370937,0.0012005076,0.0000039365586,0.00036927065,0.009722392,0.0087761115,0.22511752],"study_design_scores_gemma":[0.0076026553,0.002958705,0.8431335,0.0013024398,0.00023218749,0.000104078696,0.04969099,0.0032318896,0.008309895,0.0063148323,0.0765474,0.0005714015],"about_ca_topic_score_codex":0.0012402612,"about_ca_topic_score_gemma":0.0011826553,"teacher_disagreement_score":0.22454612,"about_ca_system_score_codex":0.00016405118,"about_ca_system_score_gemma":0.0021591878,"threshold_uncertainty_score":0.9979401},"labels":[],"label_agreement":null},{"id":"W2066564708","doi":"10.1186/1471-2288-13-112","title":"Making sense of complex data: a mapping process for analyzing findings of a realist review on guideline implementability","year":2013,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Juravinski Hospital; Juravinski Cancer Centre; St. Michael's Hospital","funders":"","keywords":"Operationalization; CLARITY; Computer science; Guideline; Set (abstract data type); Management science; Process (computing); Data science; Data extraction; Knowledge management; Data mining; MEDLINE; Medicine; Engineering; Epistemology","score_opus":0.9802235642890511,"score_gpt":0.7953916879685791,"score_spread":0.18483187632047204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066564708","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":[0.00003103509,0.8601012,0.12582152,0.0033386548,0.00017693941,0.00949208,0.00089667825,0.000030471074,0.00011138145],"genre_scores_gemma":[0.0000072727757,0.75716865,0.23647116,0.00089173205,0.00047703588,0.0004512571,0.004430291,0.00007287568,0.00002969714],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9599254,0.023365233,0.010567235,0.0016591195,0.003359085,0.0011239384],"domain_scores_gemma":[0.6290514,0.35581222,0.004547685,0.0043016784,0.0053571695,0.00092987315],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20555155,0.00052949076,0.006913619,0.0009227953,0.000120548466,0.000014758809,0.001362841,0.0007508225,0.0030909514],"category_scores_gemma":[0.7172881,0.00038764818,0.0008318045,0.0016596336,0.00094341487,0.00013917085,0.0014213818,0.0022475019,0.0000206048],"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":[0.00024895504,0.00022179927,0.00005834423,0.29129183,0.00033942237,0.000014201468,0.000029437722,1.4782198e-7,0.000011477512,0.000213847,0.027199732,0.6803708],"study_design_scores_gemma":[0.001535948,0.00088986615,0.000023136248,0.11756393,0.0019210455,0.00019237916,0.00037318227,0.00059227843,0.000006490346,0.00068636466,0.8759506,0.00026478415],"about_ca_topic_score_codex":0.0007657293,"about_ca_topic_score_gemma":0.00036547697,"teacher_disagreement_score":0.8487508,"about_ca_system_score_codex":0.00033652538,"about_ca_system_score_gemma":0.008092103,"threshold_uncertainty_score":0.99985754},"labels":[],"label_agreement":null},{"id":"W2076600566","doi":"10.1186/1471-2288-8-43","title":"Relative performance of different exposure modeling approaches for sulfur dioxide concentrations in the air in rural western Canada","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Provincial Laboratory of Public Health; University of Calgary; University of Alberta","funders":"Fondation pour la Recherche Médicale","keywords":"Context (archaeology); Statistics; Mean squared error; Linear regression; Air quality index; Air pollution; Environmental science; Regression analysis; Bayesian probability; Random effects model; Mathematics; Meteorology; Geography; Medicine; Chemistry","score_opus":0.6191462104325417,"score_gpt":0.47722526351825895,"score_spread":0.14192094691428275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076600566","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9386911,0.000080816506,0.05574717,0.0047629615,0.00003754977,0.00051853724,0.0000045198667,0.0000028504646,0.00015452011],"genre_scores_gemma":[0.9917045,0.00015717973,0.007361875,0.000535956,0.000033694363,0.0001364696,0.0000065500276,0.000005258241,0.000058511552],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9911493,0.0064968877,0.00047375725,0.00020204824,0.0010634235,0.00061458984],"domain_scores_gemma":[0.98459285,0.014932701,0.000055796536,0.00019048798,0.000018328667,0.00020983645],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011718876,0.00008514047,0.00028843308,0.000051861694,0.00015780018,0.0000019160182,0.00040051437,0.00013776,0.00008444822],"category_scores_gemma":[0.011334659,0.000055238852,0.000028916847,0.00026313632,0.0006412289,0.000096122465,0.000116212264,0.0006642383,0.0000021609042],"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":[0.00039292165,0.00016500402,0.96742415,0.00016618184,0.000005405966,0.000012692455,0.010966001,0.012783615,0.000098891345,0.0016882716,0.00031551515,0.0059813256],"study_design_scores_gemma":[0.0010807284,0.00042337322,0.7409901,0.00009596474,0.000002522962,0.000020419857,0.0061708177,0.24870981,0.0003862333,0.0018348362,0.00017937933,0.00010577871],"about_ca_topic_score_codex":0.18308449,"about_ca_topic_score_gemma":0.7685161,"teacher_disagreement_score":0.58543164,"about_ca_system_score_codex":0.0003074058,"about_ca_system_score_gemma":0.00102634,"threshold_uncertainty_score":0.9969933},"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":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"split"},{"id":"W2077643817","doi":"10.1186/1471-2288-11-25","title":"Validation of a case definition to define chronic dialysis using outpatient administrative data","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Libin Cardiovascular Institute of Alberta; University of Alberta; University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates; Fondation pour la Recherche Médicale; Government of Alberta; Alberta Heritage Foundation for Medical Research; Kidney Foundation of Canada","keywords":"Medicine; Dialysis; Cohen's kappa; Kidney disease; Population; Cohort; Outpatient clinic; Ambulatory care; Health care; Emergency medicine; Family medicine; Pediatrics; Internal medicine; Statistics","score_opus":0.9825541239168819,"score_gpt":0.7284863799768403,"score_spread":0.2540677439400416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077643817","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":[0.4566141,0.000120865174,0.5360366,0.000666619,0.00051965093,0.0011245529,0.000083570514,0.00003745807,0.004796573],"genre_scores_gemma":[0.6578617,0.00016049191,0.3402603,0.00059640076,0.0005138814,0.00023880723,0.00026749508,0.000020709815,0.000080187005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9717565,0.023880474,0.0014909994,0.00042941407,0.0015546005,0.00088798633],"domain_scores_gemma":[0.96292,0.033807565,0.00039936724,0.00091197045,0.00089548645,0.0010656217],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.061524402,0.00013019623,0.0005503402,0.00054055615,0.0006427507,0.0000038387548,0.0005682168,0.00054606627,0.005040295],"category_scores_gemma":[0.18685216,0.00010519987,0.00004878168,0.00079605746,0.00035810206,0.00015744696,0.0007588676,0.0015260552,0.00026288503],"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":[0.011763822,0.00263663,0.06853831,0.028745709,0.0006463612,0.0017422197,0.25189707,0.00008826085,0.002855156,0.19273914,0.041167997,0.3971793],"study_design_scores_gemma":[0.039074905,0.046962425,0.04588492,0.02437849,0.001907421,0.0030669817,0.23953542,0.35778606,0.023527043,0.1250333,0.08807415,0.0047688945],"about_ca_topic_score_codex":0.004908808,"about_ca_topic_score_gemma":0.0036954964,"teacher_disagreement_score":0.39241043,"about_ca_system_score_codex":0.0003648502,"about_ca_system_score_gemma":0.0067552933,"threshold_uncertainty_score":0.9988755},"labels":[],"label_agreement":null},{"id":"W2078863577","doi":"10.1186/1471-2288-9-47","title":"Interviewee Transcript Review: assessing the impact on qualitative research","year":2009,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Qualitative Research Methods and Ethics","field":"Social Sciences","cited_by":193,"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; Cancer Care Ontario","funders":"Canadian Institutes of Health Research","keywords":"Rigour; Qualitative research; Set (abstract data type); Data collection; Psychology; Process (computing); Interview; Computer science; Data science; Applied psychology; Medical education; Medicine; Sociology; Epistemology","score_opus":0.9386232119935493,"score_gpt":0.8327565621737846,"score_spread":0.10586664981976468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078863577","genre_codex":"commentary","genre_gemma":"empirical","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":[0.015454767,0.049313158,0.16308106,0.6090173,0.0006546987,0.0035342448,0.000021177771,0.0001655778,0.15875803],"genre_scores_gemma":[0.38040957,0.34390515,0.21952397,0.028684406,0.0070141307,0.0013891018,0.000049542847,0.00020634275,0.018817782],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3335936,0.6495872,0.0010118942,0.0009305247,0.011868266,0.0030084713],"domain_scores_gemma":[0.34712392,0.6446934,0.00018782857,0.0012664557,0.004595082,0.0021333455],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.7624618,0.00028610177,0.0010139876,0.0007493636,0.0030718048,0.0002702974,0.0029396794,0.00068593025,0.0039870245],"category_scores_gemma":[0.7239269,0.00015982563,0.0004936185,0.003964765,0.012597969,0.0003227265,0.00026449087,0.008804344,0.00037289193],"study_design_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":[0.00026432096,0.0003517908,0.000034615798,0.00045465332,0.000065559085,0.000066007364,0.15338923,0.0000013835913,0.0004501097,0.41556367,0.08612606,0.34323257],"study_design_scores_gemma":[0.00059369544,0.0023042844,0.0016153788,0.0038670092,0.000013415752,0.000009208014,0.19668673,0.00016148087,0.00020916731,0.62407255,0.17014681,0.00032027508],"about_ca_topic_score_codex":0.0066010808,"about_ca_topic_score_gemma":0.0016725119,"teacher_disagreement_score":0.5803329,"about_ca_system_score_codex":0.0007176773,"about_ca_system_score_gemma":0.008495869,"threshold_uncertainty_score":0.99822605},"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":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2078938402","doi":"10.1186/1471-2288-11-51","title":"A flexible Bayesian hierarchical model of preterm birth risk among US Hispanic subgroups in relation to maternal nativity and education","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Infant Development and Preterm Care","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; Canada Research Chairs","keywords":"Demography; Logistic regression; Ethnic group; Foreign born; Medicine; Covariate; Place of birth; Gestational age; Pregnancy; Population; Statistics","score_opus":0.238065033511583,"score_gpt":0.4425059206471998,"score_spread":0.20444088713561678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078938402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92986125,0.00008780736,0.06498747,0.0001483769,0.0001046522,0.00061602745,0.000010820354,0.000021911857,0.0041617127],"genre_scores_gemma":[0.8148235,0.0001574648,0.18448019,0.00009819389,0.0000615133,0.00009518239,0.000016961476,0.000015843156,0.00025114306],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99291474,0.004691677,0.0005082074,0.00042142716,0.0009774736,0.00048648482],"domain_scores_gemma":[0.9951835,0.0036431253,0.00009665934,0.00029064374,0.00023216581,0.00055385206],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014362806,0.00013413692,0.00046689692,0.0007888993,0.000066091634,0.0000075733624,0.00020323767,0.00039684636,0.00036838683],"category_scores_gemma":[0.020831462,0.00011185162,0.000054073444,0.0004139219,0.0004548925,0.00010030833,0.00022290122,0.0011272117,0.0000039487386],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018560239,0.000061359984,0.9582575,0.0003567431,0.000020393814,0.000017466024,0.005478744,0.0000039950505,0.0012085931,0.0030529446,0.0000555982,0.029630635],"study_design_scores_gemma":[0.0009213313,0.00050393306,0.9609777,0.00037368282,0.00001540782,0.000037530488,0.00012778248,0.016493585,0.0032421767,0.01713309,0.00005046262,0.00012335142],"about_ca_topic_score_codex":0.0011500578,"about_ca_topic_score_gemma":0.0012120147,"teacher_disagreement_score":0.119492725,"about_ca_system_score_codex":0.00011018952,"about_ca_system_score_gemma":0.0016607028,"threshold_uncertainty_score":0.9874165},"labels":[],"label_agreement":null},{"id":"W2080540798","doi":"10.1186/1471-2288-10-59","title":"Dichotomization: 2 × 2 (×2 × 2 × 2...) categories: infinite possibilities","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Diabetes, Cardiovascular Risks, and Lipoproteins","field":"Medicine","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":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia; University of Alberta","funders":"","keywords":"Confidence interval; Odds ratio; Cutoff; Outlier; Statistics; Medicine; Association (psychology); Econometrics; Psychology; Mathematics","score_opus":0.2760660294854124,"score_gpt":0.49194570145392663,"score_spread":0.2158796719685142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080540798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86965394,0.0021806937,0.09087574,0.0034932666,0.0021866914,0.0016018183,0.000013889127,0.0003121,0.029681882],"genre_scores_gemma":[0.75052077,0.0015860331,0.22063333,0.0022470758,0.007869053,0.0008762587,0.00019009,0.0001773537,0.015900007],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98816633,0.0064468305,0.00063598994,0.0007064009,0.0029398012,0.001104623],"domain_scores_gemma":[0.97532535,0.02073919,0.000076944445,0.001404087,0.0010385729,0.0014158359],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03752321,0.00023354689,0.0010200539,0.0005562475,0.0002542321,0.000054079457,0.00052114675,0.00079774234,0.007911349],"category_scores_gemma":[0.19105278,0.00018055848,0.0003839283,0.00086066907,0.0023194654,0.0001076035,0.00032571756,0.0028291915,0.00041466017],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011141433,0.00042750477,0.014979135,0.0010770018,0.00047498124,0.00047184547,0.0021206555,0.0000037436048,0.0020288706,0.026219888,0.0072964625,0.9437858],"study_design_scores_gemma":[0.010046987,0.0019880063,0.1259945,0.00037134934,0.0002705164,0.0012883396,0.003792301,0.0013382931,0.013367126,0.07473296,0.76597655,0.00083309214],"about_ca_topic_score_codex":0.008534109,"about_ca_topic_score_gemma":0.009271674,"teacher_disagreement_score":0.9429527,"about_ca_system_score_codex":0.00006352132,"about_ca_system_score_gemma":0.0033032394,"threshold_uncertainty_score":0.9994713},"labels":[],"label_agreement":null},{"id":"W2089198100","doi":"10.1186/1471-2288-8-70","title":"Reducing bias through directed acyclic graphs","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1410,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"McGill University Health Centre; McGill University","keywords":"Directed acyclic graph; Confounding; Causal inference; Selection bias; Computer science; Outcome (game theory); Econometrics; Simple (philosophy); Causality (physics); Statistics; Mathematics; Algorithm","score_opus":0.9122827611924192,"score_gpt":0.6583154278917019,"score_spread":0.2539673333007173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089198100","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24533026,0.0004719148,0.7387174,0.00097219244,0.0002521286,0.0006140576,0.0000037393427,0.0012540383,0.012384324],"genre_scores_gemma":[0.058896493,0.0019364805,0.93708444,0.00022798682,0.0002520871,0.00024437776,0.0000071586423,0.00006499829,0.0012859666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97646815,0.018254254,0.0008217107,0.0007357324,0.00238709,0.0013330897],"domain_scores_gemma":[0.8679871,0.1298494,0.00015319769,0.0009571065,0.000520641,0.0005325641],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025562007,0.00025241065,0.0008368503,0.00041865517,0.0003921919,0.000013905558,0.0009846976,0.0006212333,0.001962332],"category_scores_gemma":[0.4471436,0.00020130165,0.00016933294,0.0012855377,0.0021799912,0.00018523999,0.00058741437,0.0020213875,0.00011169577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037927827,0.0005769926,0.0032757928,0.00047843976,0.000119459706,0.00088728376,0.0041815974,0.0000021674482,0.0139849745,0.85528874,0.07480704,0.04601822],"study_design_scores_gemma":[0.00042319752,0.00027946048,0.000663108,0.0001834521,0.000009799307,0.00036345638,0.00026967798,0.00024007904,0.023843,0.9677824,0.00571103,0.00023134761],"about_ca_topic_score_codex":0.00053610746,"about_ca_topic_score_gemma":0.00026155575,"teacher_disagreement_score":0.42158163,"about_ca_system_score_codex":0.00013922634,"about_ca_system_score_gemma":0.0011077498,"threshold_uncertainty_score":0.99895},"labels":[],"label_agreement":null},{"id":"W2089740726","doi":"10.1186/1471-2288-8-4","title":"Negative pressure wound therapy: Potential publication bias caused by lack of access to unpublished study results data","year":2008,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Surgical site infection prevention","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agency for Healthcare Research and Quality; Gemeinsame Bundesausschuss; Bundesinstitut für Arzneimittel und Medizinprodukte; McGill University Health Centre; McGill University","keywords":"Medicine; CINAHL; MEDLINE; Cochrane Library; Randomized controlled trial; Interim; Systematic review; Psychological intervention; Negative-pressure wound therapy; PsycINFO; Meta-analysis; Clinical trial; Alternative medicine; Family medicine; Physical therapy; Surgery; Internal medicine; Pathology; Psychiatry","score_opus":0.8912564572274616,"score_gpt":0.6626123556817993,"score_spread":0.22864410154566228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089740726","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":[0.00046954094,0.96247387,0.015813401,0.0031145269,0.0010077914,0.014263304,0.00084602553,0.00018791053,0.0018236362],"genre_scores_gemma":[0.00011851282,0.98833877,0.002749749,0.00024741938,0.00082303176,0.00085201854,0.0033345362,0.00010504989,0.0034309025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9225267,0.06565786,0.0030125917,0.0022571115,0.005470854,0.0010748405],"domain_scores_gemma":[0.89927405,0.0895824,0.0014087597,0.004403802,0.0034521597,0.0018788029],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06064136,0.00056650647,0.0039156047,0.0017216259,0.00021607979,0.00017628665,0.0032632176,0.0016121345,0.0064017545],"category_scores_gemma":[0.46419495,0.00039781744,0.00047163886,0.004181562,0.00089209515,0.00053146377,0.002851208,0.0033446238,0.00014219011],"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":[0.001610925,0.0020329442,0.0001867278,0.0033583313,0.0011752534,0.00009286036,0.0001728749,7.149273e-7,0.0000056988047,0.000026309966,0.13683121,0.85450613],"study_design_scores_gemma":[0.0039079785,0.001525441,0.0010626873,0.0026633,0.0004572086,0.00015836643,0.00008875798,0.000056057535,0.000014826365,0.00007976824,0.98969656,0.00028906975],"about_ca_topic_score_codex":0.0016864133,"about_ca_topic_score_gemma":0.00032059895,"teacher_disagreement_score":0.8542171,"about_ca_system_score_codex":0.00024386669,"about_ca_system_score_gemma":0.0058644237,"threshold_uncertainty_score":0.99984735},"labels":[],"label_agreement":null},{"id":"W2091875580","doi":"10.1186/1471-2288-10-106","title":"Objectively-assessed outcome measures: a translation and cross-cultural adaptation procedure applied to the Chedoke McMaster Arm and Hand Activity Inventory (CAHAI)","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":47,"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":"Physical therapy; Medicine; Reliability (semiconductor); Stroke (engine); Psychology","score_opus":0.4674990395365474,"score_gpt":0.530613900125349,"score_spread":0.06311486058880161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091875580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9533205,0.00028423773,0.038868856,0.0050900495,0.00025946775,0.0012871394,0.0000039388055,0.000030674535,0.00085515686],"genre_scores_gemma":[0.9747996,0.00006834132,0.023726068,0.00043384056,0.00035665132,0.00024753084,0.000005333877,0.000018671013,0.00034397878],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99525213,0.0022055204,0.00034701612,0.0005470377,0.001216051,0.00043225707],"domain_scores_gemma":[0.98588014,0.012714375,0.000068339774,0.00023697935,0.0005044352,0.0005957621],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014446868,0.00016475597,0.00044468822,0.00025172805,0.00031277782,0.00009356789,0.00014868319,0.0004157044,0.00020986122],"category_scores_gemma":[0.055132795,0.00009736614,0.00007952177,0.00034288273,0.0014874337,0.00013180192,0.00008657147,0.0013640248,0.000011173013],"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":[0.005801496,0.00040646325,0.13609363,0.0011751298,0.0001378762,0.000010445288,0.014162657,0.000010379386,0.30043915,0.0017910425,0.0002979905,0.53967375],"study_design_scores_gemma":[0.0049432153,0.0009547855,0.96581346,0.000111593414,0.00006102004,0.00016035298,0.004467427,0.0063927798,0.0068845227,0.0011190397,0.00885979,0.00023199494],"about_ca_topic_score_codex":0.00013681193,"about_ca_topic_score_gemma":0.0022313576,"teacher_disagreement_score":0.82971984,"about_ca_system_score_codex":0.000054648735,"about_ca_system_score_gemma":0.0007031073,"threshold_uncertainty_score":0.9528262},"labels":[],"label_agreement":null},{"id":"W2092444466","doi":"10.1186/1471-2288-14-79","title":"Systematic review of methods for individual patient data meta- analysis with binary outcomes","year":2014,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","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":"University of Toronto; Public Health Ontario; McGill University","funders":"","keywords":"Meta-analysis; Random effects model; Covariate; Outcome (game theory); Study heterogeneity; Logistic regression; Statistics; Statistic; MEDLINE; Systematic review; Medicine; Computer science; Mathematics; Internal medicine","score_opus":0.9909096909132739,"score_gpt":0.8022789235787386,"score_spread":0.1886307673345352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092444466","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":[3.8815724e-8,0.5557717,0.43627334,0.00022156526,0.000120356824,0.0071102013,0.0003728025,0.000005681365,0.00012426739],"genre_scores_gemma":[4.852534e-8,0.5703055,0.42484984,0.0003016615,0.000049983144,0.0030313917,0.00049992895,0.00004714788,0.0009144993],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.18976732,0.73298323,0.043261666,0.0047041154,0.027904287,0.0013793882],"domain_scores_gemma":[0.036798928,0.89142174,0.030212471,0.03229938,0.0077737896,0.0014937099],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.92134535,0.0014248033,0.121578604,0.0053887093,0.00026236786,0.00038216292,0.02502603,0.0011578419,0.019292897],"category_scores_gemma":[0.9444602,0.0004887515,0.02931185,0.013744607,0.0011193557,0.00019778193,0.004805677,0.0018520392,0.0004970092],"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":[0.000005971399,0.00007917815,0.00000410337,0.6446984,0.17036705,0.00000550209,0.00002880484,6.4470714e-7,6.873028e-9,0.00074966694,0.01059938,0.17346132],"study_design_scores_gemma":[0.00009232206,0.00025196892,9.821803e-7,0.0821295,0.4812434,0.000036343452,0.000089572495,0.0005518489,5.7280772e-8,0.0004918297,0.4348075,0.0003046458],"about_ca_topic_score_codex":0.000047788908,"about_ca_topic_score_gemma":0.00013845827,"teacher_disagreement_score":0.5625689,"about_ca_system_score_codex":0.00008004242,"about_ca_system_score_gemma":0.0041438094,"threshold_uncertainty_score":0.9998502},"labels":[],"label_agreement":null},{"id":"W2093139043","doi":"10.1186/1471-2288-14-2","title":"Assessing outcomes of large-scale public health interventions in the absence of baseline data using a mixture of Cox and binomial regressions","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; FHI 360; Indian Council of Medical Research; University of Manitoba; Bill and Melinda Gates Foundation","keywords":"Condom; Psychological intervention; Scale (ratio); Negative binomial distribution; Statistics; Inference; Baseline (sea); Population; Econometrics; Medicine; Computer science; Mathematics; Environmental health; Human immunodeficiency virus (HIV); Poisson distribution; Family medicine; Geography; Artificial intelligence","score_opus":0.8928951245828125,"score_gpt":0.6854779576295542,"score_spread":0.2074171669532583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093139043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22238837,0.00018249129,0.7753323,0.0018233872,0.000038859765,0.0001646105,0.000034334735,0.000010590791,0.000025107833],"genre_scores_gemma":[0.37160903,0.000063452244,0.6282189,0.00004632611,0.000021234888,0.0000074294653,0.000020312813,0.000006764698,0.0000065239956],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9541291,0.042178873,0.0014905565,0.00038124822,0.0013106446,0.0005095677],"domain_scores_gemma":[0.87169194,0.12638906,0.00046914266,0.000930056,0.00035861807,0.00016120584],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16713138,0.00007712846,0.0006274399,0.00036779093,0.00009094915,0.000012978687,0.00070536294,0.00016024105,0.00006942501],"category_scores_gemma":[0.35632715,0.000048313927,0.00006391819,0.0004588909,0.0006404305,0.00009976712,0.0005027605,0.000512456,1.6363722e-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":[0.0003329427,0.005369903,0.4965933,0.019689541,0.00022531538,0.000010896595,0.017027883,0.000021636526,0.0056563006,0.13932696,0.011504464,0.30424085],"study_design_scores_gemma":[0.004746203,0.0012867603,0.24374044,0.012850413,0.00008006871,0.00012742977,0.022658007,0.4323807,0.002827864,0.27741438,0.0013620378,0.00052569323],"about_ca_topic_score_codex":0.000630944,"about_ca_topic_score_gemma":0.0015436113,"teacher_disagreement_score":0.43235907,"about_ca_system_score_codex":0.000017972417,"about_ca_system_score_gemma":0.0006976502,"threshold_uncertainty_score":0.8576135},"labels":[],"label_agreement":null},{"id":"W2095437242","doi":"10.1186/1471-2288-13-92","title":"A tutorial on sensitivity analyses in clinical trials: the what, why, when and how","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":901,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Waterloo; Toronto General Hospital; Hamilton Health Sciences; University of Ottawa; GlaxoSmithKline (Canada); St. Joseph’s Healthcare Hamilton; McMaster University; Population Health Research Institute","funders":"","keywords":"Sensitivity (control systems); Clinical trial; Missing data; Computer science; Protocol (science); Outlier; Data science; Robustness (evolution); Research design; Data mining; Medical physics; Medicine; Management science; Alternative medicine; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.9873875398748938,"score_gpt":0.8105356203029017,"score_spread":0.1768519195719921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095437242","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":[0.086347654,0.00080521044,0.8229362,0.07917384,0.005781418,0.004025973,0.000021535743,0.00011355627,0.0007946452],"genre_scores_gemma":[0.011275894,0.001418719,0.9789947,0.0022804206,0.005199804,0.00042939145,0.0000015454556,0.00005411499,0.00034538953],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.44284627,0.54866326,0.0028104386,0.0012005117,0.0032224753,0.0012570418],"domain_scores_gemma":[0.013512972,0.9832157,0.0004922445,0.001176087,0.0005657029,0.0010372826],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6132049,0.00031718786,0.0030573236,0.00034981317,0.0001902024,0.00033570844,0.0007733087,0.001216768,0.0022593432],"category_scores_gemma":[0.9914974,0.00017435347,0.000452038,0.00058694795,0.0036194006,0.00019956878,0.00081979966,0.0041222298,0.00010033535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020070488,0.00067586557,0.001062465,0.00023783806,0.00025956082,0.00020080878,0.00041911835,6.944042e-7,0.000443726,0.15334792,0.09015042,0.75119454],"study_design_scores_gemma":[0.0027952052,0.00073950127,0.0033425752,0.0003010958,0.00007178306,0.000023319853,0.0011466736,0.002818521,0.00017486556,0.9853399,0.0030515247,0.0001950714],"about_ca_topic_score_codex":0.0005576465,"about_ca_topic_score_gemma":0.0009740432,"teacher_disagreement_score":0.8319919,"about_ca_system_score_codex":0.00008199604,"about_ca_system_score_gemma":0.0008632043,"threshold_uncertainty_score":0.99909216},"labels":[],"label_agreement":null},{"id":"W2096496140","doi":"10.1186/1471-2288-9-84","title":"Modeling of longitudinal polytomous outcome from complex survey data - application to investigate an association between mental distress and non-malignant respiratory diseases","year":2009,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Asthma and respiratory diseases","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":"Royal University Hospital; University of Saskatchewan","funders":"","keywords":"Mental health; Medicine; Polytomous Rasch model; Longitudinal study; Population; Logistic regression; Chronic bronchitis; General Health Questionnaire; Psychiatry; Clinical psychology; Demography; Psychometrics; Item response theory; Environmental health; Internal medicine","score_opus":0.597493709944407,"score_gpt":0.5529950067117125,"score_spread":0.04449870323269445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096496140","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92934775,0.0005781975,0.067019075,0.0007127463,0.00004844116,0.0006282846,0.0016108063,0.000035102898,0.000019579098],"genre_scores_gemma":[0.9884955,0.00004234436,0.008016362,0.0006297394,0.0004440296,0.000026344329,0.002311851,0.000021054639,0.000012733022],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.989176,0.0067021376,0.0008016839,0.0008474705,0.0018838391,0.00058888947],"domain_scores_gemma":[0.98848385,0.008115151,0.00016033172,0.0010028505,0.00038494493,0.0018528946],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013233641,0.00019665634,0.00085538154,0.00027674457,0.00017853663,0.000025361796,0.0006226551,0.00028395868,0.00008738577],"category_scores_gemma":[0.042661037,0.00015837827,0.00006120606,0.0003922408,0.00038002475,0.00013967221,0.00048955873,0.00046834938,0.000011742676],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067973585,0.0002625106,0.9582327,0.0000927235,0.000059131067,0.000024204906,0.00012938352,0.000026513655,0.0034197315,0.000014950115,0.0005126146,0.036545817],"study_design_scores_gemma":[0.0010838961,0.00072103523,0.9705069,0.00010977549,0.000098383694,0.0000020669447,0.00017787138,0.026525507,0.00020047741,0.00024527547,0.0001861218,0.00014268608],"about_ca_topic_score_codex":0.0026601844,"about_ca_topic_score_gemma":0.0016784263,"teacher_disagreement_score":0.059147775,"about_ca_system_score_codex":0.00014897033,"about_ca_system_score_gemma":0.0008191875,"threshold_uncertainty_score":0.965403},"labels":[],"label_agreement":null},{"id":"W2096873892","doi":"10.1186/1471-2288-9-64","title":"Determining relative importance of variables in developing and validating predictive models","year":2009,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Acute Lymphoblastic Leukemia research","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Generalizability theory; Bootstrapping (finance); Statistics; Computer science; Receiver operating characteristic; Data set; Regression analysis; Regression; Predictive modelling; Medicine; Machine learning; Econometrics; Artificial intelligence; Mathematics","score_opus":0.4083881415443418,"score_gpt":0.5174879815880666,"score_spread":0.10909984004372486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096873892","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":[0.41811278,0.00044179813,0.57545346,0.0014965861,0.000033217595,0.00049248285,0.0000028125091,0.000025190891,0.0039416356],"genre_scores_gemma":[0.5636256,0.00044488016,0.43537754,0.00029569832,0.00009364355,0.000041192256,0.0000064587066,0.00001763944,0.00009735832],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9897649,0.0057812217,0.00086232135,0.0006386186,0.0019971617,0.00095573865],"domain_scores_gemma":[0.9474583,0.050879583,0.00015055842,0.00038267777,0.0005641531,0.0005647104],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028862525,0.00017461137,0.00085195724,0.0007099273,0.00009519731,0.000010590954,0.00030954898,0.00046813762,0.000116083014],"category_scores_gemma":[0.13960654,0.00014301183,0.000056087658,0.0010035464,0.0009070408,0.00020192003,0.00035537028,0.0013423963,0.000002459273],"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":[0.008548497,0.0007410262,0.43358105,0.002989703,0.00045961444,0.0038701952,0.016448539,0.00067388144,0.023601498,0.29335937,0.0009183906,0.21480824],"study_design_scores_gemma":[0.010576551,0.0034382313,0.15168922,0.0042423722,0.0000643299,0.0010639429,0.003509237,0.5681493,0.008932677,0.24777922,0.00013168901,0.00042323026],"about_ca_topic_score_codex":0.00013900519,"about_ca_topic_score_gemma":0.00009119775,"teacher_disagreement_score":0.56747544,"about_ca_system_score_codex":0.0005535474,"about_ca_system_score_gemma":0.0057979785,"threshold_uncertainty_score":0.9999904},"labels":[],"label_agreement":null},{"id":"W2098756124","doi":"10.1186/1471-2288-10-42","title":"Surname lists to identify South Asian and Chinese ethnicity from secondary data in Ontario, Canada: a validation study","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Migration, Health and Trauma","field":"Psychology","cited_by":224,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; University of Toronto; Ontario Ministry of Health and Long-Term Care; Banting and Best Diabetes Centre, University of Toronto; Heart and Stroke Foundation of Canada; Institute for Clinical Evaluative Sciences; Canadian Diabetes Association","keywords":"Ethnic group; Demography; Medicine; Population; Geography; Gerontology; Family medicine; Environmental health; Political science; Sociology","score_opus":0.4588016625415811,"score_gpt":0.581583771404613,"score_spread":0.12278210886303192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098756124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98972315,0.000098542354,0.0048106983,0.0021000148,0.001423521,0.0009200715,0.000106006235,0.000018494431,0.0007994764],"genre_scores_gemma":[0.99119395,0.000004912596,0.0070514916,0.0005435413,0.0003565168,0.000115844836,0.0002538594,0.000020352041,0.0004595351],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9800643,0.01600151,0.0007529147,0.0010920514,0.0012054284,0.00088381674],"domain_scores_gemma":[0.98093146,0.016280558,0.000094406045,0.0012556652,0.00018389215,0.0012540298],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03739393,0.00017880849,0.0005477363,0.00037569742,0.00017125877,0.00003938394,0.001001709,0.00042426068,0.014287375],"category_scores_gemma":[0.055321623,0.00015118286,0.000022418575,0.0004965256,0.00022891187,0.0001053163,0.0006491108,0.0034785827,0.000056050972],"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":[0.0005660341,0.00027935705,0.93059886,0.000031414962,0.000040299212,0.00022104979,0.032114603,1.6638296e-7,0.00012756466,0.00021551488,0.004845103,0.03096002],"study_design_scores_gemma":[0.0015593509,0.00019416444,0.9903327,0.000014387021,0.0000077096,0.000020186524,0.0047565685,0.00005337143,0.000005967705,0.0013611577,0.0015733173,0.000121093464],"about_ca_topic_score_codex":0.9961928,"about_ca_topic_score_gemma":0.9999747,"teacher_disagreement_score":0.059733853,"about_ca_system_score_codex":0.00016391832,"about_ca_system_score_gemma":0.007996006,"threshold_uncertainty_score":0.9988204},"labels":[],"label_agreement":null},{"id":"W2101348497","doi":"10.1186/1471-2288-12-131","title":"Learning from failure - rationale and design for a study about discontinuation of randomized trials (DISCO study)","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hospital for Sick Children; Université de Sherbrooke; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Discontinuation; Randomized controlled trial; Medicine; Informed consent; MEDLINE; Family medicine; Research design; Alternative medicine; Surgery; Pathology","score_opus":0.9409222400378311,"score_gpt":0.7313774198547984,"score_spread":0.20954482018303267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101348497","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":[0.47777796,0.0012671173,0.50741893,0.0024015878,0.00016926297,0.0108630555,0.0000068484314,0.000021308997,0.00007395882],"genre_scores_gemma":[0.79293346,0.00050923234,0.20154765,0.00006911204,0.0010010954,0.0026656901,0.000036188547,0.000037850015,0.0011997275],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.6825917,0.3011394,0.0044940417,0.0012885678,0.008889045,0.0015972932],"domain_scores_gemma":[0.109620064,0.88670236,0.00045172047,0.0005485033,0.001786195,0.00089117617],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6282194,0.00020034694,0.003236656,0.00047594702,0.00024302908,0.000037349448,0.00038711372,0.0006592441,0.0011080927],"category_scores_gemma":[0.96227425,0.00013207122,0.00035180384,0.0004237544,0.0017240249,0.00012548821,0.00045617967,0.0031691093,0.0000112377365],"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":[0.5703371,0.014424759,0.2666336,0.0012127967,0.0040301126,0.00005036232,0.04802218,0.00004304975,0.007536643,0.025722904,0.001964549,0.060021937],"study_design_scores_gemma":[0.67908967,0.02200713,0.06800216,0.0012164701,0.001956196,0.000019647561,0.096539035,0.010474393,0.0027162924,0.11671824,0.00071792986,0.0005428523],"about_ca_topic_score_codex":0.0006055954,"about_ca_topic_score_gemma":0.0010876118,"teacher_disagreement_score":0.58556294,"about_ca_system_score_codex":0.000067822795,"about_ca_system_score_gemma":0.0023440938,"threshold_uncertainty_score":0.99980503},"labels":[],"label_agreement":null},{"id":"W2101434317","doi":"10.1186/1471-2288-12-135","title":"Estimation methods with ordered exposure subject to measurement error and missingness in semi-ecological design","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Calgary","funders":"University of Birmingham","keywords":"Missing data; Statistics; Estimation; Subject (documents); Research design; Computer science; Observational error; Econometrics; Mathematics","score_opus":0.7773759964735921,"score_gpt":0.6186229033009765,"score_spread":0.15875309317261566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101434317","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02003059,0.00030915096,0.97727734,0.0009263899,0.00013125304,0.0009218004,0.000001792933,0.00004806698,0.00035363552],"genre_scores_gemma":[0.06588985,0.000019254361,0.93346196,0.00012422673,0.00009904962,0.00034325523,9.950875e-7,0.000028557817,0.000032817243],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.941389,0.05397283,0.0007128155,0.0005988925,0.002005996,0.0013204174],"domain_scores_gemma":[0.8669824,0.1307545,0.00010677408,0.0004384545,0.00045461804,0.0012632477],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12617548,0.0002512406,0.00085486186,0.00039079544,0.00016532585,0.000042978903,0.00038336372,0.00045279248,0.0008148811],"category_scores_gemma":[0.41946363,0.00016764223,0.00003916546,0.0008523751,0.0006067739,0.000095243704,0.00026673602,0.0009897032,0.000014948267],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013455641,0.00069877267,0.0092160115,0.00063427014,0.000048402064,0.00007898653,0.0018797019,0.000012416214,0.0024633405,0.14762564,0.00058690115,0.83541],"study_design_scores_gemma":[0.002778825,0.0031151036,0.07285667,0.00081301254,0.00008199525,0.0003082429,0.0015451276,0.03401347,0.005830905,0.87742573,0.0005046948,0.00072622736],"about_ca_topic_score_codex":0.00010184904,"about_ca_topic_score_gemma":0.00026726848,"teacher_disagreement_score":0.8346838,"about_ca_system_score_codex":0.00020241107,"about_ca_system_score_gemma":0.00091325364,"threshold_uncertainty_score":0.89978623},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","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":"W2103869269","doi":"10.1186/1471-2288-5-32","title":"Methods for confidence interval estimation of a ratio parameter with application to location quotients","year":2005,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Public Health","funders":"Hospital for Sick Children","keywords":"Confidence interval; Quotient; Statistics; Interval (graph theory); Estimation; Interval estimation; Computer science; Medicine; Mathematics; Combinatorics; Engineering","score_opus":0.43773344745680914,"score_gpt":0.52892417017769,"score_spread":0.09119072272088086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103869269","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009680118,0.00022820226,0.9878537,0.0013205013,0.00006247026,0.0005954325,0.000025830805,0.000011581111,0.00022215933],"genre_scores_gemma":[0.31259063,0.000025082783,0.68657327,0.00017397657,0.00008195267,0.00036757594,0.00005972453,0.000009249773,0.00011857557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710584,0.001237525,0.0007081425,0.00045442852,0.00018422068,0.00030984907],"domain_scores_gemma":[0.9863796,0.01246026,0.00022117764,0.0003990077,0.00032495873,0.0002149909],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019976765,0.000092687784,0.00048109607,0.0004553774,0.0000696772,0.000021177668,0.00040814214,0.00015348033,0.0003780971],"category_scores_gemma":[0.05057833,0.00008267181,0.00006628911,0.00069162686,0.0002056845,0.00013307887,0.00008995488,0.00018990887,0.00014136524],"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":[0.0006605103,0.00017646879,0.0039237826,0.00023975167,0.00009678355,3.071395e-7,0.0009815223,0.005972739,0.00039865007,0.22403975,0.00049411075,0.7630156],"study_design_scores_gemma":[0.0007441341,0.000654282,0.004247184,0.000060617866,0.000018121118,0.000004452383,0.00018423314,0.93481237,0.0039063096,0.045139015,0.010062824,0.00016644574],"about_ca_topic_score_codex":0.0012127839,"about_ca_topic_score_gemma":0.0009120137,"teacher_disagreement_score":0.9288396,"about_ca_system_score_codex":0.000076936754,"about_ca_system_score_gemma":0.0001679546,"threshold_uncertainty_score":0.95741904},"labels":[],"label_agreement":null},{"id":"W2104471097","doi":"10.1186/1471-2288-6-2","title":"Protocol of the COSMIN study: COnsensus-based Standards for the selection of health Measurement INstruments","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":398,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Vrije Universiteit Amsterdam","keywords":"Checklist; Protocol (science); Delphi method; Interpretability; Delphi; Health care; Medicine; Criterion validity; Consistency (knowledge bases); Computer science; Medical physics; Construct validity; Applied psychology; Management science; Psychology; Patient satisfaction; Alternative medicine; Nursing; Engineering; Artificial intelligence; Pathology","score_opus":0.7892792696623773,"score_gpt":0.6850943130718052,"score_spread":0.10418495659057203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104471097","genre_codex":"protocol","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":[0.047532238,0.0001301659,0.41084462,0.047566824,0.0004927361,0.49002266,0.0000765205,0.000111846144,0.0032224113],"genre_scores_gemma":[0.8390889,0.000009571549,0.031102218,0.00012093586,0.0002112037,0.12919176,9.0515897e-7,0.000025088795,0.00024938167],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9025127,0.08032576,0.0012470945,0.0004597597,0.014283209,0.001171456],"domain_scores_gemma":[0.9619954,0.034203045,0.00031369439,0.0004197179,0.0029077348,0.00016038503],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3081651,0.00009545575,0.00040576514,0.00021205832,0.00084608473,0.000018984023,0.0011622105,0.00018682845,0.0002584511],"category_scores_gemma":[0.166265,0.000054539796,0.000118674274,0.001142047,0.0031629084,0.000017970046,0.0002120094,0.0006513162,6.194642e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005967361,0.0043708165,0.19338244,0.0026479366,0.0001863802,0.0000034479137,0.003937534,0.00010651495,0.0037166742,0.050766855,0.11970401,0.61521006],"study_design_scores_gemma":[0.022295255,0.017619507,0.16356647,0.0017565178,0.00008940983,0.0000086237715,0.045587685,0.006894135,0.08493653,0.100032024,0.55650175,0.0007121222],"about_ca_topic_score_codex":0.025638094,"about_ca_topic_score_gemma":0.05807182,"teacher_disagreement_score":0.7915567,"about_ca_system_score_codex":0.00079498417,"about_ca_system_score_gemma":0.02439182,"threshold_uncertainty_score":0.9995499},"labels":[],"label_agreement":null},{"id":"W2104845067","doi":"10.1186/1471-2288-14-77","title":"Procedures for assessing psychological predictors of injuries in circus artists: a pilot prospective study","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Musicians’ Health and Performance","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Mood; Anxiety; Prospective cohort study; Medicine; Coping (psychology); Psychology; Clinical psychology; Psychiatry; Surgery","score_opus":0.5114540791773076,"score_gpt":0.6116459440296619,"score_spread":0.10019186485235432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104845067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95267296,0.00025206446,0.041070294,0.0010259429,0.00055962184,0.0028099976,0.000004251936,0.000041581814,0.0015632825],"genre_scores_gemma":[0.9713657,0.000066392204,0.025882363,0.00053361146,0.001125701,0.0009131213,0.000006748661,0.000022724238,0.00008365126],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98941505,0.0066137607,0.00090218795,0.0006420301,0.0014806971,0.0009462944],"domain_scores_gemma":[0.97511315,0.02317482,0.00014682765,0.00043226872,0.00052589335,0.000607032],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03840488,0.00017047576,0.00094323955,0.00053306203,0.00013706219,0.000013716163,0.00031768507,0.00030679675,0.00023091034],"category_scores_gemma":[0.19153507,0.00012218779,0.000072301234,0.0007370888,0.000959577,0.000076091535,0.0001210735,0.0011978227,0.0000065177924],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058969767,0.0024286108,0.95716107,0.0021444254,0.00003424058,0.000018139588,0.0016512374,0.0000015322822,0.00074741413,0.0024947368,0.0012888758,0.026132755],"study_design_scores_gemma":[0.005600603,0.013717917,0.97096163,0.000489924,0.000022684859,0.000036721187,0.0016289166,0.0008363381,0.0003392978,0.005501709,0.00074524496,0.000119005024],"about_ca_topic_score_codex":0.00019371173,"about_ca_topic_score_gemma":0.001488376,"teacher_disagreement_score":0.15313019,"about_ca_system_score_codex":0.00011633817,"about_ca_system_score_gemma":0.001779799,"threshold_uncertainty_score":0.9901645},"labels":[],"label_agreement":null},{"id":"W2105819266","doi":"10.1186/1471-2288-13-44","title":"Empirical comparison of methods for analyzing multiple time-to-event outcomes in a non-inferiority trial: a breast cancer study","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Breast Cancer Treatment Studies","field":"Biochemistry, Genetics and Molecular Biology","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":"Juravinski Cancer Centre; St. Joseph’s Healthcare Hamilton; McMaster University; Ontario Clinical Oncology Group","funders":"","keywords":"Breast cancer; Proportional hazards model; Medicine; Context (archaeology); Hazard ratio; Clinical trial; Radiation therapy; Oncology; Cancer; Internal medicine; Confidence interval","score_opus":0.3900527622239746,"score_gpt":0.6290385893626564,"score_spread":0.23898582713868183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105819266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84233975,0.00039289155,0.15165174,0.0022141843,0.00017443784,0.003162022,0.00003507933,0.000009974031,0.000019899984],"genre_scores_gemma":[0.84329903,0.000052454085,0.15153725,0.00014664451,0.00025429903,0.0045029554,0.000018427898,0.000034743633,0.00015416475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98823583,0.0088941185,0.00081806513,0.00073624885,0.00054801995,0.00076771784],"domain_scores_gemma":[0.98469776,0.013751212,0.00013226565,0.0005090235,0.0005148696,0.00039489314],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014045693,0.00023693881,0.0012208807,0.00029243238,0.00010289423,0.000013892468,0.00051647646,0.00031140857,0.00037859697],"category_scores_gemma":[0.035644013,0.00018020291,0.00021913872,0.00044389267,0.00032679926,0.000005600138,0.0006912726,0.00037342167,0.000018107716],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010615051,0.002039954,0.87482095,0.000079976744,0.00037239966,0.0000015139484,0.0006723645,0.000036323214,0.010086306,0.0000023285606,0.0016761284,0.0995967],"study_design_scores_gemma":[0.03064624,0.0028278723,0.9561646,0.00006722664,0.00007278898,0.0000047364865,0.0014283722,0.0028806673,0.004467996,0.00013281727,0.0010178002,0.00028890945],"about_ca_topic_score_codex":0.004183414,"about_ca_topic_score_gemma":0.004422062,"teacher_disagreement_score":0.09930779,"about_ca_system_score_codex":0.00012192369,"about_ca_system_score_gemma":0.00075351045,"threshold_uncertainty_score":0.97247916},"labels":[],"label_agreement":null},{"id":"W2106785923","doi":"10.1186/1471-2288-12-31","title":"Is it possible to estimate the minimal clinically important treatment effect needed to change practice in preterm birth prevention? Results of an obstetrician survey used to support the design of a trial","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Preterm Birth and Chorioamnionitis","field":"Medicine","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":"Alberta Health Services; University of Calgary","funders":"Abbott Laboratories","keywords":"Medicine; Pregnancy; Cervical cerclage; Obstetrics; Obstetrics and gynaecology; Randomized controlled trial; Clinical trial; Gestation; Clinical Practice; Pediatrics; Family medicine; Surgery; Internal medicine","score_opus":0.6651404417518586,"score_gpt":0.6255618568076056,"score_spread":0.03957858494425304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106785923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9736176,0.00019786923,0.0041250978,0.012983046,0.00047262432,0.008295801,0.00010691539,0.000017183762,0.00018382331],"genre_scores_gemma":[0.915126,0.00025321997,0.077985026,0.0033239953,0.0007224922,0.0020043075,0.000060556675,0.00005335215,0.0004710054],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.9401292,0.052860085,0.0023253872,0.0007170706,0.00254856,0.0014196768],"domain_scores_gemma":[0.8178042,0.17847182,0.00040466175,0.0011802741,0.0005239793,0.0016150556],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13084026,0.00026324,0.0011756124,0.0005827537,0.00010276679,0.000022169374,0.00073002005,0.00035608737,0.00023555751],"category_scores_gemma":[0.49412,0.00013827479,0.00020046746,0.0016390063,0.0003256783,0.00012960818,0.0003246643,0.0006529472,0.00003199581],"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":[0.68433917,0.003188258,0.07509345,0.00032541034,0.0003734311,0.00020541625,0.03786842,0.00000779952,0.0019051367,0.000038683465,0.005511332,0.1911435],"study_design_scores_gemma":[0.118693426,0.33257776,0.4966447,0.0011663871,0.00050253206,0.0002886332,0.005448763,0.0010227171,0.030843588,0.00015572019,0.01199953,0.0006562087],"about_ca_topic_score_codex":0.003879258,"about_ca_topic_score_gemma":0.003519619,"teacher_disagreement_score":0.56564575,"about_ca_system_score_codex":0.0001517052,"about_ca_system_score_gemma":0.0021498261,"threshold_uncertainty_score":0.8949829},"labels":[],"label_agreement":null},{"id":"W2108057161","doi":"10.1186/1471-2288-14-6","title":"Effect of numbering of return envelopes on participation, explicit refusals, and bias: experiment and meta-analysis","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social 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":"McMaster University","funders":"Hôpitaux Universitaires de Genève","keywords":"Confidence interval; Meta-analysis; Numbering; Medicine; Psychology; Family medicine; Demography; Social psychology; Mathematics; Internal medicine","score_opus":0.8259295167367556,"score_gpt":0.6596671096481198,"score_spread":0.16626240708863582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108057161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9663835,0.0013070304,0.030299114,0.0008919245,0.00006228171,0.0002747908,0.00000334374,0.00001431645,0.000763655],"genre_scores_gemma":[0.97866005,0.0003378554,0.02046363,0.000085254695,0.00006189398,0.00013074037,0.0000020469213,0.000008959477,0.00024958295],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.63335425,0.3637377,0.0005909758,0.0004647154,0.0013493382,0.000503],"domain_scores_gemma":[0.6245311,0.3745996,0.00013398039,0.00025920785,0.00017586071,0.00030025083],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42845833,0.00013516536,0.0014416877,0.00044854975,0.00022693998,0.000010582184,0.0002959719,0.0003500853,0.0011793586],"category_scores_gemma":[0.57754976,0.000090904694,0.00022579294,0.0007833514,0.0018444321,0.000048037233,0.00018896624,0.00037332874,0.0000027652068],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.061293695,0.0011016171,0.29039192,0.002004332,0.0834249,0.000057104397,0.12701544,0.00011001637,0.032838628,0.22246018,0.0011321122,0.17817006],"study_design_scores_gemma":[0.0047930586,0.011548418,0.26564074,0.00010061702,0.051038593,0.000010488129,0.0112847295,0.0022901827,0.62168026,0.018339714,0.012141561,0.0011316391],"about_ca_topic_score_codex":0.002067771,"about_ca_topic_score_gemma":0.002835803,"teacher_disagreement_score":0.5888416,"about_ca_system_score_codex":0.000020239857,"about_ca_system_score_gemma":0.00023992498,"threshold_uncertainty_score":0.9997337},"labels":[],"label_agreement":null},{"id":"W2108464813","doi":"10.1186/1471-2288-1-13","title":"Determinants of abstract acceptance for the Digestive Diseases Week – a cross sectional study","year":2001,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Deutscher Akademischer Austauschdienst","keywords":"Cross-sectional study; Medicine; Sample size determination; Family medicine; Clinical trial; Statistical significance; Presentation (obstetrics); Demography; Internal medicine; Surgery; Pathology; Statistics; Mathematics","score_opus":0.9645947845765394,"score_gpt":0.7438958041379483,"score_spread":0.22069898043859104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108464813","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":[0.8110001,0.0011871968,0.18465818,0.0002984623,0.00043912805,0.0019261986,0.000036050897,0.0000037901673,0.0004509012],"genre_scores_gemma":[0.98281956,0.00009615856,0.010970068,0.000074116324,0.0003413034,0.00057322753,0.0000021294168,0.000011857938,0.0051115993],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.82091665,0.1386925,0.011830296,0.0020583302,0.025323937,0.0011783128],"domain_scores_gemma":[0.27212593,0.71687526,0.0024250876,0.0034255905,0.0045187953,0.0006293593],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5467828,0.00020050886,0.002638108,0.00038333892,0.00044161858,0.00029141485,0.0038852906,0.0001731382,0.020283325],"category_scores_gemma":[0.84265065,0.000079038466,0.0012309673,0.0014832636,0.0011039223,0.00013664123,0.0004582376,0.00048640228,0.00030913294],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026749697,0.00033946775,0.9218225,0.000047031743,0.00010198208,0.00002162298,0.00024996616,0.000032571406,0.000009472324,0.0002853424,0.0032366135,0.073585965],"study_design_scores_gemma":[0.00046898625,0.00033996918,0.9761415,0.00001863014,0.000053763193,0.000027077487,0.0020091326,0.006200255,0.000011030994,0.0075121266,0.0071448437,0.00007268464],"about_ca_topic_score_codex":0.00014836589,"about_ca_topic_score_gemma":0.0010788045,"teacher_disagreement_score":0.57818276,"about_ca_system_score_codex":0.00003799427,"about_ca_system_score_gemma":0.00090708636,"threshold_uncertainty_score":0.9806123},"labels":[],"label_agreement":null},{"id":"W2111589117","doi":"10.1186/1471-2288-14-36","title":"Evaluating bias due to data linkage error in electronic healthcare records","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":102,"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":"Hospital for Sick Children; Intensive Care Society; Medical Research Council; National Institute for Health and Care Research; NHS Health Scotland","keywords":"Identifier; Record linkage; Linkage (software); Gold standard (test); Word error rate; Computer science; Imputation (statistics); Statistics; Probabilistic logic; Data mining; Missing data; Data set; Standard error; Medicine; Artificial intelligence; Mathematics; Population","score_opus":0.9728506852504919,"score_gpt":0.764426510343351,"score_spread":0.20842417490714094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111589117","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":[0.0874657,0.00046079277,0.85246366,0.0551026,0.0008368647,0.00096856384,0.000043540906,0.000052000672,0.002606248],"genre_scores_gemma":[0.27826628,0.00040277358,0.6975009,0.016152442,0.0016253075,0.00037707266,0.00027618324,0.000064027205,0.0053350283],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.734938,0.241934,0.0026987328,0.0031150456,0.014212316,0.0031018776],"domain_scores_gemma":[0.45397106,0.5336879,0.00040004126,0.00838872,0.0012728053,0.002279496],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.6394793,0.00016696288,0.0008231283,0.001223558,0.00022914207,0.0001526727,0.006863059,0.00032223633,0.0032934065],"category_scores_gemma":[0.8603182,0.00012445883,0.00006607333,0.002723577,0.0004164986,0.0002635641,0.0061264667,0.0017980075,0.0016729546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023313474,0.00008126542,0.0012672495,0.00007418097,0.000009832858,0.000033975448,0.00045877995,0.00002069424,0.000032079566,0.038508657,0.041158687,0.91812146],"study_design_scores_gemma":[0.001343295,0.0018717599,0.01666641,0.00019994505,0.000008734478,0.000030486835,0.0032005247,0.09765793,0.00005937495,0.40022507,0.47842166,0.00031480673],"about_ca_topic_score_codex":0.0043693315,"about_ca_topic_score_gemma":0.09030966,"teacher_disagreement_score":0.9178067,"about_ca_system_score_codex":0.00018802984,"about_ca_system_score_gemma":0.0026326496,"threshold_uncertainty_score":0.9991044},"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":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2111680408","doi":"10.1186/1471-2288-11-14","title":"Methodological criteria for the assessment of moderators in systematic reviews of randomised controlled trials: a consensus study","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":158,"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":"Keele University; National Institute for Health and Care Research; Advantage West Midlands; Programme Grants for Applied Research; Queen Mary University of London; Université Laval; University of Washington; Arizona State University","keywords":"Systematic review; Delphi method; Randomized controlled trial; MEDLINE; Grading (engineering); Meta-analysis; Psychology; Medicine; Psychological intervention; Applied psychology; Family medicine; Management science; Computer science; Psychiatry","score_opus":0.9949133789799366,"score_gpt":0.7958935538530266,"score_spread":0.19901982512690997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111680408","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":[0.02861499,0.0058497656,0.9251194,0.00042403868,0.0004516634,0.038490728,0.0000099061745,0.0000032203006,0.001036313],"genre_scores_gemma":[0.3972508,0.0005281152,0.5895296,0.00010494705,0.00010621411,0.011998187,0.0000012928505,0.00001887818,0.00046196624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.018411325,0.9271398,0.041479863,0.0012237657,0.0110784955,0.00066670723],"domain_scores_gemma":[0.006738426,0.9718366,0.0129805645,0.00408018,0.00398252,0.00038169004],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9825663,0.0003908623,0.038449842,0.0011891584,0.00013769632,0.00009242968,0.003936392,0.00035693435,0.015630051],"category_scores_gemma":[0.99295455,0.000121557234,0.005670871,0.0019492725,0.00090584706,0.00004473475,0.00041775242,0.00070409186,0.000027311136],"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":[0.17062312,0.020862013,0.08789729,0.16838498,0.03585796,0.00031984437,0.06302314,0.0003127648,0.009044252,0.23706484,0.08146366,0.12514614],"study_design_scores_gemma":[0.21614702,0.0065395585,0.0142502785,0.0060504656,0.00863631,0.00008299281,0.075060286,0.5035818,0.00042135155,0.16681181,0.001509459,0.0009086414],"about_ca_topic_score_codex":0.00013537644,"about_ca_topic_score_gemma":0.00034889943,"teacher_disagreement_score":0.5032691,"about_ca_system_score_codex":0.000047688678,"about_ca_system_score_gemma":0.001231905,"threshold_uncertainty_score":0.9852698},"labels":[],"label_agreement":null},{"id":"W2111955684","doi":"10.1186/1471-2288-14-69","title":"Evidence-based decision-making in infectious diseases epidemiology, prevention and control: matching research questions to study designs and quality appraisal tools","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; McMaster University Medical Centre","funders":"European Centre for Disease Prevention and Control","keywords":"Observational study; Grading (engineering); Public health; Medicine; Clinical study design; Quality (philosophy); Research design; Management science; Epidemiology; Family medicine; Applied psychology; Medical education; Psychology; Pathology; Statistics; Clinical trial","score_opus":0.9775469812016591,"score_gpt":0.7770561002309477,"score_spread":0.20049088097071133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111955684","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":[0.42916906,0.0014718934,0.56615007,0.0015578447,0.00011222362,0.0014615416,0.0000031512425,0.000007741373,0.000066488836],"genre_scores_gemma":[0.8815244,0.000115052346,0.11718144,0.00034853196,0.00015377255,0.0006025927,0.0000012492125,0.000013479669,0.000059468442],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.13668764,0.8389684,0.009152574,0.0025393316,0.011379549,0.0012725219],"domain_scores_gemma":[0.016707476,0.9761013,0.0011022624,0.0026116357,0.0022668866,0.0012104621],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90060514,0.0002841969,0.004342747,0.0022324028,0.00062660786,0.00051951275,0.001742371,0.00033827368,0.0016604029],"category_scores_gemma":[0.988547,0.00015901821,0.0004302988,0.0028800422,0.00095988606,0.00033737757,0.00091914204,0.0014056225,0.0001920011],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029147236,0.00025570064,0.5680989,0.00010246904,0.00005163018,0.000013766478,0.00048327705,0.00024046136,0.000050494833,0.011655116,0.00050202024,0.4182547],"study_design_scores_gemma":[0.00094436324,0.0009551193,0.71368796,0.0007913219,0.000052771393,0.000016157424,0.0017136553,0.012180157,0.0000014570119,0.26898128,0.00051608396,0.00015969294],"about_ca_topic_score_codex":0.0006235056,"about_ca_topic_score_gemma":0.005629681,"teacher_disagreement_score":0.45235536,"about_ca_system_score_codex":0.000104909406,"about_ca_system_score_gemma":0.0009003243,"threshold_uncertainty_score":0.9992522},"labels":[],"label_agreement":null},{"id":"W2112200626","doi":"10.1186/1471-2288-12-82","title":"Interpreting the concordance statistic of a logistic regression model: relation to the variance and odds ratio of a continuous explanatory variable","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":271,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Statistics; Mathematics; Statistic; Logistic regression; Sample size determination; Normal distribution; Standard deviation; Sampling distribution; PRESS statistic; Monte Carlo method; Variable (mathematics); Cumulative distribution function; Regression analysis; Econometrics; Ancillary statistic; F-test; Probability density function","score_opus":0.5031041758697814,"score_gpt":0.5613378965208847,"score_spread":0.05823372065110333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112200626","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049000666,0.00045239506,0.992688,0.0005532404,0.00016556309,0.00046775854,0.00002850211,0.000011607465,0.00073288556],"genre_scores_gemma":[0.3056449,0.000047220838,0.6939827,0.00010651616,0.00006340764,0.00007649522,0.0000011337604,0.000011185165,0.00006639726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9826901,0.01475744,0.0007447417,0.0002650896,0.0010189456,0.0005237159],"domain_scores_gemma":[0.81224084,0.1864792,0.00024773262,0.00043456285,0.00035637812,0.0002412646],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044484165,0.00012701868,0.000541539,0.00009257286,0.00015415628,0.000012909388,0.00046360368,0.0001732981,0.00021177148],"category_scores_gemma":[0.4205032,0.000066292094,0.000033875724,0.00035359952,0.0010949171,0.00005645094,0.00033108378,0.0006908388,0.0000032816774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002388986,0.000054891498,0.0006699442,0.0003294735,0.000019319466,0.0000020921218,0.0019866775,0.000016381713,0.0014590797,0.97131926,0.0010300919,0.02287387],"study_design_scores_gemma":[0.00033652515,0.0002693946,0.002442401,0.0006926664,0.000040279512,0.000027348453,0.0009263704,0.13542978,0.00042553153,0.85912675,0.00018137645,0.0001015939],"about_ca_topic_score_codex":0.00015705985,"about_ca_topic_score_gemma":0.000043676937,"teacher_disagreement_score":0.37601903,"about_ca_system_score_codex":0.00003675538,"about_ca_system_score_gemma":0.00047855187,"threshold_uncertainty_score":0.9839046},"labels":[],"label_agreement":null},{"id":"W2114158718","doi":"10.1186/1471-2288-12-127","title":"Two assessments to evaluate imagery ability: translation, test-retest reliability and concurrent validity of the German KVIQ and Imaprax","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Sport Psychology and Performance","field":"Psychology","cited_by":43,"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":"Cronbach's alpha; Intraclass correlation; Concurrent validity; Psychology; Rank correlation; Reliability (semiconductor); Physical medicine and rehabilitation; Physical therapy; Psychometrics; Medicine; Clinical psychology; Internal consistency; Statistics","score_opus":0.6122779809642963,"score_gpt":0.6443849521238374,"score_spread":0.03210697115954109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114158718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98272985,0.0011578792,0.008828607,0.002500621,0.0015351654,0.00080264435,0.000025928412,0.000023693972,0.0023956003],"genre_scores_gemma":[0.9863177,0.00013675878,0.012343472,0.00049027445,0.00030941673,0.00017226455,0.000006499856,0.000017409877,0.00020619384],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97988164,0.016766848,0.0007129713,0.0006601192,0.0010654655,0.00091294147],"domain_scores_gemma":[0.9531411,0.04488155,0.0001348002,0.0008612586,0.00032352927,0.0006577745],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07200785,0.00019085669,0.0005405504,0.00016218898,0.00022325032,0.000010765947,0.00047465586,0.000367019,0.0027722488],"category_scores_gemma":[0.031950355,0.00013172126,0.00008444283,0.00046444894,0.0025151207,0.00012649634,0.0003049733,0.001228262,0.00005779804],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030352347,0.00038693464,0.9084046,0.0001454858,0.00003075221,0.0000026618065,0.0020925063,4.2889988e-7,0.0015537419,0.0017404767,0.0018721167,0.083466776],"study_design_scores_gemma":[0.0014152825,0.0004014543,0.9858706,0.000045251654,0.000036432273,0.00006889221,0.00020456617,0.00020240508,0.00039004494,0.004379623,0.0068502105,0.00013521488],"about_ca_topic_score_codex":0.00020923991,"about_ca_topic_score_gemma":0.00012517991,"teacher_disagreement_score":0.08333156,"about_ca_system_score_codex":0.000044587025,"about_ca_system_score_gemma":0.00037358978,"threshold_uncertainty_score":0.9981394},"labels":[],"label_agreement":null},{"id":"W2117460543","doi":"10.1186/1471-2288-13-48","title":"Enhancing the scoping study methodology: a large, inter-professional team’s experience with Arksey and O’Malley’s framework","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":1930,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Inland Hospital; University of Victoria; Interior Health; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"Psychology; Knowledge management; Applied psychology; Computer science","score_opus":0.9073939510957548,"score_gpt":0.7921934918806057,"score_spread":0.1152004592151491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117460543","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":[0.5213194,0.0000897161,0.45391497,0.019792262,0.0007143077,0.0036684992,0.0000031988977,0.000060188366,0.00043746477],"genre_scores_gemma":[0.47003832,0.00014975503,0.48958418,0.028873868,0.0009204802,0.008797432,0.0000025359718,0.00005759289,0.0015758383],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.84333235,0.14866315,0.0016092286,0.0010226931,0.0027250592,0.0026475387],"domain_scores_gemma":[0.56331587,0.43277308,0.0004064211,0.001021126,0.0010331107,0.001450358],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16553131,0.00027384982,0.00085311994,0.00044769663,0.0031367096,0.0000469404,0.0013893325,0.0005688752,0.010504528],"category_scores_gemma":[0.40786874,0.00015322721,0.000046799003,0.0012379752,0.0019624683,0.0002889234,0.002097035,0.005140403,0.00043491644],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007432734,0.00036717576,0.46615344,0.0016271524,0.00009650836,0.000050545066,0.47239697,0.0000020798238,0.0014571695,0.023191247,0.013827856,0.020086592],"study_design_scores_gemma":[0.0033541599,0.0015749261,0.17095223,0.0037383267,0.00002071045,0.000060308805,0.7966134,0.00073036505,0.00021818613,0.015640711,0.00665933,0.0004373685],"about_ca_topic_score_codex":0.0035834447,"about_ca_topic_score_gemma":0.015630793,"teacher_disagreement_score":0.32421643,"about_ca_system_score_codex":0.00020268347,"about_ca_system_score_gemma":0.0068661873,"threshold_uncertainty_score":0.998764},"labels":[],"label_agreement":null},{"id":"W2119209233","doi":"10.1186/1471-2288-11-164","title":"Stopping rules employing response rates, time to progression, and early progressive disease for phase II oncology trials","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Clinical Oncology Group; McMaster University; Juravinski Hospital; Juravinski Cancer Centre","funders":"","keywords":"Medicine; Early stopping; Clinical endpoint; Stage (stratigraphy); Clinical trial; Oncology; Relative risk; Disease; Progressive disease; Internal medicine; Surrogate endpoint; Confidence interval; Computer science; Artificial intelligence","score_opus":0.9617852519897551,"score_gpt":0.7777558971622159,"score_spread":0.18402935482753913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119209233","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":[0.20882034,0.001000991,0.77599,0.0051625934,0.00060550147,0.007685617,0.00019837548,0.00021644298,0.00032012543],"genre_scores_gemma":[0.0017095135,0.00005247897,0.99305874,0.00035079324,0.0007938111,0.0032390007,0.000004542887,0.00009622811,0.0006949108],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82191116,0.16957924,0.0030891346,0.0014939915,0.0021087572,0.0018177174],"domain_scores_gemma":[0.1710286,0.8230581,0.00066681707,0.0009059695,0.0011479134,0.0031925824],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35315308,0.00039883723,0.0028375476,0.00063409016,0.00063824025,0.0000579572,0.0010082647,0.0008413583,0.003960066],"category_scores_gemma":[0.9793455,0.00028775734,0.0003287849,0.0005375921,0.002071943,0.00009898215,0.0013860433,0.0012511847,0.000119224394],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.1314074,0.0028143954,0.00020787475,0.00081937894,0.0002843793,0.0005988704,0.0025679173,7.4671156e-8,0.003144733,0.065288976,0.010350567,0.7825154],"study_design_scores_gemma":[0.009512245,0.014828242,0.0010141163,0.00092606235,0.00022934262,0.000034459295,0.00020404195,0.0003340865,0.0021650917,0.95783496,0.012480207,0.00043714698],"about_ca_topic_score_codex":0.0000149157095,"about_ca_topic_score_gemma":0.000006071581,"teacher_disagreement_score":0.892546,"about_ca_system_score_codex":0.00015889342,"about_ca_system_score_gemma":0.0029342033,"threshold_uncertainty_score":0.99995744},"labels":[],"label_agreement":null},{"id":"W2119790985","doi":"10.1186/1471-2288-7-10","title":"Development of AMSTAR: a measurement tool to assess the methodological quality of systematic reviews","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4413,"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; Institute of Population and Public Health","funders":"","keywords":"Quality (philosophy); Computer science; Data science; Systematic review; MEDLINE; Medicine; Medical physics; Management science; Political science; Engineering","score_opus":0.9972372497208365,"score_gpt":0.7946501814039316,"score_spread":0.20258706831690487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119790985","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":[0.057703372,0.003414743,0.9320829,0.000660737,0.0002818461,0.0043209814,0.0000023166301,0.00000435282,0.0015287645],"genre_scores_gemma":[0.04606115,0.0001079321,0.9521921,0.00036195107,0.00010090529,0.0004905964,0.0000011713416,0.000012580765,0.0006715908],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.022365483,0.86837757,0.04720718,0.0019636825,0.058654696,0.0014313754],"domain_scores_gemma":[0.029871114,0.93471897,0.011647055,0.009319601,0.013152779,0.0012904898],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.98310244,0.0003631593,0.011564641,0.0009208298,0.00023587646,0.00010442825,0.0065376936,0.00036521783,0.0073315767],"category_scores_gemma":[0.9800288,0.00012984213,0.0020679308,0.0039738147,0.0006883178,0.00006606116,0.0011844452,0.0008388506,0.0008237884],"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":[0.0010844789,0.0012112333,0.0143770315,0.09481447,0.0018689496,0.000035703546,0.014377823,0.000030070174,0.04862365,0.13478819,0.03693414,0.6518543],"study_design_scores_gemma":[0.003355857,0.0018411662,0.24198617,0.026251677,0.0013584378,0.00018445482,0.059638944,0.002202972,0.037673652,0.088620625,0.5344858,0.002400221],"about_ca_topic_score_codex":0.000054566557,"about_ca_topic_score_gemma":0.0012656556,"teacher_disagreement_score":0.64945406,"about_ca_system_score_codex":0.0001846127,"about_ca_system_score_gemma":0.0017686052,"threshold_uncertainty_score":0.99995416},"labels":[],"label_agreement":null},{"id":"W2120329233","doi":"10.1186/1471-2288-11-107","title":"Advancing the argument for validity of the Alberta Context Tool with healthcare aides in residential long-term care","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Geriatric Care and Nursing Homes","field":"Health Professions","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Calgary; University of Alberta","funders":"Canadian Institutes of Health Research; Killam Trusts; Ottawa Hospital Research Institute; Alberta Heritage Foundation for Medical Research; Fondation pour la Recherche Médicale; University of Alberta","keywords":"Confirmatory factor analysis; Cronbach's alpha; Context (archaeology); Health care; Psychology; Applied psychology; Psychological intervention; Criterion validity; Validity; Psychometrics; Construct validity; Nursing; Medicine; Structural equation modeling; Clinical psychology; Computer science","score_opus":0.5260671979056328,"score_gpt":0.5843235402053876,"score_spread":0.05825634229975474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120329233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9714432,0.001417141,0.013105429,0.008744456,0.001523969,0.0033061581,0.000017102924,0.000015956199,0.00042662155],"genre_scores_gemma":[0.99145967,0.0002052725,0.0061566024,0.0004153849,0.00040735348,0.00068092486,0.000010889223,0.000027339507,0.00063654926],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9713622,0.02536985,0.00072663516,0.000391046,0.0011004986,0.0010498064],"domain_scores_gemma":[0.93946373,0.058704577,0.00019039404,0.0006945684,0.00071414944,0.00023255557],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022896983,0.00014152264,0.0005443072,0.00015980678,0.0006638501,0.000004761121,0.0007915465,0.00036903593,0.0006183794],"category_scores_gemma":[0.049483553,0.00007102839,0.00012786283,0.0004226954,0.000731861,0.000046938883,0.0003971588,0.0014678142,0.000009798251],"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":[0.0059073134,0.00018408024,0.7950231,0.0047769886,0.00006691935,0.000026865197,0.10291758,0.000002019011,0.00012352657,0.010685775,0.007435756,0.0728501],"study_design_scores_gemma":[0.0037231145,0.0015420675,0.89202255,0.002073008,0.00005572307,0.000016377278,0.09071794,0.000026495649,0.001784395,0.005219696,0.0026181953,0.00020044186],"about_ca_topic_score_codex":0.038194638,"about_ca_topic_score_gemma":0.4820948,"teacher_disagreement_score":0.44390017,"about_ca_system_score_codex":0.00026521977,"about_ca_system_score_gemma":0.0040370002,"threshold_uncertainty_score":0.9682101},"labels":[],"label_agreement":null},{"id":"W2120673540","doi":"10.1186/1471-2288-3-28","title":"Pragmatic controlled clinical trials in primary care: the struggle between external and internal validity","year":2003,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":506,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Heart and Stroke Foundation of Canada","keywords":"External validity; Internal validity; Generalizability theory; Blinding; Face validity; Psychological intervention; Clinical trial; Medicine; Randomized controlled trial; Research design; Psychology; Clinical psychology; Social psychology; Psychometrics; Statistics; Nursing; Surgery","score_opus":0.9759954308528304,"score_gpt":0.8363125390958985,"score_spread":0.13968289175693183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120673540","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":[0.8045934,0.00049394165,0.1683726,0.013722476,0.0013943774,0.0050531705,0.000034171106,0.00003276069,0.0063030985],"genre_scores_gemma":[0.8196382,0.0013459409,0.14374605,0.02631456,0.003869401,0.003157442,0.000017272789,0.00006433,0.0018468056],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.29894292,0.69053596,0.0052838135,0.0006787447,0.0027854333,0.0017731193],"domain_scores_gemma":[0.13899337,0.85769004,0.0008612971,0.00059739436,0.0005147687,0.0013431109],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.68648726,0.00016422103,0.0019846107,0.00035959884,0.0006996758,0.000025180096,0.00082041137,0.0005460328,0.0025597843],"category_scores_gemma":[0.8694932,0.00009537255,0.00016186823,0.0005541526,0.0014294604,0.0000957708,0.0004961639,0.0043057515,0.00013452848],"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":[0.00096157764,0.0000601262,0.9114558,0.0009853925,0.000037093796,0.000027447706,0.00827485,3.8515893e-7,0.000080308564,0.0073812325,0.010080573,0.060655218],"study_design_scores_gemma":[0.034947064,0.0009535663,0.859389,0.0008407686,0.0000502418,0.000025790161,0.013449473,0.0002384014,0.000039734037,0.030962769,0.058848925,0.0002542589],"about_ca_topic_score_codex":0.000986093,"about_ca_topic_score_gemma":0.0020969731,"teacher_disagreement_score":0.18300591,"about_ca_system_score_codex":0.0003759357,"about_ca_system_score_gemma":0.011575809,"threshold_uncertainty_score":0.998352},"labels":[],"label_agreement":null},{"id":"W2122612273","doi":"10.1186/1471-2288-12-155","title":"Social interactions of eating behaviour among high school students: a cellular automata approach","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cellular Automata and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"SFU Community Trust Endowment Fund; Simon Fraser University","keywords":"Overweight; Cafeteria; Affect (linguistics); Obesity; Food choice; Psychology; Developmental psychology; Social psychology; Medicine","score_opus":0.36933105736852057,"score_gpt":0.5282128909256791,"score_spread":0.15888183355715857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122612273","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":[0.32963005,0.00007636706,0.66862,0.0002518126,0.00016088631,0.00027328407,0.000002525037,0.00010080458,0.00088429824],"genre_scores_gemma":[0.68672866,0.000010500296,0.3122905,0.000035124453,0.00032291052,0.00021573117,0.00001738383,0.000013156662,0.00036607432],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9890318,0.0068477816,0.0005880076,0.00047603104,0.002187701,0.00086866296],"domain_scores_gemma":[0.9906176,0.007465809,0.00016933851,0.0008081611,0.00025287343,0.0006862547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020478668,0.00014678694,0.00041834902,0.00036711822,0.0003873995,0.00007921389,0.0025592023,0.00024198284,0.0003571717],"category_scores_gemma":[0.010617808,0.0001310103,0.00013573714,0.0009899256,0.00058535766,0.00041630943,0.0018976653,0.0010679527,0.00010487317],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004660103,0.0041371,0.5129366,0.0003910287,0.00017854017,0.000026800604,0.0058854087,0.000011503789,0.014808866,0.4012222,0.007916508,0.052438844],"study_design_scores_gemma":[0.0023759292,0.0002843518,0.89878815,0.00018052562,0.00007611969,0.00011934436,0.0029512509,0.070216075,0.011549032,0.008694746,0.004075529,0.00068892486],"about_ca_topic_score_codex":0.00065848755,"about_ca_topic_score_gemma":0.000051707902,"teacher_disagreement_score":0.39252746,"about_ca_system_score_codex":0.000103414306,"about_ca_system_score_gemma":0.000510877,"threshold_uncertainty_score":0.9977162},"labels":[],"label_agreement":null},{"id":"W2123074327","doi":"10.1186/1471-2288-7-5","title":"Inclusion of zero total event trials in meta-analyses maintains analytic consistency and incorporates all available data","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":472,"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; Hospital for Sick Children; Health Sciences Centre; Sunnybrook Health Science Centre; Muscular Dystrophy Canada; University of Toronto","funders":"","keywords":"Meta-analysis; Confidence interval; Random effects model; Statistics; Relative risk; Medicine; Odds ratio; Study heterogeneity; Absolute risk reduction; Randomized controlled trial; Event (particle physics); Clinical trial; Econometrics; Mathematics; Internal medicine","score_opus":0.9930425907223072,"score_gpt":0.7755257982900672,"score_spread":0.21751679243223998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123074327","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":[0.13212794,0.021642782,0.83530307,0.003502586,0.00029372924,0.0021621594,0.00009259218,0.000007938281,0.004867213],"genre_scores_gemma":[0.6805575,0.00095330254,0.31040883,0.00047950822,0.0001582263,0.00006434876,0.0000789438,0.00002723853,0.007272139],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.10138616,0.80856234,0.04648129,0.00472929,0.036759377,0.002081569],"domain_scores_gemma":[0.06045432,0.91595685,0.008687522,0.009934805,0.0034641824,0.0015023167],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.95000714,0.00037678497,0.013712029,0.002716155,0.00023523398,0.00017481556,0.004637614,0.00043527773,0.045091514],"category_scores_gemma":[0.94489807,0.00016693927,0.0019378376,0.003986129,0.0012132168,0.0002516519,0.0071901428,0.0008739422,0.0005012299],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029841356,0.0030210798,0.1508139,0.0027801383,0.036517516,0.001770173,0.0050107744,0.0004912521,0.02615376,0.087342806,0.4002405,0.28287396],"study_design_scores_gemma":[0.0051033054,0.0015984823,0.028918173,0.00043106516,0.017630892,0.0004815657,0.009459401,0.12939385,0.0032049092,0.7073147,0.09513179,0.0013318617],"about_ca_topic_score_codex":0.0012673418,"about_ca_topic_score_gemma":0.005610886,"teacher_disagreement_score":0.61997193,"about_ca_system_score_codex":0.000082844825,"about_ca_system_score_gemma":0.001603615,"threshold_uncertainty_score":0.9557814},"labels":[],"label_agreement":null},{"id":"W2125308298","doi":"10.1186/1471-2288-13-9","title":"Comparison of population-averaged and cluster-specific models for the analysis of cluster randomized trials with missing binary outcomes: a simulation study","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Population Health Research Institute; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"Canadian Institutes of Health Research","keywords":"Cluster (spacecraft); Population; Missing data; Statistics; Randomized controlled trial; Psychology; Medicine; Computer science; Mathematics; Environmental health; Internal medicine","score_opus":0.7779863805310022,"score_gpt":0.6482697854431466,"score_spread":0.1297165950878556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125308298","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":[0.113432854,0.00014080772,0.88224995,0.0004641238,0.000044331817,0.0036288647,0.000011191911,0.000009843739,0.000018052997],"genre_scores_gemma":[0.4855902,0.000012515469,0.5141027,0.000016753938,0.00001976391,0.00023290137,0.000004608853,0.000009751133,0.000010794311],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9390843,0.05686135,0.0019860172,0.00037703128,0.0013409968,0.00035028928],"domain_scores_gemma":[0.3422115,0.65602773,0.0005421582,0.00041162333,0.00064996374,0.00015697704],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11184014,0.00017012906,0.0034208205,0.0005214386,0.00017032548,0.00003686824,0.00030186248,0.00019205028,0.0003839411],"category_scores_gemma":[0.37849486,0.00008275194,0.00028859492,0.00070883456,0.0007441396,0.00007538301,0.00014836526,0.00037555693,3.7023756e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.1548429,0.0033746047,0.061459053,0.0020988507,0.010566657,0.0000051368747,0.01626781,0.0318912,0.00025135657,0.21480241,0.0005919934,0.503848],"study_design_scores_gemma":[0.019935941,0.00028314625,0.009158123,0.000051887106,0.0008269774,3.6591814e-7,0.0012130371,0.6996346,0.000010398601,0.26881984,0.0000013462495,0.000064361004],"about_ca_topic_score_codex":0.000556716,"about_ca_topic_score_gemma":0.00017516261,"teacher_disagreement_score":0.6677434,"about_ca_system_score_codex":0.00002552245,"about_ca_system_score_gemma":0.00012712834,"threshold_uncertainty_score":0.9145475},"labels":[],"label_agreement":null},{"id":"W2126061413","doi":"10.1186/1471-2288-11-176","title":"Successful strategies for high participation in three regional healthcare surveys: an observational study","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Infection Control in Healthcare","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; University of California, Irvine; National Institutes of Health","keywords":"Health care; Representativeness heuristic; Observational study; Data collection; Medicine; Quarter (Canadian coin); General partnership; Infection control; Family medicine; Nursing; Environmental health; Geography; Business; Psychology; Political science","score_opus":0.934282184908797,"score_gpt":0.6700609760011011,"score_spread":0.26422120890769585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126061413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82542354,0.00012475769,0.16685088,0.0045382273,0.00038683857,0.0025041918,0.000010806725,0.00006452842,0.00009622493],"genre_scores_gemma":[0.9566774,0.000028613207,0.039681472,0.0007392102,0.0006675517,0.0020034332,0.00012809751,0.000033442106,0.0000407941],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.964394,0.030768337,0.0010472807,0.00075591385,0.001985296,0.0010491938],"domain_scores_gemma":[0.96602315,0.029908385,0.00014532327,0.00060800114,0.0024747911,0.0008403697],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07152699,0.00018322468,0.0007161998,0.00058388297,0.00023025143,0.000020937068,0.0003296534,0.000491442,0.0009871171],"category_scores_gemma":[0.058856547,0.00015625809,0.00007824877,0.00072059163,0.00046635664,0.0002569205,0.00009553694,0.001183467,0.000014432732],"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":[0.0023372932,0.0012366645,0.89113593,0.00041792527,0.00003945861,0.000059058057,0.0020177406,0.000008295119,0.000038282462,0.08393076,0.00009556622,0.018683055],"study_design_scores_gemma":[0.0034747943,0.0047854236,0.91407734,0.00008489265,0.000015187408,0.000021529782,0.005629229,0.0030117172,0.000027023412,0.06870146,0.00005781728,0.000113578484],"about_ca_topic_score_codex":0.03070655,"about_ca_topic_score_gemma":0.23965311,"teacher_disagreement_score":0.20894656,"about_ca_system_score_codex":0.0002710521,"about_ca_system_score_gemma":0.006396581,"threshold_uncertainty_score":0.9999261},"labels":[],"label_agreement":null},{"id":"W2127161271","doi":"10.1186/1471-2288-13-68","title":"Validation of a registry-derived risk algorithm based on treatment protocol as a proxy for disease risk in childhood acute lymphoblastic leukemia","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Acute Lymphoblastic Leukemia research","field":"Medicine","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":"Institute for Work & Health; SickKids Foundation; University of Toronto; Pediatric Oncology Group; Institute for Clinical Evaluative Sciences; Hospital for Sick Children","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Cancer registry; Population; Algorithm; Disease; Risk assessment; Confidence interval; Pediatrics; Internal medicine; Computer science; Environmental health","score_opus":0.11215430023241335,"score_gpt":0.4586356650653432,"score_spread":0.34648136483292985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127161271","genre_codex":"methods","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36589846,0.000034954548,0.46415898,0.0017835555,0.0001176657,0.16719261,0.0002550515,0.00011502614,0.00044367803],"genre_scores_gemma":[0.12183762,0.0002048284,0.3646922,0.0003372231,0.00068304595,0.5106559,0.00028673018,0.00018746237,0.0011149916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9805746,0.012038535,0.0011910546,0.0012639399,0.0033677923,0.0015640646],"domain_scores_gemma":[0.94189423,0.05310881,0.00044287156,0.001437207,0.0010847643,0.0020320949],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014350159,0.00046902214,0.0013187685,0.0011335922,0.00021192167,0.000040271567,0.00065484573,0.0006491703,0.0013338611],"category_scores_gemma":[0.17682706,0.0003249508,0.00038247128,0.0010719511,0.0012178039,0.00010381504,0.00024206769,0.001178482,0.00019526757],"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":true,"study_design_scores_codex":[0.06081007,0.010646487,0.05563283,0.0038852228,0.0013507716,0.0014572515,0.0017180352,0.0010299816,0.0067357286,0.00047116703,0.0056269886,0.85063547],"study_design_scores_gemma":[0.06853425,0.018989846,0.0765438,0.0015813658,0.0004265822,0.00011784392,0.0003891733,0.7942475,0.02834729,0.009082057,0.0012189576,0.0005213354],"about_ca_topic_score_codex":0.00434965,"about_ca_topic_score_gemma":0.00007222333,"teacher_disagreement_score":0.8501141,"about_ca_system_score_codex":0.0040462166,"about_ca_system_score_gemma":0.0281541,"threshold_uncertainty_score":0.99992025},"labels":[],"label_agreement":null},{"id":"W2127832821","doi":"10.1186/1471-2288-12-114","title":"What is the most appropriate knowledge synthesis method to conduct a review? Protocol for a scoping review","year":2012,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":347,"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; Royal College of Physicians and Surgeons of Canada; Institute of Population and Public Health; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"CINAHL; Systematic review; Psychological intervention; Computer science; Knowledge translation; Protocol (science); MEDLINE; Health care; Management science; Knowledge management; Data science; Medicine; Alternative medicine; Nursing","score_opus":0.9872001315892293,"score_gpt":0.8771516823879036,"score_spread":0.11004844920132562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127832821","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":[1.4264319e-9,0.5312324,0.0458245,0.02781585,0.00057522464,0.39409027,0.00005859684,0.000043086035,0.00036006118],"genre_scores_gemma":[6.376843e-11,0.4435361,0.08554396,0.035789628,0.000939711,0.43323347,0.000008511363,0.000073126095,0.00087549473],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6454698,0.33952618,0.005809346,0.001709321,0.0033416538,0.0041437],"domain_scores_gemma":[0.2145015,0.77243346,0.0025071336,0.0033111083,0.0032960346,0.0039507947],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.5292529,0.00082133565,0.0072294706,0.00081703294,0.002136219,0.000061734296,0.0042895367,0.001390513,0.016064076],"category_scores_gemma":[0.64679927,0.0004533543,0.00085091544,0.004615212,0.0008299575,0.0003425933,0.002632109,0.005369028,0.004243259],"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":[0.0000135275795,0.000018720597,2.7723897e-7,0.4429736,0.000025380636,7.913951e-7,0.00050696096,1.10348e-9,9.433029e-8,0.00029946782,0.091618136,0.464543],"study_design_scores_gemma":[0.00021588629,0.000074574564,1.5443739e-7,0.4654613,0.00021345365,0.000018622879,0.00019850559,0.0000024610144,8.7863424e-7,0.00012934986,0.53347725,0.00020754575],"about_ca_topic_score_codex":0.00025822033,"about_ca_topic_score_gemma":0.0006893551,"teacher_disagreement_score":0.46433547,"about_ca_system_score_codex":0.00096295535,"about_ca_system_score_gemma":0.05893253,"threshold_uncertainty_score":0.9999059},"labels":[],"label_agreement":null},{"id":"W2128047255","doi":"10.1186/1471-2288-13-59","title":"Methodological approaches to population based research of screening procedures in the presence of selection bias and exposure measurement error: colonoscopy and colorectal cancer outcomes in Ontario","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Cancer Care Ontario; Institute for Clinical Evaluative Sciences; Toronto General Hospital; University of Toronto; Public Health Ontario; St. Michael's Hospital","funders":"Ontario Ministry of Research and Innovation; Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Cancer Care Ontario","keywords":"Medicine; Colonoscopy; Cohort; Colorectal cancer; Incidence (geometry); Population; Cohort study; Propensity score matching; Referral; Retrospective cohort study; Observational study; Internal medicine; Cancer; Demography; Family medicine; Environmental health","score_opus":0.8762466781156963,"score_gpt":0.5462594586265112,"score_spread":0.3299872194891852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128047255","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9851676,0.00044565744,0.009629612,0.0026907183,0.000043076227,0.0019459286,0.000001153108,0.000011153059,0.00006507897],"genre_scores_gemma":[0.92524916,0.00003301989,0.07359802,0.000062893574,0.000034209974,0.0009862777,0.0000020812677,0.000009663026,0.000024669629],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9781885,0.017678747,0.0006304174,0.0005468402,0.0023977663,0.0005576869],"domain_scores_gemma":[0.9694793,0.029378928,0.00011080655,0.0001943886,0.0005725029,0.0002640512],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062190477,0.0001424532,0.00071664824,0.00088101067,0.000104222716,0.000018365334,0.00020334445,0.0003397974,0.00015061109],"category_scores_gemma":[0.111946054,0.00009270855,0.00005108888,0.0011645171,0.00052515836,0.000071743285,0.00016797951,0.0014090657,3.9191391e-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":[0.0076658954,0.00016774646,0.9704434,0.00032381335,0.000022937113,0.0000036301392,0.002033838,0.00017428653,0.0039824755,0.00009465046,0.00004549893,0.015041798],"study_design_scores_gemma":[0.0012309434,0.005318497,0.98028445,0.00041589575,0.000012202268,0.000019836833,0.0016750692,0.00567015,0.0046883575,0.00059648766,0.000014332609,0.000073755065],"about_ca_topic_score_codex":0.27203685,"about_ca_topic_score_gemma":0.67241627,"teacher_disagreement_score":0.4003794,"about_ca_system_score_codex":0.00032779647,"about_ca_system_score_gemma":0.0016087623,"threshold_uncertainty_score":0.96567225},"labels":[],"label_agreement":null},{"id":"W2130719042","doi":"10.1186/1471-2288-13-135","title":"Perspectives on neurological patient registries: a literature review and focus group study","year":2013,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; South Health Campus; University of Calgary","funders":"Alberta Innovates; Public Health Agency; Public Health Agency of Canada","keywords":"Focus group; Stakeholder; Medicine; MEDLINE; Data collection; Health care; Family medicine; Patient participation; Nursing; Public relations","score_opus":0.708628723791784,"score_gpt":0.6823499001419668,"score_spread":0.02627882364981715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130719042","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":[0.000023803452,0.9733752,0.00043214398,0.0028588036,0.00075137604,0.021097913,0.00003658258,0.00013004393,0.0012941113],"genre_scores_gemma":[0.000002011538,0.9786523,0.002220791,0.0013941736,0.001304796,0.014815011,0.000046375764,0.00012735414,0.0014372035],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.73412055,0.25671595,0.0025636866,0.0018804057,0.0023357042,0.0023836761],"domain_scores_gemma":[0.7927052,0.20160635,0.0010072488,0.0017955593,0.00096174085,0.0019239142],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.09155591,0.0008652157,0.0069493204,0.00086412416,0.0010682488,0.000038391245,0.0014687171,0.0031647095,0.0027957803],"category_scores_gemma":[0.30051062,0.0005101788,0.0004378663,0.0018841008,0.00095823756,0.00007548692,0.0014773972,0.020293973,0.0007026875],"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":[0.000082522194,0.00038509813,0.00004083839,0.16871187,0.00011927445,0.00028508526,0.002277573,1.5118906e-9,1.323468e-8,0.0035540357,0.0387884,0.7857553],"study_design_scores_gemma":[0.0005235721,0.006520415,0.000014185099,0.10365012,0.0002143408,0.00019383391,0.0027725145,0.0000024868318,2.4156557e-9,0.0004146389,0.88538635,0.00030751366],"about_ca_topic_score_codex":0.00057674304,"about_ca_topic_score_gemma":0.0007784,"teacher_disagreement_score":0.84659797,"about_ca_system_score_codex":0.0008248522,"about_ca_system_score_gemma":0.00880554,"threshold_uncertainty_score":0.999735},"labels":[],"label_agreement":null},{"id":"W2132268984","doi":"10.1186/1471-2288-13-150","title":"Exploratory randomized controlled trial evaluating the impact of a waiting list control design","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":330,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"Medical Research Council; Wellcome Trust","keywords":"Randomized controlled trial; Intervention (counseling); Waiting list; Research design; Exploratory research; Medicine; Psychology; Control (management); Clinical trial; Random assignment; Computer science; Psychiatry; Statistics","score_opus":0.6349216352576696,"score_gpt":0.5924382886032753,"score_spread":0.04248334665439435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132268984","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":[0.9148375,0.002146519,0.066809416,0.0014485599,0.00025525913,0.013860306,5.3006283e-7,0.000048266942,0.00059363624],"genre_scores_gemma":[0.97192645,0.00025001206,0.020870961,0.00022551147,0.00066307135,0.005481181,0.0000041934504,0.000033463824,0.000545184],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.913429,0.081277244,0.0014355981,0.00040426885,0.00253035,0.00092352874],"domain_scores_gemma":[0.43136132,0.5650887,0.0005211292,0.0007862983,0.0015172003,0.00072536943],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1407481,0.00025982116,0.0034864477,0.00033710155,0.00019873484,0.000027257242,0.00038963647,0.00031517504,0.0059147314],"category_scores_gemma":[0.4946291,0.000111312016,0.0012002817,0.00043894164,0.0016190469,0.00008946925,0.000081269005,0.00094496814,0.00008662551],"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":[0.98309976,0.00023296554,0.0012757207,0.00002832679,0.0011748614,0.000027199525,0.0011566681,0.000016335935,0.0022422527,0.00052780635,0.0009151806,0.00930291],"study_design_scores_gemma":[0.90945816,0.0032810469,0.00019846756,0.00014491197,0.00032333785,0.000021128313,0.0014536694,0.08204064,0.00027842954,0.0027134763,0.0000018437747,0.000084883286],"about_ca_topic_score_codex":0.0004708856,"about_ca_topic_score_gemma":0.000038434355,"teacher_disagreement_score":0.48381144,"about_ca_system_score_codex":0.00016304162,"about_ca_system_score_gemma":0.0036644149,"threshold_uncertainty_score":0.994994},"labels":[],"label_agreement":null},{"id":"W2132466232","doi":"10.1186/1471-2288-13-42","title":"Overview of data-synthesis in systematic reviews of studies on outcome prediction models","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Outcome (game theory); Systematic review; Computer science; MEDLINE; Data science; Medicine; Mathematics; Biology","score_opus":0.9969530836768786,"score_gpt":0.7875121862582263,"score_spread":0.20944089741865235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132466232","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":[0.12397671,0.22357264,0.6085529,0.0050910786,0.0018292507,0.026063984,0.00014893043,0.000023077591,0.010741457],"genre_scores_gemma":[0.4022158,0.048639484,0.5341928,0.00075346534,0.00038373683,0.007112179,0.000021058086,0.00007808837,0.006603367],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.35386816,0.5874832,0.03478357,0.0018750477,0.0212596,0.00073043664],"domain_scores_gemma":[0.044758294,0.9269274,0.009466317,0.01344565,0.004789531,0.0006128184],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8358776,0.00027679515,0.012770159,0.0014617952,0.00005924694,0.00005819434,0.0053837528,0.00026963255,0.011295933],"category_scores_gemma":[0.9501574,0.000115012976,0.0010628321,0.0026737954,0.00060001295,0.00037481714,0.0011632434,0.0005773438,0.0011159165],"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":[0.00018874918,0.0014609206,0.052665807,0.4700167,0.0023206428,0.000031964053,0.0055287005,0.0007504147,0.0004890157,0.12915872,0.13112542,0.20626295],"study_design_scores_gemma":[0.0014926384,0.0010037244,0.011919823,0.063996375,0.0012414348,0.00005655153,0.019287806,0.5459995,0.00037805902,0.34584,0.008039508,0.000744585],"about_ca_topic_score_codex":0.00018640039,"about_ca_topic_score_gemma":0.0003485781,"teacher_disagreement_score":0.5452491,"about_ca_system_score_codex":0.00006720656,"about_ca_system_score_gemma":0.00035794298,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null},{"id":"W2133667151","doi":"10.1186/1471-2288-6-49","title":"Structural equation and log-linear modeling: a comparison of methods in the analysis of a study on caregivers' health","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Family and Disability Support Research","field":"Psychology","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":"McMaster University; Jewish General Hospital","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Structural equation modeling; Coping (psychology); Cerebral palsy; Linear model; Psychology; Population; Cross-sectional study; Clinical psychology; Medicine; Mathematics; Psychiatry; Statistics; Environmental health","score_opus":0.8242340047163143,"score_gpt":0.7048865603646864,"score_spread":0.11934744435162781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133667151","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8940804,0.00057454105,0.10316392,0.0007649801,0.00006836064,0.00075167423,0.000010467989,0.000006909314,0.00057877187],"genre_scores_gemma":[0.9750744,0.0000086716755,0.024680119,0.000050752573,0.000044576165,0.00007194647,0.000029322428,0.000007903191,0.000032315173],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91685086,0.078647844,0.0012356341,0.0006425629,0.001898534,0.000724577],"domain_scores_gemma":[0.93945354,0.05925416,0.0001573445,0.00068523205,0.00027585292,0.00017385188],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07293696,0.00013412512,0.0010743999,0.0012109576,0.00010580567,0.000007859005,0.0006072594,0.00025519758,0.00051295426],"category_scores_gemma":[0.02529089,0.000089682035,0.00014251658,0.0022274763,0.0010079764,0.000027926475,0.00018511128,0.0010844216,0.000002836586],"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":[0.0019758323,0.0020212894,0.8896423,0.00018354681,0.00038183396,0.000014372662,0.03949913,0.004165444,0.00017609101,0.017064387,0.0004305525,0.044445224],"study_design_scores_gemma":[0.0017393051,0.0025816364,0.52001446,0.000022713319,0.00009471453,0.0000031989323,0.18001492,0.29054406,0.000049520277,0.0048078764,0.000027662534,0.00009995083],"about_ca_topic_score_codex":0.045757774,"about_ca_topic_score_gemma":0.014529006,"teacher_disagreement_score":0.36962783,"about_ca_system_score_codex":0.000073285046,"about_ca_system_score_gemma":0.0005832829,"threshold_uncertainty_score":0.9829195},"labels":[],"label_agreement":null},{"id":"W2133710899","doi":"10.1186/1471-2288-14-80","title":"Meta-ethnography 25 years on: challenges and insights for synthesising a large number of qualitative studies","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":331,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Health Services Research Programme; National Institutes of Health; Health Services and Delivery Research Programme; National Institute for Health and Care Research","keywords":"Reflexivity; Qualitative research; Ethnography; DECIPHER; Process (computing); Interpretation (philosophy); Management science; Epistemology; Sociology; Health care; Engineering ethics; Psychology; Data science; Computer science; Social science; Bioinformatics; Political science","score_opus":0.9910430930723466,"score_gpt":0.8531529516083495,"score_spread":0.13789014146399714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133710899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7697022,0.010424444,0.13121009,0.07614697,0.0010567115,0.004378786,0.00010586179,0.00011552839,0.006859409],"genre_scores_gemma":[0.52194124,0.012569309,0.44374153,0.01600044,0.0007706854,0.0042548026,0.0000051573743,0.000073197414,0.0006436575],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.88239783,0.1134272,0.001011878,0.00051232293,0.0015413567,0.0011094091],"domain_scores_gemma":[0.530417,0.46789247,0.0002342781,0.0002950931,0.00071315904,0.00044797207],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18242031,0.00013779198,0.0010534787,0.0004942649,0.00057010184,0.0000031961995,0.00035229762,0.0002910202,0.000398081],"category_scores_gemma":[0.43685424,0.00009621782,0.00011803284,0.00044183366,0.0013311865,0.00007228752,0.00031928933,0.00082070415,0.00005102992],"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":[0.00026164818,0.0000688014,0.00034891616,0.0027152766,0.0005178853,0.0000020215061,0.47699136,1.1114891e-7,0.00007173682,0.48443934,0.0039390028,0.03064392],"study_design_scores_gemma":[0.0032287952,0.0010761821,0.007433739,0.0006807266,0.00018165709,0.0000033314286,0.48247504,0.00016644203,0.00020398221,0.3323139,0.17198156,0.00025464792],"about_ca_topic_score_codex":0.000108137334,"about_ca_topic_score_gemma":0.0015857462,"teacher_disagreement_score":0.35446528,"about_ca_system_score_codex":0.00005744439,"about_ca_system_score_gemma":0.000997917,"threshold_uncertainty_score":0.8418703},"labels":[],"label_agreement":null},{"id":"W2134411641","doi":"10.1186/1471-2288-13-93","title":"Understanding recruitment: outcomes associated with alternate methods for seed selection in respondent driven sampling","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; University of Manitoba; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Respondent; Population; Demography; Logistic regression; Homophily; Selection (genetic algorithm); Sampling (signal processing); Multinomial logistic regression; Medicine; Psychology; Statistics; Social psychology; Mathematics","score_opus":0.876707078736003,"score_gpt":0.6524279278495625,"score_spread":0.22427915088644046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134411641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23587324,0.00008590001,0.75679743,0.0031070693,0.00018094192,0.0031891633,0.000003927638,0.00010256482,0.00065973646],"genre_scores_gemma":[0.18008527,0.00015348729,0.8139155,0.00056151923,0.00021673192,0.0020463234,0.000049892842,0.00011025768,0.002861008],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97638184,0.01885009,0.0008114088,0.0008112961,0.0016964527,0.0014489176],"domain_scores_gemma":[0.8858881,0.11197423,0.0002007956,0.0003847412,0.0006372011,0.00091495685],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05045347,0.00028278574,0.0011496345,0.0012017927,0.00022937632,0.00004964977,0.00040280935,0.00059775746,0.0006351834],"category_scores_gemma":[0.20309749,0.00020613804,0.00013574895,0.0012548959,0.0004966932,0.00013599399,0.00021849464,0.0017069499,0.00004401045],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008393723,0.0013895906,0.75754386,0.0009037592,0.0014256844,0.0001781024,0.011746597,0.00031425717,0.07244675,0.01371263,0.0015089704,0.13043608],"study_design_scores_gemma":[0.037721835,0.010737155,0.60738385,0.0031230971,0.0004091246,0.0003625589,0.052755065,0.15989244,0.008616498,0.11430689,0.0032628612,0.0014286587],"about_ca_topic_score_codex":0.00093569705,"about_ca_topic_score_gemma":0.0034425247,"teacher_disagreement_score":0.15957817,"about_ca_system_score_codex":0.0017618757,"about_ca_system_score_gemma":0.0015279579,"threshold_uncertainty_score":0.977758},"labels":[],"label_agreement":null},{"id":"W2134483528","doi":"10.1186/1471-2288-14-46","title":"Recruiting and motivating black subjects to complete a lengthy survey in a large cohort study: an exploration of different strategies","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Cohort; Incentive; Flexibility (engineering); Tournament; Cohort study; Medicine; Randomized controlled trial; Psychology; Family medicine; Gerontology; Medical education; Economics; Surgery","score_opus":0.9349713725007408,"score_gpt":0.6991412943084848,"score_spread":0.235830078192256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134483528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90215206,0.000023456954,0.09420017,0.0010668457,0.000064765656,0.0018187822,0.000006198548,0.000026133872,0.000641613],"genre_scores_gemma":[0.9793315,0.00017479289,0.019792939,0.00018270171,0.00018389388,0.00019525722,0.0000310621,0.00003568736,0.00007214574],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.89935553,0.08963773,0.0018842443,0.0014572188,0.0060651517,0.0016001484],"domain_scores_gemma":[0.5061637,0.4888361,0.00020353543,0.0011624234,0.0020784421,0.0015557795],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28160375,0.0001995585,0.0012458812,0.0007245271,0.00013976492,0.00004763538,0.00050728454,0.00056013395,0.0001851176],"category_scores_gemma":[0.7480862,0.00015847819,0.000055853227,0.00093921274,0.0010538363,0.0002019436,0.00088188384,0.003908309,0.000011730238],"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":[0.0012210844,0.00090658484,0.96760464,0.00069329736,0.000040596562,0.00003247685,0.0044563455,0.000008433954,0.0020917838,0.01587098,0.0000139051635,0.007059899],"study_design_scores_gemma":[0.0024857079,0.00480757,0.94815326,0.00051818305,0.000009051075,0.0000041457424,0.011747735,0.0052854796,0.00021908795,0.026631163,0.00001543475,0.00012320685],"about_ca_topic_score_codex":0.0027219302,"about_ca_topic_score_gemma":0.09012162,"teacher_disagreement_score":0.46648243,"about_ca_system_score_codex":0.00011623119,"about_ca_system_score_gemma":0.0015017639,"threshold_uncertainty_score":0.9983897},"labels":[],"label_agreement":null},{"id":"W2134792407","doi":"10.1186/1471-2288-12-159","title":"Should researchers use single indicators, best indicators, or multiple indicators in structural equation models?","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":422,"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":"Structural equation modeling; Latent variable; Path analysis (statistics); Econometrics; Computer science; Statistical model; Performance indicator; Confounding; Statistics; Risk analysis (engineering); Mathematics; Machine learning; Medicine; Economics","score_opus":0.9615285550475937,"score_gpt":0.6606017935692375,"score_spread":0.3009267614783562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134792407","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":[0.8312503,0.0017249936,0.16127895,0.0010477388,0.0013034514,0.0009707824,0.00002700877,0.000110688445,0.0022860453],"genre_scores_gemma":[0.7845387,0.00030499027,0.2131133,0.0002796279,0.0006282906,0.00016097663,0.00002340782,0.00006083049,0.0008898939],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.90006804,0.07724222,0.0029249238,0.0018473308,0.0140522765,0.0038651815],"domain_scores_gemma":[0.19536665,0.79659873,0.0010396732,0.0024140428,0.0007218213,0.0038591],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","research_integrity"],"category_scores_codex":[0.2797406,0.0004901982,0.0016074346,0.019172596,0.00055547367,0.00038098166,0.004226325,0.0015492885,0.0038931486],"category_scores_gemma":[0.93268144,0.00032583866,0.00029369813,0.02976135,0.0026445952,0.0016240469,0.0023370865,0.004276934,0.00019182298],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062986737,0.00029545717,0.65682465,0.000037798167,0.00003448917,0.000049767918,0.0014975249,0.00007872343,0.00017919876,0.005745786,0.0013952096,0.3332315],"study_design_scores_gemma":[0.007153624,0.0024055955,0.75109595,0.0004744467,0.000057487054,0.0002498536,0.02222594,0.06022914,0.0026702452,0.10261958,0.04893985,0.0018782992],"about_ca_topic_score_codex":0.0015309831,"about_ca_topic_score_gemma":0.0011562316,"teacher_disagreement_score":0.7193565,"about_ca_system_score_codex":0.0006479849,"about_ca_system_score_gemma":0.0025908367,"threshold_uncertainty_score":0.99991935},"labels":[],"label_agreement":null},{"id":"W2135146202","doi":"10.1186/1471-2288-12-187","title":"Systematic reviews need to consider applicability to disadvantaged populations: inter-rater agreement for a health equity plausibility algorithm","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; St. Michael's Hospital; University of Toronto; Institute of Population and Public Health; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research; University of Ottawa","keywords":"Confidence interval; Socioeconomic status; Medicine; Systematic review; Disadvantaged; Psychological intervention; Meta-analysis; Kappa; Inter-rater reliability; Population; Credibility; MEDLINE; Demography; Statistics; Environmental health; Mathematics; Psychiatry; Pathology","score_opus":0.9807797522398772,"score_gpt":0.7814288583116233,"score_spread":0.1993508939282539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135146202","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":[0.0047154655,0.0024213349,0.960118,0.012285726,0.0007396916,0.019390393,0.00005486949,0.000012138147,0.00026239603],"genre_scores_gemma":[0.024458164,0.000053881628,0.95737803,0.0060892464,0.0005021812,0.008899698,0.000025163177,0.000027640544,0.0025659744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3448684,0.5956627,0.031375844,0.0036610803,0.021108517,0.003323432],"domain_scores_gemma":[0.32256144,0.63583,0.0070804497,0.018233074,0.0066546025,0.009640427],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.87808,0.0004675564,0.009248682,0.0008495563,0.00046865136,0.00033603632,0.0031782752,0.00028061954,0.0114101665],"category_scores_gemma":[0.9063965,0.00022286714,0.0017628521,0.0025775628,0.00033073162,0.00021160756,0.0019611472,0.0006858711,0.005407482],"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":[0.00030982762,0.001196159,0.025153711,0.035723478,0.00039354802,0.0000039599463,0.007574645,0.000015396958,0.00017633302,0.016509058,0.37773755,0.5352063],"study_design_scores_gemma":[0.0029845193,0.0028140082,0.03477047,0.009099654,0.000690869,0.00015029756,0.019189201,0.024434995,0.00016418347,0.18108791,0.72259367,0.002020213],"about_ca_topic_score_codex":0.0002606422,"about_ca_topic_score_gemma":0.0021684365,"teacher_disagreement_score":0.53318614,"about_ca_system_score_codex":0.0005957016,"about_ca_system_score_gemma":0.0008645108,"threshold_uncertainty_score":0.99536693},"labels":[],"label_agreement":null},{"id":"W2136604958","doi":"10.1186/1471-2288-13-118","title":"Towards a methodology for cluster searching to provide conceptual and contextual “richness” for systematic reviews of complex interventions: case study (CLUSTER)","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":279,"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 Institute for Health and Care Research","keywords":"Context (archaeology); Systematic review; Psychological intervention; Computer science; Data science; Psychology; Intervention (counseling); Management science; MEDLINE","score_opus":0.9784724983140504,"score_gpt":0.8165912940575061,"score_spread":0.1618812042565443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136604958","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":[0.17465371,0.00016217196,0.7644108,0.0105848005,0.0003136554,0.049718592,0.00006410097,0.000032082004,0.00006010099],"genre_scores_gemma":[0.15432788,0.000047766367,0.7607127,0.011563853,0.00044467085,0.07210167,0.000013573206,0.00005754461,0.00073033426],"study_design_codex":"systematic_review","study_design_gemma":"qualitative","domain_scores_codex":[0.7959505,0.19588637,0.0041325563,0.0008707083,0.0013220174,0.001837874],"domain_scores_gemma":[0.43135437,0.56255335,0.0009662858,0.0008083994,0.0027094393,0.0016081304],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29253554,0.00026960525,0.0023452567,0.00090701703,0.0010352005,0.000029382927,0.0008691291,0.00035559016,0.001175314],"category_scores_gemma":[0.7194202,0.00019277525,0.0002359844,0.0007631466,0.0011547355,0.00019793506,0.0012209434,0.0010663806,0.00008645488],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020490922,0.0007818696,0.006887091,0.42599323,0.0003484589,0.000049383718,0.35843992,0.0000066406324,0.0013982046,0.026395623,0.08705821,0.090592295],"study_design_scores_gemma":[0.019177124,0.012204937,0.0026598654,0.014570576,0.00021098397,0.00063236523,0.9009613,0.010009382,0.00006222179,0.010055584,0.02875894,0.0006967523],"about_ca_topic_score_codex":0.0069935136,"about_ca_topic_score_gemma":0.012522847,"teacher_disagreement_score":0.54252136,"about_ca_system_score_codex":0.00025373264,"about_ca_system_score_gemma":0.0030196928,"threshold_uncertainty_score":0.99973774},"labels":[],"label_agreement":null},{"id":"W2139928433","doi":"10.1186/1471-2288-11-135","title":"Study protocol: the empirical investigation of methods to correct for measurement error in biobanks with dietary assessment","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Nutrition, Genetics, and Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Aberdeen; Canadian Institutes of Health Research; University of Leicester","keywords":"Biobank; Compendium; Protocol (science); Nutritional epidemiology; Computer science; Pooling; Population; Data science; Calibration; Harmonization; Management science; Data mining; Epidemiology; Medicine; Environmental health; Bioinformatics; Statistics; Alternative medicine; Biology; Geography; Artificial intelligence; Engineering; Mathematics","score_opus":0.8440482375429057,"score_gpt":0.6383768785587111,"score_spread":0.20567135898419464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139928433","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4445818,0.00019840451,0.4857876,0.0009035896,0.00016398769,0.06800383,0.0000112963135,0.000012050053,0.0003374471],"genre_scores_gemma":[0.21926898,0.000016818036,0.67020524,0.0005246299,0.00021899551,0.10967688,0.000018506238,0.000031921376,0.000038016806],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9831506,0.014409163,0.0004959253,0.0005457849,0.0009409169,0.00045759673],"domain_scores_gemma":[0.9963979,0.001891506,0.000084167674,0.00052582554,0.0007038546,0.00039676277],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034028273,0.00014666418,0.00032368826,0.00016955109,0.00009053155,0.0000077445275,0.00048353468,0.00019148561,0.000060173134],"category_scores_gemma":[0.018330328,0.00009243447,0.00007770828,0.00032990417,0.0005394685,0.0000029686937,0.0002477318,0.0002776609,0.0000010634324],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02200379,0.004680682,0.7303775,0.0011819958,0.00035222794,0.000027216482,0.005421842,0.00002596616,0.15958562,0.0002113673,0.01117267,0.0649591],"study_design_scores_gemma":[0.0085037425,0.02320616,0.7800582,0.00017878167,0.00008388164,0.00001730207,0.008053801,0.00025756875,0.1669154,0.0049058637,0.0073982566,0.00042104928],"about_ca_topic_score_codex":0.00019132225,"about_ca_topic_score_gemma":0.0022529587,"teacher_disagreement_score":0.22531281,"about_ca_system_score_codex":0.000049506743,"about_ca_system_score_gemma":0.0019595998,"threshold_uncertainty_score":0.99467117},"labels":[],"label_agreement":null},{"id":"W2142198188","doi":"10.1186/1471-2288-3-2","title":"Development and evaluation of a quality score for abstracts","year":2003,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Academic Writing and Publishing","field":"Arts and Humanities","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 Calgary","funders":"Deutscher Akademischer Austauschdienst","keywords":"Inter-rater reliability; Reliability (semiconductor); Quality (philosophy); Quality Score; Presentation (obstetrics); Construct validity; Psychology; Medicine; Medical physics; Computer science; Applied psychology; Psychometrics; Clinical psychology; Rating scale; Surgery; Operations management","score_opus":0.8999800917436473,"score_gpt":0.6148170622517605,"score_spread":0.2851630294918869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142198188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9515835,0.0009593551,0.0083358,0.0007945925,0.00024543097,0.0004074327,0.000005481225,0.000017006052,0.037651405],"genre_scores_gemma":[0.8714447,0.000041388117,0.12645103,0.00021852914,0.00053154316,0.00018158263,0.00001632158,0.000014144249,0.0011007593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9878964,0.0092143,0.00055029406,0.0002498374,0.0017006153,0.00038859117],"domain_scores_gemma":[0.96039546,0.03800242,0.00012646297,0.00014025513,0.0010976571,0.00023773877],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17770326,0.00006208407,0.00023615961,0.00013358901,0.00023284751,0.000037565558,0.0001590714,0.00016016114,0.0010974684],"category_scores_gemma":[0.24522394,0.000048942216,0.000030345609,0.000042761607,0.0005876295,0.00008201411,0.000049157425,0.00042229143,0.0000040009104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005663787,0.00004195931,0.00047369135,0.0003591027,0.000018969364,4.7372356e-7,0.016618486,0.0000020142857,0.000109876826,0.83809566,0.0022694375,0.1419537],"study_design_scores_gemma":[0.0024093348,0.00016670884,0.0063962755,0.00030825118,0.000033658456,0.000012128019,0.03664529,0.0006509369,0.003168508,0.18083814,0.7691301,0.00024065467],"about_ca_topic_score_codex":0.00021778118,"about_ca_topic_score_gemma":0.0016098546,"teacher_disagreement_score":0.76686066,"about_ca_system_score_codex":0.000037797618,"about_ca_system_score_gemma":0.0017236725,"threshold_uncertainty_score":0.99981564},"labels":[],"label_agreement":null},{"id":"W2146188179","doi":"10.1186/1471-2288-13-141","title":"Reference management software for systematic reviews and meta-analyses: an exploration of usage and usability","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Systematic review; Computer science; Usability; Software; Software project management; Software review; Software peer review; Software engineering; Software development; MEDLINE; Software construction","score_opus":0.9910376391907982,"score_gpt":0.7508285751187257,"score_spread":0.24020906407207254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146188179","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":[0.0096350685,0.0056372285,0.97543126,0.00072701875,0.00004709871,0.008112264,0.000010253841,0.0000051984744,0.0003946339],"genre_scores_gemma":[0.037108894,0.0011882464,0.9513515,0.00026509358,0.00005095041,0.0061656996,0.000013426064,0.000017014341,0.0038391475],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6285061,0.34608328,0.013208881,0.0019070315,0.009683072,0.0006115913],"domain_scores_gemma":[0.31344846,0.6568038,0.0080795,0.010531168,0.009182218,0.0019548517],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.69771373,0.0002972677,0.00864208,0.00064294244,0.00019122064,0.0003517908,0.0017886447,0.00022555642,0.010149099],"category_scores_gemma":[0.79969823,0.00012018672,0.0009278693,0.0013177694,0.00067102123,0.00074778445,0.0005355751,0.00031308478,0.0002588203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002512608,0.0010039128,0.007512268,0.32963806,0.013566678,0.000019002118,0.0063053058,0.000042501266,0.0010955819,0.15132043,0.051294424,0.43795058],"study_design_scores_gemma":[0.0016336403,0.0017397023,0.008080294,0.0020136226,0.0205159,0.00005761799,0.02051424,0.04001199,0.0002109724,0.87790704,0.026337856,0.0009771427],"about_ca_topic_score_codex":0.00012564613,"about_ca_topic_score_gemma":0.00033356913,"teacher_disagreement_score":0.7265866,"about_ca_system_score_codex":0.000026782533,"about_ca_system_score_gemma":0.00014658913,"threshold_uncertainty_score":0.99075574},"labels":[],"label_agreement":null},{"id":"W2147132115","doi":"10.1186/1471-2288-10-55","title":"A probit- log- skew-normal mixture model for repeated measures data with excess zeros, with application to a cohort study of paediatric respiratory symptoms","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Respiratory viral infections research","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":"St. Joseph’s Healthcare Hamilton; McMaster University; Public Health Ontario; University of Toronto","funders":"Higher Education Commision, Pakistan; University of Toronto","keywords":"Statistics; Medicine; Cohort; Econometrics; Skew; Probit model; Mixture model; Cohort study; Repeated measures design; Probit; Mathematics; Psychology; Computer science","score_opus":0.3788989351555122,"score_gpt":0.5324291654170971,"score_spread":0.15353023026158485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147132115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5576608,0.00009402392,0.43487194,0.00035026218,0.000047359208,0.0067299036,0.000032002627,0.000072347735,0.00014134993],"genre_scores_gemma":[0.8925846,0.00002296143,0.09984335,0.00039289353,0.0005959233,0.005912151,0.000113357375,0.00012645104,0.00040831568],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98563606,0.0060010836,0.0009938593,0.0016527594,0.004511619,0.0012046093],"domain_scores_gemma":[0.9821584,0.009561788,0.00023623511,0.0033717854,0.003296604,0.0013751932],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047311958,0.00034341562,0.0011504057,0.0013199047,0.0003264294,0.000043062293,0.001552978,0.000843246,0.000103536775],"category_scores_gemma":[0.059571452,0.0002254962,0.000072677554,0.0024943566,0.0011295862,0.00020587759,0.00084412994,0.0034491047,0.000017508186],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025758035,0.0049468237,0.7991335,0.0016595442,0.00093308615,0.0001568368,0.0012696184,0.00092353194,0.08672091,0.0009705594,0.007330619,0.07019698],"study_design_scores_gemma":[0.05517943,0.1072843,0.51245046,0.0010022235,0.0018909799,0.0009865026,0.003016824,0.24847299,0.029560523,0.0014489219,0.036048833,0.0026580212],"about_ca_topic_score_codex":0.00069026265,"about_ca_topic_score_gemma":0.008328785,"teacher_disagreement_score":0.3350286,"about_ca_system_score_codex":0.00013277873,"about_ca_system_score_gemma":0.005531933,"threshold_uncertainty_score":0.99885},"labels":[],"label_agreement":null},{"id":"W2147146607","doi":"10.1186/1471-2288-7-21","title":"Copula based prediction models: an application to an aortic regurgitation study","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Hemodynamic Monitoring and Therapy","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":"Western University; University of Northern British Columbia","funders":"","keywords":"Copula (linguistics); Statistics; Pearson product-moment correlation coefficient; Concordance correlation coefficient; Mathematics; Correlation ratio; Confidence interval; Multivariate statistics; Regression; Regression analysis; Correlation coefficient; Replicate; Correlation; Monte Carlo method; Bivariate analysis; Measure (data warehouse); Econometrics; Computer science; Data mining","score_opus":0.560156224468183,"score_gpt":0.6112146205930937,"score_spread":0.0510583961249107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147146607","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":[0.48587748,0.000016963957,0.5124735,0.00031723542,0.0001432083,0.0008731986,0.0000015299606,0.00009401714,0.00020281682],"genre_scores_gemma":[0.88834286,0.000012044672,0.11002785,0.00028157036,0.000790217,0.00027386972,0.00008263802,0.00003635062,0.00015259675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9889871,0.0067400145,0.0005961687,0.00070764375,0.0022630426,0.0007060347],"domain_scores_gemma":[0.99013156,0.006762209,0.00006032711,0.00086586113,0.00062354724,0.0015565174],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05343946,0.0001490243,0.00041201207,0.0006520966,0.00018390284,0.000018972094,0.0002954453,0.0003417427,0.000112941074],"category_scores_gemma":[0.014759506,0.0001277797,0.00005188882,0.0007738214,0.00018603275,0.00013124385,0.00004921223,0.00076787925,0.000031303494],"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":[0.005388678,0.003286029,0.04527063,0.00013164394,0.000058428246,0.000090057954,0.0032754685,0.0010639667,0.015578901,0.0023317907,0.00014464662,0.9233798],"study_design_scores_gemma":[0.0046357126,0.010393567,0.14871548,0.0001272358,0.00005171395,0.000043859796,0.0053262166,0.82215446,0.001971087,0.0054150512,0.00094071706,0.00022492402],"about_ca_topic_score_codex":0.00089744985,"about_ca_topic_score_gemma":0.0008754246,"teacher_disagreement_score":0.92315483,"about_ca_system_score_codex":0.00026351865,"about_ca_system_score_gemma":0.00088243093,"threshold_uncertainty_score":0.9935396},"labels":[],"label_agreement":null},{"id":"W2148112176","doi":"10.1186/1471-2288-10-49","title":"Testing for heterogeneity among the components of a binary composite outcome in a clinical trial","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Logistic regression; Statistics; Outcome (game theory); Generalized estimating equation; Gee; Population; Regression analysis; Regression; Mathematics; Random effects model; Statistical power; Econometrics; Medicine; Meta-analysis; Internal medicine","score_opus":0.8556687575528438,"score_gpt":0.6744447666117647,"score_spread":0.1812239909410791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148112176","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":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59770215,0.000008566532,0.4006213,0.00023928477,0.00044415638,0.00084993313,0.000011594047,0.000013377858,0.00010964768],"genre_scores_gemma":[0.28761157,0.0000021866872,0.7118441,0.00005467107,0.0002734091,0.00018443943,0.0000024251942,0.000015964146,0.000011267975],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9693331,0.026258359,0.0019277849,0.0004998944,0.0012168805,0.0007639975],"domain_scores_gemma":[0.49725658,0.5011182,0.00027416748,0.0005936784,0.00037992722,0.00037748265],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12151432,0.00015685888,0.0010342676,0.00024974992,0.00014633522,0.00001917762,0.0009838854,0.0005010291,0.00014879167],"category_scores_gemma":[0.67887485,0.000096958735,0.0002174585,0.0005709809,0.0024292332,0.000032153213,0.0005038628,0.0022244162,0.000004958957],"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":[0.015396586,0.0014205219,0.561272,0.00073625776,0.000067031746,0.00005704506,0.00017853724,2.759278e-7,0.012475083,0.295,0.00027179622,0.113124855],"study_design_scores_gemma":[0.014410568,0.001461166,0.42981592,0.0001372427,0.000027279924,0.000017078128,0.000060543945,0.010034992,0.0003155588,0.5434755,0.00010290274,0.00014122605],"about_ca_topic_score_codex":0.00030774734,"about_ca_topic_score_gemma":0.0008053974,"teacher_disagreement_score":0.55736053,"about_ca_system_score_codex":0.000020852543,"about_ca_system_score_gemma":0.0004377702,"threshold_uncertainty_score":0.9664106},"labels":[],"label_agreement":null},{"id":"W2148806857","doi":"10.1186/1471-2288-11-52","title":"Cross-cultural adaptation and validation of Behçet's disease quality of life questionnaire","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ocular Diseases and Behçet’s Syndrome","field":"Medicine","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":"University of Toronto","funders":"","keywords":"Quality of life (healthcare); Activities of daily living; Construct validity; Medicine; Cross-sectional study; Arabic; Reliability (semiconductor); Test (biology); Cronbach's alpha; Scale (ratio); Convergent validity; Concurrent validity; Physical therapy; Gerontology; Clinical psychology; Psychology; Psychometrics; Internal consistency","score_opus":0.6789326013967412,"score_gpt":0.5835607957037268,"score_spread":0.0953718056930144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148806857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9754162,0.0015201345,0.021971434,0.00036031188,0.00009681605,0.00032657702,0.000016962595,0.000019595143,0.00027196793],"genre_scores_gemma":[0.97706676,0.0003047221,0.022254866,0.00005213468,0.00009367316,0.000030011865,0.000043818083,0.000011219407,0.0001427787],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99201393,0.0052746306,0.00067004666,0.00032798253,0.0014087426,0.0003046499],"domain_scores_gemma":[0.99371207,0.0035038714,0.00018655183,0.00036201556,0.0011519839,0.0010835131],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012353004,0.000106115,0.00052031456,0.00018829547,0.00006782523,0.000007761156,0.00015125838,0.00020585423,0.0013888263],"category_scores_gemma":[0.12357614,0.00007934054,0.0001380158,0.0002708734,0.0016349402,0.00013201302,0.00013816239,0.00031370748,0.0000071768927],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004806156,0.0007275042,0.9477415,0.0028406011,0.00010770426,0.000042970874,0.0011122004,0.000004064777,0.0031720381,0.012317606,0.000092822826,0.027034799],"study_design_scores_gemma":[0.0016453535,0.00053460547,0.98923403,0.00028055688,0.00006487794,0.000014692548,0.00057817856,0.0005354774,0.0020831486,0.0049026757,0.000044541768,0.00008184184],"about_ca_topic_score_codex":0.0014119246,"about_ca_topic_score_gemma":0.000089305664,"teacher_disagreement_score":0.11122314,"about_ca_system_score_codex":0.000030370471,"about_ca_system_score_gemma":0.0012988787,"threshold_uncertainty_score":0.99952406},"labels":[],"label_agreement":null},{"id":"W2152000087","doi":"10.1186/1471-2288-10-64","title":"The importance of adjusting for potential confounders in Bayesian hierarchical models synthesising evidence from randomised and non-randomised studies: an application comparing treatments for abdominal aortic aneurysms","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Aortic aneurysm repair treatments","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Programs for Assessment of Technology in Health Research Institute; St. Joseph’s Healthcare Hamilton; McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Ontario Ministry of Health and Long-Term Care","keywords":"Confounding; Medicine; Observational study; Odds ratio; Randomized controlled trial; Odds; Covariate; Meta-analysis; Comparative effectiveness research; Statistics; Internal medicine; Logistic regression; Mathematics; Alternative medicine; Pathology","score_opus":0.35821058384204596,"score_gpt":0.5110641304731038,"score_spread":0.15285354663105788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152000087","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5904397,0.0005175767,0.40513295,0.00050906977,0.00008143532,0.0032877123,0.000003966352,0.000015397061,0.000012214595],"genre_scores_gemma":[0.82012373,0.00042057206,0.17730053,0.00004936316,0.00016757677,0.0018671269,0.000017757713,0.000032357108,0.000021001415],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99331915,0.0028508373,0.0012282196,0.0008072128,0.0009997949,0.000794791],"domain_scores_gemma":[0.862178,0.13571765,0.0003635124,0.0006778374,0.0004716263,0.0005913598],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020082979,0.0002516348,0.0012557536,0.00019453865,0.00036920395,0.00002445015,0.00033958463,0.00030626587,0.000012583996],"category_scores_gemma":[0.0863737,0.00016913407,0.00019366964,0.00019576128,0.0016162877,0.00013564777,0.00013663893,0.0006705544,4.944489e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.4368966,0.0014910692,0.17950264,0.0022660596,0.001871302,0.00023303894,0.005706926,0.00032151595,0.15796003,0.0010909259,0.0000771296,0.21258278],"study_design_scores_gemma":[0.0818967,0.0010753771,0.018163525,0.0005210291,0.0006176527,0.00009454648,0.0025374456,0.87753904,0.0025601797,0.014814593,0.0000026732514,0.0001772369],"about_ca_topic_score_codex":0.00040195708,"about_ca_topic_score_gemma":0.0012454347,"teacher_disagreement_score":0.87721753,"about_ca_system_score_codex":0.0001330048,"about_ca_system_score_gemma":0.00092223234,"threshold_uncertainty_score":0.92132217},"labels":[],"label_agreement":null},{"id":"W2153048764","doi":"10.1186/1471-2288-13-24","title":"The effects of capping the alcohol consumption distribution and relative risk functions on the estimated number of deaths attributable to alcohol consumption in the European Union in 2004","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"National Institute on Alcohol Abuse and Alcoholism; Ontario Ministry of Health and Long-Term Care","keywords":"Per capita; Attributable risk; Alcohol; Relative risk; European union; Alcohol consumption; Consumption (sociology); Environmental health; Medicine; Demography; Distribution (mathematics); Population; Chemistry; Confidence interval; Mathematics; Internal medicine; Economics","score_opus":0.3416457408863121,"score_gpt":0.48940356598435525,"score_spread":0.14775782509804314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153048764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.981701,0.00084469136,0.010892116,0.0041984105,0.000098536315,0.0020007554,0.000006567363,0.000012463735,0.00024541336],"genre_scores_gemma":[0.99707025,0.0017080795,0.0005970147,0.00011582254,0.000039152586,0.00028890843,0.000033669585,0.000011263545,0.00013585623],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.969675,0.028363902,0.00046369672,0.0002589969,0.0008029942,0.00043539476],"domain_scores_gemma":[0.9019094,0.09721944,0.00013416915,0.0004236212,0.00020236506,0.00011102245],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032335263,0.00013607045,0.00034902323,0.00011395563,0.0003043169,0.000017187165,0.00023980212,0.00013541336,0.00012938914],"category_scores_gemma":[0.070781246,0.00005598863,0.00006270264,0.0006083194,0.0010107139,0.00006412721,0.00009840596,0.0009275144,0.00010104107],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004445589,0.00016283111,0.9683684,0.00009593661,0.00009951256,0.000018980088,0.002334719,0.000023394672,0.0012637909,0.004121698,0.0015978293,0.021468326],"study_design_scores_gemma":[0.0023646387,0.00027000785,0.9915542,0.0005807584,0.00007224029,0.000028610966,0.0016704858,0.00068911473,0.0009745967,0.0015975095,0.0001431741,0.000054653712],"about_ca_topic_score_codex":0.0009984755,"about_ca_topic_score_gemma":0.0012461591,"teacher_disagreement_score":0.06885554,"about_ca_system_score_codex":0.00013903267,"about_ca_system_score_gemma":0.00013739814,"threshold_uncertainty_score":0.9964145},"labels":[],"label_agreement":null},{"id":"W2153750729","doi":"10.1186/1471-2288-11-48","title":"Estimating uncertainty of alcohol-attributable fractions for infectious and chronic diseases","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Alcohol Consumption and Health Effects","field":"Medicine","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Public Health Ontario; Centre for Addiction and Mental Health","funders":"National Institute on Alcohol Abuse and Alcoholism; Ontario Ministry of Health and Long-Term Care","keywords":"Confidence interval; Statistics; Variance (accounting); Monte Carlo method; Computation; Mathematics; Random effects model; Estimation; Medicine; Meta-analysis; Algorithm; Pathology","score_opus":0.7181675042075331,"score_gpt":0.6089036609105509,"score_spread":0.10926384329698213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153750729","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":[0.3883421,0.0032801877,0.6032861,0.0011448622,0.0005669643,0.001911235,0.00003072491,0.00010457907,0.0013332416],"genre_scores_gemma":[0.79020387,0.0006611348,0.20704123,0.0004677328,0.00064151734,0.00058956275,0.000039675753,0.00003274996,0.0003224943],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9953857,0.0026343476,0.00041541897,0.00033676505,0.0006198632,0.000607905],"domain_scores_gemma":[0.9665325,0.031721596,0.00010699285,0.0002884106,0.000515947,0.00083451194],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010863683,0.00010973769,0.00058791763,0.00030781102,0.00024036346,0.0000051902334,0.000108862034,0.00026528642,0.001383762],"category_scores_gemma":[0.08937842,0.00008788144,0.00009138096,0.00028647613,0.0008358009,0.00004988738,0.00012029364,0.0006148811,0.000019246783],"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":[0.007144834,0.0021721502,0.4315234,0.024225349,0.00063576514,0.00015270666,0.0026007262,0.000087652086,0.008345783,0.05642682,0.011833445,0.45485136],"study_design_scores_gemma":[0.032535125,0.01678831,0.6426804,0.0034336846,0.0008892225,0.0013271725,0.0015130047,0.20315427,0.005854762,0.06295517,0.028003572,0.0008653236],"about_ca_topic_score_codex":0.00083575916,"about_ca_topic_score_gemma":0.00047963375,"teacher_disagreement_score":0.45398602,"about_ca_system_score_codex":0.00014168529,"about_ca_system_score_gemma":0.0025031157,"threshold_uncertainty_score":0.9995291},"labels":[],"label_agreement":null},{"id":"W2154175900","doi":"10.1186/1471-2288-13-109","title":"Beyond case fatality rate: using potential impact fraction to estimate the effect of increasing treatment uptake on mortality","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University Health Network; Sunnybrook Health Science Centre; University of Toronto; Toronto General Hospital; Toronto Public Health","funders":"","keywords":"Case fatality rate; Fraction (chemistry); Medicine; Mortality rate; Demography; Environmental health; Statistics; Emergency medicine; Population; Internal medicine; Mathematics; Chemistry","score_opus":0.6528163280579211,"score_gpt":0.6790984179224019,"score_spread":0.026282089864480773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154175900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6599902,0.00001611647,0.3385017,0.00011259275,0.00006569871,0.0011105121,0.0000103268385,0.00006093162,0.00013192596],"genre_scores_gemma":[0.7770167,0.000010890757,0.2225688,0.000028068165,0.00012094049,0.00020986337,0.000005693447,0.000026766726,0.000012255538],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9670363,0.029922951,0.0006676745,0.000462945,0.0011577298,0.0007524105],"domain_scores_gemma":[0.91136473,0.086581714,0.00021565272,0.0009286679,0.00035190178,0.0005573238],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042977784,0.0002691529,0.0008019207,0.00023798164,0.00026999754,0.00004035945,0.00035392656,0.00032990685,0.00081751234],"category_scores_gemma":[0.16013522,0.00014741419,0.00019281574,0.00041962607,0.00061622576,0.00014649355,0.00027504645,0.0007744949,0.000027614406],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007636567,0.0015332368,0.027560785,0.0017110382,0.001205537,0.0038233013,0.0014935437,0.0019137175,0.3893634,0.03793882,0.0014295976,0.52439046],"study_design_scores_gemma":[0.0024883205,0.0125836395,0.032473136,0.0005137389,0.00034996722,0.003260406,0.0007679777,0.041691776,0.31696913,0.58821845,0.000050914656,0.00063255633],"about_ca_topic_score_codex":0.015306306,"about_ca_topic_score_gemma":0.00070017995,"teacher_disagreement_score":0.5502796,"about_ca_system_score_codex":0.00056403305,"about_ca_system_score_gemma":0.0004586217,"threshold_uncertainty_score":0.9912509},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2154701217","doi":"10.1186/1471-2288-14-15","title":"An overview of the statistical methods reported by studies using the Canadian community health survey","year":2014,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social 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":true,"ca_institutions":"University of Calgary","funders":"","keywords":"MEDLINE; Data science; Medicine; Environmental health; Computer science; Political science","score_opus":0.9840356380549445,"score_gpt":0.8183119414876181,"score_spread":0.16572369656732644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154701217","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":[0.00006210802,0.9420886,0.054070313,0.0006397974,0.0013100596,0.0013757874,0.0002985525,0.000022217275,0.0001325496],"genre_scores_gemma":[0.000011916015,0.91730607,0.08146357,0.0005582194,0.00022816958,0.00009329499,0.00011115214,0.000047201673,0.00018042931],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.06873687,0.92424434,0.0020330036,0.0006941848,0.0025554446,0.0017361519],"domain_scores_gemma":[0.1425823,0.85098255,0.0011253697,0.0023841956,0.0013024379,0.0016231886],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","sts","research_integrity"],"category_scores_codex":[0.9094546,0.0004321426,0.004486665,0.00044507842,0.005384626,0.000053647942,0.004372263,0.0017106013,0.00059544307],"category_scores_gemma":[0.9202586,0.00022789255,0.0004574935,0.0025587813,0.015287737,0.000054120985,0.00084146386,0.0070413,0.0000066811167],"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":[0.00021155574,0.00011494462,0.00050132134,0.005086293,0.00054279785,0.000010276254,0.0039963345,4.0006475e-7,4.616118e-7,0.010771252,0.009796966,0.9689674],"study_design_scores_gemma":[0.00015894938,0.0002445684,0.003344897,0.0030169706,0.00022197871,0.000038670605,0.0030620832,0.000023289162,0.0000010249314,0.0062334333,0.9833664,0.00028775423],"about_ca_topic_score_codex":0.9094087,"about_ca_topic_score_gemma":0.99035054,"teacher_disagreement_score":0.9735694,"about_ca_system_score_codex":0.0011657563,"about_ca_system_score_gemma":0.062290072,"threshold_uncertainty_score":0.9995854},"labels":[],"label_agreement":null},{"id":"W2154893715","doi":"10.1186/1471-2288-15-11","title":"Determine the therapeutic role of radiotherapy in administrative data: a data mining approach","year":2015,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","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":"Queen's University","funders":"Cancer Care Ontario","keywords":"Medicine; Audit; Decision tree; Population; Radiation therapy; Classifier (UML); Medical record; Medical physics; Family medicine; Data mining; Computer science; Artificial intelligence; Surgery; Environmental health","score_opus":0.7608941371846628,"score_gpt":0.6023576568770039,"score_spread":0.15853648030765888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154893715","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010815829,0.003921165,0.9817446,0.00047964536,0.00005903014,0.00057975,0.000069887064,0.000024427429,0.00230567],"genre_scores_gemma":[0.12289455,0.0001990658,0.8757975,0.00010774046,0.00053794065,0.00013385745,0.0001753332,0.000037141996,0.00011687112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9875846,0.009719523,0.00048519953,0.00064034876,0.001012479,0.0005578473],"domain_scores_gemma":[0.97926086,0.018018588,0.00013627211,0.002198257,0.00013505282,0.0002509894],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028985823,0.00016213849,0.0005319715,0.00016696638,0.0000637948,0.000019323465,0.0034897167,0.00013827278,0.00028123896],"category_scores_gemma":[0.005151762,0.000104363484,0.000036927584,0.0005226434,0.0011364832,0.00020097058,0.0008632409,0.00083094666,0.0000010388167],"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":[0.00076349033,0.00059075304,0.039446376,0.000043979653,0.00022929462,0.000011660943,0.0041929055,0.000021636479,0.003743774,0.018402232,0.0019844892,0.9305694],"study_design_scores_gemma":[0.009271195,0.0027753736,0.0047723725,0.00031250608,0.000074826065,0.00011921995,0.045627467,0.62553096,0.011256823,0.097786665,0.20134132,0.0011312896],"about_ca_topic_score_codex":0.00062264124,"about_ca_topic_score_gemma":0.00015341083,"teacher_disagreement_score":0.9294381,"about_ca_system_score_codex":0.00004737764,"about_ca_system_score_gemma":0.0017487401,"threshold_uncertainty_score":0.99986345},"labels":[],"label_agreement":null},{"id":"W2155454561","doi":"10.1186/1471-2288-11-46","title":"The care unit in nursing home research: Evidence in support of a definition","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Geriatric Care and Nursing Homes","field":"Health Professions","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Calgary; University of Saskatchewan; University of Alberta","funders":"Canadian Institutes of Health Research; Saskatchewan Health Research Foundation","keywords":"Unit (ring theory); Context (archaeology); Debriefing; Health care; Nursing; Nursing Minimum Data Set; Data collection; Session (web analytics); Observational study; Medicine; Psychology; Nursing research; Medical education; Team nursing; Nursing Outcomes Classification; Computer science; Sociology; Geography","score_opus":0.93312266897277,"score_gpt":0.7113386012446162,"score_spread":0.22178406772815373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155454561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9450074,0.00762367,0.002158958,0.005929362,0.0015029276,0.0017940667,0.000008674583,0.00003937007,0.03593559],"genre_scores_gemma":[0.98022777,0.0041187196,0.0144237075,0.000092067035,0.00026633876,0.0004228697,0.000010897081,0.000030190613,0.0004074278],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91180235,0.082702786,0.001036215,0.00045522486,0.002251896,0.0017515266],"domain_scores_gemma":[0.83010095,0.16763712,0.000117048534,0.00061561464,0.0011583782,0.00037084424],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11424125,0.0001110395,0.0004898794,0.0011778153,0.00054827845,0.000005902996,0.0008567677,0.0006051696,0.0013710211],"category_scores_gemma":[0.17167321,0.00007879722,0.000067063644,0.0021932027,0.0019714157,0.00008522367,0.00034354263,0.0038454987,0.0001365658],"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":[0.0069866986,0.00048394225,0.3824853,0.00204688,0.000018168526,0.00033457624,0.26260662,6.268695e-7,0.0006035678,0.09772084,0.019212293,0.22750048],"study_design_scores_gemma":[0.0020295477,0.0014516923,0.5637533,0.004727454,0.000009746619,0.000017228154,0.25712645,0.000027092907,0.0003043013,0.16598849,0.004379145,0.00018553548],"about_ca_topic_score_codex":0.00848775,"about_ca_topic_score_gemma":0.028571287,"teacher_disagreement_score":0.22731495,"about_ca_system_score_codex":0.0003512805,"about_ca_system_score_gemma":0.0057870126,"threshold_uncertainty_score":0.99984926},"labels":[],"label_agreement":null},{"id":"W2155802102","doi":"10.1186/1471-2288-12-170","title":"30-day in-hospital mortality after acute myocardial infarction in Tuscany (Italy): An observational study using hospital discharge data","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Acute Myocardial Infarction Research","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Medicine; Myocardial infarction; Emergency medicine; Logistic regression; Mortality rate; Observational study; Population; Hospital discharge; Internal medicine","score_opus":0.6558080718035887,"score_gpt":0.5890341660583046,"score_spread":0.06677390574528408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155802102","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9852674,0.00034031054,0.0058711553,0.003914202,0.0014282024,0.0027528224,0.00011398283,0.000060089988,0.00025182133],"genre_scores_gemma":[0.98449767,0.0001868791,0.010875478,0.0007007228,0.0025385031,0.00058603217,0.00044734377,0.00008026017,0.000087126515],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9696164,0.020165838,0.0013429492,0.0013983283,0.0052057686,0.0022706937],"domain_scores_gemma":[0.987113,0.008169136,0.00014279959,0.0021352426,0.00063757633,0.0018022179],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.068502575,0.00039302363,0.0012382155,0.001208796,0.00018433861,0.0000672374,0.0011456009,0.0007115278,0.0022456245],"category_scores_gemma":[0.050980635,0.0003443818,0.0002121171,0.0018697659,0.0011321421,0.0013773831,0.0022539655,0.0032873114,0.00015330064],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070584955,0.003660078,0.98726034,0.00006491653,0.00050269085,0.00036522062,0.00219909,0.000005553633,0.00040065908,0.00023367396,0.0012239842,0.0033779338],"study_design_scores_gemma":[0.0031507858,0.00150372,0.9855572,0.00007574626,0.0001254326,0.000046257162,0.002732045,0.004242107,0.000029709641,0.00025115494,0.00196268,0.00032314222],"about_ca_topic_score_codex":0.0046491725,"about_ca_topic_score_gemma":0.0010127963,"teacher_disagreement_score":0.01752194,"about_ca_system_score_codex":0.00080694037,"about_ca_system_score_gemma":0.002775589,"threshold_uncertainty_score":0.9999008},"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":"W2156298041","doi":"10.1186/1471-2288-11-104","title":"A review of equity issues in quantitative studies on health inequalities: the case of asthma in adults","year":2011,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Asthma and respiratory diseases","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":"Kwantlen Polytechnic University; University of Ottawa; Institute of Population and Public Health","funders":"Institute of Population and Public Health; Canadian Institutes of Health Research; Government of Ontario; Canadian Health Services Research Foundation","keywords":"Asthma; Equity (law); Inequality; Health equity; Medicine; Actuarial science; Psychology; Public health; Political science; Economics; Immunology; Mathematics; Pathology","score_opus":0.8482855615316639,"score_gpt":0.7131428146077085,"score_spread":0.13514274692395545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156298041","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":[0.0001925522,0.99576974,0.00006533374,0.0008369575,0.0001409464,0.0026993544,0.00006369134,0.000008389892,0.00022302207],"genre_scores_gemma":[0.000014725266,0.9956356,0.0028346318,0.00077950803,0.00012068634,0.00049124955,0.000021684442,0.000034704168,0.000067194516],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.91173285,0.08207294,0.0032747425,0.0007108741,0.001359529,0.00084907067],"domain_scores_gemma":[0.8607155,0.13476925,0.0013914629,0.0013454511,0.0010534734,0.00072487677],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.090114854,0.0003720074,0.0063341646,0.0010365692,0.000057310674,0.0000019934141,0.0006087389,0.00046502025,0.00035326023],"category_scores_gemma":[0.33636,0.0001911913,0.0005291622,0.0015059861,0.002525404,0.00002654998,0.000717523,0.0021889035,0.000018685607],"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":[0.00036967243,0.00029638218,0.000014083499,0.43896297,0.000082047816,0.00082695746,0.0018449138,3.0645694e-8,1.99338e-8,0.006464809,0.0012308663,0.54990727],"study_design_scores_gemma":[0.00079108885,0.0036042717,0.00002497129,0.6994661,0.00007737713,0.00033577488,0.008360917,0.0000034222792,0.0000010414599,0.0008172005,0.28638178,0.00013604289],"about_ca_topic_score_codex":0.0032161903,"about_ca_topic_score_gemma":0.0061700875,"teacher_disagreement_score":0.5497712,"about_ca_system_score_codex":0.00027255467,"about_ca_system_score_gemma":0.009119365,"threshold_uncertainty_score":0.996498},"labels":[],"label_agreement":null},{"id":"W2156618128","doi":"10.1186/1471-2288-13-154","title":"Facilitating accrual to cancer control and supportive care trials: the clinical research associate perspective","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hospital for Sick Children; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research","keywords":"Accrual; Reimbursement; Cog; Clinical trial; Medicine; Perspective (graphical); Control (management); Family medicine; Institutional review board; Accounting; Health care; Business; Political science; Internal medicine; Management; Surgery; Computer science; Economics","score_opus":0.9677599381163642,"score_gpt":0.8217371519205594,"score_spread":0.14602278619580478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156618128","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":[0.6710157,0.010757131,0.014597544,0.28171444,0.0010994559,0.01131442,0.00014044826,0.00012497333,0.009235934],"genre_scores_gemma":[0.9284441,0.0064679915,0.03937861,0.0072960593,0.0044478555,0.0052021,0.000014817917,0.00012963875,0.008618828],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7093254,0.2661095,0.003556371,0.0025301694,0.0146637615,0.0038148034],"domain_scores_gemma":[0.016500741,0.96006453,0.00027310092,0.0013701494,0.018170185,0.0036212802],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5748997,0.0003171596,0.0023496612,0.000701521,0.0009532663,0.00017213977,0.0014581478,0.0020039189,0.0047751376],"category_scores_gemma":[0.97720844,0.00018833872,0.0004916175,0.0015628666,0.008078045,0.00011590228,0.001929792,0.019596461,0.0007587371],"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":[0.009699896,0.0009065189,0.1317661,0.0016046399,0.0018398872,0.00045595388,0.056531493,0.000005179227,0.0021515216,0.07090662,0.075258,0.6488742],"study_design_scores_gemma":[0.01576499,0.011174898,0.20704901,0.001775256,0.00023780059,0.00007700379,0.51514363,0.0014594028,0.00049871765,0.23261404,0.013553689,0.0006515536],"about_ca_topic_score_codex":0.013074599,"about_ca_topic_score_gemma":0.011391504,"teacher_disagreement_score":0.69395506,"about_ca_system_score_codex":0.0010029012,"about_ca_system_score_gemma":0.015550375,"threshold_uncertainty_score":0.9992917},"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":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2156741466","doi":"10.1186/1471-2288-10-22","title":"The COSMIN checklist for evaluating the methodological quality of studies on measurement properties: A clarification of its content","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":1844,"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":"Vrije Universiteit Amsterdam","keywords":"Checklist; Delphi method; Content validity; Relevance (law); Construct validity; Psychology; Quality (philosophy); Criterion validity; Delphi; Applied psychology; Formative assessment; Management science; Computer science; Psychometrics; Clinical psychology; Cognitive psychology; Engineering; Artificial intelligence","score_opus":0.9906184913252002,"score_gpt":0.7661254438681674,"score_spread":0.2244930474570328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156741466","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":[0.7289357,0.0075123855,0.14781047,0.09889955,0.0018557246,0.011848686,0.000016340757,0.000118847216,0.003002283],"genre_scores_gemma":[0.9127864,0.0011588726,0.08253819,0.00014068522,0.0003113193,0.0024818187,7.9823013e-7,0.000016918128,0.0005649896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.7449377,0.23428601,0.0026803399,0.0009599031,0.015427892,0.0017081021],"domain_scores_gemma":[0.45561075,0.5265525,0.000948579,0.0015108506,0.014880665,0.0004966722],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.66512215,0.00013044308,0.00063303614,0.00014200255,0.0012041789,0.00003392896,0.0020246725,0.00044509085,0.00006287645],"category_scores_gemma":[0.9190369,0.0000620433,0.00020009339,0.00060247676,0.008473732,0.000043036132,0.0004081533,0.0017455668,0.0000046522878],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002485144,0.0002678237,0.00030403072,0.0006604718,0.00011688153,6.53098e-7,0.008258435,0.000004279612,0.3803614,0.5084951,0.0011123213,0.09793344],"study_design_scores_gemma":[0.0029454196,0.0066910046,0.010401421,0.0011801899,0.00008348981,0.0000052796777,0.2185767,0.0034856112,0.5130468,0.22344346,0.019615289,0.00052530045],"about_ca_topic_score_codex":0.0012463178,"about_ca_topic_score_gemma":0.009481233,"teacher_disagreement_score":0.2922665,"about_ca_system_score_codex":0.00020667777,"about_ca_system_score_gemma":0.0033812686,"threshold_uncertainty_score":0.9942246},"labels":[],"label_agreement":null},{"id":"W2157473400","doi":"10.1186/1471-2288-12-116","title":"Melanocortin-1 receptor, skin cancer and phenotypic characteristics (M-SKIP) project: study design and methods for pooling results of genetic epidemiological studies","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Regulation of Appetite and Obesity","field":"Neuroscience","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Brookhaven National Laboratory; BC Cancer Agency; Cancer Council NSW; University of California, Irvine; National Institutes of Health; Deutsches Krebsforschungszentrum; Pomorski Uniwersytet Medyczny W Szczecinie; Perelman School of Medicine, University of Pennsylvania; Universiteit Leiden; Università degli Studi dell'Aquila; Karolinska Institutet; National and Kapodistrian University of Athens; Universidad de Murcia; University of Leeds; INCLIVA Instituto de Investigación Sanitaria; Memorial Sloan-Kettering Cancer Center; Università degli Studi di Genova; Purdue University; Cancer Research UK; University of Sydney; University of Tasmania; National Cancer Institute; Menzies Institute for Medical Research; Leids Universitair Medisch Centrum; Missouri Department of Health and Senior Services; Cancer Care Ontario; University of Ottawa; University of Pennsylvania; University of North Carolina at Chapel Hill; Brigham and Women's Hospital; State of New Jersey Department of Health","keywords":"Pooling; Epidemiology; Logistic regression; Disease; Computer science; Medicine; Machine learning; Pathology; Artificial intelligence","score_opus":0.6778283784123487,"score_gpt":0.6075584964660946,"score_spread":0.07026988194625405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157473400","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":[0.656749,0.0029962033,0.3377377,0.0004819694,0.0003427074,0.0016372878,0.00001237516,0.000022006585,0.000020714022],"genre_scores_gemma":[0.21751148,0.006529156,0.7746228,0.00018404456,0.00046245434,0.000460732,0.0000020921198,0.000021555868,0.00020570714],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95890325,0.037709136,0.0010416288,0.0007519718,0.0006986443,0.00089537713],"domain_scores_gemma":[0.83094597,0.16777095,0.00029830635,0.0003017588,0.00030193615,0.00038107298],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06866436,0.00019540272,0.0009506663,0.00024297141,0.00027273936,0.0000149265625,0.00032146022,0.00026707386,0.000038402482],"category_scores_gemma":[0.37784773,0.00013532267,0.000059594466,0.0003633979,0.0013939328,0.00007870437,0.0004836821,0.00048550926,0.0000022642976],"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":[0.0063264086,0.00093461544,0.080487825,0.0009026041,0.00014858462,0.000010412816,0.010443062,0.00001989921,0.096919104,0.0049361703,0.0014429265,0.79742837],"study_design_scores_gemma":[0.010847113,0.008756423,0.6582046,0.0005849108,0.00029735177,0.00012861768,0.008175976,0.020169849,0.24507548,0.024313832,0.022251518,0.0011943227],"about_ca_topic_score_codex":0.000105772364,"about_ca_topic_score_gemma":0.000024992485,"teacher_disagreement_score":0.7962341,"about_ca_system_score_codex":0.000044547025,"about_ca_system_score_gemma":0.00032815762,"threshold_uncertainty_score":0.959006},"labels":[],"label_agreement":null},{"id":"W2158075303","doi":"10.1186/1471-2288-12-20","title":"Using a single question to assess physical activity in older adults: a reliability and validity study","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Physical Activity and Health","field":"Medicine","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":"Robarts Clinical Trials; Western University; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Ontario Ministry of Research and Innovation; Ontario Neurotrauma Foundation; Health Canada; U.S. Department of Veterans Affairs","keywords":"Discriminant validity; Physical activity; Psychology; Convergent validity; Reliability (semiconductor); Test (biology); Criterion validity; Sample (material); Relative risk; Correlation; Clinical psychology; Physical therapy; Medicine; Statistics; Psychometrics; Confidence interval; Construct validity; Mathematics; Internal consistency","score_opus":0.8199303559571518,"score_gpt":0.6541801377200305,"score_spread":0.16575021823712133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158075303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9508437,0.000030398369,0.04612299,0.0012633749,0.00012188232,0.001457051,0.000002661647,0.00003491684,0.00012302413],"genre_scores_gemma":[0.97777647,0.000012508367,0.021229086,0.00012983222,0.0006994169,0.00011697108,0.0000016375847,0.00001749112,0.000016563374],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9733389,0.023234894,0.0002759425,0.0006046547,0.001527701,0.0010178922],"domain_scores_gemma":[0.970196,0.02761743,0.000052948,0.00043213106,0.0002303529,0.0014711285],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034389745,0.00016557793,0.00090601516,0.0002685733,0.00012998954,0.000012917892,0.00014480419,0.00025925637,0.00006441894],"category_scores_gemma":[0.09410056,0.00013141967,0.000067227455,0.00072623865,0.0004196818,0.00022008517,0.00039916197,0.0017077546,0.000013932364],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009791853,0.08163407,0.7132968,0.0021556658,0.00004297318,0.00010038922,0.010940191,0.000006903954,0.030116064,0.0012276969,0.00011671598,0.15057069],"study_design_scores_gemma":[0.002718283,0.0034177927,0.98177344,0.00043780208,0.00003155353,0.00004095965,0.001289269,0.005414546,0.0034133233,0.0012283206,0.00007201783,0.00016267889],"about_ca_topic_score_codex":0.0032659525,"about_ca_topic_score_gemma":0.00094302784,"teacher_disagreement_score":0.26847667,"about_ca_system_score_codex":0.0004465085,"about_ca_system_score_gemma":0.0008192942,"threshold_uncertainty_score":0.99429893},"labels":[],"label_agreement":null},{"id":"W2158927222","doi":"10.1186/1471-2288-11-11","title":"A multidisciplinary systematic review of the use of diagrams as a means of collecting data from research subjects: application, benefits and recommendations","year":2011,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":81,"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; Cancer Care Ontario","funders":"Canadian Institutes of Health Research","keywords":"Multidisciplinary approach; Data science; MEDLINE; Computer science; Medicine; Management science; Psychology; Engineering; Sociology","score_opus":0.8778009256423671,"score_gpt":0.6352939642163241,"score_spread":0.242506961426043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158927222","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.2050254e-7,0.7499209,0.24736191,0.00026556596,0.000056357832,0.0020463162,0.00023187866,0.000011785335,0.000104864244],"genre_scores_gemma":[9.2715754e-7,0.89207363,0.10718274,0.000034217872,0.000027174376,0.0002216424,0.00021094728,0.000026958987,0.00022174325],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9441481,0.05035777,0.0021467626,0.0008785882,0.0020363706,0.0004323668],"domain_scores_gemma":[0.83884907,0.15204906,0.0016086211,0.0053369915,0.0017642006,0.00039206148],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062946066,0.00021088606,0.0024596632,0.00063513935,0.00018728108,0.00003427524,0.0058016377,0.00034540668,0.00017525838],"category_scores_gemma":[0.30409372,0.00013080485,0.00018244512,0.0038335146,0.0010545829,0.00017082145,0.0075042266,0.0009312625,0.000017664406],"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":[0.0000048673137,0.0002001343,0.000020532383,0.7350497,0.00018536739,0.0000014278943,0.00030098163,1.6945013e-7,6.5025046e-7,0.04443931,0.0037306293,0.21606624],"study_design_scores_gemma":[0.000212699,0.00013845915,0.000007155001,0.82451093,0.00042534946,0.000033140623,0.00016864778,0.008428734,0.000007189541,0.0015082686,0.16436984,0.00018956595],"about_ca_topic_score_codex":0.0011811752,"about_ca_topic_score_gemma":0.001106841,"teacher_disagreement_score":0.24114765,"about_ca_system_score_codex":0.000041887088,"about_ca_system_score_gemma":0.0030247737,"threshold_uncertainty_score":0.99957746},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2161104930","doi":"10.1186/1471-2288-10-102","title":"Reliability of anthropometric measures in a longitudinal cohort of patients initiating ART in West Africa","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV-related health complications and treatments","field":"Medicine","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":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"Canadian Institutes of Health Research","keywords":"Anthropometry; Waist; Circumference; Medicine; Cohort; Reliability (semiconductor); Prospective cohort study; Cohort study; Statistics; Population; Demography; Body mass index; Physical therapy; Mathematics; Surgery; Environmental health; Internal medicine","score_opus":0.3955747919556945,"score_gpt":0.5429056309610131,"score_spread":0.14733083900531857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161104930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99276286,0.00018023653,0.0018085341,0.0004273371,0.00010549215,0.00084292947,0.000010507835,0.000009476513,0.003852635],"genre_scores_gemma":[0.96356076,0.00022625708,0.035966754,0.000013086303,0.000028741148,0.00012708726,0.000024195362,0.000012231673,0.0000409032],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9921836,0.0041879555,0.0010836059,0.00043480418,0.0015419428,0.0005680483],"domain_scores_gemma":[0.97066504,0.026871584,0.00020477841,0.00067082245,0.0011087151,0.00047903825],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024376031,0.000113499336,0.0007846032,0.0014924083,0.000053070664,0.0000021148853,0.00023708784,0.0003965831,0.0009246951],"category_scores_gemma":[0.2053545,0.00008933983,0.000071332484,0.002615839,0.0009803994,0.000041397074,0.00015197844,0.0016180783,0.00003263771],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004004598,0.0021204217,0.9854085,0.00034637272,0.000017127633,0.000027789634,0.000262773,0.0000012687303,0.0002639091,0.000473864,0.000113096234,0.010564437],"study_design_scores_gemma":[0.002250561,0.00085612084,0.99470603,0.00023877468,0.000014431604,0.000010113268,0.000096821495,0.00031291548,0.00020769812,0.0009486854,0.0003066261,0.00005124657],"about_ca_topic_score_codex":0.0015612486,"about_ca_topic_score_gemma":0.0025493733,"teacher_disagreement_score":0.18097846,"about_ca_system_score_codex":0.00013874468,"about_ca_system_score_gemma":0.0016104376,"threshold_uncertainty_score":0.9999886},"labels":[],"label_agreement":null},{"id":"W2161467505","doi":"10.1186/1471-2288-11-120","title":"Potential risk factors associated with human encephalitis: application of canonical correlation analysis","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Mosquito-borne diseases and control","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Public Health Ontario; University of Toronto","funders":"","keywords":"Canonical correlation; Medicine; Correlation; Encephalitis; Environmental health; Statistics; Virology; Mathematics","score_opus":0.3249111744307694,"score_gpt":0.48732753807863166,"score_spread":0.16241636364786227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161467505","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.628522,0.0001358942,0.3703419,0.000048000093,0.00002946075,0.00034045396,0.00002198605,0.00002599758,0.00053433626],"genre_scores_gemma":[0.9959357,0.000043049942,0.0033698482,0.000035257835,0.00009378437,0.00009562656,0.00023611712,0.000016833315,0.00017381347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98976564,0.006934492,0.00056069036,0.00047884972,0.0017459246,0.0005144126],"domain_scores_gemma":[0.99168134,0.006193998,0.00026439014,0.00050659006,0.00068229117,0.00067138806],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009973566,0.00013951691,0.00076311646,0.00045571406,0.0001444334,0.000006043983,0.00027731218,0.00038597363,0.0023850345],"category_scores_gemma":[0.02768452,0.000098605546,0.0002696267,0.0011385637,0.0007720934,0.000040506788,0.00008830146,0.0007360939,0.000007745931],"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":[0.0011597668,0.0006417614,0.98104775,0.00005688806,0.0013969033,0.00003942885,0.00041125316,0.000039533785,0.0010122308,0.004472225,0.00006913559,0.009653135],"study_design_scores_gemma":[0.001863869,0.0009442993,0.9789194,0.000042928506,0.0016800339,0.000003926987,0.0005545916,0.01450142,0.00034495126,0.0010144735,0.0000344797,0.00009563728],"about_ca_topic_score_codex":0.008675752,"about_ca_topic_score_gemma":0.0043077446,"teacher_disagreement_score":0.3674137,"about_ca_system_score_codex":0.00009423373,"about_ca_system_score_gemma":0.0009892136,"threshold_uncertainty_score":0.99852693},"labels":[],"label_agreement":null},{"id":"W2163281668","doi":"10.1186/s12874-015-0037-7","title":"Development, inter-rater reliability and feasibility of a checklist to assess implementation (Ch-IMP) in systematic reviews: the case of provider-based prevention and treatment programs targeting children and youth","year":2015,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"University of South Australia","keywords":"Checklist; Inter-rater reliability; Psychological intervention; Kappa; Systematic review; Medicine; Reliability (semiconductor); CLARITY; Cohen's kappa; MEDLINE; Family medicine; Psychology; Computer science; Psychiatry; Rating scale","score_opus":0.9381736434202586,"score_gpt":0.7627407484559746,"score_spread":0.17543289496428394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163281668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9759602,0.00018293354,0.01217917,0.0015126935,0.000043988606,0.010083239,0.000018808687,0.000008273678,0.000010727122],"genre_scores_gemma":[0.9126764,0.000058023717,0.08508783,0.0002558752,0.000028945442,0.0018438408,0.000022046526,0.000008916636,0.000018109467],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93338674,0.0626783,0.002179287,0.0005015735,0.0006404699,0.0006136516],"domain_scores_gemma":[0.9777457,0.020370625,0.00052153703,0.00033445703,0.00047941058,0.0005482344],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15693544,0.00013350409,0.00073355605,0.00022485488,0.0002356955,0.000013035491,0.00016689947,0.0001309695,0.00003421218],"category_scores_gemma":[0.12591124,0.00007856226,0.000025934074,0.00049839506,0.0004983695,0.00009835675,0.0002988187,0.0003553083,0.0000015594508],"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":[0.00027799833,0.00016369834,0.83614546,0.01905153,0.000016266282,0.0000044229705,0.08644249,4.6195154e-7,0.00011464829,0.00016592805,0.00008895238,0.05752813],"study_design_scores_gemma":[0.01389157,0.0047782105,0.5644988,0.012102264,0.0001241706,0.000101190206,0.399252,0.0012379452,0.001002233,0.0019943549,0.00054649095,0.00047077783],"about_ca_topic_score_codex":0.009350934,"about_ca_topic_score_gemma":0.039808158,"teacher_disagreement_score":0.3128095,"about_ca_system_score_codex":0.0003823765,"about_ca_system_score_gemma":0.0035762028,"threshold_uncertainty_score":0.9972459},"labels":[],"label_agreement":null},{"id":"W2166006618","doi":"10.1186/1471-2288-8-57","title":"Sampling 'hard-to-reach' populations in health research: yield from a study targeting Americans living in Canada","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; St. Michael's Hospital; University of Calgary","funders":"Fondation pour la Recherche Médicale; Max Bell Foundation; Government of Canada; Canadian Institute for Advanced Research","keywords":"Newspaper; Population; Sample (material); Descriptive statistics; Sample size determination; News media; Psychology; Medicine; Public relations; Sociology; Political science; Media studies; Statistics; Environmental health","score_opus":0.963350536016819,"score_gpt":0.6941101253945071,"score_spread":0.26924041062231185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166006618","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":[0.96392745,0.0005506023,0.026145665,0.007387767,0.00054581475,0.0010477846,0.000010580529,0.000030834773,0.00035350642],"genre_scores_gemma":[0.8660635,0.0003024517,0.13203757,0.000674038,0.00040451958,0.00024335166,0.0000066918496,0.000025170164,0.00024271391],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.27255517,0.71517146,0.0016663999,0.0014080817,0.005575376,0.0036235303],"domain_scores_gemma":[0.2979328,0.69944197,0.00012948095,0.0005341466,0.00043149994,0.0015300983],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5546083,0.00017963008,0.00092807994,0.0014444895,0.0015395569,0.000022672517,0.001213724,0.00031165915,0.0015262553],"category_scores_gemma":[0.88740295,0.00017473563,0.00006109891,0.0044605085,0.0013252215,0.00009800743,0.00058498245,0.0034718106,0.000030565818],"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":[0.0008774057,0.00024990158,0.9311587,0.000013081697,0.000012841115,0.00025468387,0.05553443,0.00012545557,0.00007590842,0.00036141,0.0016896799,0.009646492],"study_design_scores_gemma":[0.00028069058,0.00021212823,0.8860607,0.00016836498,0.0000011409729,0.000002375823,0.10981407,0.00014662262,0.0000054121297,0.0011920759,0.0019775417,0.00013884081],"about_ca_topic_score_codex":0.99765396,"about_ca_topic_score_gemma":0.99945563,"teacher_disagreement_score":0.33279467,"about_ca_system_score_codex":0.0021777675,"about_ca_system_score_gemma":0.03728485,"threshold_uncertainty_score":0.9997603},"labels":[],"label_agreement":null},{"id":"W2166025830","doi":"10.1186/1471-2288-14-45","title":"Newcastle-Ottawa Scale: comparing reviewers’ to authors’ assessments","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2472,"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; University of Toronto","funders":"Hamilton Health Sciences Foundation; McMaster University; Hamilton Health Sciences","keywords":"Interquartile range; Confidence interval; Medicine; Observational study; Systematic review; MEDLINE; Reliability (semiconductor); Cohort study; Family medicine; Internal medicine","score_opus":0.984244127367729,"score_gpt":0.7712171098175411,"score_spread":0.21302701755018794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166025830","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":[0.02990034,0.0006254403,0.9165124,0.005103908,0.0013102998,0.0011207415,0.0000026609655,0.000015836262,0.04540832],"genre_scores_gemma":[0.10361075,0.000120022014,0.8489254,0.0027462996,0.001094203,0.00031507108,0.000010459392,0.00004577285,0.043132],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.2896103,0.64384764,0.01675395,0.0035956455,0.0439964,0.0021960533],"domain_scores_gemma":[0.2656914,0.69597435,0.0047714133,0.016661502,0.009566881,0.007334445],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.84876585,0.00038971953,0.0067337607,0.0013821581,0.00039450827,0.0006685706,0.006748289,0.00042451985,0.049040753],"category_scores_gemma":[0.89860874,0.00019718705,0.0014655659,0.0042847465,0.0004945977,0.0001624495,0.0016438166,0.0014361974,0.02191382],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003392752,0.00008682355,0.05671593,0.00021036936,0.000091967886,0.000013050619,0.00030402275,0.000028569864,0.00013745812,0.015507367,0.5285709,0.3982996],"study_design_scores_gemma":[0.00034621012,0.00023858644,0.022224704,0.00021811141,0.000057947807,0.00003920779,0.00050783454,0.02558428,0.00003401432,0.017656673,0.93286425,0.0002281973],"about_ca_topic_score_codex":0.00014195437,"about_ca_topic_score_gemma":0.0012113767,"teacher_disagreement_score":0.40429333,"about_ca_system_score_codex":0.000109089444,"about_ca_system_score_gemma":0.00078365114,"threshold_uncertainty_score":0.9986257},"labels":[],"label_agreement":null},{"id":"W2166290337","doi":"10.1186/1471-2288-3-18","title":"How does correlation structure differ between real and fabricated data-sets?","year":2003,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Reliability and Agreement in Measurement","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":"Population Health Research Institute; McMaster University","funders":"Shiraz University; Shiraz University of Medical Sciences; McMaster University","keywords":"Correlation; Data set; Set (abstract data type); Correlation coefficient; Statistics; Data mining; Pearson product-moment correlation coefficient; Misconduct; Computer science; Mathematics","score_opus":0.8378742148671262,"score_gpt":0.607124913089742,"score_spread":0.23074930177738417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166290337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59226984,0.00030566144,0.39537004,0.009644175,0.0006638045,0.0005914786,0.00008988853,0.000034983714,0.001030121],"genre_scores_gemma":[0.92327195,0.00034543814,0.07417823,0.00014868614,0.00028531576,0.000019364255,0.00007933628,0.000014262733,0.0016574428],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9432103,0.045661774,0.0008612231,0.0013922144,0.008049086,0.0008253783],"domain_scores_gemma":[0.84601533,0.14953129,0.00023829573,0.0022761258,0.00096664677,0.0009723126],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12796389,0.0001786839,0.00062961463,0.0003621969,0.0003470515,0.00028238562,0.0018413641,0.00048391632,0.0021465875],"category_scores_gemma":[0.49407032,0.00009412664,0.00005690762,0.0009426007,0.001262025,0.0002897707,0.00081246486,0.0011527167,0.00004761652],"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":[0.0001428909,0.000085095744,0.6715367,0.000062518164,0.000059192294,0.00001991747,0.0004321679,0.0000063920697,0.001974785,0.012627829,0.01889576,0.29415676],"study_design_scores_gemma":[0.0013542962,0.00034425507,0.42518017,0.000050047947,0.000036707243,0.000020636991,0.002297207,0.0037063248,0.0014016273,0.46710184,0.09819328,0.00031358478],"about_ca_topic_score_codex":0.00015068817,"about_ca_topic_score_gemma":0.0006638402,"teacher_disagreement_score":0.45447403,"about_ca_system_score_codex":0.00006474154,"about_ca_system_score_gemma":0.0006000768,"threshold_uncertainty_score":0.9987656},"labels":[],"label_agreement":null},{"id":"W2166786174","doi":"10.1186/1471-2288-12-168","title":"Reporting guidelines for modelling studies","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Bruyère; University of Ottawa; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Population; Population health; Consistency (knowledge bases); Quality (philosophy); Thematic analysis; Data science; MEDLINE; Health care; Management science; Computer science; Medicine; Qualitative research; Environmental health","score_opus":0.9943409981609255,"score_gpt":0.7865172203671771,"score_spread":0.2078237777937484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166786174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030070977,0.028215146,0.88437074,0.053684235,0.0016657719,0.0008128469,0.000024216879,0.000055447123,0.0011005921],"genre_scores_gemma":[0.018663956,0.0018566082,0.9617809,0.010111245,0.0049132635,0.00080101524,0.000018236567,0.000055384164,0.0017993891],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9748823,0.00888949,0.01310575,0.00080165005,0.0005697191,0.001751059],"domain_scores_gemma":[0.57957995,0.39950874,0.012462109,0.002077087,0.0037833247,0.0025888206],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6106186,0.00016959812,0.001821078,0.00052618,0.00040278313,0.000028079456,0.00045989518,0.0003692474,0.00052520377],"category_scores_gemma":[0.87813663,0.00017418219,0.00021663631,0.00029058402,0.0003750529,0.00029757275,0.00024147077,0.0005200882,0.0006417019],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009251737,0.00014885035,0.044896062,0.0025194476,0.00025793497,0.000003106771,0.00515078,0.0010622785,0.000009649597,0.6976749,0.24331972,0.0048647686],"study_design_scores_gemma":[0.0014550218,0.00022513054,0.0013737003,0.0004312442,0.000014638362,0.000060361755,0.014531997,0.17887886,0.00005553567,0.34825218,0.45415342,0.0005679128],"about_ca_topic_score_codex":0.00059447356,"about_ca_topic_score_gemma":0.00016834955,"teacher_disagreement_score":0.3953024,"about_ca_system_score_codex":0.00040620897,"about_ca_system_score_gemma":0.0007824077,"threshold_uncertainty_score":0.82479936},"labels":[],"label_agreement":null},{"id":"W2167133263","doi":"10.1186/1471-2288-12-158","title":"Do health care institutions value research? A mixed methods study of barriers and facilitators to methodological rigor in pediatric randomized trials","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Manitoba; University of Alberta","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale","keywords":"Randomized controlled trial; Research design; Relevance (law); Knowledge translation; Medicine; External validity; Medical education; Health care; Psychology; MEDLINE; Family medicine; Applied psychology; Nursing; Social psychology; Knowledge management","score_opus":0.9605955428081054,"score_gpt":0.8092016026772021,"score_spread":0.15139394013090335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167133263","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":[0.82408804,0.0141191725,0.13795811,0.009468473,0.0010190537,0.011904566,0.000034175177,0.00007145817,0.0013369748],"genre_scores_gemma":[0.3601999,0.005141749,0.6315503,0.00043291043,0.00063566567,0.0018463604,0.0000089849345,0.00004606751,0.00013805678],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.104273744,0.8676641,0.0070235636,0.0024958882,0.01381149,0.004731237],"domain_scores_gemma":[0.041525718,0.9453735,0.00044183384,0.0018207467,0.0032843074,0.007553946],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.88153213,0.00043547232,0.006767303,0.004399093,0.00059213844,0.00004423291,0.0012999363,0.0018506721,0.0007671838],"category_scores_gemma":[0.9863365,0.00029852305,0.0005791343,0.0052639036,0.005872604,0.00013229657,0.00272708,0.012031519,0.000041574593],"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":[0.24397545,0.005129211,0.09361269,0.008444322,0.0009843785,0.0002808324,0.09396526,0.000041192452,0.001088048,0.365866,0.0039992174,0.18261337],"study_design_scores_gemma":[0.3394271,0.025128294,0.08431005,0.0017880191,0.0006877364,0.00019522298,0.45026818,0.00035067188,0.0013038887,0.085903086,0.009382591,0.0012551458],"about_ca_topic_score_codex":0.003468351,"about_ca_topic_score_gemma":0.0023937207,"teacher_disagreement_score":0.4935922,"about_ca_system_score_codex":0.00078786275,"about_ca_system_score_gemma":0.01685329,"threshold_uncertainty_score":0.9999467},"labels":[],"label_agreement":null},{"id":"W2167137688","doi":"10.1186/1471-2288-9-63","title":"oA novel nonparametric approach for estimating cut-offs in continuous risk indicators with application to diabetes epidemiology","year":2009,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"Pfizer","keywords":"Nonparametric statistics; Youden's J statistic; Statistics; Estimator; Receiver operating characteristic; Regression analysis; Epidemiology; Econometrics; Regression; Mathematics; Computer science; Medicine; Internal medicine","score_opus":0.4924268610478432,"score_gpt":0.5675606180349302,"score_spread":0.07513375698708696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167137688","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045983914,0.00008188407,0.95062864,0.00072119513,0.00007095959,0.0018043165,0.0000247306,0.000060313287,0.0006240634],"genre_scores_gemma":[0.039752416,0.000015067889,0.9582716,0.00053990755,0.00022369967,0.0011211358,0.000014934765,0.00003170574,0.000029497149],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9820739,0.013172858,0.0012013998,0.0010285664,0.0009697095,0.0015535499],"domain_scores_gemma":[0.68126076,0.31679863,0.000303803,0.00058114016,0.00030120794,0.00075446715],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08715822,0.0002662067,0.0014015011,0.0011261743,0.00017682799,0.000019231424,0.00082510425,0.0005530788,0.00006188255],"category_scores_gemma":[0.7379931,0.00019325895,0.000091490525,0.0022401116,0.0006355707,0.00004060619,0.00018073317,0.0014291668,0.000011886839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035197363,0.0005701066,0.029357778,0.0003101319,0.000033154323,0.0000029132777,0.00024992126,0.00015731741,0.00026492283,0.29905725,0.00052340946,0.66912115],"study_design_scores_gemma":[0.0016158458,0.0021423628,0.021419868,0.00012791708,0.000038473358,0.000012312016,0.00023355578,0.3888254,0.00035084315,0.58460134,0.00030245326,0.00032965583],"about_ca_topic_score_codex":0.00015941082,"about_ca_topic_score_gemma":0.0000707534,"teacher_disagreement_score":0.6687915,"about_ca_system_score_codex":0.0001336908,"about_ca_system_score_gemma":0.0004709447,"threshold_uncertainty_score":0.9399627},"labels":[],"label_agreement":null},{"id":"W2170182466","doi":"10.1186/1471-2288-10-1","title":"A tutorial on pilot studies: the what, why and how","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3439,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"GlaxoSmithKline (Canada); St. Joseph’s Healthcare Hamilton; University of Waterloo; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Clinical trial; Medicine; Pilot trial; Psychological intervention; Intervention (counseling); Research design; Clinical study design; Medical physics; Randomized controlled trial; Nursing; Surgery","score_opus":0.9876457482859581,"score_gpt":0.7589303971843917,"score_spread":0.22871535110156638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170182466","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":[0.4419507,0.016829643,0.17642574,0.3303159,0.021275843,0.004235539,0.000009428359,0.000031002015,0.008926184],"genre_scores_gemma":[0.50500304,0.013215098,0.3468096,0.023622213,0.022611298,0.0019518697,0.000008575037,0.00013434327,0.086643994],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5185942,0.44324216,0.005348859,0.0022212572,0.029403314,0.0011901876],"domain_scores_gemma":[0.07611386,0.9117685,0.0014474603,0.0060079005,0.0035924753,0.0010697922],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.80124205,0.0002380548,0.003086618,0.000493243,0.00047994306,0.0012505406,0.0035009903,0.00025518212,0.011501934],"category_scores_gemma":[0.94872093,0.00008060721,0.0005846202,0.0014635697,0.0020709503,0.00020749627,0.00089488603,0.0019236068,0.0012286081],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017539338,0.00009438108,0.0012153075,0.00009053646,0.00028611478,0.0000352605,0.0015001266,7.308905e-7,0.00066007185,0.09040518,0.6395152,0.26602164],"study_design_scores_gemma":[0.00048201234,0.0006071592,0.0010901658,0.000061746796,0.00005090133,0.000054501874,0.007814477,0.001069928,0.000056277095,0.090739414,0.8978522,0.00012120705],"about_ca_topic_score_codex":0.00003513182,"about_ca_topic_score_gemma":0.0017102213,"teacher_disagreement_score":0.46852633,"about_ca_system_score_codex":0.000021628957,"about_ca_system_score_gemma":0.0005655257,"threshold_uncertainty_score":0.99978626},"labels":[],"label_agreement":null},{"id":"W2171017911","doi":"10.1186/1471-2288-10-86","title":"Prediction of two month modified Rankin Scale with an ordinal prediction model in patients with aneurysmal subarachnoid haemorrhage","year":2010,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Intracranial Aneurysms: Treatment and Complications","field":"Medicine","cited_by":33,"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; Canadian Institutes of Health Research; European Commission; Stroke Association","keywords":"Medicine; Modified Rankin Scale; Subarachnoid hemorrhage; Population; Aneurysm; Internal medicine; Surgery","score_opus":0.17933863121594432,"score_gpt":0.4081744071228485,"score_spread":0.2288357759069042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171017911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90716153,0.00001172563,0.09029913,0.0003692185,0.00008047535,0.0010962044,0.000060873663,0.00006186303,0.0008589938],"genre_scores_gemma":[0.9031748,0.0000039023275,0.09585342,0.000046752746,0.00017274088,0.0002445837,0.00026044503,0.00003253363,0.00021079961],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99466014,0.0017493528,0.00053309504,0.000632526,0.0017890177,0.0006358814],"domain_scores_gemma":[0.9965788,0.0014024288,0.00011147383,0.00065943884,0.00071129773,0.0005365635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004682937,0.00021809105,0.00056975347,0.0005244603,0.0001597113,0.000012868309,0.00030302384,0.00033728153,0.00023969488],"category_scores_gemma":[0.0021111344,0.00014825953,0.000058349833,0.0006750703,0.0009337145,0.00018176176,0.0000764034,0.0015155943,0.000007191962],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02384934,0.004198626,0.93595934,0.00034626658,0.00004415748,0.00013478984,0.0006004229,0.00089738,0.009473948,0.0040733926,0.000048244616,0.020374091],"study_design_scores_gemma":[0.013710195,0.0076784925,0.6667992,0.00006101304,0.0001343824,0.00024380113,0.00012154843,0.30766726,0.0016041683,0.0018266513,0.0000067431256,0.00014656062],"about_ca_topic_score_codex":0.0007126993,"about_ca_topic_score_gemma":0.003068497,"teacher_disagreement_score":0.30676988,"about_ca_system_score_codex":0.000076013406,"about_ca_system_score_gemma":0.000963717,"threshold_uncertainty_score":0.6584587},"labels":[],"label_agreement":null},{"id":"W2204236607","doi":"10.1186/s12874-015-0101-3","title":"Bayesian estimation of associations between identified longitudinal hormone subgroups and age at final menstrual period","year":2015,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ovarian function and disorders","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":"University of Alberta","funders":"National Cancer Institute; National Institute on Aging; National Institutes of Health","keywords":"Subgroup analysis; Follicle-stimulating hormone; Medicine; Longitudinal study; Demography; Hormone; Internal medicine; Luteinizing hormone; Meta-analysis","score_opus":0.547910693898897,"score_gpt":0.5182852696216899,"score_spread":0.029625424277207157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2204236607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7268777,0.00045429432,0.2662682,0.0035564692,0.00018605508,0.00038371678,0.00002111377,0.000041792933,0.0022106944],"genre_scores_gemma":[0.9299932,0.000056189536,0.06787742,0.000087381384,0.00023693366,0.000026645086,0.00019470851,0.000018207087,0.0015092756],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.993062,0.0037351346,0.000537108,0.00038212206,0.001804204,0.0004794339],"domain_scores_gemma":[0.9909937,0.007241683,0.00012344471,0.0002839344,0.00040781457,0.000949421],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017459115,0.00012718825,0.0006264502,0.00037926555,0.00015980098,0.000019668067,0.00013960645,0.00037618086,0.000643191],"category_scores_gemma":[0.08211054,0.00011034832,0.00008275697,0.00046143084,0.00089477265,0.000074355354,0.0002297637,0.0006170014,0.00005181031],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004023064,0.0007054191,0.83990026,0.00051421474,0.0005915659,0.0004977531,0.0051098815,0.000041545463,0.002805504,0.013531358,0.0404384,0.09184107],"study_design_scores_gemma":[0.00784649,0.0015869648,0.9751936,0.0000673757,0.00016105211,0.00018463221,0.0020258653,0.0044086045,0.00029772855,0.0070474194,0.0010056569,0.00017457936],"about_ca_topic_score_codex":0.0004541125,"about_ca_topic_score_gemma":0.00056112674,"teacher_disagreement_score":0.20311555,"about_ca_system_score_codex":0.00018356011,"about_ca_system_score_gemma":0.0011256668,"threshold_uncertainty_score":0.9256212},"labels":[],"label_agreement":null},{"id":"W2261406464","doi":"10.1186/s12874-016-0116-4","title":"A scoping review on the conduct and reporting of scoping reviews","year":2016,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":2221,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Ottawa; University of Toronto; University of Calgary; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Systematic review; Inclusion (mineral); MEDLINE; Protocol (science); Grey literature; Medicine; Psychology; Alternative medicine; Political science","score_opus":0.9964033037350372,"score_gpt":0.8939342699261918,"score_spread":0.10246903380884531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261406464","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":[0.0000020290317,0.9693027,0.0027222806,0.010342697,0.00048039894,0.015499827,0.0000150258975,0.000023293518,0.0016117607],"genre_scores_gemma":[5.2683877e-8,0.97494596,0.008829672,0.010180849,0.0006008005,0.004963511,0.0000044580065,0.00004229253,0.0004324118],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.67100173,0.3094722,0.0133607695,0.0011360446,0.002960646,0.0020685743],"domain_scores_gemma":[0.14930235,0.8320417,0.014012807,0.0021640193,0.0010772772,0.0014018948],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5448813,0.0003725159,0.006587156,0.0005345605,0.0010143215,0.000009207275,0.0012780572,0.00071280805,0.0068378025],"category_scores_gemma":[0.9262681,0.00016846048,0.00035274064,0.0013913036,0.0015622025,0.000071236056,0.0012183882,0.0038303935,0.0006446354],"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":[0.0000035183418,0.000003135232,0.000006215859,0.485946,0.0000075464086,0.0000046895298,0.00015480876,3.319545e-10,4.1119642e-7,0.0014694908,0.007933888,0.5044703],"study_design_scores_gemma":[0.00008807025,0.00006526556,0.0000010714208,0.54820764,0.000023657381,0.000019234172,0.0000615064,2.2831986e-7,3.5781088e-7,0.00015944308,0.4512994,0.00007416779],"about_ca_topic_score_codex":0.00014756802,"about_ca_topic_score_gemma":0.00041931056,"teacher_disagreement_score":0.5225694,"about_ca_system_score_codex":0.00027810052,"about_ca_system_score_gemma":0.03206723,"threshold_uncertainty_score":0.9984678},"labels":[],"label_agreement":null},{"id":"W2272919951","doi":"10.1186/s12874-016-0113-7","title":"Mixed-strain housing for female C57BL/6, DBA/2, and BALB/c mice: validating a split-plot design that promotes refinement and reduction","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Animal Behavior and Welfare Studies","field":"Veterinary","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Federation for Animal Welfare","keywords":"Statistics; Strain (injury); Analysis of variance; Wasting; Psychology; Biology; Mathematics; Demography; Medicine; Internal medicine","score_opus":0.8162918437552569,"score_gpt":0.5686356204009425,"score_spread":0.24765622335431436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2272919951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7123517,0.0009020378,0.28189853,0.0034507348,0.00019555274,0.0009807508,0.00003367566,0.00007362761,0.00011340049],"genre_scores_gemma":[0.693698,0.00045330933,0.30481833,0.000042286614,0.00033107802,0.00038455753,0.000006244945,0.000041277122,0.00022491511],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990376,0.006843441,0.0004162237,0.00074567675,0.00077078905,0.0008478804],"domain_scores_gemma":[0.9791189,0.019967604,0.000102149825,0.0002366205,0.00021994075,0.00035481792],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023877077,0.00021768609,0.0005127611,0.00019784366,0.000519264,0.000042809548,0.0002055512,0.00028305798,0.0002383747],"category_scores_gemma":[0.03046951,0.00014410618,0.000070106864,0.00014443368,0.0010851037,0.000111931164,0.00047807035,0.00035003957,0.000008773396],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032870397,0.00016018914,0.010110398,0.00080775865,0.00010685814,0.00010737166,0.0014962082,1.19057006e-7,0.47583136,0.0052562472,0.0016090907,0.5012274],"study_design_scores_gemma":[0.028037379,0.046259858,0.60010165,0.0066529033,0.0008760421,0.006029125,0.059072897,0.0018277807,0.15297388,0.0687025,0.025429748,0.004036217],"about_ca_topic_score_codex":0.00017473736,"about_ca_topic_score_gemma":0.000046375284,"teacher_disagreement_score":0.5899913,"about_ca_system_score_codex":0.00008353071,"about_ca_system_score_gemma":0.00023257475,"threshold_uncertainty_score":0.97769725},"labels":[],"label_agreement":null},{"id":"W2284187917","doi":"10.1186/s12874-016-0119-1","title":"Head to head comparison of the propensity score and the high-dimensional propensity score matching methods","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Joseph’s Healthcare Hamilton; University of British Columbia; Centre Hospitalier de l’Université de Montréal; McGill University; McMaster University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Confounding; Medicine; Matching (statistics); Cohort; Context (archaeology); Confidence interval; Cohort study; Internal medicine; Statistics; Mathematics; Pathology; Biology","score_opus":0.8646910788517377,"score_gpt":0.6556494814906167,"score_spread":0.20904159736112093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284187917","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.503865,0.00009819942,0.48806724,0.006489794,0.00011545069,0.0011994423,0.000004123753,0.000055464472,0.00010526153],"genre_scores_gemma":[0.3814385,0.000029406718,0.6176556,0.00034665395,0.00009682463,0.00014191498,6.4712776e-7,0.000029021727,0.00026145906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95408076,0.040948227,0.0010054029,0.0007242552,0.002323078,0.00091828214],"domain_scores_gemma":[0.88438785,0.112810455,0.00028751278,0.0012232964,0.0008272503,0.00046363476],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07210784,0.00026121578,0.0013160573,0.00016898446,0.00041193617,0.000023765158,0.0012131133,0.0003558075,0.00023886168],"category_scores_gemma":[0.22236341,0.000104261286,0.00013339115,0.00052644825,0.0038925437,0.00010635567,0.002790788,0.0014110282,0.00001401488],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033911911,0.00035310007,0.02721664,0.0006163572,0.000109065404,0.000023755205,0.0016743842,0.000005585768,0.07140673,0.6145967,0.003108137,0.27749833],"study_design_scores_gemma":[0.0014347014,0.00041791142,0.027950937,0.0011441691,0.00003213374,0.00008739744,0.0001255658,0.00018127407,0.06975344,0.89831555,0.00035288237,0.00020405729],"about_ca_topic_score_codex":0.0009765957,"about_ca_topic_score_gemma":0.0027650609,"teacher_disagreement_score":0.2837188,"about_ca_system_score_codex":0.00012543848,"about_ca_system_score_gemma":0.00087313063,"threshold_uncertainty_score":0.9988183},"labels":[],"label_agreement":null},{"id":"W2343727684","doi":"10.1186/s12874-016-0146-y","title":"A scoping review of indirect comparison methods and applications using individual patient data","year":2016,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; Institute for Work & Health; Canada Research Chairs; St. Michael's Hospital","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Medicine; CINAHL; MEDLINE; Data extraction; Meta-analysis; Protocol (science); Psychological intervention; Alternative medicine; Internal medicine; Pathology; Psychiatry","score_opus":0.959632606431749,"score_gpt":0.808578461235593,"score_spread":0.151054145196156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2343727684","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.049692e-7,0.8702867,0.12081283,0.00010142385,0.0003891979,0.0070289504,0.00032676975,0.000029146742,0.0010243903],"genre_scores_gemma":[3.5864748e-8,0.759776,0.23757865,0.00012740734,0.00040294707,0.0017124407,0.0002620046,0.00006588827,0.000074622585],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.83950526,0.15029708,0.003407748,0.0018790179,0.0031973196,0.001713605],"domain_scores_gemma":[0.8287361,0.16470009,0.0012339473,0.0034556887,0.00044271006,0.0014314029],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.14091358,0.00048270036,0.00534211,0.0011599615,0.00027363142,0.00002524237,0.0034263195,0.0013034011,0.005465589],"category_scores_gemma":[0.09793843,0.00033764038,0.00024989093,0.0015067752,0.0021154727,0.000083937535,0.0057006394,0.0031762128,0.00014134603],"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":[0.000016774982,0.00011074225,0.000009320193,0.31765622,0.00017277485,0.000011673815,0.000071321716,2.2983206e-9,2.3664295e-7,0.00088332477,0.0011222535,0.67994535],"study_design_scores_gemma":[0.00021224862,0.00021102838,0.0000028070915,0.4014388,0.00022771249,0.00015329372,0.00007457816,0.000009331605,0.0000016204866,0.00022691861,0.5972515,0.00019016798],"about_ca_topic_score_codex":0.00026117938,"about_ca_topic_score_gemma":0.0001061312,"teacher_disagreement_score":0.6797552,"about_ca_system_score_codex":0.00022997444,"about_ca_system_score_gemma":0.008545659,"threshold_uncertainty_score":0.99999315},"labels":[],"label_agreement":null},{"id":"W2345521921","doi":"10.1186/s12874-016-0149-8","title":"Complex intervention modelling should capture the dynamics of adaptation","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary; Athabasca University","funders":"Canadian Institutes of Health Research; Alberta Innovates - Health Solutions","keywords":"Psychological intervention; Intervention (counseling); Adaptation (eye); Computer science; Complex adaptive system; Management science; Risk analysis (engineering); Property (philosophy); System dynamics; Variety (cybernetics); Process management; Medicine; Psychology; Artificial intelligence; Engineering","score_opus":0.8901200006286084,"score_gpt":0.619562429059487,"score_spread":0.2705575715691214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345521921","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":[0.06041903,0.00018292748,0.92964095,0.008388189,0.0002649209,0.0001805747,0.000012152052,0.000020513473,0.0008907641],"genre_scores_gemma":[0.9243729,0.00022422666,0.07407878,0.000104653176,0.00008503033,0.000029064748,0.000010552112,0.0000112823345,0.0010834854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97365004,0.019011658,0.0011593761,0.0005259573,0.0051693264,0.00048362114],"domain_scores_gemma":[0.893967,0.103225745,0.00030478495,0.0007155154,0.0015514509,0.0002355522],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.107856795,0.00010547201,0.00037021737,0.0004950666,0.00019275736,0.000042393935,0.0012288077,0.0002796564,0.0014170823],"category_scores_gemma":[0.11666336,0.00004745727,0.00021497936,0.0009822068,0.0010346085,0.00013299038,0.00025046116,0.00046960477,0.00007033698],"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":[0.00035594119,0.000097729644,0.0016554107,0.00003396652,0.000028334782,0.0000042970455,0.0012295771,0.00912505,0.00054496573,0.18751772,0.0016928216,0.7977142],"study_design_scores_gemma":[0.00037059232,0.00009312798,0.0007543131,0.00006901139,0.000006252483,0.000007473849,0.0048400634,0.77972156,0.000035416546,0.21329905,0.00075334165,0.00004982061],"about_ca_topic_score_codex":0.00085354625,"about_ca_topic_score_gemma":0.004568624,"teacher_disagreement_score":0.8639539,"about_ca_system_score_codex":0.00005400049,"about_ca_system_score_gemma":0.00031507836,"threshold_uncertainty_score":0.99949574},"labels":[],"label_agreement":null},{"id":"W2347004310","doi":"10.1186/s12874-016-0151-1","title":"Patient enrollment and logistical problems top the list of difficulties in clinical research: a cross-sectional survey","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Hôpitaux Universitaires de Genève","keywords":"Cross-sectional study; Family medicine; Medicine; Survey research; Clinical research; MEDLINE; Data collection; Research design; Research ethics; Medical education; Psychology; Psychiatry; Pathology; Applied psychology; Political science","score_opus":0.9613583380799149,"score_gpt":0.7599064808911581,"score_spread":0.2014518571887568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2347004310","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":[0.97869945,0.0007769071,0.0062001008,0.011493743,0.00037204515,0.0013834112,0.00003624716,0.000021209706,0.0010169179],"genre_scores_gemma":[0.9850123,0.004703661,0.0074005662,0.00028209863,0.0004350491,0.0002836666,0.000009835403,0.000032624906,0.0018402106],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8381724,0.13620034,0.004565258,0.0022398776,0.01593052,0.0028916544],"domain_scores_gemma":[0.15352115,0.83923167,0.0001838694,0.0012972752,0.004319509,0.0014465364],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.45372775,0.00020371635,0.0010328963,0.00058542273,0.0002822652,0.000049781363,0.000938788,0.0015825279,0.0013704889],"category_scores_gemma":[0.9039386,0.00009851471,0.00020722607,0.0010668783,0.023753153,0.00005416517,0.0023276217,0.008484858,0.00006317562],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039335038,0.00092146575,0.9445463,0.00042851962,0.00005854334,0.00009673176,0.0002451775,0.000001110508,0.00047585525,0.027509263,0.0007250737,0.021058453],"study_design_scores_gemma":[0.0029172855,0.0032061606,0.94625473,0.00052296044,0.0000039799006,0.000056898498,0.00027387752,0.00016263666,0.00022074055,0.045031726,0.00124951,0.000099498815],"about_ca_topic_score_codex":0.0022509715,"about_ca_topic_score_gemma":0.011423137,"teacher_disagreement_score":0.7030313,"about_ca_system_score_codex":0.00028254036,"about_ca_system_score_gemma":0.0053962376,"threshold_uncertainty_score":0.9997136},"labels":[],"label_agreement":null},{"id":"W2347172321","doi":"10.1186/s12874-016-0246-8","title":"Statistical methodology for age-adjustment of the GH-2000 score detecting growth hormone misuse","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Growth Hormone and Insulin-like Growth Factors","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"David Geffen School of Medicine, University of California, Los Angeles; Partnership for Clean Competition; Deutsche Sporthochschule Köln; World Anti-Doping Agency; University of Southampton; University of Washington","keywords":"Population; Residual; Medicine; Growth hormone; Athletes; Statistics; Internal medicine; Hormone; Mathematics; Physical therapy","score_opus":0.5101245193569307,"score_gpt":0.5084997470625345,"score_spread":0.0016247722943961707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2347172321","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":[0.38290247,0.0016675751,0.60698515,0.005219503,0.0007410842,0.0017088872,0.00006270377,0.000065820655,0.0006467899],"genre_scores_gemma":[0.5622523,0.0014343192,0.43184608,0.0010702963,0.0011954491,0.0005164722,0.000022536226,0.00011846266,0.0015441302],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9781265,0.015739705,0.0012927118,0.0009048823,0.0022971826,0.0016389849],"domain_scores_gemma":[0.8766829,0.1201131,0.00025008575,0.00093650754,0.00096754,0.001049884],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03356899,0.00034620773,0.0014117548,0.0005092564,0.00026302374,0.000010250219,0.0008789519,0.0008259283,0.00068636826],"category_scores_gemma":[0.34027705,0.0001791064,0.00040028,0.0007865449,0.0028081264,0.000073724164,0.0006077873,0.0012628911,0.00004283668],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013089469,0.000997846,0.025316758,0.0019653009,0.0007408254,0.00030331206,0.0017582646,6.622373e-7,0.44574186,0.07069143,0.02364351,0.41575077],"study_design_scores_gemma":[0.028231882,0.014860716,0.45035195,0.0015367059,0.0008812222,0.0010720022,0.0021099232,0.00045926144,0.33780771,0.14013067,0.02142306,0.0011348729],"about_ca_topic_score_codex":0.0004374088,"about_ca_topic_score_gemma":0.00018714205,"teacher_disagreement_score":0.4250352,"about_ca_system_score_codex":0.00031965977,"about_ca_system_score_gemma":0.0031079482,"threshold_uncertainty_score":0.99990565},"labels":[],"label_agreement":null},{"id":"W2397859546","doi":"10.1186/s12874-016-0153-z","title":"Cross-cultural adaptation of the drug-taking confidence questionnaire drug version for use in Brazil","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Substance Abuse Treatment and Outcomes","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":false,"ca_institutions":"Centre for Addiction and Mental Health; University of Toronto","funders":"Universidade de Pernambuco; Universidade Federal de Pernambuco","keywords":"Cronbach's alpha; Reliability (semiconductor); CLARITY; Psychosocial; Psychology; Relevance (law); Test (biology); Adaptation (eye); Medicine; Clinical psychology; Psychometrics; Psychiatry","score_opus":0.4504254062879707,"score_gpt":0.5555378666607447,"score_spread":0.105112460372774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397859546","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97004795,0.00045667007,0.024887769,0.0036432745,0.00029480294,0.0005924701,0.0000024902977,0.000019960687,0.000054583033],"genre_scores_gemma":[0.9764307,0.00027477762,0.02049633,0.00016698701,0.000117133575,0.000083179446,0.000004993475,0.000012067282,0.0024138137],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9947149,0.0031295472,0.00038552473,0.0003048102,0.0010397814,0.0004253973],"domain_scores_gemma":[0.96138644,0.03726975,0.00013940068,0.00034148534,0.0006802068,0.00018272173],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0097727,0.00010514656,0.00036069343,0.00016774012,0.00011887059,0.000011994416,0.00025479318,0.00015914625,0.000319078],"category_scores_gemma":[0.14029637,0.000049736154,0.00013225303,0.00033894167,0.0011178385,0.00021580665,0.00009088441,0.00027933705,0.000015820442],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020174675,0.00008274627,0.93513906,0.00012411471,0.000026887601,0.000021741578,0.0018950275,0.0000054899538,0.0032199507,0.0052932696,0.00083601754,0.0513382],"study_design_scores_gemma":[0.011980861,0.00025273123,0.9521451,0.0030597772,0.00004352879,0.00003817131,0.0031598543,0.0013389476,0.022764886,0.0037547043,0.001317568,0.00014386255],"about_ca_topic_score_codex":0.00070273306,"about_ca_topic_score_gemma":0.008334377,"teacher_disagreement_score":0.13052367,"about_ca_system_score_codex":0.00018932844,"about_ca_system_score_gemma":0.0007642192,"threshold_uncertainty_score":0.86694527},"labels":[],"label_agreement":null},{"id":"W2400420884","doi":"10.1186/s12874-016-0165-8","title":"Using the modified Delphi method to establish clinical consensus for the diagnosis and treatment of patients with rotator cuff pathology","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":432,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary; Mount Royal University","funders":"","keywords":"Rotator cuff; Medicine; Delphi method; Guideline; Delphi; Health care; MEDLINE; Physical therapy; Medical physics; Pathology; Surgery; Computer science; Artificial intelligence","score_opus":0.895516367431202,"score_gpt":0.7062424009973984,"score_spread":0.18927396643380356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400420884","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":[0.482544,0.0001367784,0.49400926,0.02101498,0.00014704683,0.002090891,0.00004131539,0.000008724276,0.000007012386],"genre_scores_gemma":[0.24426356,0.0007543285,0.7512977,0.0019898673,0.00057680294,0.0009991141,0.00001276311,0.000044341945,0.00006150173],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97735596,0.018696874,0.0015001103,0.00062994345,0.0011732243,0.00064391166],"domain_scores_gemma":[0.45365238,0.5431934,0.00033800706,0.00072810345,0.0014663542,0.0006217304],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051992144,0.00017647933,0.000825354,0.00015935116,0.00020060803,0.0000125156475,0.0002700492,0.00028068485,0.0001933221],"category_scores_gemma":[0.41012353,0.00006789191,0.00015050553,0.0003677942,0.0015617358,0.000038455975,0.00023003679,0.00036014902,0.000003500057],"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":[0.012131948,0.0007276636,0.1721254,0.00005748968,0.00028454798,0.000033015065,0.00034495347,0.0000088075685,0.0002715035,0.0015307176,0.0017579659,0.810726],"study_design_scores_gemma":[0.076097414,0.05009208,0.7603635,0.0006458074,0.0028126673,0.0004587786,0.0069281636,0.013640427,0.0042739483,0.010710458,0.07326419,0.00071252894],"about_ca_topic_score_codex":0.0005788815,"about_ca_topic_score_gemma":0.0007895272,"teacher_disagreement_score":0.8100135,"about_ca_system_score_codex":0.00011332672,"about_ca_system_score_gemma":0.0014467206,"threshold_uncertainty_score":0.9761736},"labels":[],"label_agreement":null},{"id":"W2418770449","doi":"10.1186/s12874-016-0166-7","title":"Evaluation of a multi-arm multi-stage Bayesian design for phase II drug selection trials – an example in hemato-oncology","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut National Du Cancer; CNIB","keywords":"Sample size determination; Bayes' theorem; Bayesian probability; Statistics; Decision rule; Interim analysis; Computer science; Medicine; Mathematics; Randomized controlled trial; Surgery","score_opus":0.9863969453268049,"score_gpt":0.7938781117172434,"score_spread":0.19251883360956146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2418770449","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":[0.014287604,0.00010596653,0.9785431,0.00062984275,0.0005863,0.0056498903,0.000075826916,0.00006703599,0.000054436543],"genre_scores_gemma":[0.012539185,0.0000968888,0.9840139,0.00007893764,0.00045038585,0.0024820606,0.00000488155,0.00007277283,0.000261001],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.39750397,0.58686775,0.0061235144,0.0019191836,0.005608144,0.0019774183],"domain_scores_gemma":[0.0985032,0.8960858,0.001005922,0.0008647149,0.0026488977,0.00089149113],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7471657,0.00032296695,0.0029321099,0.0008065608,0.00020464374,0.000015448644,0.0008802612,0.0011061559,0.0036239277],"category_scores_gemma":[0.9751024,0.00021456362,0.00032419825,0.0007912522,0.0012456867,0.00013708824,0.00032020084,0.0008946568,0.000011675814],"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":[0.0069693434,0.008421285,0.00007213695,0.00054632785,0.00019521087,0.00001543544,0.0013525306,0.000023086854,0.040442966,0.051139202,0.001241429,0.889581],"study_design_scores_gemma":[0.040481754,0.0054720254,0.0000366253,0.00029934247,0.00023950363,0.00001092307,0.0006100783,0.1605206,0.03820771,0.75331086,0.0005440382,0.00026656795],"about_ca_topic_score_codex":0.00036411107,"about_ca_topic_score_gemma":0.0024258774,"teacher_disagreement_score":0.8893145,"about_ca_system_score_codex":0.00063126866,"about_ca_system_score_gemma":0.005019238,"threshold_uncertainty_score":0.9972869},"labels":[],"label_agreement":null},{"id":"W2484780171","doi":"10.1186/s12874-016-0201-8","title":"The effect of a monetary incentive for administrative assistants on the survey response rate: a randomized controlled trial","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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":"McMaster University","funders":"University at Buffalo","keywords":"Incentive; Medicine; Incentive program; Randomized controlled trial; Productivity; Family medicine; Confidence interval; Actuarial science; Business; Economics; Surgery; Internal medicine","score_opus":0.6878138855619732,"score_gpt":0.6325673890398611,"score_spread":0.05524649652211211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484780171","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":[0.9288272,0.00046036954,0.04124053,0.015323462,0.0015780026,0.011886394,0.000059699953,0.000025909378,0.0005983866],"genre_scores_gemma":[0.98505443,0.0005688288,0.0017441391,0.00019486145,0.00046428145,0.006669154,0.0000040920168,0.000025950232,0.005274278],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.044011857,0.9513463,0.0010774658,0.00054122956,0.0019659456,0.0010572345],"domain_scores_gemma":[0.04208444,0.95572025,0.00044775574,0.00055940973,0.0008084825,0.00037968697],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.9510353,0.00023703121,0.0022153193,0.00022057506,0.0014635258,0.000035216766,0.0013219353,0.00062295544,0.0005941976],"category_scores_gemma":[0.9934363,0.00008165932,0.00068584725,0.00063351967,0.012636913,0.000050636416,0.00016120852,0.00077259314,0.000021381129],"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":[0.98456067,0.000072452836,0.00027579186,0.000008392927,0.00033482717,0.00000865999,0.00096276094,8.491305e-8,0.0003387185,0.008248743,0.0011190575,0.0040698564],"study_design_scores_gemma":[0.9642905,0.005982139,0.014865962,0.00009019427,0.0000786465,8.456108e-7,0.0010823965,0.000038558403,0.0027853148,0.009076407,0.0015636228,0.00014541158],"about_ca_topic_score_codex":0.0007241616,"about_ca_topic_score_gemma":0.007734502,"teacher_disagreement_score":0.05622717,"about_ca_system_score_codex":0.00012101863,"about_ca_system_score_gemma":0.0053139017,"threshold_uncertainty_score":0.99983644},"labels":[],"label_agreement":null},{"id":"W2510270066","doi":"10.1186/s12874-016-0211-6","title":"Rasch modelling to deal with changes in the questionnaires used during long-term follow-up of cohort studies: a simulation study","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal; Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Rasch model; Raw score; Latent variable; Statistics; Raw data; Cohort; Term (time); Latent class model; Variable (mathematics); Computation; Computer science; Medicine; Mathematics; Algorithm","score_opus":0.894932611749861,"score_gpt":0.6602056242677833,"score_spread":0.23472698748207776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510270066","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":[0.5778363,0.00022175051,0.42000857,0.0010025473,0.00012949947,0.00075724407,0.0000011195502,0.000016939686,0.000026039525],"genre_scores_gemma":[0.92828524,0.00015827078,0.0709204,0.000050991533,0.0001771617,0.00023423808,3.2088073e-7,0.000015117591,0.00015825457],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9322214,0.056447838,0.0013929249,0.0012180896,0.007660384,0.0010593754],"domain_scores_gemma":[0.25521725,0.7412634,0.0003572316,0.0011789474,0.0016006822,0.00038249936],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21693848,0.00020062148,0.0009588072,0.001776901,0.00025920718,0.000054378954,0.0018080047,0.00018739754,0.00013561652],"category_scores_gemma":[0.6410719,0.00008672346,0.00007993244,0.0043152734,0.0006443909,0.00012951533,0.0006083602,0.0005342676,0.000014238551],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010247038,0.00016767759,0.9152924,0.00004363329,0.00009068865,0.00007458709,0.005384112,0.0038499183,0.00020212932,0.00015669456,0.000035962494,0.07367749],"study_design_scores_gemma":[0.0033308563,0.0017920936,0.968586,0.00057827897,0.000030439243,0.000024430496,0.012403421,0.0052216407,0.00027632472,0.0075212303,0.000035868386,0.00019938493],"about_ca_topic_score_codex":0.0003335273,"about_ca_topic_score_gemma":0.004917231,"teacher_disagreement_score":0.6848155,"about_ca_system_score_codex":0.000117272626,"about_ca_system_score_gemma":0.00042783932,"threshold_uncertainty_score":0.8063266},"labels":[],"label_agreement":null},{"id":"W2515865037","doi":"10.1186/s12874-016-0190-7","title":"Establishing the Canadian HIV Women’s Sexual and Reproductive Health Cohort Study (CHIWOS): Operationalizing Community-based Research in a Large National Quantitative Study","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Adolescent Sexual and Reproductive Health","field":"Health Professions","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Women's Health In Women's Hands; AIDS Vancouver; Simon Fraser University; McGill University; McGill University Health Centre; York University; McMaster University; Women's College Hospital; Dalhousie University; University of Toronto","funders":"British Columbia Centre for Disease Control; Social Sciences and Humanities Research Council of Canada; University of Toronto; Canadian Institutes of Health Research; University of Ottawa; McGill University; McGill University Health Centre; Simon Fraser University; Providence Health Care; Ontario HIV Treatment Network; McMaster University; Ottawa Hospital Research Institute","keywords":"Operationalization; Reproductive health; Human immunodeficiency virus (HIV); Cohort study; Medicine; Cohort; Environmental health; Psychology; Gerontology; Family medicine; Population","score_opus":0.8634863859120957,"score_gpt":0.6900051265886114,"score_spread":0.17348125932348435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515865037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92398095,0.00019404633,0.0033210278,0.06336649,0.0004162957,0.008170165,0.00007321421,0.000037780832,0.00044005373],"genre_scores_gemma":[0.9898517,0.00002761196,0.0022374736,0.002363533,0.00077298423,0.0032188422,0.000032513926,0.00004380403,0.001451533],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6539275,0.3358449,0.0012883086,0.0014130229,0.00473547,0.002790793],"domain_scores_gemma":[0.82269746,0.17123291,0.00022570365,0.001184389,0.0031906215,0.001468943],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5206069,0.00024501042,0.00082246226,0.0015250548,0.009213385,0.000049803217,0.0009954693,0.00032674585,0.0005176003],"category_scores_gemma":[0.27345768,0.00013981131,0.000024549574,0.0018673015,0.0017900247,0.0002456532,0.0010620472,0.008295201,0.00007341867],"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":true,"study_design_scores_codex":[0.0008275737,0.002055065,0.8869615,0.00024720738,0.000057470403,0.000027422726,0.09627635,0.0000058849428,0.00001798407,0.008613139,0.00370509,0.001205279],"study_design_scores_gemma":[0.002430942,0.0023231267,0.63479495,0.00019042681,0.000002408825,0.0000037854238,0.353542,0.00016299951,0.0000010320695,0.0035465623,0.0028735627,0.0001282151],"about_ca_topic_score_codex":0.3370121,"about_ca_topic_score_gemma":0.881222,"teacher_disagreement_score":0.5442099,"about_ca_system_score_codex":0.0045645945,"about_ca_system_score_gemma":0.035638947,"threshold_uncertainty_score":0.99925673},"labels":[],"label_agreement":null},{"id":"W2521376868","doi":"10.1186/s12874-016-0223-2","title":"Predictor characteristics necessary for building a clinically useful risk prediction model: a simulation study","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":35,"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","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Canadian Institutes of Health Research; National Institute of Child Health and Human Development; National Institutes of Health; Michael Smith Health Research BC; Harvard T.H. Chan School of Public Health","keywords":"Predictive modelling; Outcome (game theory); Population; Spurious relationship; Risk assessment; Statistics; Medicine; Computer science; Econometrics; Machine learning; Mathematics; Environmental health","score_opus":0.49247018021573596,"score_gpt":0.5808302681588722,"score_spread":0.08836008794313621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521376868","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":[0.22669032,0.000026764394,0.7690008,0.002033706,0.0006350564,0.0012877113,0.000040708324,0.00026442079,0.000020463629],"genre_scores_gemma":[0.60214096,0.000076145596,0.39646196,0.00015010175,0.0006676557,0.00035568082,0.0000048386264,0.000027821041,0.00011484143],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96907705,0.02472882,0.0013847715,0.0012520684,0.0024633082,0.001093986],"domain_scores_gemma":[0.83823526,0.1582239,0.00039078225,0.0012258658,0.0010795847,0.0008445849],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07025383,0.00022292037,0.0006359704,0.00045559905,0.00047057346,0.00007984176,0.0020005123,0.00070502807,0.0000770676],"category_scores_gemma":[0.38958645,0.00015336576,0.00014525522,0.0005671808,0.0003422042,0.0003325428,0.0010935435,0.0018117605,0.000019396224],"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":[0.0010446662,0.000573349,0.5996689,0.00026869745,0.00007520612,0.000026612059,0.0013347988,0.0064689294,0.00016282676,0.0075280285,0.00045811065,0.38238984],"study_design_scores_gemma":[0.0015850746,0.0019803094,0.08691192,0.00012077495,0.000014117315,0.000006561523,0.00004804953,0.8936993,0.000005830934,0.014831827,0.00066487066,0.00013135748],"about_ca_topic_score_codex":0.00009586826,"about_ca_topic_score_gemma":0.00007484182,"teacher_disagreement_score":0.8872304,"about_ca_system_score_codex":0.00019419822,"about_ca_system_score_gemma":0.0019258009,"threshold_uncertainty_score":0.9573693},"labels":[],"label_agreement":null},{"id":"W2522161560","doi":"10.1186/s12874-016-0225-0","title":"The use of relative incidence ratios in self-controlled case series studies: an overview","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Children's Hospital of Eastern Ontario; Ottawa Hospital; Manitoba Beekeepers' Association; University of Ottawa","funders":"Canadian Institutes of Health Research; Crohn's and Colitis Canada; Ontario Ministry of Health and Long-Term Care; Canadian Association of Gastroenterology; Institute for Clinical Evaluative Sciences","keywords":"Context (archaeology); Medicine; Subgroup analysis; Incidence (geometry); Covariate; Vaccination; Statistics; Mathematics; Meta-analysis; Internal medicine; Immunology","score_opus":0.920688573393072,"score_gpt":0.6823189290759659,"score_spread":0.23836964431710606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2522161560","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26643342,0.004237265,0.72153896,0.0045178253,0.00016933336,0.002716503,0.000010371353,0.00024181919,0.00013448458],"genre_scores_gemma":[0.04224757,0.01756074,0.93828934,0.00010530288,0.00009017234,0.00094356114,5.0083077e-7,0.000034892597,0.0007279109],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9607515,0.035881035,0.0010588905,0.00040719556,0.0012420514,0.0006593478],"domain_scores_gemma":[0.5761961,0.4214779,0.00026866337,0.0008107908,0.0010024138,0.00024413754],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053492635,0.00017627345,0.00097386923,0.00022419883,0.000186293,0.000015349986,0.00053917046,0.0002874657,0.00013867879],"category_scores_gemma":[0.669033,0.00008343782,0.00008833467,0.00049714674,0.0019281341,0.00061884394,0.000513784,0.00070359564,0.0000075814696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014742316,0.00017219724,0.0010071323,0.0002854177,0.00013275482,0.0010293709,0.0033708748,9.041681e-7,0.0013582081,0.96160406,0.00072121597,0.028843615],"study_design_scores_gemma":[0.0017228905,0.000801851,0.00006399803,0.00059420464,0.000020395813,0.00052923465,0.0021537186,0.00021583865,0.0021737625,0.9904248,0.0011700001,0.0001293127],"about_ca_topic_score_codex":0.00013772631,"about_ca_topic_score_gemma":0.010806753,"teacher_disagreement_score":0.6155404,"about_ca_system_score_codex":0.0002192929,"about_ca_system_score_gemma":0.00092766783,"threshold_uncertainty_score":0.9746285},"labels":[],"label_agreement":null},{"id":"W2524295027","doi":"10.1186/s12874-016-0232-1","title":"The contribution of databases to the results of systematic reviews: a cross-sectional study","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":120,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Meta-analysis; Medicine; Systematic review; Cochrane Library; Internal medicine","score_opus":0.979871063956532,"score_gpt":0.7564594682756122,"score_spread":0.22341159568091984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2524295027","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":[0.13205427,0.007830997,0.8422447,0.0052742125,0.00092395826,0.010981952,0.000107529944,0.00000491386,0.00057747046],"genre_scores_gemma":[0.98006004,0.00082220795,0.010409942,0.00012832755,0.000329068,0.001306911,0.000004792061,0.000011780046,0.0069269417],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.10325479,0.83093464,0.03018377,0.00170379,0.032967903,0.0009550887],"domain_scores_gemma":[0.047618993,0.9294251,0.0060747103,0.007967329,0.008439854,0.00047401883],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9113326,0.00018495765,0.0042813146,0.00039470498,0.00037158214,0.00015233841,0.004990158,0.00011113497,0.0022232493],"category_scores_gemma":[0.9856555,0.000044261214,0.001062325,0.0022556162,0.0010112463,0.000092203954,0.00090084266,0.00033817466,0.0011245379],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031076297,0.0012794329,0.51161563,0.009108686,0.001765277,0.000026424797,0.0032399837,0.000027742099,0.0022136944,0.11955041,0.2798273,0.0682378],"study_design_scores_gemma":[0.0063910214,0.0033819235,0.52578837,0.0110747805,0.000668661,0.00016539164,0.011257125,0.0026162234,0.0010236476,0.02897034,0.4080582,0.0006043263],"about_ca_topic_score_codex":0.00016208098,"about_ca_topic_score_gemma":0.0022567096,"teacher_disagreement_score":0.8480058,"about_ca_system_score_codex":0.00005393838,"about_ca_system_score_gemma":0.0006638859,"threshold_uncertainty_score":0.9996532},"labels":[],"label_agreement":null},{"id":"W2528392151","doi":"10.1186/s12874-016-0230-3","title":"Improving measurement-invariance assessments: correcting entrenched testing deficiencies","year":2016,"lang":"en","type":"editorial","venue":"BMC Medical Research Methodology","topic":"Qualitative Comparative Analysis Research","field":"Social 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":"University of Alberta","funders":"","keywords":"Measurement invariance; Structural equation modeling; Path analysis (statistics); Reliability (semiconductor); Econometrics; Latent variable; Computer science; Invariant (physics); Path (computing); Confirmatory factor analysis; Factor analysis; Psychology; Statistics; Mathematics; Artificial intelligence; Machine learning","score_opus":0.7943632318924707,"score_gpt":0.6639451147764183,"score_spread":0.13041811711605245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528392151","genre_codex":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","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":[0.00011733804,0.0019454963,0.6166361,0.0008321187,0.34515807,0.00095693883,0.000038789065,0.0001807827,0.03413439],"genre_scores_gemma":[0.0016495982,0.0010010349,0.114976004,0.000079189726,0.865393,0.0007451537,0.00005228612,0.00013520314,0.015968533],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.77395535,0.18668953,0.0017106156,0.0022566903,0.031373367,0.00401446],"domain_scores_gemma":[0.23321466,0.73929083,0.0011810991,0.0013780161,0.022688285,0.0022471093],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"category_scores_codex":[0.37343827,0.00056067365,0.0018160138,0.001395326,0.0027316588,0.00047221695,0.00403843,0.0022543534,0.005573665],"category_scores_gemma":[0.95042586,0.00044418234,0.0003575058,0.0034457482,0.006100906,0.00039852477,0.0016678387,0.0062651387,0.0007932357],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016398367,0.00016295997,0.00046901972,0.00037897326,0.00020491128,0.00006708171,0.004186956,0.000001427991,0.002040899,0.00400324,0.8440473,0.14427324],"study_design_scores_gemma":[0.0011110243,0.00052483415,0.00006933289,0.0015555387,0.00007405984,0.000002200097,0.018463714,0.00094051566,0.00033113087,0.009222095,0.9669297,0.00077588775],"about_ca_topic_score_codex":0.019906737,"about_ca_topic_score_gemma":0.04073089,"teacher_disagreement_score":0.57698756,"about_ca_system_score_codex":0.003669783,"about_ca_system_score_gemma":0.05217314,"threshold_uncertainty_score":0.99998474},"labels":[],"label_agreement":null},{"id":"W2544651403","doi":"10.1186/s12874-016-0247-7","title":"Why sex and gender matter in implementation research","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Sex and Gender in Healthcare","field":"Medicine","cited_by":408,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"British Columbia Centre of Excellence for Women's Health; Institute of Gender and Health; University of Ottawa; Canadian Institutes of Health Research","funders":"Canadian Institutes of Health Research; Bangor University; Institute of Gender and Health; Ottawa Hospital Research Institute","keywords":"Psychology; Medicine; Computer science","score_opus":0.8680714952997681,"score_gpt":0.7037639602905658,"score_spread":0.16430753500920237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544651403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8925747,0.0016223743,0.016249662,0.08418978,0.00023470016,0.0012137298,0.000007481041,0.00003373888,0.003873788],"genre_scores_gemma":[0.94670045,0.0022561045,0.03776179,0.009110031,0.0010447985,0.00048927846,0.00002054261,0.000062661784,0.0025543247],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97238106,0.02266443,0.0005047311,0.00073132344,0.0024262231,0.0012922303],"domain_scores_gemma":[0.958399,0.039900202,0.000024145984,0.00047110344,0.000418158,0.00078738766],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06868602,0.00011208271,0.00039521704,0.00086435187,0.00013312546,0.000012686975,0.00021782826,0.0003780824,0.0103297755],"category_scores_gemma":[0.02890233,0.000069938906,0.000039643204,0.0005906885,0.00092105014,0.00005779787,0.00034566733,0.0011430077,0.00023988578],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048650056,0.000071049246,0.65248466,0.0005500157,0.000024771865,0.00019022003,0.002069142,1.46414e-8,0.0032393155,0.0020991336,0.05000952,0.28877565],"study_design_scores_gemma":[0.0059762173,0.0009141307,0.83800673,0.00026163465,0.000009474399,0.00047147478,0.013256678,0.0000468961,0.0035777611,0.05769408,0.079593144,0.00019178691],"about_ca_topic_score_codex":0.0017502372,"about_ca_topic_score_gemma":0.0025224038,"teacher_disagreement_score":0.28858387,"about_ca_system_score_codex":0.00020035195,"about_ca_system_score_gemma":0.0013105335,"threshold_uncertainty_score":0.9905749},"labels":[],"label_agreement":null},{"id":"W2551343228","doi":"10.1186/s12874-016-0251-y","title":"Autoregressive transitional ordinal model to test for treatment effect in neurological trials with complex endpoints","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; International Collaboration On Repair Discoveries; Vancouver Coastal Health","funders":"International Foundation for Research in Paraplegia","keywords":"Statistical power; Clinical trial; Computer science; Statistical model; Autoregressive model; Statistical hypothesis testing; Econometrics; Statistics; Medicine; Data mining; Artificial intelligence; Mathematics","score_opus":0.9662030711366986,"score_gpt":0.7484280647731535,"score_spread":0.21777500636354508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551343228","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":[0.043053284,0.000013903906,0.94321865,0.009650578,0.00016268293,0.0032751495,0.00034060926,0.00006549735,0.0002196627],"genre_scores_gemma":[0.025450949,0.000029004199,0.9705542,0.00045765968,0.00056894345,0.0026549841,0.0000048727256,0.00005212547,0.00022729515],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9233817,0.07028244,0.001825442,0.0011593613,0.002011755,0.0013393053],"domain_scores_gemma":[0.12283748,0.8749487,0.0002142223,0.0005492078,0.00038147334,0.001068959],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14105572,0.00038615448,0.00299701,0.00040660118,0.00013482242,0.000023574927,0.00069224404,0.00063032814,0.002093849],"category_scores_gemma":[0.9352511,0.00017412602,0.00036087024,0.00037320034,0.001113224,0.000041630516,0.00018243569,0.00050560135,0.000048129496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.08363462,0.004307845,0.0057154032,0.00074508536,0.00037072788,0.0008572266,0.00040713666,0.00009493718,0.0127278855,0.28947887,0.008981752,0.59267855],"study_design_scores_gemma":[0.014532013,0.016349116,0.0021644824,0.00036367515,0.00009676308,0.000047931127,0.000017453882,0.010794269,0.002374869,0.95259,0.0003889231,0.00028052964],"about_ca_topic_score_codex":0.000019885685,"about_ca_topic_score_gemma":0.00028793194,"teacher_disagreement_score":0.8046662,"about_ca_system_score_codex":0.00019105767,"about_ca_system_score_gemma":0.0012379191,"threshold_uncertainty_score":0.9988184},"labels":[],"label_agreement":null},{"id":"W2553325816","doi":"10.1186/s12874-016-0258-4","title":"Does size really matter? A sensitivity analysis of number of seeds in a respondent-driven sampling study of gay, bisexual and other men who have sex with men in Vancouver, Canada","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","cited_by":44,"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; AIDS Vancouver; Simon Fraser University; University of Victoria","funders":"National Institute on Drug Abuse; Canadian HIV Trials Network, Canadian Institutes of Health Research; Michael Smith Health Research BC; Canadian Institutes of Health Research; Canadian Foundation for AIDS Research","keywords":"Respondent; Psychology; Sampling (signal processing); Homosexuality; Demography; Medicine; Sociology; Political science; Computer science","score_opus":0.2641721911566846,"score_gpt":0.5154612508039202,"score_spread":0.25128905964723564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553325816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994022,0.00001694308,0.0030954345,0.0004652186,0.000022714046,0.00075504754,0.00006477741,0.0000059956024,0.0015518669],"genre_scores_gemma":[0.98924446,0.00003604828,0.007666969,0.000071465285,0.00003682461,0.00004700508,0.0000022469587,0.000034224187,0.0028607268],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9798366,0.015204897,0.0010715082,0.00068795256,0.0024967054,0.00070238166],"domain_scores_gemma":[0.9431008,0.05510606,0.0002700562,0.00067761,0.00041065618,0.00043481338],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023975408,0.0002176257,0.0019184161,0.0010185329,0.000027913524,0.0000033764948,0.00025894414,0.00025632503,0.00056781765],"category_scores_gemma":[0.03195611,0.000116738796,0.000049204187,0.0014927791,0.0008903777,0.000049828355,0.00037030384,0.00060341234,8.3999765e-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":[0.005044404,0.0005745362,0.96704674,0.00032246305,0.0007299885,0.0003121211,0.0106123565,0.00003971238,0.010468242,0.000014118569,0.0006310546,0.004204255],"study_design_scores_gemma":[0.0075264876,0.0012930498,0.8813598,0.0005599479,0.000327695,0.000023059729,0.103906326,0.0030680045,0.0015578242,0.00011720272,0.00007488034,0.00018569859],"about_ca_topic_score_codex":0.66644883,"about_ca_topic_score_gemma":0.98063445,"teacher_disagreement_score":0.31418568,"about_ca_system_score_codex":0.00029000826,"about_ca_system_score_gemma":0.002720606,"threshold_uncertainty_score":0.97619814},"labels":[],"label_agreement":null},{"id":"W2555044821","doi":"10.1186/s12874-016-0263-7","title":"Conducting a large, multi-site survey about patients’ views on broad consent: challenges and solutions","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of Environmental Health Sciences; National Human Genome Research Institute; Canada Excellence Research Chairs, Government of Canada; National Institute of Diabetes and Digestive and Kidney Diseases; Cincinnati Children's Hospital Medical Center; Children's Hospital of Philadelphia","keywords":"MEDLINE; Data science; Informed consent; Medicine; Family medicine; Psychology; Computer science; Alternative medicine; Political science; Pathology; Law","score_opus":0.9812601039631286,"score_gpt":0.7303355044491237,"score_spread":0.2509245995140049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555044821","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":[0.8378078,0.024315795,0.06485447,0.05733924,0.0014327021,0.0033994745,0.0002662339,0.00024292742,0.010341374],"genre_scores_gemma":[0.70400906,0.18366414,0.0907791,0.0038914022,0.0012874807,0.0005377135,0.000101307196,0.00020063033,0.015529171],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9422745,0.048296798,0.001184207,0.0014284551,0.0046471907,0.0021688435],"domain_scores_gemma":[0.3379309,0.6557602,0.0001726652,0.0012263228,0.0026933046,0.0022165794],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.21560094,0.0002651706,0.0010497497,0.0005535752,0.0004297763,0.000022805729,0.00054362003,0.0013673521,0.001344359],"category_scores_gemma":[0.88899153,0.00016342431,0.00016162427,0.00040975335,0.0039055378,0.00007242104,0.0012990372,0.0047337865,0.00058403896],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005259099,0.0042162607,0.29208848,0.0028386742,0.0003785964,0.00032730162,0.002833458,1.5911397e-7,0.0034688215,0.1319536,0.0063961986,0.5502394],"study_design_scores_gemma":[0.016662354,0.003843824,0.9364448,0.0039405017,0.000040755167,0.00007950634,0.00092415215,0.0002505184,0.00063123216,0.016764948,0.019974453,0.00044293917],"about_ca_topic_score_codex":0.0004990442,"about_ca_topic_score_gemma":0.028210655,"teacher_disagreement_score":0.6733906,"about_ca_system_score_codex":0.00018677993,"about_ca_system_score_gemma":0.0032452275,"threshold_uncertainty_score":0.9999291},"labels":[],"label_agreement":null},{"id":"W2560415181","doi":"10.1186/s12874-016-0270-8","title":"Sexual Health questions included in the Health Behaviour in School-aged Children (HBSC) Study: an international methodological pilot investigation","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Adolescent Sexual and Reproductive Health","field":"Health Professions","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","funders":"Medical Research Council; Universitetet i Bergen; University of St Andrews","keywords":"CLARITY; Inclusion (mineral); Psychology; Reproductive health; Relevance (law); Adolescent health; Medical education; Medicine; Social psychology; Nursing; Environmental health; Political science; Population","score_opus":0.8325304163189888,"score_gpt":0.6873145975738479,"score_spread":0.1452158187451409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560415181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88645566,0.00022114685,0.020060824,0.08783162,0.00080554845,0.004426028,0.000028040193,0.00009586989,0.00007524729],"genre_scores_gemma":[0.9599651,0.00055405183,0.027489869,0.0085547585,0.0017189963,0.0011501823,0.00009409359,0.00004533118,0.00042762727],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.675671,0.31580508,0.002244202,0.0014940943,0.0027526526,0.0020329857],"domain_scores_gemma":[0.94821507,0.04820696,0.00051976653,0.0011052865,0.00041367262,0.0015392449],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26164395,0.0003083946,0.0010814572,0.0010606046,0.0012809334,0.00001769161,0.0016411444,0.00047989897,0.000786921],"category_scores_gemma":[0.16523726,0.00016713492,0.000049445553,0.001337415,0.0010836557,0.00030089653,0.00083966745,0.0054475674,0.00014741225],"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":[0.0007962547,0.0021692694,0.97077537,0.00010219431,0.000015072586,0.000020350939,0.009559582,0.000001962515,0.00015418114,0.002582126,0.0016623965,0.012161265],"study_design_scores_gemma":[0.0033104406,0.0049385875,0.96664625,0.00032585073,0.0000028813133,0.000024066308,0.017966457,0.000024297806,0.0000018467427,0.006424927,0.00017722604,0.00015717004],"about_ca_topic_score_codex":0.03056618,"about_ca_topic_score_gemma":0.07375033,"teacher_disagreement_score":0.2725441,"about_ca_system_score_codex":0.0014394803,"about_ca_system_score_gemma":0.010496858,"threshold_uncertainty_score":0.9968469},"labels":[],"label_agreement":null},{"id":"W2582007303","doi":"10.1186/s12874-017-0294-8","title":"Assessing and adjusting for non-response in the Millennium Cohort Family Study","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; National Institute of Environmental Health Sciences; U.S. Department of Veterans Affairs; U.S. Navy; U.S. Department of Defense","keywords":"Representativeness heuristic; Non-response bias; Millennium Cohort Study (United States); Cohort; Population; Logistic regression; Multivariate statistics; Ranking (information retrieval); Medicine; Demography; Affect (linguistics); Cohort study; Psychology; Environmental health; Statistics; Social psychology","score_opus":0.8736591640156701,"score_gpt":0.703767546407381,"score_spread":0.16989161760828908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582007303","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":[0.951917,0.00037254574,0.03819296,0.0059769927,0.00058822247,0.0015038359,0.0000020995149,0.000017861823,0.0014284938],"genre_scores_gemma":[0.95658207,0.00026481415,0.04131047,0.00042100882,0.0005123197,0.0005100261,0.0000011072639,0.000016758475,0.00038143786],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.38666987,0.6076985,0.00067632855,0.0009425288,0.002347854,0.0016649308],"domain_scores_gemma":[0.43036023,0.5683777,0.00012041439,0.0005952561,0.00026206387,0.0002843433],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.778086,0.0001459533,0.0005495761,0.0003072731,0.0035111345,0.00028450473,0.0017243284,0.00049849926,0.00010834756],"category_scores_gemma":[0.88425916,0.0001007235,0.00007771608,0.00026938992,0.0036839312,0.00020000835,0.00045373282,0.0012101314,0.000007845234],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0355019,0.0005587535,0.77907246,0.00008599167,0.00008745859,0.00035917945,0.054380078,0.0000018027464,0.0010964383,0.0017743673,0.002584482,0.124497056],"study_design_scores_gemma":[0.0011107599,0.00040526505,0.9097814,0.000039653525,0.000014871399,0.0000052361243,0.08278587,0.00013575816,0.00001781973,0.0013159037,0.004284298,0.00010319198],"about_ca_topic_score_codex":0.0058285943,"about_ca_topic_score_gemma":0.01384412,"teacher_disagreement_score":0.13070889,"about_ca_system_score_codex":0.00007185625,"about_ca_system_score_gemma":0.002260166,"threshold_uncertainty_score":0.9990275},"labels":[],"label_agreement":null},{"id":"W2582676648","doi":"10.1186/s12874-016-0288-y","title":"Estimating cardiovascular disease incidence from prevalence: a spreadsheet based model","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV-related health complications and treatments","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; University of Ottawa","funders":"Canada Research Chairs","keywords":"Incidence (geometry); Medicine; Population; Cohort; Cohort study; Disease; Demography; Environmental health; Internal medicine","score_opus":0.49030144329853975,"score_gpt":0.5640664026210113,"score_spread":0.07376495932247151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582676648","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":[0.20278768,0.0037055719,0.78431743,0.005625379,0.00017322248,0.0011073109,0.00005661666,0.00008815459,0.0021386226],"genre_scores_gemma":[0.50973374,0.00032736448,0.4883749,0.00027437427,0.000258027,0.00041328205,0.00005046688,0.000028905477,0.0005389614],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912807,0.0042097485,0.0004803034,0.00082263455,0.0024234364,0.0007832132],"domain_scores_gemma":[0.9827711,0.011829354,0.00012499567,0.0028595414,0.000499688,0.0019153197],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0151579045,0.00018372541,0.00067784125,0.00020353725,0.0009628402,0.000046828918,0.0008123509,0.0003254026,0.0009286236],"category_scores_gemma":[0.14344355,0.00014617287,0.00028009005,0.00015234441,0.00094747765,0.000102361955,0.0004099831,0.0010992186,0.00027285612],"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":[0.0044935215,0.0022688264,0.61007535,0.0059784623,0.0017230321,0.0037506465,0.00090279646,0.017433584,0.0004476496,0.0055991295,0.005106057,0.3422209],"study_design_scores_gemma":[0.0021780212,0.00015067111,0.12273841,0.0012198937,0.00025603166,0.000018908568,0.000016990467,0.8647042,0.000038533108,0.008046128,0.00051362935,0.00011856729],"about_ca_topic_score_codex":0.001953457,"about_ca_topic_score_gemma":0.0001213366,"teacher_disagreement_score":0.8472706,"about_ca_system_score_codex":0.00018786652,"about_ca_system_score_gemma":0.004878282,"threshold_uncertainty_score":0.9999847},"labels":[],"label_agreement":null},{"id":"W2587384815","doi":"10.1186/s12874-017-0298-4","title":"Testing a systematic approach to identify and prioritise barriers to successful implementation of a complex healthcare intervention","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","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","funders":"Medical Research Council; Australian Catholic University","keywords":"Psychological intervention; Medicine; Intervention (counseling); Health care; Triage; Multidisciplinary approach; Clinical trial; MEDLINE; Debriefing; Nursing; Medical education; Medical emergency; Pathology","score_opus":0.9465724299522467,"score_gpt":0.8168530896245352,"score_spread":0.12971934032771149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587384815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79570353,0.000048700753,0.17172061,0.023863755,0.00045657804,0.0072982465,0.000077290046,0.00004664981,0.0007846551],"genre_scores_gemma":[0.8330503,0.000011944758,0.16147445,0.0033143964,0.00018034638,0.0018610734,0.0000068086833,0.000020710115,0.000079944126],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94830054,0.045274694,0.0021304586,0.00066511857,0.0022258095,0.001403368],"domain_scores_gemma":[0.9465141,0.04753908,0.0007621311,0.0008463425,0.0014416199,0.0028967068],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.114946656,0.0001474931,0.0007967338,0.00068651803,0.0022823974,0.00005889394,0.0011106736,0.00021772704,0.0006659056],"category_scores_gemma":[0.4753357,0.00013046068,0.000052818064,0.00062787917,0.0004803326,0.0002120331,0.0013375159,0.00080038165,0.00007482263],"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":[0.00029963296,0.00007237383,0.6664708,0.16161096,0.000054790606,0.000014657597,0.07367837,0.0000019591182,0.004719327,0.019455437,0.0074969362,0.066124715],"study_design_scores_gemma":[0.0020448156,0.00066716666,0.8863233,0.0058375583,0.000016620492,0.000018769284,0.10188706,0.0005920692,0.0000820355,0.0017264328,0.0006298097,0.0001743635],"about_ca_topic_score_codex":0.025685733,"about_ca_topic_score_gemma":0.017964229,"teacher_disagreement_score":0.36038902,"about_ca_system_score_codex":0.00032763864,"about_ca_system_score_gemma":0.004163613,"threshold_uncertainty_score":0.99995536},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"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":"W2588268847","doi":"10.1186/s12874-017-0308-6","title":"Generating evidence on a risk-based monitoring approach in the academic setting – lessons learned","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"European Commission","keywords":"Observational study; Medicine; Risk management; Missing data; Population; Risk assessment; Inclusion (mineral); Environmental health; Psychology; Computer science; Business; Finance; Computer security; Pathology","score_opus":0.9224280178717253,"score_gpt":0.7478724834187337,"score_spread":0.17455553445299166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588268847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80455714,0.0026414494,0.11728575,0.06631448,0.0018350601,0.003682578,0.000005998516,0.00012160904,0.0035559419],"genre_scores_gemma":[0.9207014,0.0018776094,0.06820445,0.0013326545,0.004553023,0.0027568648,0.0000039393744,0.00006571634,0.0005043784],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7968291,0.19491966,0.0013632713,0.0009683143,0.0030153503,0.0029043143],"domain_scores_gemma":[0.727107,0.26977557,0.0006844209,0.0015888761,0.0002832088,0.00056093966],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3454523,0.00024316202,0.00075211946,0.00041280634,0.0054270094,0.00004830885,0.003095886,0.0013035074,0.00012484871],"category_scores_gemma":[0.618773,0.00016153786,0.00010416566,0.00044028336,0.0006571471,0.00014407287,0.00059331744,0.018087132,0.00019674267],"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":[0.0006457115,0.00012436608,0.6996591,0.0024056754,0.000023186463,0.00007325754,0.008854446,0.00030864225,0.0016090826,0.0055652387,0.0026000156,0.27813128],"study_design_scores_gemma":[0.009422427,0.002445899,0.5558597,0.026219053,0.000061754414,0.000062775296,0.047980353,0.3264102,0.0009046004,0.012702234,0.016627105,0.0013039117],"about_ca_topic_score_codex":0.0072723166,"about_ca_topic_score_gemma":0.0023719484,"teacher_disagreement_score":0.32610157,"about_ca_system_score_codex":0.00079527346,"about_ca_system_score_gemma":0.010615971,"threshold_uncertainty_score":0.999993},"labels":[],"label_agreement":null},{"id":"W2588671950","doi":"10.1186/s12874-017-0307-7","title":"A comparison of analytic approaches for individual patient data meta-analyses with binary outcomes","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Random effects model; Statistics; Generalized linear mixed model; Sample size determination; Quasi-likelihood; Mathematics; Binary data; Mixed model; Mean squared error; Binary number; Meta-analysis; Medicine; Count data; Poisson distribution","score_opus":0.9984275080037718,"score_gpt":0.8154567280360211,"score_spread":0.18297077996775069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588671950","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":[0.09953835,0.0053690323,0.8829683,0.0063349917,0.0002542182,0.002764364,0.00033059192,0.000008232135,0.0024319445],"genre_scores_gemma":[0.58934027,0.000018478255,0.4086335,0.00009638806,0.00007270503,0.00026730628,0.00007371473,0.000019075864,0.0014785569],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.7699465,0.18206565,0.013399291,0.0030222007,0.030429384,0.0011369332],"domain_scores_gemma":[0.38575205,0.5647737,0.013192633,0.0303937,0.004535305,0.0013526098],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6236474,0.0003907003,0.011549703,0.001086595,0.000644669,0.00065936754,0.014840024,0.00029989946,0.008250999],"category_scores_gemma":[0.8428744,0.00014523946,0.0024149602,0.00097004196,0.0018692546,0.00033265198,0.0033692599,0.0006737989,0.00016301409],"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":[0.0006015023,0.0014552524,0.5250447,0.0009226001,0.0462061,0.00004452833,0.0023129103,0.00045932364,0.000063685715,0.0141151585,0.1475602,0.26121405],"study_design_scores_gemma":[0.0038320315,0.0045941356,0.2696511,0.00019614458,0.052580014,0.000067878675,0.026622994,0.48794326,0.00075599895,0.050596498,0.101833336,0.0013266071],"about_ca_topic_score_codex":0.00021031649,"about_ca_topic_score_gemma":0.0013969021,"teacher_disagreement_score":0.4898019,"about_ca_system_score_codex":0.000020900887,"about_ca_system_score_gemma":0.0011667185,"threshold_uncertainty_score":0.9926556},"labels":[],"label_agreement":null},{"id":"W2591072037","doi":"10.1186/s12874-017-0304-x","title":"Estimation of treatment preference effects in clinical trials when some participants are indifferent to treatment choice","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Preference; Test (biology); Clinical trial; Medicine; Randomized controlled trial; Treatment effect; Psychological intervention; Treatment and control groups; Research design; Psychology; Statistics; Surgery; Psychiatry; Mathematics","score_opus":0.9639534187192589,"score_gpt":0.7552924577096153,"score_spread":0.2086609610096436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591072037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76412773,0.00009900045,0.23221545,0.00075649243,0.00020913465,0.0024079075,0.000013821989,0.00006715124,0.00010329842],"genre_scores_gemma":[0.67490613,0.00044112807,0.32231295,0.000047846577,0.00022746545,0.0017919685,0.000005918428,0.00003105556,0.00023555254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95186496,0.0423804,0.0023575807,0.0008584771,0.0013526909,0.0011859093],"domain_scores_gemma":[0.74146223,0.25478414,0.00092924555,0.0016757511,0.00022389492,0.0009247428],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058668025,0.0003041794,0.002344364,0.00040480483,0.00016297304,0.000040815215,0.00093275384,0.0005840863,0.00020287716],"category_scores_gemma":[0.70189774,0.00020146236,0.00023152994,0.00012549253,0.00071443367,0.00015898277,0.00046849516,0.0005935897,0.000037543607],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010819105,0.002044104,0.04886312,0.0005214944,0.00017512227,0.00007449433,0.0014325066,0.000019554314,0.0009919881,0.04446522,0.00026583878,0.90006465],"study_design_scores_gemma":[0.004697363,0.007891436,0.13237977,0.0013528968,0.00011184705,0.000004259579,0.00014778682,0.0040475414,0.035418414,0.8134112,0.00024562725,0.00029185798],"about_ca_topic_score_codex":0.0010908821,"about_ca_topic_score_gemma":0.005053068,"teacher_disagreement_score":0.89977276,"about_ca_system_score_codex":0.00068712933,"about_ca_system_score_gemma":0.0011642769,"threshold_uncertainty_score":0.9692994},"labels":[],"label_agreement":null},{"id":"W2593623602","doi":"10.1186/s12874-017-0314-8","title":"AIMD - a validated, simplified framework of interventions to promote and integrate evidence into health practices, systems, and policies","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"University of Toronto; McMaster University; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Psychological intervention; Medicine; MEDLINE; Computer science; Process management; Data science; Business; Nursing; Political science","score_opus":0.97671003119586,"score_gpt":0.851628278677212,"score_spread":0.12508175251864795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593623602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41747344,0.0015457501,0.31376404,0.26231351,0.0007983667,0.0037516074,0.00005238214,0.000053732936,0.0002471877],"genre_scores_gemma":[0.580717,0.0046268813,0.40166828,0.010111535,0.00062299386,0.001279735,0.000005237023,0.000043941047,0.0009243846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9400679,0.054140743,0.0018718865,0.0007211114,0.001723868,0.0014744934],"domain_scores_gemma":[0.82213086,0.17050411,0.002169102,0.001393972,0.0012773564,0.002524584],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14845897,0.00016373875,0.0008109399,0.0005747118,0.0025104706,0.000099564524,0.001101876,0.00038241484,0.00031292246],"category_scores_gemma":[0.75646263,0.00012790329,0.000046164587,0.0004949591,0.001572738,0.00040355374,0.0018560215,0.0020316995,0.00006825571],"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":[0.0017050751,0.0002813677,0.17714462,0.068675764,0.00014350716,0.00004370869,0.19892722,0.0000044612084,0.003298297,0.28927222,0.06982671,0.19067705],"study_design_scores_gemma":[0.0056571774,0.009115182,0.3857282,0.085646145,0.000102746264,0.00021221084,0.14935398,0.0029746299,0.00051307835,0.10504068,0.2544275,0.0012284808],"about_ca_topic_score_codex":0.06450381,"about_ca_topic_score_gemma":0.016428,"teacher_disagreement_score":0.6080037,"about_ca_system_score_codex":0.0002451353,"about_ca_system_score_gemma":0.0067677815,"threshold_uncertainty_score":0.9988629},"labels":[],"label_agreement":null},{"id":"W2594513694","doi":"10.1186/s12874-017-0309-5","title":"Why sample selection matters in exploratory factor analysis: implications for the 12-item World Health Organization Disability Assessment Schedule 2.0","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute on Aging","keywords":"Exploratory factor analysis; Stratified sampling; International Classification of Functioning, Disability and Health; Schedule; Sample (material); Psychology; Affect (linguistics); Gerontology; Sampling (signal processing); Statistics; Medicine; Mathematics; Clinical psychology; Psychometrics; Physical therapy; Computer science","score_opus":0.8952002098229414,"score_gpt":0.6886173406428713,"score_spread":0.20658286918007007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594513694","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":[0.043928497,0.0001221278,0.86229,0.09236051,0.0004085026,0.0007767281,0.00003298229,0.000037315167,0.000043291784],"genre_scores_gemma":[0.39885545,0.00014289391,0.59731805,0.0027035302,0.00032702956,0.00049504085,0.000025433246,0.000024625573,0.000107915854],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96756524,0.02697399,0.0012786805,0.0010549278,0.002231528,0.000895653],"domain_scores_gemma":[0.3242561,0.6713426,0.0007274147,0.0020344001,0.0011380413,0.000501398],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16672559,0.0001662518,0.00080007105,0.0012604949,0.0019192988,0.000441861,0.0026915872,0.0001908134,0.0012199141],"category_scores_gemma":[0.8623073,0.00010366888,0.0001883624,0.0063565844,0.001116478,0.00029472538,0.00068316894,0.00088043645,0.000009187157],"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":[0.000035686546,0.000099276775,0.8854572,0.000021616414,0.000057563175,1.879251e-7,0.00014737825,0.00009489119,0.0000799058,0.0035401555,0.00602971,0.10443642],"study_design_scores_gemma":[0.0003733531,0.00009651769,0.9470139,0.0000142116705,0.000017458266,0.0000014458669,0.0010898067,0.010241698,0.000037250382,0.035193786,0.0058271005,0.000093481154],"about_ca_topic_score_codex":0.002696781,"about_ca_topic_score_gemma":0.036941618,"teacher_disagreement_score":0.69558173,"about_ca_system_score_codex":0.00044936535,"about_ca_system_score_gemma":0.0014027251,"threshold_uncertainty_score":0.9996931},"labels":[],"label_agreement":null},{"id":"W2596380178","doi":"10.1186/s12874-017-0324-6","title":"Implementation of clinical research trials using web-based and mobile devices: challenges and solutions","year":2017,"lang":"en","type":"editorial","venue":"BMC Medical Research Methodology","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":31,"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 Health Research Institute; London Health Sciences Centre; Western University","funders":"Children's Health Foundation; Academic Medical Organization of Southwestern Ontario","keywords":"Computer science; Clinical trial; MEDLINE; Data science; World Wide Web; Medicine; Political science","score_opus":0.9403252626784555,"score_gpt":0.8027009193777168,"score_spread":0.1376243433007387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596380178","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":[0.01746857,0.16208187,0.016201789,0.012130673,0.7436944,0.043216366,0.0019501004,0.00022571173,0.003030486],"genre_scores_gemma":[0.0017838521,0.33773834,0.050359037,0.00021551819,0.58125347,0.027638173,0.00043147546,0.00015101877,0.0004290957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.69712055,0.2845234,0.0066783135,0.0020751508,0.0060807187,0.0035219043],"domain_scores_gemma":[0.33504638,0.6536125,0.0023431443,0.0017035775,0.0046026735,0.0026917509],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","research_integrity"],"category_scores_codex":[0.543768,0.0003568859,0.0033692603,0.0012605735,0.003562054,0.000025759771,0.0011105025,0.0051204814,0.001043296],"category_scores_gemma":[0.5562852,0.00029519317,0.0002162366,0.0003536643,0.0037944037,0.000099746285,0.0014312719,0.010877871,0.000042602904],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083797734,0.00017399876,0.001968818,0.013175076,0.00007629636,0.0000073259853,0.0006276139,3.4467539e-7,0.000021869724,0.0036911962,0.57932836,0.4000911],"study_design_scores_gemma":[0.0049992395,0.00094623654,0.0025031327,0.0016663094,0.00008287901,0.0000016770688,0.004677636,0.00052422925,0.0000030167396,0.0030059158,0.9814068,0.00018294143],"about_ca_topic_score_codex":0.0075076628,"about_ca_topic_score_gemma":0.037390515,"teacher_disagreement_score":0.40207842,"about_ca_system_score_codex":0.00030376925,"about_ca_system_score_gemma":0.07766437,"threshold_uncertainty_score":0.99995},"labels":[],"label_agreement":null},{"id":"W2597390287","doi":"10.1186/s12874-017-0320-x","title":"Assignment of adverse event indexing terms in randomized clinical trials involving spinal manipulative therapy: an audit of records in MEDLINE and EMBASE databases","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"University of Calgary","funders":"","keywords":"MEDLINE; Medicine; Adverse effect; Randomized controlled trial; Internal medicine","score_opus":0.9885935331056589,"score_gpt":0.791544892742086,"score_spread":0.19704864036357295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597390287","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":[0.80289125,0.0017227568,0.19174287,0.00092551514,0.0003228252,0.0021129062,0.000012876575,0.0000015206535,0.00026746525],"genre_scores_gemma":[0.9029592,0.0024317186,0.09392181,0.00008561484,0.00018871119,0.00016403578,0.0000080976615,0.000011907676,0.0002288631],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.16650699,0.79358053,0.026813185,0.001670257,0.010757922,0.0006711388],"domain_scores_gemma":[0.10920113,0.86627257,0.015973704,0.006057354,0.001503757,0.0009914924],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9419001,0.00024909468,0.0118724955,0.0012609558,0.00011847882,0.00006256962,0.0024005778,0.0002859705,0.0047366447],"category_scores_gemma":[0.96474266,0.000117254785,0.0012915813,0.00059368275,0.0019254151,0.00029871985,0.000900153,0.00090345397,0.000012877726],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0397826,0.0008474304,0.5183582,0.0003847133,0.00041333452,0.0001236101,0.0012462282,0.000044197262,0.0006280525,0.0069696032,0.00051749777,0.4306846],"study_design_scores_gemma":[0.16155924,0.002090133,0.5272208,0.003594432,0.0003033739,0.000030493171,0.0081283655,0.19317569,0.00083883735,0.10069371,0.0017825579,0.00058237556],"about_ca_topic_score_codex":0.0015479937,"about_ca_topic_score_gemma":0.0060953666,"teacher_disagreement_score":0.43010223,"about_ca_system_score_codex":0.00005069832,"about_ca_system_score_gemma":0.0010150454,"threshold_uncertainty_score":0.99617314},"labels":[],"label_agreement":null},{"id":"W2600652237","doi":"10.1186/s12874-017-0316-6","title":"Methods for conceptualising ‘visual ability’ as a measurable construct in children with cerebral palsy","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cerebral Palsy and Movement Disorders","field":"Medicine","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":"McMaster University","funders":"","keywords":"Construct (python library); CLARITY; Thematic analysis; Psychology; Cerebral palsy; International Classification of Functioning, Disability and Health; Cognitive psychology; Construct validity; Developmental psychology; Applied psychology; Computer science; Psychometrics; Qualitative research; Rehabilitation","score_opus":0.3835584081482237,"score_gpt":0.5785798234759478,"score_spread":0.19502141532772416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600652237","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":[0.85204756,0.0007449779,0.13498566,0.004277794,0.00020881534,0.0027894732,0.000008617022,0.000052458112,0.0048846737],"genre_scores_gemma":[0.49776205,0.00014715095,0.49958873,0.0010492803,0.0003119739,0.0004168475,0.000041880554,0.00005472022,0.0006273763],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98598033,0.009750168,0.0006702897,0.0009100872,0.0013666258,0.0013224804],"domain_scores_gemma":[0.97642964,0.021050248,0.00019550712,0.0009791087,0.0004842859,0.0008611906],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045365658,0.00026808755,0.0011452433,0.0003477122,0.00054640905,0.00007708003,0.00065488124,0.0004836285,0.0017254985],"category_scores_gemma":[0.19449359,0.00019704676,0.00019053392,0.00025938734,0.0035729152,0.00015935145,0.00033668225,0.0012511755,0.000020791957],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035354064,0.00035948073,0.700361,0.00034117934,0.00025553358,0.000027148146,0.00051981845,0.0000017298939,0.0021971741,0.015023798,0.0003958232,0.27698192],"study_design_scores_gemma":[0.04410071,0.0071902573,0.849066,0.001335167,0.00025661368,0.000869513,0.0058629,0.0024842562,0.01461573,0.063612364,0.009649676,0.0009567948],"about_ca_topic_score_codex":0.0033753226,"about_ca_topic_score_gemma":0.0023304892,"teacher_disagreement_score":0.36460307,"about_ca_system_score_codex":0.00014146986,"about_ca_system_score_gemma":0.0029288677,"threshold_uncertainty_score":0.99918705},"labels":[],"label_agreement":null},{"id":"W2602088386","doi":"10.1186/s12874-017-0325-5","title":"Evaluation of AMSTAR to assess the methodological quality of systematic reviews in overviews of reviews of healthcare interventions","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health; University of Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Systematic review; Medicine; Psychological intervention; Health care; Cochrane Library; MEDLINE; Quality (philosophy); Scope (computer science); Medical physics; Meta-analysis; Management science; Family medicine; Computer science; Nursing; Pathology","score_opus":0.9987260750253654,"score_gpt":0.8550359325589857,"score_spread":0.14369014246637968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602088386","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":[0.13095295,0.13407668,0.7039677,0.005964598,0.00070469896,0.02201287,0.000054721026,0.0000027525261,0.0022630477],"genre_scores_gemma":[0.49244577,0.013471777,0.490611,0.00021401813,0.000117725256,0.0025269103,0.000007660141,0.00002343517,0.0005817219],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.013805374,0.92351735,0.038006965,0.0011123137,0.023022763,0.0005352326],"domain_scores_gemma":[0.06738887,0.8304491,0.055828515,0.022038803,0.023418823,0.00087589],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9754147,0.0002844338,0.016401842,0.000949093,0.00014843958,0.000057932888,0.0075327912,0.0003422061,0.0073953317],"category_scores_gemma":[0.98721623,0.000113225986,0.0041161487,0.0020714318,0.0011776068,0.00013446315,0.0012509106,0.0007301748,0.000105641986],"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":[0.00031249344,0.0011728697,0.05235121,0.3717307,0.00066557276,0.000003164865,0.0055845273,0.00007123866,0.0041395877,0.093195215,0.009012229,0.4617612],"study_design_scores_gemma":[0.0036045955,0.002866029,0.49542144,0.14630869,0.003330969,0.00003342278,0.014605265,0.01413745,0.0028298686,0.29558793,0.020363137,0.0009112282],"about_ca_topic_score_codex":0.0014024558,"about_ca_topic_score_gemma":0.008096982,"teacher_disagreement_score":0.46085,"about_ca_system_score_codex":0.00009946433,"about_ca_system_score_gemma":0.0011263019,"threshold_uncertainty_score":0.9982007},"labels":[],"label_agreement":null},{"id":"W2605614499","doi":"10.1186/s12874-017-0339-z","title":"Does the association between adherence to statin medications and mortality depend on measurement approach? A retrospective cohort study","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Medication Adherence and Compliance","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Royal University Hospital; University of Manitoba; University of Saskatchewan; University of Alberta; University of Waterloo","funders":"College of Pharmacy and Nutrition, University of Saskatchewan; Pfizer Canada; Ministry of Health, Saskatchewan; Canadian Institutes of Health Research; AstraZeneca Canada; Merck Canada; Fondation pour la Recherche Médicale; AstraZeneca; Pfizer","keywords":"Medicine; Retrospective cohort study; Hydroxymethylglutaryl-CoA Reductase Inhibitors; Medication adherence; Statin; Cohort; Association (psychology); Cohort study; MEDLINE; Internal medicine; Emergency medicine; Psychology","score_opus":0.6887183712591032,"score_gpt":0.5895127158553388,"score_spread":0.09920565540376436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605614499","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9026905,0.00006858668,0.06657105,0.016255945,0.0003408874,0.004642147,0.000019474634,0.000053531112,0.009357901],"genre_scores_gemma":[0.9880514,0.00011845303,0.0075205974,0.00059278705,0.00048226034,0.0014582949,0.000010623015,0.000015027296,0.0017505354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9833096,0.007977376,0.00058771105,0.0008539067,0.006645825,0.0006255502],"domain_scores_gemma":[0.98516506,0.0103995735,0.00036478054,0.0017335481,0.0013129393,0.0010240779],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07538567,0.00016987369,0.00067633134,0.00014530643,0.0009192484,0.000080197824,0.000889713,0.00023013094,0.0007640359],"category_scores_gemma":[0.23056301,0.0000873979,0.000058985544,0.00026363932,0.0005967,0.00006225353,0.000378605,0.0013719155,0.000182981],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010005932,0.00029765497,0.9827265,0.000056344597,0.00028620494,0.000007885978,0.0006356323,1.738952e-7,0.00004422851,0.0010354528,0.0024585822,0.012351242],"study_design_scores_gemma":[0.0010446182,0.0010461364,0.9927423,0.000131622,0.0001236126,0.0000032844657,0.0015567106,0.0001456927,0.00009016986,0.002292369,0.00072866865,0.000094832874],"about_ca_topic_score_codex":0.0018816614,"about_ca_topic_score_gemma":0.0018249834,"teacher_disagreement_score":0.15517734,"about_ca_system_score_codex":0.00048073754,"about_ca_system_score_gemma":0.0014456392,"threshold_uncertainty_score":0.952085},"labels":[],"label_agreement":null},{"id":"W2607509261","doi":"10.1186/s12874-017-0347-z","title":"Grey literature in systematic reviews: a cross-sectional study of the contribution of non-English reports, unpublished studies and dissertations to the results of meta-analyses in child-relevant reviews","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":319,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Grey literature; Meta-analysis; Cross-sectional study; Systematic review; Medicine; MEDLINE; Psychology; Family medicine; Political science; Pathology","score_opus":0.9431944957606768,"score_gpt":0.7244683342400873,"score_spread":0.21872616152058955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607509261","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":[0.86920947,0.10886038,0.0031331999,0.002389226,0.0007122696,0.015341349,0.000032374766,0.000002070721,0.00031965988],"genre_scores_gemma":[0.9923389,0.002112809,0.0036823342,0.000042333413,0.00006489961,0.0011694739,0.000004627215,0.0000071500403,0.00057749765],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.35844615,0.5684512,0.050033797,0.0027380725,0.019412845,0.00091790786],"domain_scores_gemma":[0.34762236,0.5470673,0.04659528,0.02315849,0.034804415,0.00075213506],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.75531304,0.00029682257,0.010561478,0.0009261007,0.00038634945,0.00043735537,0.0032701222,0.00020493008,0.00016999041],"category_scores_gemma":[0.9816445,0.000091949485,0.0016774657,0.003349427,0.000793328,0.00031872204,0.00090970023,0.0008418006,0.000007334212],"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":[0.000594053,0.0012882062,0.89495397,0.028281344,0.006011262,0.00006996554,0.05259082,0.00030435968,0.0003474337,0.0030037125,0.0106073255,0.0019475565],"study_design_scores_gemma":[0.0011122075,0.00032132704,0.972266,0.007419392,0.001658172,0.00004209316,0.01096758,0.00058032083,0.000058442794,0.0041385083,0.0012831828,0.00015277459],"about_ca_topic_score_codex":0.00055667834,"about_ca_topic_score_gemma":0.01891867,"teacher_disagreement_score":0.2263315,"about_ca_system_score_codex":0.00004934258,"about_ca_system_score_gemma":0.00032464787,"threshold_uncertainty_score":0.9989835},"labels":[],"label_agreement":null},{"id":"W2608508808","doi":"10.1186/s12874-017-0349-x","title":"Assessing the complexity of interventions within systematic reviews: development, content and use of a new tool (iCAT_SR)","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":152,"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; Ottawa Hospital; Institute of Population and Public Health; Bruyère; University of Ottawa","funders":"South African Medical Research Council; National Institute for Health and Care Research","keywords":"Psychological intervention; Systematic review; Intervention (counseling); Flexibility (engineering); Computer science; Management science; Psychology; MEDLINE; Medicine; Nursing; Mathematics; Engineering","score_opus":0.9971246787546161,"score_gpt":0.8511525892659478,"score_spread":0.14597208948866824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2608508808","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47809297,0.00064580824,0.48998153,0.023718625,0.00061535515,0.0066023218,0.000014236422,0.000020871674,0.00030828983],"genre_scores_gemma":[0.2768309,0.00063160993,0.7154071,0.0032082833,0.00019879761,0.0011586078,0.000004646263,0.000024517218,0.0025355308],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.9135731,0.08020401,0.00349,0.00034909276,0.001614944,0.0007688493],"domain_scores_gemma":[0.76214695,0.23052137,0.0034207858,0.0017048488,0.0013113323,0.00089469284],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.18585256,0.00010825566,0.0010041299,0.00020739634,0.0016033599,0.000044598353,0.0010323068,0.00016932015,0.00077009044],"category_scores_gemma":[0.7133734,0.000062291045,0.000093073184,0.0002332409,0.0031428798,0.0002959646,0.0010377615,0.0009691423,0.00002976713],"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":[0.00024553903,0.00025693368,0.21049984,0.40505308,0.00022709927,0.000011634129,0.096295506,7.089601e-7,0.0029265676,0.21825223,0.025123745,0.04110713],"study_design_scores_gemma":[0.0033743603,0.00036694622,0.8381069,0.08701999,0.00009147308,0.000033976852,0.033244863,0.001114809,0.00059798965,0.015035998,0.020708805,0.0003039366],"about_ca_topic_score_codex":0.004516892,"about_ca_topic_score_gemma":0.0079426225,"teacher_disagreement_score":0.627607,"about_ca_system_score_codex":0.000109874076,"about_ca_system_score_gemma":0.0056491024,"threshold_uncertainty_score":0.99998796},"labels":[],"label_agreement":null},{"id":"W2609185034","doi":"10.1186/s12874-017-0338-0","title":"Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":491,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"University of Oxford; Cancer Research UK","keywords":"Covariate; Propensity score matching; Confounding; Statistics; Residual; Matching (statistics); Logistic regression; Regression; Mathematics; Regression analysis; Econometrics; Medicine","score_opus":0.8896096151371321,"score_gpt":0.6436425630183503,"score_spread":0.24596705211878178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609185034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39532194,0.0001911004,0.6014486,0.0008138763,0.00010317587,0.0011657444,0.0000043447076,0.00010862676,0.0008426167],"genre_scores_gemma":[0.37699646,0.00012543866,0.62187684,0.00008545961,0.00020854383,0.0005257433,0.000005235831,0.00003314762,0.00014314277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930576,0.0028071294,0.00078562397,0.000777531,0.0014094921,0.0011625884],"domain_scores_gemma":[0.9699904,0.027565664,0.0003175496,0.0013668399,0.0003975896,0.0003619612],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042841017,0.00023788527,0.0011410471,0.00057748234,0.00053838396,0.00011859877,0.0012160272,0.00042111467,0.00012745187],"category_scores_gemma":[0.10085806,0.00019675477,0.00016239504,0.00034404694,0.0009582182,0.00026173465,0.0010800585,0.0014114397,0.0000053518006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037872123,0.0005952665,0.14929408,0.0022556984,0.0007084965,0.0005073908,0.0026770516,0.00015959605,0.013009514,0.8007784,0.0020105364,0.024216767],"study_design_scores_gemma":[0.0020142405,0.00020917128,0.030842185,0.0006806706,0.00010476349,0.000029077473,0.0004129297,0.0018470479,0.012631017,0.9508296,0.00009583295,0.00030343974],"about_ca_topic_score_codex":0.00079586287,"about_ca_topic_score_gemma":0.012711878,"teacher_disagreement_score":0.15005122,"about_ca_system_score_codex":0.00031799285,"about_ca_system_score_gemma":0.00087638944,"threshold_uncertainty_score":0.9855966},"labels":[],"label_agreement":null},{"id":"W2609725774","doi":"10.1186/s12874-017-0352-2","title":"Measurement properties of the Danish version of the Awareness and Beliefs about Cancer (ABC) measure","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":7,"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":"TrygFonden; Sundhedsstyrelsen; Aarhus Universitet; Novo Nordisk; Novo Nordisk Fonden; Kræftens Bekæmpelse","keywords":"Danish; Measure (data warehouse); MEDLINE; Medicine; Psychology; Family medicine; Computer science; Data mining; Political science","score_opus":0.6392947405004253,"score_gpt":0.5070475449315945,"score_spread":0.1322471955688308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609725774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.968436,0.016152214,0.00072703115,0.011156623,0.0014025123,0.0007744921,0.000011588357,0.0000097838865,0.0013297588],"genre_scores_gemma":[0.9979375,0.0010708395,0.00015940145,0.00016915317,0.00022348468,0.00007039974,2.7439538e-7,0.000013915736,0.00035504554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99073553,0.0048745135,0.0003287758,0.00029773466,0.0033923786,0.00037109206],"domain_scores_gemma":[0.9963153,0.0009499514,0.00018049589,0.001102251,0.0012260367,0.00022594134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018657863,0.00011391005,0.0004810138,0.00006020841,0.00052607356,0.00001380528,0.0008868577,0.0002400815,0.00014406351],"category_scores_gemma":[0.05482202,0.000053709315,0.0001416159,0.00015737706,0.0027074094,0.00003758402,0.0008423707,0.0007017148,0.0000011326686],"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":[0.0026947812,0.00023533826,0.7302608,0.005548808,0.00028705227,0.000009864899,0.005214519,0.0000029395808,0.14904039,0.0013780426,0.0026610768,0.10266638],"study_design_scores_gemma":[0.002284876,0.00028092114,0.76846975,0.006855461,0.00011908614,0.000025577388,0.0019094466,0.00008950143,0.21221867,0.00043264573,0.007192767,0.00012127982],"about_ca_topic_score_codex":0.016403165,"about_ca_topic_score_gemma":0.0387264,"teacher_disagreement_score":0.1025451,"about_ca_system_score_codex":0.00012115343,"about_ca_system_score_gemma":0.0035690696,"threshold_uncertainty_score":0.99755627},"labels":[],"label_agreement":null},{"id":"W2622299066","doi":"10.1186/s12874-017-0361-1","title":"Limitations of pulmonary embolism ICD-10 codes in emergency department administrative data: let the buyer beware","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Venous Thromboembolism Diagnosis and Management","field":"Medicine","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; Alberta Health Services; Alberta Health; University of Calgary","funders":"Alberta Innovates; Alberta Innovates - Health Solutions","keywords":"Medical diagnosis; Medicine; Diagnosis code; Pulmonary embolism; Coding (social sciences); ICD-10; Emergency department; Medical record; False positive paradox; Current Procedural Terminology; Ambulatory; Ambulatory care; Health care; Emergency medicine; Medical emergency; Statistics; Computer science; Population; Surgery; Psychiatry; Artificial intelligence","score_opus":0.762252205952658,"score_gpt":0.5818989053351912,"score_spread":0.1803533006174668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2622299066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41319773,0.033566404,0.026620265,0.3797018,0.002848068,0.011294693,0.00063836994,0.00013250412,0.13200015],"genre_scores_gemma":[0.89172816,0.08637933,0.01595372,0.001076662,0.0006347731,0.0008423429,0.0004204582,0.000043233544,0.0029213477],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99144226,0.0048245303,0.00073979597,0.00059399277,0.0017226085,0.0006768306],"domain_scores_gemma":[0.9810831,0.0154613415,0.00024450742,0.0023472067,0.0004383243,0.00042549605],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02091313,0.00016889586,0.00084044796,0.0002065142,0.00039765026,0.000018610228,0.0016153434,0.00020395427,0.0026377395],"category_scores_gemma":[0.11655068,0.00011093744,0.00010508409,0.00023529191,0.001207968,0.00012360355,0.0014800243,0.0007485755,0.00006570301],"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":[0.0016726861,0.008115875,0.0493613,0.004712359,0.0012095799,0.0018689339,0.003356218,0.00001179667,0.0011747692,0.072075896,0.508701,0.34773958],"study_design_scores_gemma":[0.0016119246,0.0010121466,0.85378635,0.0011940754,0.0002627181,0.000067921625,0.003656528,0.0010881682,0.00054444233,0.0071607763,0.1293735,0.00024142399],"about_ca_topic_score_codex":0.00095346244,"about_ca_topic_score_gemma":0.006609844,"teacher_disagreement_score":0.80442506,"about_ca_system_score_codex":0.00006017667,"about_ca_system_score_gemma":0.0013307943,"threshold_uncertainty_score":0.99827397},"labels":[],"label_agreement":null},{"id":"W2734881695","doi":"10.1186/s12874-017-0388-3","title":"Protocol adherence for continuously titrated interventions in randomized trials: an overview of the current methodology and case study","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Medication Adherence and Compliance","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":"Kingston General Hospital; Centre Hospitalier Universitaire de Sherbrooke; The Quebec Population Health Research Network; McMaster University; University of Toronto; Western University; Université de Sherbrooke; Sunnybrook Health Science Centre; St. Michael's Hospital; Health Sciences Centre; Ottawa Hospital; University of Ottawa; Université Laval","funders":"","keywords":"Protocol (science); Psychological intervention; Randomized controlled trial; Medicine; Current (fluid); Research design; Alternative medicine; Nursing; Surgery; Statistics","score_opus":0.9626901659501493,"score_gpt":0.7572651492364603,"score_spread":0.20542501671368907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734881695","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29478112,0.0038936306,0.3289272,0.004406795,0.0010253242,0.36638564,0.000023150202,0.000047656806,0.0005094945],"genre_scores_gemma":[0.30738157,0.0009725611,0.14908195,0.00034381764,0.0005661746,0.53981507,0.000012636235,0.00005699352,0.0017692439],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.89197975,0.103971966,0.0019869553,0.0006090572,0.00095925195,0.000493033],"domain_scores_gemma":[0.84297705,0.15159407,0.0014663307,0.001982051,0.0012781917,0.0007023174],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23931871,0.00016691422,0.0024553242,0.0002421565,0.00027709315,0.00003107408,0.00076680764,0.00020999683,0.00096936425],"category_scores_gemma":[0.6090979,0.00009465332,0.0003938578,0.00024442165,0.0021399304,0.00007988581,0.00037697275,0.0010395689,0.000006979318],"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":[0.061261818,0.003019097,0.022234954,0.0053678923,0.0002797505,0.00031416188,0.0020380304,3.9482345e-7,0.00046403432,0.009123302,0.0012444681,0.89465207],"study_design_scores_gemma":[0.8047434,0.0119747855,0.05422387,0.013021171,0.0011288254,0.0025877103,0.015187348,0.012349002,0.0013690311,0.074732386,0.008015331,0.000667131],"about_ca_topic_score_codex":0.0017081442,"about_ca_topic_score_gemma":0.004515179,"teacher_disagreement_score":0.893985,"about_ca_system_score_codex":0.00003412724,"about_ca_system_score_gemma":0.0018639299,"threshold_uncertainty_score":0.9999439},"labels":[],"label_agreement":null},{"id":"W2750914869","doi":"10.1186/s12874-017-0419-0","title":"Addressing data privacy in matched studies via virtual pooling","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"National Institute of Environmental Health Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Pooling; Computer science; Covariate; Logistic regression; Confidentiality; Data mining; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.8676991431862193,"score_gpt":0.6308222743262581,"score_spread":0.23687686885996118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750914869","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03252193,0.0017271327,0.90996045,0.053912073,0.0009571293,0.000311491,0.000009016459,0.0003254459,0.0002753606],"genre_scores_gemma":[0.10168389,0.0013410037,0.8963816,0.00018624344,0.000256065,0.00005943116,0.0000129439395,0.000022785618,0.000056014185],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98249453,0.010586837,0.0008018701,0.0018029533,0.0026573131,0.0016564945],"domain_scores_gemma":[0.71629286,0.17032696,0.00094228523,0.11000319,0.001106106,0.0013285773],"candidate_categories":["metaresearch","sts","open_science","research_integrity"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.08131346,0.00024882457,0.0008763253,0.0006657876,0.0008399299,0.00038680894,0.14064087,0.00056592416,0.000073475676],"category_scores_gemma":[0.9277346,0.0002093485,0.00005328181,0.0006032855,0.002872147,0.0015608362,0.48694107,0.0025238178,0.000104484396],"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":[0.00011562694,0.00020341521,0.008910061,0.00029300287,0.00012227903,0.0015884505,0.0009293758,0.0000047678514,0.0019825462,0.013990864,0.07740474,0.8944549],"study_design_scores_gemma":[0.001412585,0.00020384972,0.009789869,0.00073073193,0.000007392582,0.00015962795,0.0007995842,0.3324952,0.0023317302,0.6491744,0.0024833863,0.0004116663],"about_ca_topic_score_codex":0.00064596895,"about_ca_topic_score_gemma":0.0009874646,"teacher_disagreement_score":0.8940432,"about_ca_system_score_codex":0.00019686866,"about_ca_system_score_gemma":0.0013717732,"threshold_uncertainty_score":0.99984145},"labels":[],"label_agreement":null},{"id":"W2753693494","doi":"10.1186/s12874-017-0418-1","title":"Longitudinal studies that use data collected as part of usual care risk reporting biased results: a systematic review","year":2017,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University Health Network; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Medicine; MEDLINE; Reporting bias; Systematic review; Publication bias; Longitudinal data; Family medicine; Meta-analysis; Demography","score_opus":0.9850133789418091,"score_gpt":0.7701827484072934,"score_spread":0.21483063053451568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753693494","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":[0.000027626453,0.9912514,0.0006732999,0.00020104676,0.0012868559,0.00514395,0.00073538075,0.00008135826,0.0005990929],"genre_scores_gemma":[0.00000190603,0.982372,0.013262522,0.00005449283,0.00059897156,0.0008028769,0.00048908795,0.00006622514,0.0023519553],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.19648422,0.78586406,0.007530483,0.0024139807,0.0057676104,0.0019396502],"domain_scores_gemma":[0.06705299,0.9079273,0.013844178,0.006489236,0.0035538601,0.0011324509],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science","research_integrity"],"consensus_categories":["metaresearch","sts","research_integrity"],"category_scores_codex":[0.78832954,0.0007123377,0.013067013,0.0009603606,0.0022659374,0.00011636317,0.0062339758,0.0022047719,0.00036754654],"category_scores_gemma":[0.9969174,0.0004820732,0.001057117,0.0019356867,0.0074991784,0.00035838177,0.0032200485,0.0039727506,0.00007945992],"study_design_candidate":"systematic_review","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":[0.001209666,0.000082046805,0.00022337443,0.84930706,0.0015565683,0.00080609496,0.0024056644,3.3764906e-8,2.2542887e-8,0.00014641245,0.009033426,0.13522963],"study_design_scores_gemma":[0.0003668913,0.00020512889,0.00006469547,0.48435763,0.0028918665,0.00010463336,0.003660135,0.000001229486,4.6586464e-7,0.0001131759,0.5078901,0.00034406662],"about_ca_topic_score_codex":0.0055083884,"about_ca_topic_score_gemma":0.028743727,"teacher_disagreement_score":0.49885666,"about_ca_system_score_codex":0.00047784502,"about_ca_system_score_gemma":0.027492585,"threshold_uncertainty_score":0.9997631},"labels":[],"label_agreement":null},{"id":"W2755473612","doi":"10.1186/s12874-017-0421-6","title":"Systematic review of statistical approaches to quantify, or correct for, measurement error in a continuous exposure in nutritional epidemiology","year":2017,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":87,"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":"Epidemiology; MEDLINE; Medicine; Computer science; Data science; Statistics; Pathology; Biology; Mathematics","score_opus":0.9541278448169002,"score_gpt":0.66261791631817,"score_spread":0.29150992849873014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755473612","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":[9.434182e-7,0.9571881,0.028685244,0.002327091,0.00023789682,0.011151263,0.00024408057,0.000009957984,0.00015540632],"genre_scores_gemma":[0.000003467776,0.90503067,0.084521145,0.00040685915,0.00025579263,0.009367694,0.00025261854,0.000042127504,0.0001196549],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.94940823,0.041017804,0.004518155,0.0011360382,0.0026042578,0.0013154956],"domain_scores_gemma":[0.7921012,0.20436083,0.00082138233,0.0009447435,0.0009518136,0.0008200405],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15226403,0.00045259032,0.012881316,0.00085133023,0.000098364646,0.0000065461245,0.00077682047,0.00092311704,0.00034946183],"category_scores_gemma":[0.7485296,0.00028133258,0.0007097643,0.00056155433,0.00090350315,0.000020190399,0.00040965687,0.0016624425,0.000029166316],"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":[0.0009444431,0.0006750856,0.00010642397,0.92363054,0.0002625498,0.0002044565,0.000016759417,3.8820595e-8,8.5030635e-8,0.008878393,0.0074800756,0.057801165],"study_design_scores_gemma":[0.0018244875,0.001797452,0.00015551022,0.855256,0.00058924593,0.00036439596,0.000113401176,0.000016594757,1.3207374e-7,0.0018589043,0.13780677,0.00021709784],"about_ca_topic_score_codex":0.00022441988,"about_ca_topic_score_gemma":0.0015574396,"teacher_disagreement_score":0.5962656,"about_ca_system_score_codex":0.00060071767,"about_ca_system_score_gemma":0.005109105,"threshold_uncertainty_score":0.9999639},"labels":[],"label_agreement":null},{"id":"W2772738494","doi":"10.1186/s12874-018-0477-y","title":"Correction to: On the use of the outcome variable “small for gestational age” when gestational age is a potential mediator: a maternal asthma perspective","year":2018,"lang":"en","type":"erratum","venue":"BMC Medical Research Methodology","topic":"Pregnancy and Medication Impact","field":"Medicine","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":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Perspective (graphical); Gestational age; Asthma; Medicine; Outcome (game theory); Gestation; Obstetrics; Small for gestational age; Pediatrics; Psychology; Pregnancy; Computer science; Internal medicine; Artificial intelligence","score_opus":0.5371452665124308,"score_gpt":0.5235803078697353,"score_spread":0.013564958642695468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772738494","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054981573,0.00084834266,0.7952909,0.09588396,0.07995601,0.009342148,0.0017232544,0.00014261286,0.011314638],"genre_scores_gemma":[0.002526003,0.00068418955,0.27320385,0.021326462,0.016796427,0.0029147675,0.0012333415,0.0002785009,0.6810365],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9845945,0.008231998,0.0010316543,0.00087528134,0.004295682,0.0009708604],"domain_scores_gemma":[0.9407557,0.054204155,0.0005309928,0.0010783392,0.002493542,0.0009372721],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018145159,0.0003840502,0.0010018648,0.00061887386,0.0004102562,0.000060490915,0.0010410112,0.0010538616,0.0049921656],"category_scores_gemma":[0.32784906,0.0002221931,0.00044064684,0.0005581482,0.0017889517,0.00007139738,0.00040361148,0.003413916,0.000092285925],"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":[0.0018727963,0.00023528884,0.0004123211,0.0004231577,0.00031034544,0.000055378438,0.002170192,0.000009886303,0.00016533973,0.010087716,0.9821341,0.0021234779],"study_design_scores_gemma":[0.004309348,0.0035942923,0.06851538,0.0058497284,0.00043057653,0.00059818686,0.0016510212,0.004890764,0.0005823915,0.03398425,0.87504214,0.00055194163],"about_ca_topic_score_codex":0.0015223061,"about_ca_topic_score_gemma":0.0009390366,"teacher_disagreement_score":0.66972184,"about_ca_system_score_codex":0.000645966,"about_ca_system_score_gemma":0.009937075,"threshold_uncertainty_score":0.9988853},"labels":[],"label_agreement":null},{"id":"W2773509967","doi":"10.1186/s12874-017-0435-0","title":"What does it mean when people say that they have received expressions of concern about their drinking or advice to cut down on the AUDIT scale?","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Substance Abuse Treatment and Outcomes","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":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"Canada Research Chairs","keywords":"Advice (programming); Scale (ratio); Audit; Psychology; MEDLINE; Medicine; Computer science; Business; Geography","score_opus":0.46766392176626786,"score_gpt":0.5173004967556084,"score_spread":0.04963657498934054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773509967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9187126,0.0005117256,0.0015358721,0.07075287,0.0011061371,0.0016174254,0.000007671465,0.00007933637,0.0056763473],"genre_scores_gemma":[0.95802206,0.0051146504,0.013227164,0.0035022066,0.0007762245,0.00035747976,0.000016353233,0.000068851026,0.018915012],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9885771,0.0067534535,0.00056136557,0.0007528867,0.002307484,0.0010476828],"domain_scores_gemma":[0.92747885,0.06888744,0.00027249422,0.0021159675,0.00044622584,0.0007989956],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01676117,0.00033086853,0.0011563526,0.00027653444,0.00080103887,0.00013333576,0.0016121559,0.00041954374,0.0067155627],"category_scores_gemma":[0.07037332,0.0001364617,0.00026808522,0.00012285785,0.0011753951,0.00022841361,0.0007004477,0.001173327,0.00015357239],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020287676,0.0010217138,0.41399702,0.00047254338,0.001206835,0.0005281397,0.3597679,0.000007689834,0.013027757,0.0035072034,0.03681433,0.1493612],"study_design_scores_gemma":[0.017853992,0.003954059,0.26582962,0.018693758,0.00050914986,0.00018603474,0.44660494,0.0006221459,0.15544699,0.025991147,0.06309752,0.0012106511],"about_ca_topic_score_codex":0.0007573623,"about_ca_topic_score_gemma":0.14287303,"teacher_disagreement_score":0.1481674,"about_ca_system_score_codex":0.00015220817,"about_ca_system_score_gemma":0.0010279036,"threshold_uncertainty_score":0.9941924},"labels":[],"label_agreement":null},{"id":"W2774161706","doi":"10.1186/s12874-017-0441-2","title":"Classification schemes for knowledge translation interventions: a practical resource for researchers","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Alberta Health Services; University of Calgary; University of Alberta","funders":"","keywords":"Knowledge translation; Classification scheme; Psychological intervention; Context (archaeology); Computer science; Health care; Quality (philosophy); Scheme (mathematics); Medicine; Knowledge management; Artificial intelligence; Machine learning; Nursing; Mathematics","score_opus":0.9962429945388183,"score_gpt":0.885538711299546,"score_spread":0.11070428323927228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774161706","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004197847,0.00015469472,0.85101026,0.13440046,0.00047668724,0.0050099595,0.00006483107,0.00005961828,0.004625648],"genre_scores_gemma":[0.04217838,0.00027835296,0.9246772,0.0027957857,0.002443519,0.018216347,0.0000986119,0.00008061529,0.009231197],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95399636,0.04017361,0.0014996292,0.00078033935,0.0016208905,0.0019291777],"domain_scores_gemma":[0.5231523,0.47156802,0.0006029022,0.0011828273,0.002219944,0.0012739887],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21566918,0.00013984929,0.00046896402,0.0005263211,0.004854765,0.00006949041,0.0012062892,0.0006372843,0.0011337181],"category_scores_gemma":[0.82143897,0.00012144827,0.00021679596,0.0003259109,0.001564675,0.00035507107,0.0003598827,0.0016951221,0.00023169538],"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":[0.0026180076,0.0002662188,0.0038329603,0.0072334064,0.000058419446,0.0000025151999,0.012977842,2.9383494e-7,0.0013482356,0.28108093,0.23273832,0.45784286],"study_design_scores_gemma":[0.0033882477,0.0004972063,0.0058006817,0.00050206785,0.000014859662,0.000002717104,0.010547131,0.008939776,0.00008667054,0.017712684,0.9523841,0.00012383304],"about_ca_topic_score_codex":0.00020470253,"about_ca_topic_score_gemma":0.0036101628,"teacher_disagreement_score":0.7196458,"about_ca_system_score_codex":0.00040298078,"about_ca_system_score_gemma":0.009597989,"threshold_uncertainty_score":0.9997794},"labels":[],"label_agreement":null},{"id":"W2775716135","doi":"10.1186/s12874-017-0440-3","title":"Using Mechanical Turk to recruit participants for internet intervention research: experience from recruitment for four trials targeting hazardous alcohol consumption","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Substance Abuse Treatment and Outcomes","field":"Medicine","cited_by":59,"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; Centre for Addiction and Mental Health","funders":"Canada Research Chairs","keywords":"Intervention (counseling); Payment; Brief intervention; Medicine; Sample (material); Alcohol consumption; Clinical trial; Consumption (sociology); Randomized controlled trial; Family medicine; Alcohol; Nursing; World Wide Web; Computer science","score_opus":0.9806769927475556,"score_gpt":0.7320107486936438,"score_spread":0.2486662440539118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775716135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63710386,0.0005058671,0.35374013,0.0018804681,0.0009896357,0.00569262,0.000018810764,0.000043755746,0.000024855306],"genre_scores_gemma":[0.6507104,0.0002481291,0.34106076,0.00019947148,0.0011326186,0.00574421,0.0000700268,0.00005375483,0.00078062725],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9793806,0.014090532,0.0014607027,0.0011551022,0.002118809,0.0017942531],"domain_scores_gemma":[0.9106051,0.085776635,0.00036619804,0.000998285,0.0010433525,0.0012104717],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10785146,0.00026918817,0.001509195,0.00045910446,0.00073391036,0.00014697055,0.00085304567,0.00053128734,0.0012199535],"category_scores_gemma":[0.51281834,0.00020292142,0.00051500974,0.00016806523,0.0006824709,0.00017057256,0.00056816393,0.00076895906,0.00006913532],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.08414806,0.001933369,0.103343464,0.0012118982,0.0020361901,0.0005829443,0.01771409,0.000008941712,0.16696258,0.012061494,0.023848176,0.5861488],"study_design_scores_gemma":[0.09624685,0.015747268,0.03459609,0.012322928,0.0015783227,0.00015348295,0.025795305,0.0616854,0.61954945,0.072782025,0.05769632,0.0018465624],"about_ca_topic_score_codex":0.0006573407,"about_ca_topic_score_gemma":0.0015941121,"teacher_disagreement_score":0.58430225,"about_ca_system_score_codex":0.00057951116,"about_ca_system_score_gemma":0.00068897847,"threshold_uncertainty_score":0.9996931},"labels":[],"label_agreement":null},{"id":"W2775861707","doi":"10.1186/s12874-017-0451-0","title":"The development of CHAMP: a checklist for the appraisal of moderators and predictors","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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":"Bruyère","funders":"Vrije Universiteit Amsterdam; Universiteit Utrecht; Universität Bremen; Ludwig-Maximilians-Universität München; European Commission; Universiteit van Amsterdam; University of Warwick; Warwick Medical School; ZonMw; National Institute for Health and Care Research","keywords":"Checklist; Delphi method; Critical appraisal; Moderation; Delphi; Psychology; Applied psychology; Identification (biology); Set (abstract data type); Test (biology); Transferability; MEDLINE; Medicine; Clinical psychology; Computer science; Alternative medicine; Social psychology","score_opus":0.9564106014940739,"score_gpt":0.7208012533896963,"score_spread":0.23560934810437761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775861707","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":[0.15193763,0.0019635826,0.84001005,0.003018496,0.00042544387,0.0010436357,0.00000778924,0.0000014535402,0.0015919318],"genre_scores_gemma":[0.78040487,0.00028971836,0.21501958,0.0000405763,0.00021768172,0.00041891466,0.0000015043529,0.000013704483,0.003593476],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.87177753,0.09902407,0.010239892,0.0011543547,0.016956251,0.00084788847],"domain_scores_gemma":[0.24361806,0.74290246,0.0041993367,0.005642534,0.0031516037,0.00048603833],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7010106,0.00013662102,0.0019979663,0.00016869736,0.0011912063,0.0002562751,0.0044526914,0.00016400444,0.00074817974],"category_scores_gemma":[0.8864675,0.000043206022,0.00052086025,0.00028315198,0.002427293,0.000058725265,0.00088292954,0.0003294942,0.000018430714],"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":[0.00028172036,0.0000836896,0.044517286,0.0004346825,0.00069674046,0.0000013342633,0.0060439454,0.000007523222,0.00032736617,0.059825785,0.027888963,0.85989094],"study_design_scores_gemma":[0.0015761524,0.0003797827,0.19393887,0.00020646532,0.00016540081,0.000019556912,0.01459994,0.090856396,0.0021448066,0.06728498,0.62855756,0.00027010773],"about_ca_topic_score_codex":0.000041862848,"about_ca_topic_score_gemma":0.0009957982,"teacher_disagreement_score":0.85962087,"about_ca_system_score_codex":0.000011689518,"about_ca_system_score_gemma":0.0013320824,"threshold_uncertainty_score":0.91619164},"labels":[],"label_agreement":null},{"id":"W2780532712","doi":"10.1186/s12874-017-0459-5","title":"A scoping review of comparisons between abstracts and full reports in primary biomedical research","year":2017,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Programs for Assessment of Technology in Health Research Institute; Impact; McMaster University","funders":"","keywords":"Interquartile range; CINAHL; MEDLINE; Medicine; Systematic review; Research design; Family medicine; Sample size determination; Statistics; Psychological intervention; Internal medicine; Mathematics","score_opus":0.9935523205966393,"score_gpt":0.8165069929284386,"score_spread":0.1770453276682007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780532712","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":[0.00002365195,0.98231393,0.005480729,0.0007962071,0.0003347709,0.006184746,0.000027200933,0.0000052234154,0.0048335376],"genre_scores_gemma":[0.0000055193004,0.95736855,0.04030386,0.000055848526,0.00046816576,0.0006551716,0.000089843175,0.000045102224,0.0010079169],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.11578841,0.74915695,0.06311077,0.005664262,0.06337587,0.0029037145],"domain_scores_gemma":[0.090497844,0.8620447,0.022102494,0.015988767,0.0062436727,0.0031225223],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.9351437,0.0007421589,0.037639488,0.0052700606,0.0004295145,0.00045909948,0.008131036,0.0018630495,0.00825094],"category_scores_gemma":[0.95030254,0.00037085783,0.0032325098,0.004991783,0.0048024766,0.00017849608,0.0043343706,0.0063090865,0.0008325907],"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":[0.0000055878286,0.00006827803,0.00036579458,0.31190616,0.0001349857,0.00032835538,0.000029831337,1.6322264e-8,2.1046723e-7,0.000086110245,0.027375365,0.6596993],"study_design_scores_gemma":[0.0001011752,0.00011182687,0.00042389418,0.4072571,0.00022787877,0.000289658,0.00003705796,0.000005931476,9.2571284e-8,0.0011438987,0.5902265,0.0001749919],"about_ca_topic_score_codex":0.00024376767,"about_ca_topic_score_gemma":0.0006107673,"teacher_disagreement_score":0.6595243,"about_ca_system_score_codex":0.00025369812,"about_ca_system_score_gemma":0.017335562,"threshold_uncertainty_score":0.9999454},"labels":[],"label_agreement":null},{"id":"W2782749611","doi":"10.1186/s12874-017-0465-7","title":"A systematic review of comparisons between protocols or registrations and full reports in primary biomedical research","year":2018,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Programs for Assessment of Technology in Health Research Institute; Impact; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"CINAHL; MEDLINE; Systematic review; Observational study; Medicine; Protocol (science); Data extraction; Research design; Meta-analysis; Family medicine; Reporting bias; Clinical trial; Medical physics; Alternative medicine; Pathology; Psychological intervention; Statistics; Nursing","score_opus":0.9885280043170334,"score_gpt":0.7979694208306354,"score_spread":0.19055858348639798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782749611","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":[0.000002391544,0.9140452,0.020239158,0.000612917,0.00012401717,0.063359685,0.000048118847,0.000007977027,0.0015605122],"genre_scores_gemma":[5.30789e-7,0.9053399,0.05501549,0.000066479675,0.0003824587,0.035598125,0.00009992043,0.0000492325,0.0034478393],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.09656229,0.7793008,0.066190414,0.0044451496,0.051441446,0.002059876],"domain_scores_gemma":[0.09633132,0.85240644,0.02189495,0.016463002,0.01023221,0.0026720844],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.9201274,0.0008083689,0.042113062,0.005126741,0.00033203542,0.00040944514,0.0071951156,0.0017303834,0.009425594],"category_scores_gemma":[0.956582,0.0003435732,0.0031393506,0.0132974535,0.0049139163,0.00014854982,0.0026323625,0.004387284,0.0009200575],"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":[0.000015761547,0.00014775389,0.00007627875,0.8518956,0.00033150412,0.00022620009,0.00006495754,4.192283e-9,1.7523013e-7,0.00042971884,0.10205429,0.044757783],"study_design_scores_gemma":[0.00010905623,0.00036065647,0.000023103907,0.50959694,0.0005837479,0.00056192325,0.00011837545,0.000016718372,6.64039e-8,0.0012890897,0.48716384,0.0001764555],"about_ca_topic_score_codex":0.00008926479,"about_ca_topic_score_gemma":0.0005352489,"teacher_disagreement_score":0.38510957,"about_ca_system_score_codex":0.00036534868,"about_ca_system_score_gemma":0.016935559,"threshold_uncertainty_score":0.99990165},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2782791289","doi":"10.1186/s12874-017-0456-8","title":"Comparison of nuisance parameters in pediatric versus adult randomized trials: a meta-epidemiologic empirical evaluation","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"European Commission","keywords":"Medicine; Meta-analysis; Randomized controlled trial; Relative risk; Confidence interval; Sample size determination; Pediatrics; Rate ratio; Adverse effect; Internal medicine; Statistics","score_opus":0.9932412847400476,"score_gpt":0.8328314045220102,"score_spread":0.16040988021803737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782791289","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":[0.10519962,0.0013603038,0.88424057,0.0021142026,0.0020869963,0.0036398962,0.00001822067,0.0000621327,0.00127809],"genre_scores_gemma":[0.0785919,0.0006344561,0.91820806,0.00020267903,0.0010002693,0.0013011895,0.0000034109294,0.000034755445,0.000023252012],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.17814496,0.80271274,0.009695373,0.0015430994,0.0062574274,0.0016464023],"domain_scores_gemma":[0.0095328195,0.9846292,0.0017221255,0.0010674766,0.0023604305,0.0006879287],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7843372,0.00039322264,0.010927012,0.00079576176,0.000108873544,0.000018344082,0.0012506543,0.001298959,0.004288663],"category_scores_gemma":[0.9985229,0.00024604838,0.0013717175,0.0017552207,0.0049213204,0.000059076203,0.00049251015,0.0022188548,0.000084934174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5459636,0.0029788965,0.013321831,0.0015979018,0.0033966913,0.000035865232,0.0019773587,0.00005674143,0.00008113761,0.26747844,0.024957588,0.13815397],"study_design_scores_gemma":[0.08712043,0.0012550122,0.00045730767,0.0000722751,0.0024031908,0.000002388638,0.0002481988,0.034380138,0.00058167643,0.8732274,0.00004228523,0.00020969922],"about_ca_topic_score_codex":0.00019745981,"about_ca_topic_score_gemma":0.00057547906,"teacher_disagreement_score":0.60574895,"about_ca_system_score_codex":0.00019734808,"about_ca_system_score_gemma":0.0017998529,"threshold_uncertainty_score":0.99999917},"labels":[],"label_agreement":null},{"id":"W2805369172","doi":"10.1186/s12874-018-0503-0","title":"A realist approach to eliciting the initial programme theory of the antiretroviral treatment adherence club intervention in the Western Cape Province, South Africa","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":72,"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; African Population and Health Research Center; South African Medical Research Council; International Development Research Centre","keywords":"Intervention (counseling); Context (archaeology); Club; Poverty; Medicine; Qualitative research; Psychology; Nursing; Psychotherapist; Sociology; Political science; Social science; Geography","score_opus":0.5405414028250509,"score_gpt":0.539362828185073,"score_spread":0.0011785746399779473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805369172","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7757063,0.0009840983,0.16093159,0.0073871017,0.00024186709,0.008148837,0.000057077592,0.00008765348,0.046455506],"genre_scores_gemma":[0.98717254,0.00003362351,0.005991756,0.00024788472,0.0006093238,0.0010048581,0.000013539284,0.000029924286,0.0048965625],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9671639,0.02842778,0.0007588273,0.00049908593,0.0020555682,0.0010948445],"domain_scores_gemma":[0.98617274,0.011646876,0.00016897354,0.0010639703,0.0005223591,0.00042510076],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04141867,0.00019338334,0.00050502,0.00034138493,0.0003453314,0.00005726533,0.0013114697,0.00021742289,0.00021277402],"category_scores_gemma":[0.06884007,0.00008254845,0.00037456243,0.0010825404,0.0029164092,0.000056929806,0.00059201184,0.0012415216,0.000059487633],"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":[0.0040087723,0.0027585216,0.021770129,0.0006536671,0.00019725168,0.000076663164,0.035592325,7.2420784e-7,0.00087514037,0.0163785,0.0043764208,0.9133119],"study_design_scores_gemma":[0.032910895,0.27615264,0.2005377,0.010752151,0.00075520785,0.0014625589,0.29444098,0.01843321,0.014975322,0.03773322,0.11029474,0.0015513516],"about_ca_topic_score_codex":0.002732767,"about_ca_topic_score_gemma":0.005729664,"teacher_disagreement_score":0.9117605,"about_ca_system_score_codex":0.00017905307,"about_ca_system_score_gemma":0.0014468367,"threshold_uncertainty_score":0.9997971},"labels":[],"label_agreement":null},{"id":"W2805786630","doi":"10.1186/s12874-018-0491-0","title":"Influence of blinding on treatment effect size estimate in randomized controlled trials of oral health interventions","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates; Killam Trusts; University of Alberta; Alberta Innovates - Health Solutions; Women and Children's Health Research Institute; Children's Health Research Institute; Fondation pour la Recherche Médicale; Alpha Omega Foundation","keywords":"Blinding; Medicine; Randomized controlled trial; Meta-analysis; Clinical trial; Sample size determination; Psychological intervention; Publication bias; Strictly standardized mean difference; Internal medicine; Psychiatry; Statistics","score_opus":0.9704042456570404,"score_gpt":0.7912493658991594,"score_spread":0.17915487975788102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805786630","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":[0.87001896,0.0015867776,0.12042167,0.0013837571,0.00021139182,0.005726178,0.000009589806,0.0000033642075,0.00063828414],"genre_scores_gemma":[0.919071,0.00031749235,0.07841106,0.00008283412,0.000076387085,0.00075808633,0.0000024291003,0.000010075855,0.0012706463],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.07721631,0.87981224,0.030793784,0.0009882367,0.010508357,0.00068107096],"domain_scores_gemma":[0.0080047455,0.9776168,0.00989203,0.0020723084,0.001926907,0.0004872171],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9535553,0.0002801855,0.035915818,0.0019044117,0.00009753107,0.00006508082,0.0015664573,0.00021568043,0.010942832],"category_scores_gemma":[0.98998857,0.00009644286,0.0070500583,0.002043587,0.0014444779,0.0000570957,0.000211147,0.00036798237,0.00026454547],"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":[0.44534916,0.0025976594,0.035592556,0.0034627712,0.0070795882,0.000051969553,0.005196828,0.001554632,0.0017605479,0.042682756,0.0073973,0.44727424],"study_design_scores_gemma":[0.81216043,0.017729316,0.016263729,0.0070018475,0.0015892382,0.000028638266,0.0010961683,0.052437156,0.0037439838,0.086206004,0.0013161206,0.0004273788],"about_ca_topic_score_codex":0.0007222791,"about_ca_topic_score_gemma":0.001384434,"teacher_disagreement_score":0.44684687,"about_ca_system_score_codex":0.0001175089,"about_ca_system_score_gemma":0.0012736323,"threshold_uncertainty_score":0.9899613},"labels":[],"label_agreement":null},{"id":"W2805935905","doi":"10.1186/s12874-018-0494-x","title":"Measuring colorectal cancer incidence: the performance of an algorithm using administrative health data","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":11,"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; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; McGill University; Centre Hospitalier de l’Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research","keywords":"Cancer registry; Medicine; Incidence (geometry); Algorithm; Colorectal cancer; Population; Socioeconomic status; Cancer; Diagnosis code; Demography; Computer science; Environmental health; Internal medicine; Mathematics","score_opus":0.8980113531281599,"score_gpt":0.6673111394494222,"score_spread":0.23070021367873772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805935905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9599357,0.0016223952,0.035634905,0.0016668971,0.00030761375,0.00052436144,0.000034042027,0.000022832934,0.0002512545],"genre_scores_gemma":[0.7581032,0.0006943944,0.23900495,0.000715123,0.0013634481,0.000036992285,0.000021884354,0.000018551067,0.00004148154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98770857,0.007322637,0.000623245,0.0006127553,0.002848125,0.00088467257],"domain_scores_gemma":[0.9905639,0.006544118,0.00020199947,0.0009088374,0.0010316843,0.00074940594],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046356518,0.00014946866,0.0006273978,0.00016479236,0.00045309,0.000017146644,0.0012322334,0.00021418356,0.0006928019],"category_scores_gemma":[0.028498987,0.00009680169,0.000051482868,0.00078873144,0.0027080532,0.00023039618,0.00075771695,0.0011095806,0.0000106336],"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":[0.0039315107,0.00023396537,0.062119078,0.00062619394,0.00019413375,0.00013576023,0.0040043355,0.000020766061,0.008537917,0.00040535434,0.0018171187,0.9179739],"study_design_scores_gemma":[0.003339315,0.017154288,0.16897222,0.0035604124,0.00013303514,0.0020899647,0.0121722175,0.72647566,0.0612749,0.0005945297,0.0037540293,0.00047943782],"about_ca_topic_score_codex":0.009378906,"about_ca_topic_score_gemma":0.00805584,"teacher_disagreement_score":0.9174944,"about_ca_system_score_codex":0.00027066338,"about_ca_system_score_gemma":0.012495813,"threshold_uncertainty_score":0.9977935},"labels":[],"label_agreement":null},{"id":"W2809157516","doi":"10.1186/s12874-018-0524-8","title":"Comparison of response rates on invitation mode of a web-based survey on influenza vaccine adverse events among healthcare workers: a pilot study","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Influenza Virus Research Studies","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":true,"ca_institutions":"Nova Scotia Health Authority; St. Michael's Hospital; Toronto East General Hospital; Dalhousie University; University of Toronto; Université Laval; Izaak Walton Killam Health Centre; Institut National de Santé Publique du Québec; North York General Hospital; Sinai Health System; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Adverse effect; Receipt; Influenza vaccine; Family medicine; Vaccination; Health care; Internal medicine; Immunology","score_opus":0.7627100424735963,"score_gpt":0.6669085242758839,"score_spread":0.09580151819771243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809157516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944199,0.00016658216,0.0013021247,0.0012626658,0.00014730862,0.0025278253,0.00005776794,0.00004245971,0.00007337714],"genre_scores_gemma":[0.99272054,0.000030353614,0.0059549073,0.0007280002,0.00014314502,0.0002664673,0.000026585783,0.00004966467,0.0000803473],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91840386,0.07307893,0.0016021277,0.0008184445,0.0049589355,0.0011377133],"domain_scores_gemma":[0.8736051,0.12051964,0.000421036,0.0011203126,0.0034788374,0.0008551039],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07573928,0.00032862637,0.0017396448,0.0018426282,0.00025411637,0.0000047144263,0.0006133552,0.0003123555,0.0003149243],"category_scores_gemma":[0.40844005,0.0002510059,0.00013184959,0.0019276502,0.001579182,0.00006456548,0.00038749186,0.0018028362,0.00006876972],"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":[0.21146539,0.003653554,0.7757082,0.00045401172,0.00020684718,0.000029347157,0.0016239467,0.00009828967,0.0031340532,0.000032452608,0.0021465288,0.0014473491],"study_design_scores_gemma":[0.011657779,0.07063166,0.9013608,0.001152622,0.000032158965,9.998039e-7,0.0030509147,0.003902442,0.007868752,0.00010587454,0.00009299603,0.00014301295],"about_ca_topic_score_codex":0.008715342,"about_ca_topic_score_gemma":0.018810967,"teacher_disagreement_score":0.33270076,"about_ca_system_score_codex":0.00037473487,"about_ca_system_score_gemma":0.004041144,"threshold_uncertainty_score":0.9999942},"labels":[],"label_agreement":null},{"id":"W2809902003","doi":"10.1186/s12874-018-0576-9","title":"A systematic survey shows that reporting and handling of missing outcome data in networks of interventions is poor","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"McMaster University; Impact","funders":"Deutsche Forschungsgemeinschaft","keywords":"Missing data; Outcome (game theory); Systematic review; Meta-analysis; Psychological intervention; Acknowledgement; Medicine; Data collection; MEDLINE; Data science; Data mining; Computer science; Statistics; Psychiatry; Machine learning","score_opus":0.992748190618118,"score_gpt":0.7766634075139893,"score_spread":0.2160847831041287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809902003","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":[0.18697658,0.003826426,0.807547,0.00036797815,0.00022903798,0.0007748032,0.000015759882,0.000002117592,0.00026033042],"genre_scores_gemma":[0.89233285,0.00005618881,0.10675315,0.000068446025,0.000073627256,0.000023562287,0.00000950557,0.000010961876,0.0006716797],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.30492038,0.6118305,0.059026886,0.0029032144,0.020017048,0.0013020266],"domain_scores_gemma":[0.12315704,0.8277204,0.030654036,0.011772062,0.005753099,0.00094336004],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.900315,0.00017701503,0.0067929896,0.0010179604,0.000118073454,0.00015409224,0.0031725524,0.0002558352,0.004430159],"category_scores_gemma":[0.96038544,0.00008895684,0.00070598297,0.0020104963,0.0009485408,0.00015335885,0.0017892729,0.0005484343,0.0000317321],"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":[0.000045902765,0.000082284874,0.9624444,0.013391658,0.00022452402,0.000023152521,0.0007358111,0.0000029021455,0.00006231859,0.0003581417,0.0018674245,0.020761466],"study_design_scores_gemma":[0.00084583147,0.00032790855,0.39661303,0.023263184,0.00035805136,0.00019950446,0.005738832,0.56355184,0.0001533157,0.008453222,0.00018890086,0.00030637946],"about_ca_topic_score_codex":0.0008359027,"about_ca_topic_score_gemma":0.0071024164,"teacher_disagreement_score":0.7053563,"about_ca_system_score_codex":0.000022989028,"about_ca_system_score_gemma":0.00041329543,"threshold_uncertainty_score":0.9964799},"labels":[],"label_agreement":null},{"id":"W2831634732","doi":"10.1186/s12874-018-0533-7","title":"Creation of a new clinical framework – why women choose mastectomy versus breast conserving therapy","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","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":"University of Saskatchewan; Saskatchewan Health Authority","funders":"","keywords":"Conceptual framework; Breast cancer; Mastectomy; Medicine; Multitude; Health care; Psychology; Management science; Cancer; Sociology; Social science","score_opus":0.8927123966767095,"score_gpt":0.7053405497423559,"score_spread":0.1873718469343536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2831634732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80553937,0.004031572,0.12978499,0.042759232,0.0060306564,0.0037555941,0.000036981222,0.00028195253,0.007779628],"genre_scores_gemma":[0.5217246,0.0040470115,0.45681226,0.00888466,0.005728263,0.0013563232,0.0000433845,0.00012754707,0.0012759806],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9103115,0.08415385,0.0017886854,0.00060095964,0.0017683653,0.0013766051],"domain_scores_gemma":[0.6293525,0.36134136,0.0008353549,0.0028153767,0.0032883033,0.0023671186],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04036629,0.00019957732,0.00088884187,0.0004186902,0.00081851764,0.000009284787,0.0016331818,0.0014118227,0.013227145],"category_scores_gemma":[0.3004143,0.0001653611,0.00012720766,0.001078812,0.0021847363,0.0001087161,0.0011477673,0.004227239,0.00050263305],"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":[0.025055896,0.0005078196,0.30074972,0.0010636705,0.00023546333,0.000010387239,0.054430395,5.544309e-7,0.00015193135,0.02263321,0.03853612,0.5566248],"study_design_scores_gemma":[0.030108318,0.00874344,0.38838065,0.0047121164,0.000036311445,0.000034216464,0.10890418,0.0022000796,0.00020794656,0.1453351,0.3105137,0.0008239521],"about_ca_topic_score_codex":0.0042007593,"about_ca_topic_score_gemma":0.0016100182,"teacher_disagreement_score":0.55580086,"about_ca_system_score_codex":0.00039716548,"about_ca_system_score_gemma":0.010966972,"threshold_uncertainty_score":0.99988455},"labels":[],"label_agreement":null},{"id":"W2890953957","doi":"10.1186/s12874-018-0553-3","title":"The Ottawa SAH search algorithms: protocol for a multi- centre validation study of primary subarachnoid hemorrhage prediction models using health administrative data (the SAHepi prediction study protocol)","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Intracerebral and Subarachnoid Hemorrhage Research","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; Hamilton Health Sciences; University of British Columbia; Centre hospitalier de l'Université Laval; The Quebec Population Health Research Network; Centre Hospitalier de l’Université de Montréal; University of Manitoba; Ottawa Hospital; Université Laval; University of Ottawa","funders":"","keywords":"Medicine; Subarachnoid hemorrhage; Algorithm; Radiology; Diagnosis code; Epidemiology; Emergency medicine; Surgery; Internal medicine; Computer science","score_opus":0.7394828313244168,"score_gpt":0.6074666925070582,"score_spread":0.13201613881735863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890953957","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032556377,0.000017689854,0.2628899,0.001558417,0.00013584133,0.7025206,0.00014304959,0.00009139543,0.000086754495],"genre_scores_gemma":[0.024976458,0.0000034109914,0.15053357,0.000083555686,0.0014993036,0.8219132,0.00016443597,0.00009370818,0.0007324021],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9599307,0.029384878,0.0021138676,0.0015740937,0.0051990557,0.0017973756],"domain_scores_gemma":[0.97954714,0.013441266,0.00046506175,0.002496162,0.003208903,0.0008414385],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09919907,0.00042887637,0.0011330689,0.0005007144,0.002253607,0.00011830546,0.0019088611,0.0004602023,0.00021134038],"category_scores_gemma":[0.030257767,0.0002463196,0.00015312192,0.0015064928,0.002080946,0.00041265163,0.0014439,0.002549062,0.000011208106],"study_design_candidate":"simulation_or_modeling","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":[0.046519976,0.03414811,0.053131256,0.011160896,0.00080148515,0.0001885959,0.02209322,0.0001638355,0.0025351914,0.00054423657,0.0042742607,0.8244389],"study_design_scores_gemma":[0.015636848,0.019548628,0.0043825274,0.00017338668,0.00009181132,0.00014083137,0.026033014,0.93185157,0.0012743903,0.000303084,0.00038205084,0.00018188971],"about_ca_topic_score_codex":0.00158746,"about_ca_topic_score_gemma":0.0023970576,"teacher_disagreement_score":0.9316877,"about_ca_system_score_codex":0.00074464094,"about_ca_system_score_gemma":0.009082919,"threshold_uncertainty_score":0.9999989},"labels":[],"label_agreement":null},{"id":"W2893862487","doi":"10.1186/s12874-018-0562-2","title":"A descriptive analysis of non-Cochrane child-relevant systematic reviews published in 2014","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Cochrane; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Cochrane Library; Systematic review; Medicine; CINAHL; MEDLINE; Family medicine; Meta-analysis; Pediatrics; Psychological intervention; Psychiatry; Pathology","score_opus":0.9246853710327179,"score_gpt":0.6888051513207256,"score_spread":0.23588021971199225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893862487","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":[0.058471814,0.014353872,0.903878,0.0024232746,0.00077319815,0.005693624,0.00001732128,0.000009179366,0.014379732],"genre_scores_gemma":[0.62553585,0.0044717533,0.35492587,0.0009651626,0.00087886123,0.0019908028,0.00004176863,0.00007129955,0.011118651],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.3529842,0.5838801,0.030484062,0.0029300747,0.028174583,0.0015469868],"domain_scores_gemma":[0.16898724,0.7775969,0.01558395,0.01934571,0.015995195,0.0024909843],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8770362,0.0004311211,0.018399317,0.006824966,0.00018710105,0.000345004,0.0061845826,0.0005065915,0.07543354],"category_scores_gemma":[0.951105,0.00019112002,0.0036268744,0.017914072,0.0015085592,0.000275493,0.00085552695,0.001142895,0.0047457293],"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":[0.0009919911,0.0024348784,0.15444803,0.08622779,0.016182581,0.00032303008,0.03265838,0.00012532085,0.0027383144,0.04153493,0.58563215,0.07670259],"study_design_scores_gemma":[0.0049319705,0.0029178949,0.2038496,0.03573424,0.012116989,0.0002513117,0.025227329,0.60073614,0.0007259115,0.057736244,0.053572502,0.002199891],"about_ca_topic_score_codex":0.0005652519,"about_ca_topic_score_gemma":0.0077150897,"teacher_disagreement_score":0.6006108,"about_ca_system_score_codex":0.00013704579,"about_ca_system_score_gemma":0.0008957169,"threshold_uncertainty_score":0.9991924},"labels":[],"label_agreement":null},{"id":"W2895713118","doi":"10.1186/s12874-018-0600-0","title":"Improving reporting of meta-ethnography: the eMERGe reporting guidance","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":483,"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":"Norwegian Institute of Public Health; Medical Research Council; Economic and Social Research Council; University of North Carolina at Chapel Hill; University of Stirling; South African Medical Research Council; University of Nottingham; United Kingdom Clinical Research Collaboration; University of Southampton; National Institute for Health and Care Research; Cancer Research UK; British Heart Foundation; Wellcome Trust; McMaster University","keywords":"CLARITY; Ethnography; Audit; Bespoke; Best practice; Medical education; Medicine; Psychology; Management science; Sociology; Political science; Business; Engineering","score_opus":0.9822940030074859,"score_gpt":0.7359007192625816,"score_spread":0.24639328374490432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895713118","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":[0.5345457,0.00926759,0.43371958,0.0036451092,0.0011767584,0.0018671943,0.000003998811,0.00001702552,0.015757022],"genre_scores_gemma":[0.6052027,0.00010174166,0.37839416,0.00045988586,0.00037657117,0.00027046347,0.0000034957236,0.00003868463,0.015152313],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.2027829,0.5915134,0.1356745,0.004954237,0.06229942,0.0027755422],"domain_scores_gemma":[0.053095847,0.7513867,0.15948705,0.020122863,0.014625822,0.0012817268],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9437912,0.00032388562,0.008714945,0.0008985921,0.00032029452,0.00021589198,0.0049215797,0.0003388004,0.041646153],"category_scores_gemma":[0.9851087,0.00012049199,0.005032954,0.0044576665,0.0008250461,0.00016732884,0.0013196064,0.0014269871,0.00074993906],"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":[0.0001265439,0.00018909131,0.5457725,0.001689771,0.004550548,0.0002157018,0.0032251268,0.00022357736,0.016136426,0.02363802,0.057461128,0.34677157],"study_design_scores_gemma":[0.0019910007,0.0013402024,0.16033001,0.0008724097,0.0051923585,0.0012754189,0.040916994,0.16552036,0.011021658,0.18067658,0.42895898,0.0019040598],"about_ca_topic_score_codex":0.0006997962,"about_ca_topic_score_gemma":0.0004807955,"teacher_disagreement_score":0.3854425,"about_ca_system_score_codex":0.00002865936,"about_ca_system_score_gemma":0.0011829671,"threshold_uncertainty_score":0.96392},"labels":[],"label_agreement":null},{"id":"W2898817230","doi":"10.1186/s12874-018-0578-7","title":"Mediation analysis with a time-to-event outcome: a review of use and reporting in healthcare research","year":2018,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Conflict Management and Negotiation","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; St. Michael's Hospital; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Women's College Hospital; University Health Network; University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Mediation; Causal inference; Proportional hazards model; MEDLINE; Outcome (game theory); Event (particle physics); Regression analysis; Health care; Psychology; Medicine; Data science; Computer science; Statistics; Political science; Mathematics","score_opus":0.8872002479299586,"score_gpt":0.7193641690009707,"score_spread":0.1678360789289879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898817230","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":[0.000089814166,0.9886667,0.0019342292,0.0056143855,0.000060397324,0.0030221932,0.000005674384,0.000020095551,0.00058647525],"genre_scores_gemma":[0.000012517387,0.9907093,0.0067005977,0.00016119229,0.00025325693,0.00041083354,0.000057931447,0.00002183436,0.0016725151],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8907453,0.09743445,0.00354879,0.0010457454,0.0060119103,0.0012138091],"domain_scores_gemma":[0.91369045,0.0809,0.0017459398,0.00077476416,0.0020476524,0.00084116677],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3405562,0.00020451858,0.0029646629,0.0032524331,0.00029356265,0.000057874895,0.00071836455,0.00057286397,0.00117994],"category_scores_gemma":[0.5692979,0.00014906182,0.0002992909,0.0094859665,0.0011170412,0.00011664429,0.00062540063,0.0014820193,0.00007455518],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048479153,0.000057836103,0.0074234195,0.07998884,0.00025607942,0.000052232128,0.0012980822,1.2232658e-7,6.826229e-8,0.0018657963,0.0020227472,0.9069863],"study_design_scores_gemma":[0.00012867725,0.00023161502,0.0012415639,0.037328504,0.00030454926,0.0000026679465,0.00021789025,0.000036773283,6.5905624e-8,0.0001499616,0.96019876,0.0001589564],"about_ca_topic_score_codex":0.0102830995,"about_ca_topic_score_gemma":0.042983152,"teacher_disagreement_score":0.958176,"about_ca_system_score_codex":0.00045718323,"about_ca_system_score_gemma":0.0046249726,"threshold_uncertainty_score":0.9997331},"labels":[],"label_agreement":null},{"id":"W2899522301","doi":"10.1186/s12874-018-0588-5","title":"Putting family into family-based obesity prevention: enhancing participant engagement through a novel integrated knowledge translation strategy","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","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":"University of Guelph","funders":"Canadian Institutes of Health Research; Ministry of Agriculture, Food and Rural Affairs; Ontario Ministry of Agriculture, Food and Rural Affairs; University of Guelph","keywords":"Knowledge translation; Medicine; Psychology; Computer science; Knowledge management","score_opus":0.9813358194724019,"score_gpt":0.8027502729468163,"score_spread":0.17858554652558556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899522301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24125193,0.00014901954,0.7490835,0.0039583137,0.00075776683,0.0016699044,0.000011775883,0.00012821399,0.002989576],"genre_scores_gemma":[0.43816128,0.0000774585,0.5540405,0.004871122,0.0011901234,0.0010901283,0.000030344267,0.00004067075,0.0004984082],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9116914,0.08016722,0.0023017742,0.0009874847,0.0023778856,0.0024742193],"domain_scores_gemma":[0.878392,0.11745417,0.00041451963,0.0006783153,0.0019450327,0.0011159906],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.15414038,0.000273045,0.0007317709,0.0004873958,0.0025768953,0.000032739335,0.00085041183,0.00060510734,0.0031953398],"category_scores_gemma":[0.12522398,0.00022896055,0.00011420323,0.0020762319,0.0013617832,0.0002851554,0.00036598,0.0027257428,0.0011524549],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014867551,0.0015905801,0.012026634,0.006144378,0.0001884812,0.000037779653,0.24102406,0.000059482638,0.23685792,0.03324933,0.027252346,0.44008222],"study_design_scores_gemma":[0.019412497,0.0065505966,0.07726369,0.005559879,0.00016373098,0.00001128299,0.17043726,0.09326158,0.017912472,0.05302196,0.55492836,0.0014767163],"about_ca_topic_score_codex":0.003249382,"about_ca_topic_score_gemma":0.026838033,"teacher_disagreement_score":0.527676,"about_ca_system_score_codex":0.00064054073,"about_ca_system_score_gemma":0.022051973,"threshold_uncertainty_score":0.99962527},"labels":[],"label_agreement":null},{"id":"W2900090810","doi":"10.1186/s12874-018-0580-0","title":"Barriers in general practitioners’ dementia diagnostics among people with a migration background in Germany (BaDeMi) - study protocol for a cross-sectional survey","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Global Health Workforce Issues","field":"Health Professions","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 Tasmania; Deutsche Alzheimer Gesellschaft; Alzheimer Society","keywords":"Cross-sectional study; Dementia; Medicine; Protocol (science); Family medicine; Gerontology; Alternative medicine; Disease; Pathology","score_opus":0.5804128696994395,"score_gpt":0.6756458068877997,"score_spread":0.09523293718836023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900090810","genre_codex":"empirical","genre_gemma":"protocol","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":[0.8422638,0.000012979906,0.015856849,0.00034752398,0.0003251622,0.14087911,0.00002220376,0.000035851826,0.00025648263],"genre_scores_gemma":[0.36975628,0.000020788895,0.026064131,0.00042997234,0.0009918963,0.60197663,0.0000713148,0.000054606066,0.0006344053],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9438036,0.050373457,0.0014360491,0.0008258175,0.001821188,0.0017398986],"domain_scores_gemma":[0.9187593,0.07825624,0.00031716237,0.00041972607,0.0014176742,0.00082988694],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08842614,0.0002326227,0.00063684955,0.0005829153,0.00096828345,0.000035274403,0.0005043182,0.00079303014,0.0034034515],"category_scores_gemma":[0.13169011,0.0001885829,0.00004563654,0.0014364808,0.0009277181,0.0002571578,0.00031723338,0.0022550225,0.000072749564],"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":[0.004428038,0.00031276568,0.9883094,0.00037503027,0.000026850648,0.000019977464,0.0029461621,0.00001776852,0.000008042087,0.00047480265,0.002974495,0.0001066808],"study_design_scores_gemma":[0.006635469,0.0018981863,0.9801478,0.00029106517,0.0000050375074,0.0000041069857,0.0043993173,0.0021184653,0.0000054789593,0.00069163216,0.003641464,0.00016198674],"about_ca_topic_score_codex":0.04107377,"about_ca_topic_score_gemma":0.7725738,"teacher_disagreement_score":0.7315,"about_ca_system_score_codex":0.0007458533,"about_ca_system_score_gemma":0.0058255764,"threshold_uncertainty_score":0.99981046},"labels":[],"label_agreement":null},{"id":"W2901730891","doi":"10.1186/s12874-018-0593-8","title":"Variable participation of knowledge users in cancer health services research: results of a multiple case study","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Sunnybrook Hospital; Health Sciences Centre; Ottawa Hospital; Public Health Ontario; Ontario Institute for Cancer Research; Cancer Care Ontario; McMaster University; University of Ottawa; Institute for Clinical Evaluative Sciences; University of Calgary; Sunnybrook Health Science Centre; University of Toronto","funders":"Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research; Cancer Care Ontario","keywords":"Knowledge translation; Psychology; Health care; Cancer; Health services research; Knowledge management; Medical education; Medicine; Applied psychology; Nursing; Computer science; Public health","score_opus":0.9732657886506941,"score_gpt":0.846909237837385,"score_spread":0.1263565508133091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901730891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9867292,0.00010931422,0.0053287507,0.0032918009,0.0004485015,0.0031577903,0.00008991938,0.00002091378,0.0008238053],"genre_scores_gemma":[0.97264135,0.00010136751,0.024683837,0.0007538486,0.0003581478,0.0011643736,0.0000046725063,0.000019504658,0.0002728766],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.7898093,0.20024128,0.0033444164,0.000814001,0.0031998842,0.0025911424],"domain_scores_gemma":[0.74975103,0.24380684,0.0006282446,0.0008644999,0.0037373335,0.0012120694],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31324172,0.00012650118,0.00079236773,0.0014104114,0.0008377149,0.0000048175702,0.00076722633,0.00031151934,0.0012582764],"category_scores_gemma":[0.21050657,0.000105226354,0.000030954357,0.004227366,0.0015855269,0.00013965738,0.0008140329,0.0017812176,0.000071134615],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021907385,0.001211081,0.4271377,0.0044833515,0.000030372157,0.00007451807,0.53487635,0.0000110160445,0.00074828166,0.0019367976,0.0066281906,0.0206716],"study_design_scores_gemma":[0.021020167,0.0092858365,0.22550602,0.0035184175,0.000014372482,0.000030003539,0.6932064,0.019127948,0.0012227631,0.003227626,0.02352147,0.00031891876],"about_ca_topic_score_codex":0.35617676,"about_ca_topic_score_gemma":0.67029524,"teacher_disagreement_score":0.31411844,"about_ca_system_score_codex":0.00059511734,"about_ca_system_score_gemma":0.021083565,"threshold_uncertainty_score":0.9996547},"labels":[],"label_agreement":null},{"id":"W2902193528","doi":"10.1186/s12874-018-0617-4","title":"Methods for evaluating adverse drug event preventability in emergency department patients","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","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 British Columbia; Simon Fraser University; Vancouver Coastal Health; Vancouver General Hospital","funders":"Canadian Institutes of Health Research; Health Canada","keywords":"Emergency department; Medicine; Adverse drug event; Adverse effect; Medical emergency; Drug; MEDLINE; Emergency medicine; Pharmacology; Psychiatry","score_opus":0.7224820786822599,"score_gpt":0.7322219610896736,"score_spread":0.009739882407413747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902193528","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8932108,0.0004993657,0.09464208,0.001521596,0.004786682,0.0030706606,0.000074562675,0.00007838332,0.0021158264],"genre_scores_gemma":[0.7474252,0.0012293094,0.24270366,0.00140698,0.0016050162,0.003467778,0.00015803977,0.00007117803,0.0019328125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.954109,0.04158685,0.0011224137,0.00085232436,0.00087734574,0.0014520397],"domain_scores_gemma":[0.9593711,0.038267646,0.00021066159,0.00043142756,0.0008252275,0.0008939439],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08546105,0.00026440254,0.00059408066,0.0003836414,0.0005210525,0.0000056913777,0.00072256284,0.000486389,0.010214932],"category_scores_gemma":[0.06982922,0.00023809607,0.00025479854,0.0007311029,0.00086229795,0.00015003978,0.00042957903,0.0018182296,0.0002320665],"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":[0.005118507,0.003977362,0.22077121,0.0006032087,0.00029793783,0.000017664912,0.0025630551,0.00024208985,0.017148,0.0020217707,0.022064425,0.7251748],"study_design_scores_gemma":[0.020978456,0.0026834821,0.10882507,0.0001935847,0.00033589485,0.000023889103,0.0020744689,0.10918596,0.07513882,0.06308688,0.61629295,0.0011805058],"about_ca_topic_score_codex":0.00012163112,"about_ca_topic_score_gemma":0.0007764607,"teacher_disagreement_score":0.72399426,"about_ca_system_score_codex":0.00041624313,"about_ca_system_score_gemma":0.0012422376,"threshold_uncertainty_score":0.9906899},"labels":[],"label_agreement":null},{"id":"W2903230932","doi":"10.1186/s12874-018-0621-8","title":"Methods for trustworthy nutritional recommendations NutriRECS (Nutritional Recommendations and accessible Evidence summaries Composed of Systematic reviews): a protocol","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","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":"Impact; McMaster University; Dalhousie University","funders":"","keywords":"Guideline; Systematic review; Grading (engineering); Protocol (science); Medicine; MEDLINE; Publication; Evidence-based medicine; Peer review; Trustworthiness; Medical education; Alternative medicine; Psychology; Business; Political science; Engineering; Pathology","score_opus":0.9398031176009238,"score_gpt":0.7717683616212156,"score_spread":0.16803475597970818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903230932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039377972,0.0014109785,0.8518782,0.05459767,0.00033500054,0.09106496,0.00010131394,0.000046937166,0.0001711403],"genre_scores_gemma":[0.00034493444,0.0024664518,0.87874705,0.0011812932,0.0007704237,0.116002,0.00029869567,0.000027071163,0.00016210874],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9611442,0.032869585,0.0034496994,0.00070155656,0.0012202678,0.0006146863],"domain_scores_gemma":[0.6480525,0.34650323,0.00088854006,0.00060755236,0.0033296254,0.00061855314],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.113216706,0.00022734069,0.0014814527,0.00060434564,0.00046458855,0.0000523818,0.0004170382,0.0003497309,0.0031236832],"category_scores_gemma":[0.6080072,0.00018117069,0.0002529538,0.0009967594,0.0014619598,0.00038455176,0.00033305684,0.00080119213,0.000022775836],"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":[0.016207967,0.0040886546,0.008636909,0.20856073,0.00069338264,0.0000116820775,0.00078989344,4.5885267e-7,0.008928335,0.047200236,0.21670854,0.48817322],"study_design_scores_gemma":[0.026734933,0.010327896,0.0036866898,0.10153071,0.0011660003,0.0006588886,0.0032513922,0.019093204,0.009308938,0.10286401,0.72051924,0.0008580878],"about_ca_topic_score_codex":0.00011577153,"about_ca_topic_score_gemma":0.00024876336,"teacher_disagreement_score":0.5038107,"about_ca_system_score_codex":0.00015886808,"about_ca_system_score_gemma":0.002200374,"threshold_uncertainty_score":0.9977876},"labels":[],"label_agreement":null},{"id":"W2905992589","doi":"10.1186/s12874-018-0641-4","title":"Mechanisms, contexts and points of contention: operationalizing realist-informed research for complex health interventions","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hôpital Charles-Le Moyne; Sinai Health System; Trillium Health Centre; Université de Montréal; Lunenfeld-Tanenbaum Research Institute; University of Toronto; Université de Sherbrooke; Women's College Hospital","funders":"Canadian Institutes of Health Research; University of Toronto; Massey University; Health Research Council of New Zealand; Université de Montréal; Université de Sherbrooke","keywords":"Operationalization; Psychological intervention; Health services research; MEDLINE; Psychology; Medicine; Data science; Computer science; Public health; Epistemology; Nursing; Political science","score_opus":0.9855169283511372,"score_gpt":0.8505520599018759,"score_spread":0.13496486844926137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905992589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00923737,0.0001654399,0.8761891,0.10701553,0.0006424555,0.004291639,0.00023959839,0.000046285324,0.0021725774],"genre_scores_gemma":[0.17271605,0.0005922658,0.79752475,0.021848321,0.0010050384,0.002750444,0.00017243536,0.00005317625,0.0033375346],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9307254,0.061484583,0.002410039,0.0006223603,0.0027665664,0.0019910585],"domain_scores_gemma":[0.7756524,0.21519709,0.00054480974,0.00061886484,0.0063769314,0.0016098889],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.22364277,0.00013406546,0.0007418966,0.0009064211,0.0028611529,0.00002183964,0.0006710158,0.0003126729,0.005151197],"category_scores_gemma":[0.35286537,0.00011470058,0.000103652616,0.0009627081,0.0028619743,0.00017736631,0.0007050101,0.0011851251,0.00012827042],"study_design_candidate":"theoretical_or_conceptual","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":[0.00046403296,0.00007054697,0.0010859552,0.0036735663,0.000029147503,0.00000132388,0.009546347,6.3892e-8,0.0014819305,0.8249887,0.14116958,0.017488766],"study_design_scores_gemma":[0.014286836,0.008865741,0.07673534,0.00541838,0.000018774123,0.0000491967,0.07116216,0.004065984,0.000697816,0.37358657,0.44464687,0.00046634534],"about_ca_topic_score_codex":0.0041947537,"about_ca_topic_score_gemma":0.034356494,"teacher_disagreement_score":0.45140216,"about_ca_system_score_codex":0.0004539025,"about_ca_system_score_gemma":0.012351877,"threshold_uncertainty_score":0.99985164},"labels":[],"label_agreement":null},{"id":"W2907723909","doi":"10.1186/s12874-018-0644-1","title":"Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"Horizon 2020; Hellenic Cardiological Society; European Commission; World Health Organization","keywords":"Random forest; Machine learning; Bootstrapping (finance); Artificial intelligence; Decision tree; Predictive value; Predictive modelling; Computer science; Medicine; Statistics; Econometrics; Internal medicine; Mathematics","score_opus":0.8049045884280996,"score_gpt":0.6719449449497101,"score_spread":0.1329596434783895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907723909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6944368,0.015265933,0.27769697,0.0015212874,0.0052656927,0.0025809214,0.00007848283,0.00048062459,0.0026732949],"genre_scores_gemma":[0.7537305,0.021615168,0.21581312,0.00030909484,0.006311697,0.0013632221,0.000054554053,0.00017156122,0.0006311354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7689701,0.22380182,0.001369187,0.0011077044,0.0024801502,0.002271069],"domain_scores_gemma":[0.65684307,0.33836043,0.0004257334,0.0014164868,0.0012789654,0.0016753369],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.23029256,0.00034231882,0.0012510911,0.0008871278,0.0027931684,0.000017946502,0.0012925369,0.0011286094,0.0033094392],"category_scores_gemma":[0.8392196,0.00028396852,0.00036384581,0.0015574918,0.0026491934,0.00014507081,0.0016975903,0.011344863,0.0011065832],"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":[0.0039020565,0.000040411225,0.8416525,0.0004042349,0.00012297233,0.00013128479,0.003531514,0.00031335812,0.000008993284,0.0015379231,0.00030393177,0.14805081],"study_design_scores_gemma":[0.0064528296,0.0039756782,0.46812835,0.0027259388,0.0004039593,0.000014375551,0.05486481,0.26033804,0.0004134494,0.10125477,0.10007186,0.0013559083],"about_ca_topic_score_codex":0.09180237,"about_ca_topic_score_gemma":0.08970269,"teacher_disagreement_score":0.6089271,"about_ca_system_score_codex":0.0006274525,"about_ca_system_score_gemma":0.0047665024,"threshold_uncertainty_score":0.99996126},"labels":[],"label_agreement":null},{"id":"W2920466137","doi":"10.1186/s12874-018-0657-9","title":"Methods of sample size calculation in descriptive retrospective burden of illness studies","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","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":"Vancouver Coastal Health","funders":"","keywords":"Sample size determination; Confidence interval; Observational study; Statistics; Medicine; Sample (material); Population; Chart; Pharmacoepidemiology; Computer science; Econometrics; Medical physics; Mathematics","score_opus":0.39035391823633325,"score_gpt":0.557492027787349,"score_spread":0.1671381095510157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920466137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8743183,0.00078755483,0.11976044,0.0007882766,0.00056715426,0.0012176535,0.000005131007,0.00002384405,0.0025316135],"genre_scores_gemma":[0.7179101,0.0003894017,0.28028536,0.000042723725,0.00009702109,0.00005131966,0.000002290025,0.000015096748,0.0012067002],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9876147,0.0096143065,0.00066622347,0.00040920655,0.0012894734,0.00040607702],"domain_scores_gemma":[0.9291352,0.0689748,0.00018555784,0.0004927583,0.0009835805,0.0002280784],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026988795,0.00011921847,0.00102785,0.0005409076,0.00003285033,0.0000024323474,0.00017940199,0.00023527294,0.0013127049],"category_scores_gemma":[0.2484339,0.000094165145,0.00012217267,0.00086961716,0.0006559081,0.00003147914,0.00029095574,0.0006149553,0.000013566684],"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":[0.014335456,0.0011248891,0.17535351,0.0072125196,0.0017503178,0.00034827375,0.051187184,0.0002999536,0.23049724,0.05106763,0.0015136063,0.4653094],"study_design_scores_gemma":[0.021433346,0.013983745,0.4037279,0.003506827,0.00042387523,0.0005280008,0.21537605,0.024568273,0.18856469,0.11004329,0.016816892,0.0010271196],"about_ca_topic_score_codex":0.0023829364,"about_ca_topic_score_gemma":0.0005535651,"teacher_disagreement_score":0.46428227,"about_ca_system_score_codex":0.00032473606,"about_ca_system_score_gemma":0.00048473215,"threshold_uncertainty_score":0.99960023},"labels":[],"label_agreement":null},{"id":"W2921710211","doi":"10.1186/s12874-019-0680-5","title":"A comparison of the polytomous Rasch analysis output of RUMM2030 and R (ltm/eRm/TAM/lordif)","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St Joseph's Health Centre; Western University","funders":"Canadian Institutes of Health Research","keywords":"Rasch model; Polytomous Rasch model; Likert scale; Computer science; Differential item functioning; Item response theory; Rating scale; Reliability (semiconductor); Consistency (knowledge bases); Ordinal data; Software; Statistics; Scale (ratio); Psychometrics; Psychology; Econometrics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.9064755610915639,"score_gpt":0.6992995594836466,"score_spread":0.20717600160791727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921710211","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":[0.8439105,0.001625037,0.1483466,0.001147522,0.000554735,0.00035173362,0.00000852014,0.000014883495,0.0040404326],"genre_scores_gemma":[0.894804,0.00008831879,0.103385985,0.00008189271,0.00009253022,0.00001145903,0.0000010993678,0.000010783993,0.0015239156],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.944759,0.04443556,0.0019891,0.0009617411,0.006986684,0.0008678876],"domain_scores_gemma":[0.40404478,0.59136593,0.0008780507,0.0019812381,0.0012242224,0.00050577306],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16925737,0.00018647769,0.0019843774,0.0022397474,0.00016292694,0.000045722478,0.002913674,0.0004334073,0.001955254],"category_scores_gemma":[0.7406399,0.00010169143,0.0004651567,0.010617425,0.0018997674,0.000074537755,0.0018681247,0.0011338054,0.00004026009],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016665134,0.00009399831,0.8534713,0.000051772193,0.00015074943,0.0000022903885,0.00044935336,0.0000618959,0.0010979071,0.0019796074,0.0012619828,0.14121252],"study_design_scores_gemma":[0.0009650953,0.00053579774,0.94951826,0.000062447405,0.00011242405,0.000018386605,0.0045271064,0.015800426,0.0023493129,0.022811713,0.0031397108,0.00015934369],"about_ca_topic_score_codex":0.0006328039,"about_ca_topic_score_gemma":0.00027907937,"teacher_disagreement_score":0.5713825,"about_ca_system_score_codex":0.000032259555,"about_ca_system_score_gemma":0.0006497951,"threshold_uncertainty_score":0.9989571},"labels":[],"label_agreement":null},{"id":"W2924517740","doi":"10.1186/s12874-019-0666-3","title":"A review of spline function procedures in R","year":2019,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Data Analysis with R","field":"Computer Science","cited_by":577,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Univariate; Computer science; Spline (mechanical); Observational study; Software; Data science; Regression analysis; Machine learning; Thin plate spline; Data mining; Management science; Statistics; Mathematics; Multivariate statistics; Spline interpolation; Engineering","score_opus":0.7468500022474139,"score_gpt":0.6371901037000626,"score_spread":0.10965989854735136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924517740","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.312882e-8,0.7334698,0.2648272,0.0002228065,0.00024115606,0.0008904077,0.000005431768,0.000021829075,0.00032133065],"genre_scores_gemma":[3.9524082e-8,0.90569794,0.09307776,0.00037349382,0.00015493025,0.00027194343,0.000060485123,0.00002247025,0.00034092416],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9535694,0.03928413,0.0020144768,0.0012974055,0.0029345464,0.000900034],"domain_scores_gemma":[0.93063176,0.06472965,0.0007106696,0.0027961642,0.0006402386,0.0004915264],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09173721,0.00032592114,0.0042429706,0.0016171754,0.000033804856,0.000025835854,0.0048497003,0.00073440303,0.0006804765],"category_scores_gemma":[0.23153578,0.00022198824,0.00055771956,0.004455541,0.00039576518,0.00016752805,0.0023030406,0.0021950596,0.0005031926],"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":[0.0000053974213,0.000054979868,0.0000030914928,0.29895163,0.00004435897,0.000016379761,0.0000063688653,1.07628495e-7,9.702676e-8,0.0046034143,0.0074110874,0.6889031],"study_design_scores_gemma":[0.0001455988,0.00014983291,0.000004700388,0.18993726,0.00011937768,0.000058974572,0.00000305319,0.00030973394,2.3822513e-7,0.00077620597,0.8083482,0.00014686295],"about_ca_topic_score_codex":0.00013738753,"about_ca_topic_score_gemma":0.00043067324,"teacher_disagreement_score":0.80093706,"about_ca_system_score_codex":0.0001552832,"about_ca_system_score_gemma":0.011627218,"threshold_uncertainty_score":0.99397594},"labels":[],"label_agreement":null},{"id":"W2925234113","doi":"10.1186/s12874-019-0669-0","title":"Challenges and benefits of integrating diverse sampling strategies in the observation of cardiovascular risk factors (ORISCAV-LUX 2) study","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Promotion and Cardiovascular Prevention","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Université de Liège; Ministère de l'Enseignement Supérieur et de la Recherche","keywords":"Medicine; Population; Representativeness heuristic; Demography; Sample size determination; Obesity; Cross-sectional study; Gerontology; Environmental health; Psychology; Statistics; Internal medicine; Social psychology","score_opus":0.6724238314717124,"score_gpt":0.5376690718576099,"score_spread":0.13475475961410244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2925234113","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9596945,0.009264583,0.02924437,0.00016459028,0.000100004625,0.0012047167,0.000001931514,0.000008477438,0.00031685093],"genre_scores_gemma":[0.98436254,0.009250603,0.0062535014,0.000009239699,0.0000599878,0.000039745548,0.000006838929,0.000009457297,0.000008067785],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96280015,0.034103476,0.00056767877,0.00034800198,0.0018690631,0.00031162836],"domain_scores_gemma":[0.98823106,0.010651137,0.00011745653,0.00051628426,0.0003518135,0.00013224817],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10821143,0.00010671368,0.000784076,0.00028279852,0.00005785341,0.0000061144437,0.0001976164,0.00022012596,0.00006582711],"category_scores_gemma":[0.030132046,0.000067157904,0.00024342607,0.00037725383,0.00020391861,0.00007942919,0.0001347074,0.00088370766,0.0000021108715],"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":[0.00015910149,0.0005591554,0.28457275,0.002146471,0.0007257204,0.000011758189,0.025815494,0.00038422315,0.00015743959,0.0049904566,0.00000366158,0.6804738],"study_design_scores_gemma":[0.0016702936,0.0010287147,0.8594361,0.00033445098,0.00010219231,0.0000109551665,0.13611817,0.00028543043,0.000088963905,0.00073409267,0.00014055405,0.00005007006],"about_ca_topic_score_codex":0.0018431034,"about_ca_topic_score_gemma":0.0010167438,"teacher_disagreement_score":0.68042374,"about_ca_system_score_codex":0.000036215955,"about_ca_system_score_gemma":0.00045703244,"threshold_uncertainty_score":0.97803754},"labels":[],"label_agreement":null},{"id":"W2939022384","doi":"10.1186/s12874-019-0689-9","title":"Two new approaches for the visualisation of models for network meta-analysis","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Mental Health Research Topics","field":"Psychology","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":"St. Michael's Hospital","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Computer science; Meta-analysis; Network analysis; Visualization; Bootstrapping (finance); Data mining; Parametric statistics; Machine learning; Artificial intelligence; Statistics; Econometrics; Mathematics; Medicine","score_opus":0.9636633545570837,"score_gpt":0.710408294246267,"score_spread":0.2532550603108168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939022384","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001549667,0.0061970665,0.97845185,0.006687715,0.00045329222,0.004133656,0.000034377743,0.000019484178,0.0024728857],"genre_scores_gemma":[0.12969862,0.0003232429,0.814784,0.0016517626,0.002678647,0.0076077236,0.00020976618,0.000121133475,0.042925097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97609216,0.018986722,0.0009161174,0.00073683535,0.0018830134,0.0013851407],"domain_scores_gemma":[0.83276683,0.16522379,0.00019521195,0.0009784178,0.0003142783,0.0005214879],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.098604776,0.00017909406,0.0014376526,0.00040173164,0.00021151986,0.000019455792,0.0011698902,0.00039367625,0.008277353],"category_scores_gemma":[0.019994868,0.00010963707,0.00107624,0.0012024173,0.00054772303,0.00006544487,0.0002851601,0.0007461521,0.00005567301],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022114615,0.00017723808,0.00052698876,0.00048140297,0.027409777,0.000001121591,0.0012199274,0.0063542696,0.000012569461,0.89858043,0.014848141,0.04817667],"study_design_scores_gemma":[0.0043689995,0.0019215705,0.00095312734,0.000013904406,0.016119309,0.000008188727,0.0027706963,0.49930692,0.00015713839,0.44688886,0.0272091,0.00028220777],"about_ca_topic_score_codex":0.0024673678,"about_ca_topic_score_gemma":0.0022663355,"teacher_disagreement_score":0.49295264,"about_ca_system_score_codex":0.00007871546,"about_ca_system_score_gemma":0.0012533881,"threshold_uncertainty_score":0.99262923},"labels":[],"label_agreement":null},{"id":"W2939722761","doi":"10.1186/s12874-019-0706-z","title":"Adaptation and psychometric properties of the Norwegian version of the heart continuity of care questionnaire (HCCQ)","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Heart Failure Treatment and Management","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 Regina","funders":"Novo Nordisk Fonden; Høgskulen på Vestlandet","keywords":"Cronbach's alpha; Confirmatory factor analysis; Norwegian; Structural equation modeling; Construct validity; Medicine; Psychometrics; Psychology; Convergent validity; Reliability (semiconductor); Clinical psychology; Internal consistency; Statistics","score_opus":0.2596220750919317,"score_gpt":0.44989036520331005,"score_spread":0.19026829011137836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939722761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99082166,0.0014478097,0.000591565,0.0055010635,0.00019367925,0.0009994926,0.000002014448,0.00000554583,0.00043717207],"genre_scores_gemma":[0.9941886,0.0001903983,0.0049511623,0.00006414069,0.000029104887,0.000015695807,0.0000013205884,0.0000059725994,0.00055359764],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99453443,0.0036784692,0.0002905675,0.00017702761,0.0011289,0.00019058082],"domain_scores_gemma":[0.9971828,0.0018092674,0.0000865988,0.00039417605,0.0004268975,0.00010027469],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005426711,0.00006917196,0.0003763717,0.00020622794,0.000049721562,0.0000020245898,0.00017304489,0.00013151181,0.00012310561],"category_scores_gemma":[0.017134117,0.000032704516,0.00009962908,0.0006202729,0.0007064323,0.00002520638,0.00022223333,0.0002785844,0.0000055049336],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002067374,0.0003823416,0.83238184,0.0057821656,0.00015374407,0.0000017573985,0.005473563,0.000007579471,0.03725532,0.0038724137,0.0023402784,0.11028161],"study_design_scores_gemma":[0.0027200899,0.0013237839,0.9547835,0.001740477,0.000081636914,0.000011500675,0.0044671395,0.00022229491,0.027445752,0.00019952578,0.0069474843,0.000056800163],"about_ca_topic_score_codex":0.0005333613,"about_ca_topic_score_gemma":0.000327402,"teacher_disagreement_score":0.12240167,"about_ca_system_score_codex":0.00004259581,"about_ca_system_score_gemma":0.00053005764,"threshold_uncertainty_score":0.99114496},"labels":[],"label_agreement":null},{"id":"W2942641342","doi":"10.1186/s12874-019-0713-0","title":"Strategies for eliciting and synthesizing evidence for guidelines in rare diseases","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Hemophilia Treatment and Research","field":"Medicine","cited_by":108,"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; Hamilton Regional Laboratory Medicine Program; Hamilton General Hospital","funders":"","keywords":"Guideline; Medicine; Disease; Grading (engineering); MEDLINE; Evidence-based medicine; Clinical Practice; Systematic review; Evidence-based practice; Alternative medicine; Family medicine; Intensive care medicine; Pathology; Political science","score_opus":0.8020287486296619,"score_gpt":0.6558715841374072,"score_spread":0.1461571644922547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942641342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9148818,0.01344194,0.048085403,0.018819127,0.00016804352,0.0040506106,0.000018746547,0.00005343891,0.00048086152],"genre_scores_gemma":[0.6405708,0.004502873,0.34785682,0.0007054709,0.00136314,0.0019341802,0.000039783296,0.00007851043,0.0029483943],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99464285,0.0023832014,0.000495643,0.00057010533,0.001016986,0.0008912122],"domain_scores_gemma":[0.8586482,0.13972858,0.00004515456,0.0003167044,0.0007219931,0.0005393558],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020454917,0.0001453622,0.0006468084,0.000425205,0.00012274054,0.000038684462,0.0002298068,0.00026734,0.0002651479],"category_scores_gemma":[0.25840017,0.000099851284,0.00012024081,0.00029531616,0.0004205509,0.00012571234,0.0001805373,0.00041619796,0.000013825234],"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":[0.010359924,0.0003039109,0.2940272,0.012164536,0.0001727148,0.00021521245,0.0007721577,0.000015244371,0.02439888,0.022502841,0.005049884,0.6300175],"study_design_scores_gemma":[0.057545718,0.022701357,0.1792832,0.046029773,0.0006297099,0.0008468792,0.0744959,0.26178056,0.02510621,0.25481123,0.0744129,0.002356572],"about_ca_topic_score_codex":0.00021098349,"about_ca_topic_score_gemma":0.00023944145,"teacher_disagreement_score":0.62766093,"about_ca_system_score_codex":0.0000867152,"about_ca_system_score_gemma":0.0025137076,"threshold_uncertainty_score":0.74784666},"labels":[],"label_agreement":null},{"id":"W2942733342","doi":"10.1186/s12874-019-0683-2","title":"Barriers and recruitment strategies for precarious status migrants in Montreal, Canada","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Migration, Health and Trauma","field":"Psychology","cited_by":71,"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","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Political science; Gerontology","score_opus":0.43568247421239475,"score_gpt":0.5534045438975003,"score_spread":0.11772206968510551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942733342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98318297,0.0038767946,0.0043079136,0.0012991213,0.0009046476,0.0024463746,0.00005523677,0.000017229519,0.0039097075],"genre_scores_gemma":[0.98735976,0.0006198516,0.007196457,0.0007716013,0.00015146405,0.0014139349,0.0000365009,0.000026375865,0.002424039],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9887309,0.008039795,0.0004885466,0.000587431,0.0007884764,0.0013648495],"domain_scores_gemma":[0.9730958,0.025199786,0.000059715192,0.00035613825,0.00014680366,0.0011418066],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0133383395,0.0001453281,0.000468772,0.00024775445,0.000111035224,0.00002029011,0.0002610522,0.00034935644,0.0032019955],"category_scores_gemma":[0.012274198,0.00012279622,0.000035917008,0.00026105825,0.0002460866,0.0000485581,0.00006346717,0.0006615645,0.000027400403],"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":[0.0060197352,0.00020462852,0.4265517,0.001297521,0.00017420456,0.00020133666,0.041215893,0.00003096225,0.00013521076,0.04851146,0.091732636,0.3839247],"study_design_scores_gemma":[0.0097384835,0.002059423,0.7368093,0.00015543356,0.000017676106,0.000055173878,0.06118352,0.0014223552,0.000052430758,0.028771497,0.15932843,0.0004062707],"about_ca_topic_score_codex":0.9075429,"about_ca_topic_score_gemma":0.9962121,"teacher_disagreement_score":0.38351843,"about_ca_system_score_codex":0.00020056067,"about_ca_system_score_gemma":0.008417626,"threshold_uncertainty_score":0.9977092},"labels":[],"label_agreement":null},{"id":"W2944599912","doi":"10.1186/s12874-019-0742-8","title":"The relationship between statistical power and predictor distribution in multilevel logistic regression: a simulation-based approach","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Learning Partnership; University of British Columbia","funders":"Lawson Foundation","keywords":"Logistic regression; Multilevel model; Statistics; Statistical power; Regression analysis; Computer science; Regression; Econometrics; Distribution (mathematics); Psychology; Mathematics","score_opus":0.6827948773904509,"score_gpt":0.5984411841336096,"score_spread":0.08435369325684128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944599912","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":[0.024780916,0.00007856704,0.9734315,0.00045696492,0.00011489895,0.00069390563,0.00012510164,0.00003279905,0.00028529647],"genre_scores_gemma":[0.54271597,0.000004192366,0.45703256,0.000017574337,0.000055706787,0.00006690016,0.00003835394,0.00001216298,0.00005660413],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9773515,0.019042192,0.00076019275,0.0005660301,0.0015413921,0.00073873287],"domain_scores_gemma":[0.49988535,0.49917975,0.00008443615,0.00035032397,0.00017752175,0.000322606],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03266031,0.00018203899,0.00054320326,0.00013771391,0.00027229686,0.000055404842,0.00039848426,0.00045778678,0.00038728362],"category_scores_gemma":[0.67037046,0.0001106535,0.000046819117,0.00040059382,0.0013255501,0.000045499317,0.00020824837,0.0014659584,0.000030072302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023337027,0.00007993201,0.24868308,0.00025042085,0.00000841649,0.000010224507,0.00008927894,0.00002097717,0.0000030883016,0.7342202,0.00022764217,0.016173348],"study_design_scores_gemma":[0.0006999803,0.00014279381,0.31556255,0.00013068698,0.0000087854805,0.0000022150273,0.000107487765,0.13170761,0.0000028883276,0.55139786,0.00014610878,0.00009107632],"about_ca_topic_score_codex":0.000052680363,"about_ca_topic_score_gemma":0.0000331493,"teacher_disagreement_score":0.63771015,"about_ca_system_score_codex":0.000119913035,"about_ca_system_score_gemma":0.000762225,"threshold_uncertainty_score":0.9960798},"labels":[],"label_agreement":null},{"id":"W2945500023","doi":"10.1186/s12874-019-0726-8","title":"Reliability of routinely collected anthropometric measurements in primary care","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Toronto Western Hospital; University of Toronto; University Health Network; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"Institute of Nutrition, Metabolism and Diabetes; Sick Kids Foundation; Canadian Institutes of Health Research; Hospital for Sick Children; Institute of Human Development, Child and Youth Health; St. Michael's Hospital Foundation","keywords":"Reliability (semiconductor); Medicine; Primary care; Anthropometry; Family medicine","score_opus":0.39059824126256654,"score_gpt":0.5095364124085014,"score_spread":0.11893817114593491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945500023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9838402,0.00038160942,0.0006267605,0.00029499395,0.0002568514,0.0013256808,0.000007694287,0.000038948405,0.013227241],"genre_scores_gemma":[0.98134977,0.000104920655,0.017829329,0.0000976176,0.00012615797,0.000053483443,0.000031461623,0.000030303929,0.00037695846],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98071414,0.012674111,0.0007923628,0.00078110065,0.004100406,0.00093785336],"domain_scores_gemma":[0.9697518,0.027321894,0.0001310263,0.0008861988,0.0012930527,0.00061607943],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022140877,0.00020213968,0.0014320924,0.0011065247,0.000055826837,0.000006453044,0.0005027432,0.0005050557,0.0018325977],"category_scores_gemma":[0.12007991,0.00016174489,0.00019237945,0.0034384434,0.0010571788,0.00007918394,0.0006036988,0.0017090257,0.0001579134],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011019255,0.0057579125,0.9727737,0.002977203,0.00003920115,0.000028555703,0.00024857523,0.0000040195396,0.011318897,0.00018928549,0.000282197,0.0052785287],"study_design_scores_gemma":[0.0037489315,0.0020187893,0.9844267,0.00031622362,0.000022835557,0.000011229296,0.00038348252,0.00019291736,0.0076759947,0.00086155615,0.00021541772,0.00012591587],"about_ca_topic_score_codex":0.0014054669,"about_ca_topic_score_gemma":0.0006079289,"teacher_disagreement_score":0.09793904,"about_ca_system_score_codex":0.0008663167,"about_ca_system_score_gemma":0.0033871254,"threshold_uncertainty_score":0.9990799},"labels":[],"label_agreement":null},{"id":"W2946571535","doi":"10.1186/s12874-019-0737-5","title":"The utility of multivariate outlier detection techniques for data quality evaluation in large studies: an application within the ONDRI project","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":72,"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; Canada Research Chairs; Health Sciences Centre; University of New Brunswick; University of Toronto; Western University; Sunnybrook Health Science Centre; Lawson Health Research Institute; Parkwood Institute; University of Waterloo; McMaster University; Baycrest Hospital","funders":"Ontario Ministry of Research and Innovation; Western University; University of Toronto; Strong; Canadian Institutes of Health Research; Sunnybrook Research Institute; Ontario Brain Institute; Ontario Ministry of Research, Innovation and Science; Heart and Stroke Foundation of Canada","keywords":"Multivariate statistics; Computer science; Outlier; Multivariate analysis; Data mining; Anomaly detection; Data science; Quality (philosophy); Data quality; Information retrieval; Machine learning; Artificial intelligence; Operations management; Engineering","score_opus":0.7549132218594857,"score_gpt":0.6851126797262486,"score_spread":0.06980054213323716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946571535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64781904,0.000496122,0.337465,0.0018191207,0.00016448669,0.011666349,0.000026011137,0.00003515748,0.0005087331],"genre_scores_gemma":[0.98040974,0.00019488636,0.01635857,0.00010385927,0.00012155397,0.0024697757,0.00011221181,0.000015132668,0.00021426541],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9571357,0.037090458,0.0009617342,0.00083024474,0.003274126,0.00070776977],"domain_scores_gemma":[0.94117737,0.05377441,0.0002711334,0.0019616834,0.0026375542,0.00017787244],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27824783,0.00011462485,0.00043087287,0.00021209911,0.00023307909,0.000017180788,0.0007208892,0.00020939829,0.00008891346],"category_scores_gemma":[0.18595968,0.000059663456,0.000062453575,0.0006119853,0.00069909496,0.00012118886,0.0005684907,0.0008338876,0.000006885384],"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":[0.007655292,0.001122362,0.10540258,0.0011019653,0.00020651816,0.0000016130681,0.0022313034,3.8332314e-7,0.022078706,0.0036146878,0.00030876766,0.8562758],"study_design_scores_gemma":[0.0076303133,0.0036307008,0.45897254,0.00029307778,0.0001408462,0.000014453856,0.024133373,0.43922246,0.034900256,0.02145493,0.009399719,0.000207309],"about_ca_topic_score_codex":0.0010720717,"about_ca_topic_score_gemma":0.008421349,"teacher_disagreement_score":0.8560685,"about_ca_system_score_codex":0.00012578882,"about_ca_system_score_gemma":0.0019226628,"threshold_uncertainty_score":0.82089734},"labels":[],"label_agreement":null},{"id":"W2947482998","doi":"10.1186/s12874-019-0725-9","title":"A Bayesian multivariate latent t-regression model for assessing the association between corticosteroid and cranial radiation exposures and cardiometabolic complications in survivors of childhood acute lymphoblastic leukemia: a PETALE study","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Childhood Cancer Survivors' Quality of Life","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Hospital for Sick Children; Garron Family Cancer Centre; Université de Montréal; Canadian Cancer Society; Pediatric Oncology Group of Ontario; Ontario Institute for Cancer Research; Ministère de l'Économie, de la Science et de l'Innovation - Québec; Compute Canada; Canadian Institutes of Health Research; Cancer Research Society","keywords":"Medicine; Multivariate statistics; Multivariate analysis; Bayesian probability; Lymphoblastic Leukemia; Regression analysis; Association (psychology); Leukemia; Pediatrics; Internal medicine; Statistics; Psychology","score_opus":0.19952190963940653,"score_gpt":0.48901795400115283,"score_spread":0.2894960443617463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947482998","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8794277,0.00044993858,0.11614921,0.0014034698,0.00012733077,0.0023697158,0.000032709173,0.000019570967,0.000020408403],"genre_scores_gemma":[0.9901163,0.0002001657,0.00905441,0.0001176097,0.0001693279,0.00022978772,0.0000368102,0.000029883235,0.000045686407],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98803663,0.008351082,0.0009109058,0.00058679393,0.0015745665,0.0005400333],"domain_scores_gemma":[0.965995,0.032563157,0.00035001233,0.0004406699,0.00033253574,0.0003185881],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024289336,0.00019422022,0.0010840464,0.00045792913,0.00018476487,0.00004228788,0.00022604963,0.00031059235,0.000011135873],"category_scores_gemma":[0.02773973,0.00013864897,0.000104456216,0.0005058844,0.00025990262,0.000121678466,0.0002556746,0.00066832086,0.0000014040208],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030858984,0.00028868055,0.97390765,0.0002787204,0.00034039016,0.00000265533,0.007923961,0.00010899228,0.0015542856,0.00009732915,0.000015907019,0.01517286],"study_design_scores_gemma":[0.0064073238,0.00048973586,0.92137116,0.00023378595,0.00023154663,0.000014791667,0.001587709,0.0688827,0.00008603268,0.0005771775,0.00001043938,0.00010758878],"about_ca_topic_score_codex":0.0021987995,"about_ca_topic_score_gemma":0.0016620435,"teacher_disagreement_score":0.11068867,"about_ca_system_score_codex":0.00031554583,"about_ca_system_score_gemma":0.0014112326,"threshold_uncertainty_score":0.98045003},"labels":[],"label_agreement":null},{"id":"W2949818370","doi":"10.1186/s12874-019-0770-4","title":"Outcomes of two randomized controlled trials, employing participants recruited through Mechanical Turk, of Internet interventions targeting unhealthy alcohol use","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"Canada Research Chairs","keywords":"Psychological intervention; Randomized controlled trial; Medicine; Intervention (counseling); Crowdsourcing; Brief intervention; Physical therapy; Psychiatry; Surgery; World Wide Web","score_opus":0.7414199475487552,"score_gpt":0.5968544408829294,"score_spread":0.1445655066658258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949818370","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":[0.36022472,0.0004791446,0.6358533,0.00070872786,0.0008788586,0.0017062733,0.0000027192384,0.000059606755,0.00008665653],"genre_scores_gemma":[0.7199074,0.00014591521,0.27916896,0.0001533586,0.000066826084,0.00019672477,0.0000049646655,0.000020779438,0.0003350731],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8523323,0.13721332,0.0053707203,0.0009876072,0.0026777904,0.0014182726],"domain_scores_gemma":[0.5878575,0.40760612,0.0016632307,0.0012307472,0.0010703702,0.00057201536],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2591137,0.00028352346,0.00662572,0.0005741999,0.00010177137,0.00008506201,0.0014982343,0.00037102486,0.00051313784],"category_scores_gemma":[0.5893766,0.000182872,0.001811141,0.0007812139,0.0007493769,0.00027260146,0.0011343015,0.0011743959,0.000030177252],"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":[0.1880624,0.002409858,0.036734216,0.00394258,0.0062859575,0.00014975882,0.012912893,0.00078371377,0.046606366,0.6534058,0.0030029481,0.045703527],"study_design_scores_gemma":[0.5785689,0.001433406,0.0013166056,0.0041199457,0.0005055827,0.000048309477,0.0013094649,0.3349996,0.027938033,0.048775226,0.00030351052,0.00068142224],"about_ca_topic_score_codex":0.0023745273,"about_ca_topic_score_gemma":0.00025802574,"teacher_disagreement_score":0.60463053,"about_ca_system_score_codex":0.00007134748,"about_ca_system_score_gemma":0.0009278487,"threshold_uncertainty_score":0.7628983},"labels":[],"label_agreement":null},{"id":"W2953399894","doi":"10.1186/s12874-019-0769-x","title":"Ranking hospital performance based on individual indicators: can we increase reliability by creating composite indicators?","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Patient Satisfaction in Healthcare","field":"Health Professions","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":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Reliability (semiconductor); Ranking (information retrieval); Computer science; Reliability engineering; Statistics; Psychology; Medicine; Information retrieval; Mathematics; Engineering","score_opus":0.2795359781563761,"score_gpt":0.5469929941505802,"score_spread":0.26745701599420413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953399894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9847601,0.00015991324,0.0025470797,0.00475039,0.001400233,0.0026965933,0.00016578897,0.00019620627,0.0033237087],"genre_scores_gemma":[0.9779157,0.00015986172,0.017811636,0.0021955587,0.0004464563,0.00083537464,0.00025861987,0.000073487274,0.00030327402],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9337101,0.05702439,0.001517733,0.0011728501,0.004490932,0.0020839733],"domain_scores_gemma":[0.8791316,0.11707927,0.00059721206,0.0011443648,0.00039095592,0.0016565832],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.05770243,0.00037365375,0.0010047806,0.0015665451,0.0017354025,0.000020233843,0.0011855187,0.001397201,0.0063260244],"category_scores_gemma":[0.09367735,0.0003200439,0.00013729658,0.0018577762,0.00092542276,0.0001568935,0.00074647204,0.0072791115,0.0007769043],"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":[0.0006048662,0.00014310783,0.9664741,0.0014865532,0.00002409462,0.000007958699,0.002576321,0.00002026092,0.00005194003,0.00035406687,0.0027876494,0.025469078],"study_design_scores_gemma":[0.004508093,0.0021588414,0.9728236,0.0024581184,0.00002484085,0.0000034694956,0.0030440378,0.005673833,0.00037036798,0.0005230281,0.0079019,0.0005098708],"about_ca_topic_score_codex":0.0033749288,"about_ca_topic_score_gemma":0.0002554233,"teacher_disagreement_score":0.060054883,"about_ca_system_score_codex":0.0010641338,"about_ca_system_score_gemma":0.0062788012,"threshold_uncertainty_score":0.99992514},"labels":[],"label_agreement":null},{"id":"W2963820072","doi":"10.1186/s12874-019-0801-1","title":"The association between influenza vaccination and socioeconomic status in high income countries varies by the measure used: a systematic review","year":2019,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Blood Services; University of Alberta; Ministry of Health; University of Calgary","funders":"University of Calgary","keywords":"Socioeconomic status; Medicine; Population; Social class; MEDLINE; Vaccination; Ethnic group; Demography; Marital status; Gerontology; Environmental health; Immunology","score_opus":0.4836820172130709,"score_gpt":0.5751888638084325,"score_spread":0.09150684659536157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963820072","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":[0.00007059093,0.9867061,0.00015029174,0.0032671297,0.00018452933,0.009360393,0.00011817055,0.00003469859,0.000108106484],"genre_scores_gemma":[0.000013990123,0.99510103,0.00022575674,0.00071758317,0.0002761027,0.0027321882,0.00006553891,0.00007388927,0.0007939077],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9097558,0.078782514,0.0031478282,0.0009841324,0.0052081537,0.0021215621],"domain_scores_gemma":[0.65355736,0.34204406,0.0012534552,0.0013140292,0.0013025076,0.00052859256],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16253711,0.00056743715,0.006454425,0.00055065757,0.0007068512,0.0001783727,0.0011069747,0.0012961285,0.0001861065],"category_scores_gemma":[0.41152966,0.00027963388,0.00040437028,0.00082393055,0.0010244144,0.00014016939,0.001045913,0.0048130355,0.00038019917],"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":[0.00007902598,0.000022772641,0.0063980953,0.9257497,0.0014423333,0.000010148552,0.00028902187,5.4447064e-8,6.025766e-8,0.00144297,0.004556824,0.060008984],"study_design_scores_gemma":[0.001456436,0.00029783114,0.0021149046,0.2966526,0.0024747772,0.00003290026,0.00025446524,0.000009229064,4.138061e-7,0.0006495581,0.6957361,0.00032075722],"about_ca_topic_score_codex":0.0007351657,"about_ca_topic_score_gemma":0.00085092726,"teacher_disagreement_score":0.69117934,"about_ca_system_score_codex":0.0031748516,"about_ca_system_score_gemma":0.0073596686,"threshold_uncertainty_score":0.9999656},"labels":[],"label_agreement":null},{"id":"W2964564601","doi":"10.1186/s12874-019-0809-6","title":"High-performing physicians are more likely to participate in a research study: findings from a quality improvement study","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Ottawa; Bruyère","funders":"Canadian Institutes of Health Research; Pfizer Canada; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Pfizer","keywords":"Medicine; Generalizability theory; Family medicine; Odds ratio; Confidence interval; Health care; Quality management; MEDLINE; Randomized controlled trial; Psychology; Internal medicine","score_opus":0.9666743594940868,"score_gpt":0.8324360759965769,"score_spread":0.13423828349750988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964564601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9660603,0.000009501951,0.0018457235,0.020667328,0.0007147974,0.010490806,0.000049987266,0.00005838891,0.00010317307],"genre_scores_gemma":[0.9800855,0.000011192513,0.0066119344,0.006222935,0.00047675773,0.005660641,0.0000060967723,0.00004498247,0.00087995303],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.79052603,0.18792798,0.0034658348,0.0021818501,0.010367357,0.0055309273],"domain_scores_gemma":[0.8060617,0.18930456,0.00028664796,0.0014776828,0.0013053284,0.0015640644],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.312451,0.00026534975,0.0012966726,0.0014194283,0.0012246233,0.000039173014,0.001785584,0.0003739406,0.004136599],"category_scores_gemma":[0.26250872,0.00022349515,0.00006375421,0.0036336337,0.00047751464,0.0002073194,0.0026087742,0.0051679136,0.0022755552],"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":[0.0007023295,0.0008635,0.8350427,0.00026371534,0.000026541542,0.0000473252,0.14615712,0.0000085408,0.0018015202,0.00029550595,0.0023697496,0.012421451],"study_design_scores_gemma":[0.003576465,0.0022345714,0.6863435,0.00026632962,0.000004365902,1.680564e-7,0.30515116,0.0001941402,0.00015340249,0.00084619015,0.0010730898,0.00015659093],"about_ca_topic_score_codex":0.10690552,"about_ca_topic_score_gemma":0.14764884,"teacher_disagreement_score":0.15899406,"about_ca_system_score_codex":0.0013607882,"about_ca_system_score_gemma":0.0057801576,"threshold_uncertainty_score":0.9998562},"labels":[],"label_agreement":null},{"id":"W2966928705","doi":"10.1186/s12874-019-0815-8","title":"Consolidated criteria for strengthening reporting of health research involving indigenous peoples: the CONSIDER statement","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Indigenous Health, Education, and Rights","field":"Social Sciences","cited_by":532,"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":"Health Research Council of New Zealand","keywords":"Indigenous; Statement (logic); MEDLINE; Medicine; Family medicine; Environmental health; Political science; Psychology","score_opus":0.6896195728371073,"score_gpt":0.6408542495531911,"score_spread":0.04876532328391614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966928705","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760277,0.0021870108,0.0063312612,0.0045800875,0.001157669,0.0042504794,0.000013989055,0.000043779673,0.005408001],"genre_scores_gemma":[0.9059165,0.018459687,0.06705478,0.00032085937,0.0012960351,0.00019300994,0.000067484696,0.00006586416,0.006625783],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.895233,0.09329699,0.0033909385,0.00076800835,0.0042450796,0.0030660145],"domain_scores_gemma":[0.74599767,0.24525687,0.002023221,0.0010155919,0.004669779,0.0010368908],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4242062,0.00013638519,0.0007747364,0.0005124859,0.008128214,0.00007840006,0.00088290015,0.00035810657,0.0013858755],"category_scores_gemma":[0.09743724,0.00009065497,0.00010661357,0.0009807331,0.0025834693,0.00010839439,0.00004002639,0.0012397208,0.000034745543],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012899975,0.00016583705,0.004605585,0.0010203257,0.000045920773,0.0000051710035,0.8422758,0.0000023244988,0.00008204166,0.14575188,0.0015425739,0.0043735243],"study_design_scores_gemma":[0.00092200324,0.0010090728,0.0020393333,0.0006434524,0.000009681687,0.000017550528,0.6451066,0.00019313979,0.0006727931,0.024323821,0.32484323,0.0002192865],"about_ca_topic_score_codex":0.23679534,"about_ca_topic_score_gemma":0.6835849,"teacher_disagreement_score":0.44678956,"about_ca_system_score_codex":0.00057746744,"about_ca_system_score_gemma":0.1710617,"threshold_uncertainty_score":0.999527},"labels":[],"label_agreement":null},{"id":"W2971382867","doi":"10.1186/s12874-019-0823-8","title":"Integrating expert opinion with clinical trial data to extrapolate long-term survival: a case study of CAR-T therapy for children and young adults with relapsed or refractory acute lymphoblastic leukemia","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"CAR-T cell therapy research","field":"Medicine","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":"Precision Nanosystems (Canada)","funders":"Novartis Pharmaceuticals Corporation","keywords":"Medicine; Refractory (planetary science); Lymphoblastic Leukemia; Pediatrics; Expert opinion; Young adult; Clinical trial; Term (time); Leukemia; Oncology; Intensive care medicine; Internal medicine","score_opus":0.5060217933686972,"score_gpt":0.5783941496880564,"score_spread":0.07237235631935912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971382867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97657377,0.00046931126,0.011647563,0.00018546131,0.0004946779,0.0105088195,0.00004269734,0.000047126992,0.00003059312],"genre_scores_gemma":[0.95073473,0.0036752368,0.041298762,0.0001855533,0.0015395561,0.0009129354,0.000253291,0.00021324288,0.0011866892],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.98068225,0.012544605,0.0012605985,0.0017052783,0.0027116202,0.0010956546],"domain_scores_gemma":[0.947708,0.04783482,0.0002528687,0.0021444706,0.0008321916,0.0012276378],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036670323,0.00039464273,0.0017932898,0.00056411483,0.00016894494,0.000046309127,0.000993931,0.0005398434,0.0007370544],"category_scores_gemma":[0.031068854,0.00022434095,0.00011236211,0.0007876318,0.00090580113,0.00014820784,0.0007197771,0.0017492716,0.0000053079048],"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":[0.6928522,0.0015872156,0.10698953,0.00022926935,0.001211967,0.0016166953,0.0041072406,7.1869147e-7,0.0031162126,0.000010443191,0.00023081561,0.1880477],"study_design_scores_gemma":[0.53942,0.29621077,0.12712882,0.002315009,0.00023588962,0.011115542,0.018991165,0.0028361522,0.00044743056,0.000010872568,0.00048500646,0.0008033215],"about_ca_topic_score_codex":0.005555432,"about_ca_topic_score_gemma":0.01118065,"teacher_disagreement_score":0.29462355,"about_ca_system_score_codex":0.00024083561,"about_ca_system_score_gemma":0.005480793,"threshold_uncertainty_score":0.99195063},"labels":[],"label_agreement":null},{"id":"W2972327833","doi":"10.1186/s12874-019-0827-4","title":"Graphical comparisons of relative disease burden across multiple risk factors","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Acute Ischemic Stroke Management","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":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"Health Research Board","keywords":"Disease; Burden of disease; Medicine; Computer science; Pathology","score_opus":0.341606675089123,"score_gpt":0.5272008957352242,"score_spread":0.1855942206461012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972327833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89477825,0.00045595464,0.09922925,0.0016648134,0.00027477616,0.0010629455,0.000066212684,0.000055967965,0.0024118354],"genre_scores_gemma":[0.9476604,0.00035419746,0.049349304,0.00009619059,0.00021612694,0.00006078559,0.00006404839,0.0000366285,0.0021623413],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9872643,0.0074524176,0.00070703257,0.00072254124,0.0028034556,0.0010502517],"domain_scores_gemma":[0.9423292,0.05469123,0.00019186208,0.0009708684,0.0004187766,0.0013980507],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016326416,0.00022739443,0.0010414176,0.0002800623,0.00012195901,0.000008443185,0.0005967563,0.0004158946,0.0022188094],"category_scores_gemma":[0.16168511,0.00016730746,0.00032879857,0.0007268002,0.0017739268,0.0000635964,0.0009854761,0.0021714545,0.00021552162],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021388384,0.00026891773,0.9778682,0.00040792432,0.00033103715,0.000084302745,0.0009347095,0.000017011209,0.0014582565,0.0016234402,0.012213942,0.0026533992],"study_design_scores_gemma":[0.0064152507,0.00110109,0.9276159,0.00038010307,0.00020078103,0.000016539643,0.0064877877,0.01319211,0.0018239163,0.0010078878,0.041477572,0.00028107778],"about_ca_topic_score_codex":0.0010946052,"about_ca_topic_score_gemma":0.00011012614,"teacher_disagreement_score":0.1453587,"about_ca_system_score_codex":0.00011733359,"about_ca_system_score_gemma":0.00078913703,"threshold_uncertainty_score":0.9986933},"labels":[],"label_agreement":null},{"id":"W2980554789","doi":"10.1186/s12874-019-0837-2","title":"Incorporating adjustments for variability in control group response rates in network meta-analysis: a case study of biologics for rheumatoid arthritis","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Amgen (Canada); McMaster University","funders":"Amgen Canada; Amgen","keywords":"Rheumatoid arthritis; Meta-analysis; Medicine; Arthritis; Physical therapy; Internal medicine","score_opus":0.4211965493035814,"score_gpt":0.5182475355651054,"score_spread":0.09705098626152397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980554789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92115384,0.0075188046,0.062978916,0.00051588105,0.00008424139,0.007659889,0.000053464646,0.000020141693,0.000014829377],"genre_scores_gemma":[0.944578,0.0014685674,0.04996447,0.00010333002,0.00004269135,0.003760933,0.000030572814,0.000027976257,0.000023446104],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9384273,0.056176197,0.0018265273,0.00097365974,0.0012988914,0.0012973971],"domain_scores_gemma":[0.81966746,0.1782569,0.00025524577,0.0007106024,0.00066746137,0.00044235212],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19459751,0.00027214194,0.003475428,0.001156085,0.00013060805,0.000022667062,0.00039498153,0.00042650255,0.00048237876],"category_scores_gemma":[0.18658437,0.00019954072,0.00066090137,0.00191343,0.0006003193,0.000092970404,0.00021877974,0.0009599167,0.00000437287],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.078125745,0.0056953663,0.84870434,0.0007012787,0.030172473,0.0019585285,0.0025545915,0.0007513886,0.0015289552,0.0050462727,0.00015975836,0.024601279],"study_design_scores_gemma":[0.2550359,0.10618328,0.20328534,0.0013294618,0.005314883,0.0026828516,0.084494576,0.21516924,0.00077390583,0.1221874,0.0014991733,0.0020439874],"about_ca_topic_score_codex":0.002552162,"about_ca_topic_score_gemma":0.022848347,"teacher_disagreement_score":0.645419,"about_ca_system_score_codex":0.00013120647,"about_ca_system_score_gemma":0.001266835,"threshold_uncertainty_score":0.9949821},"labels":[],"label_agreement":null},{"id":"W2981452012","doi":"10.1186/s12874-019-0829-2","title":"BUGSnet: an R package to facilitate the conduct and reporting of Bayesian network Meta-analyses","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":319,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Public Health Ontario; University of Waterloo","funders":"University of Waterloo","keywords":"Computer science; Bayesian probability; Nice; Inference; Bayesian network; Gibbs sampling; Data mining; Data science; Machine learning; Operations research; Artificial intelligence; Mathematics","score_opus":0.9946169984997515,"score_gpt":0.76499760368872,"score_spread":0.22961939481103144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981452012","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":[0.36908162,0.0056183627,0.60977155,0.006320025,0.00037330383,0.0021630444,0.000015589885,0.000008703097,0.006647803],"genre_scores_gemma":[0.6383692,0.000107677515,0.338438,0.0012314655,0.0003124656,0.00019474061,0.000008182651,0.000029255301,0.021309022],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.34276947,0.5956274,0.030910378,0.0031233954,0.025926845,0.0016424797],"domain_scores_gemma":[0.30743033,0.65759236,0.0143437665,0.013019063,0.005401393,0.0022130946],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8535877,0.00030346314,0.008746522,0.0005479185,0.00023338929,0.00028210226,0.0032286053,0.00023946345,0.04568693],"category_scores_gemma":[0.87369347,0.00010597341,0.0019820647,0.0028321731,0.00072819274,0.00015132719,0.0008943671,0.0007870075,0.00090432947],"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":[0.0006698034,0.00035436268,0.23097485,0.0013924437,0.018903952,0.0002171597,0.014885277,0.0029771423,0.013885071,0.06421934,0.31888664,0.33263394],"study_design_scores_gemma":[0.001350477,0.0031891312,0.084973305,0.00022677613,0.0072230506,0.00044071476,0.034020357,0.061883107,0.0014144424,0.3134416,0.49056616,0.0012708562],"about_ca_topic_score_codex":0.00048232914,"about_ca_topic_score_gemma":0.0014029606,"teacher_disagreement_score":0.33136308,"about_ca_system_score_codex":0.000018956785,"about_ca_system_score_gemma":0.00059702503,"threshold_uncertainty_score":0.9998736},"labels":[],"label_agreement":null},{"id":"W2981984059","doi":"10.1186/s12874-019-0831-8","title":"A comparison of the statistical performance of different meta-analysis models for the synthesis of subgroup effects from randomized clinical trials","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"University of Toronto; St. Michael's Hospital","funders":"Arthritis Society","keywords":"Meta-analysis; Subgroup analysis; Variation (astronomy); Statistics; Clinical trial; Econometrics; Aggregate data; Medicine; Mathematics; Internal medicine","score_opus":0.9800549714273895,"score_gpt":0.7562543709335068,"score_spread":0.22380060049388273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981984059","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":[0.2184549,0.0027287696,0.77394694,0.0006432425,0.00027624326,0.0037238451,0.00010378703,0.0000012828835,0.000120986835],"genre_scores_gemma":[0.9215968,0.00022222317,0.077039406,0.000048373942,0.00006161961,0.0006337874,0.0000051494458,0.000010853934,0.00038175192],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.11989362,0.8306524,0.029377332,0.0013336341,0.018148389,0.00059462624],"domain_scores_gemma":[0.020313032,0.9625124,0.00955902,0.004879338,0.002425487,0.00031072067],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8911476,0.00030822546,0.036546286,0.0005546022,0.000109716115,0.000058128702,0.0049339104,0.00039230738,0.015888883],"category_scores_gemma":[0.9532602,0.00008588859,0.018645432,0.0018705671,0.002203634,0.000056326902,0.00067949493,0.00073502905,0.000044791257],"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":[0.0654921,0.002014678,0.1365099,0.0031913985,0.50692755,0.0000013981966,0.0018733713,0.004331913,0.0008292828,0.11617941,0.00957745,0.15307154],"study_design_scores_gemma":[0.007175176,0.00022675275,0.0064103934,0.00004166161,0.11558362,3.66279e-7,0.00040215606,0.8377673,0.0014981241,0.030702928,0.00010082556,0.000090676534],"about_ca_topic_score_codex":0.00022174265,"about_ca_topic_score_gemma":0.00022205488,"teacher_disagreement_score":0.8334354,"about_ca_system_score_codex":0.000017321594,"about_ca_system_score_gemma":0.00052029965,"threshold_uncertainty_score":0.99118257},"labels":[],"label_agreement":null},{"id":"W2982642576","doi":"10.1186/s12874-019-0842-5","title":"Unweighted regression models perform better than weighted regression techniques for respondent-driven sampling data: results from a simulation study","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","cited_by":136,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; St. Michael's Hospital; Aboriginal Affairs Northern Dev Canada; York University","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Regression analysis; Regression; Respondent; Sampling (signal processing); Computer science; Linear regression; Mathematics","score_opus":0.6636363935943407,"score_gpt":0.5996986958659981,"score_spread":0.06393769772834257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982642576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7592945,0.00021296454,0.23247033,0.0018891088,0.00039554475,0.004725359,0.00026068994,0.0002767524,0.0004747581],"genre_scores_gemma":[0.62602866,0.00019874044,0.36797956,0.00025857257,0.0013171044,0.00028255125,0.0023679822,0.00012941298,0.0014374293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97753716,0.012785003,0.0016233437,0.0022894994,0.0043732417,0.0013917781],"domain_scores_gemma":[0.9007813,0.09241553,0.0004595467,0.0038801772,0.0013449731,0.0011185202],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04040043,0.00049583125,0.0015377132,0.0011537398,0.00040142226,0.00006404381,0.0016378989,0.0011993153,0.0006259203],"category_scores_gemma":[0.08420838,0.00033018886,0.00017410272,0.0009586886,0.00043539927,0.0005066029,0.0018240751,0.0024585072,0.00011030981],"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":[0.14295547,0.0045946497,0.057487458,0.0012723956,0.0008960498,0.00052352855,0.026509106,0.00045351827,0.06206245,0.00050780247,0.014987258,0.68775034],"study_design_scores_gemma":[0.014425271,0.00473536,0.0070914845,0.002762848,0.00022016357,0.000026175847,0.012342527,0.9358325,0.0057851104,0.009036449,0.007168352,0.00057373126],"about_ca_topic_score_codex":0.0007606512,"about_ca_topic_score_gemma":0.0005792549,"teacher_disagreement_score":0.935379,"about_ca_system_score_codex":0.00034615357,"about_ca_system_score_gemma":0.0015743516,"threshold_uncertainty_score":0.999915},"labels":[],"label_agreement":null},{"id":"W2988407356","doi":"10.1186/s12874-019-0861-2","title":"Modeling perinatal mortality in twins via generalized additive mixed models: a comparison of estimation approaches","year":2019,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Assisted Reproductive Technology and Twin Pregnancy","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Fonds de Recherche du Québec - Santé","keywords":"Birth order; Frequentist inference; Birth weight; Statistics; Multiple birth; Perinatal mortality; Bayesian probability; Gestational age; Generalized linear mixed model; Bayes' theorem; Medicine; Mathematics; Obstetrics; Bayesian inference; Pregnancy; Fetus; Population; Biology","score_opus":0.6556950360871304,"score_gpt":0.537649864861985,"score_spread":0.11804517122514546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2988407356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58157367,0.0009470568,0.41561455,0.00025713688,0.000103756436,0.00060704886,0.0000042652446,0.000040373623,0.0008521819],"genre_scores_gemma":[0.8346375,0.00007124235,0.16489604,0.00001791373,0.00005433661,0.00015057843,0.000050987557,0.000019793946,0.0001015859],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99059784,0.0059188306,0.0007957359,0.00078277057,0.0012936348,0.00061117765],"domain_scores_gemma":[0.9941837,0.004370163,0.00011720735,0.0007583271,0.0003391486,0.00023141864],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014390759,0.00018401437,0.0011211785,0.00060295535,0.00006297102,0.0000035934238,0.00034522507,0.00074346724,0.00039309962],"category_scores_gemma":[0.024149805,0.00015181028,0.00014067578,0.0006775438,0.0009500195,0.00011521713,0.0003380744,0.001753101,0.000025770181],"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":[0.007401031,0.004253944,0.30960307,0.0044057714,0.0009416888,0.00028902866,0.0067122662,0.07319387,0.009335288,0.13650937,0.00016366215,0.447191],"study_design_scores_gemma":[0.0021695339,0.0004493554,0.013934617,0.00035862892,0.000034761386,0.000057468475,0.0014652014,0.95422995,0.0048819454,0.022287296,0.000010471771,0.00012076321],"about_ca_topic_score_codex":0.0005294637,"about_ca_topic_score_gemma":0.00036593317,"teacher_disagreement_score":0.8810361,"about_ca_system_score_codex":0.00014139812,"about_ca_system_score_gemma":0.0008856781,"threshold_uncertainty_score":0.9840702},"labels":[],"label_agreement":null},{"id":"W2991222514","doi":"10.1186/s12874-019-0838-1","title":"A review and synthesis of frameworks for engagement in health research to identify concepts of knowledge user engagement","year":2019,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Mental Health and Patient Involvement","field":"Health Professions","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; McMaster University Medical Centre; Ottawa Hospital; Queen's University","funders":"Canadian Institutes of Health Research","keywords":"Knowledge management; Process (computing); Knowledge translation; Knowledge sharing; User engagement; Health care; Computer science; Medical education; Psychology; Data science; Medicine; World Wide Web; Political science","score_opus":0.9605792290406496,"score_gpt":0.790036834336076,"score_spread":0.17054239470457366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991222514","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":[0.000031599477,0.9652473,0.0047812676,0.0011290412,0.00083017023,0.027248377,0.00021479595,0.000012432333,0.0005050615],"genre_scores_gemma":[0.000011542899,0.9539326,0.029321134,0.0014381347,0.00023402498,0.013977788,0.00013277165,0.00007944618,0.00087257486],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.6753317,0.31054536,0.0063173757,0.0015107233,0.0031213267,0.0031734786],"domain_scores_gemma":[0.64479417,0.35028213,0.0010097426,0.0011676122,0.0012933015,0.0014530314],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.40929973,0.00045100928,0.0061588516,0.0020215425,0.00059229153,0.000005721014,0.001464795,0.0018204097,0.0017728098],"category_scores_gemma":[0.20019689,0.00034511977,0.00036847038,0.0020090675,0.0007371975,0.00004292747,0.0025380654,0.009768097,0.00022168859],"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":[0.000098684315,0.0002834551,0.00012948425,0.54742604,0.000058235444,0.0000012548189,0.0012501252,5.1910046e-8,2.2837848e-7,0.002790571,0.018409215,0.42955264],"study_design_scores_gemma":[0.0005292989,0.0009963247,0.00004290742,0.3392475,0.00008282054,6.618617e-7,0.0012185945,0.000004448725,0.0000015362897,0.00033904903,0.6574024,0.00013445038],"about_ca_topic_score_codex":0.0012133758,"about_ca_topic_score_gemma":0.0014849078,"teacher_disagreement_score":0.6389932,"about_ca_system_score_codex":0.0012262294,"about_ca_system_score_gemma":0.018984327,"threshold_uncertainty_score":0.9999001},"labels":[],"label_agreement":null},{"id":"W2992207804","doi":"10.1186/s12874-019-0871-0","title":"Analysis of reporting completeness in exercise cancer trials: a systematic review","year":2019,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Checklist; Psychological intervention; Medicine; Physical therapy; MEDLINE; Clinical trial; Randomized controlled trial; Family medicine; Psychology; Internal medicine; Psychiatry","score_opus":0.91069482570319,"score_gpt":0.7111078870252757,"score_spread":0.19958693867791433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992207804","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":[0.000008387037,0.99037313,0.0016695735,0.00013306028,0.00054544664,0.0069962824,0.000060236016,0.000021255604,0.00019262973],"genre_scores_gemma":[0.0000045508887,0.99437296,0.00090093893,0.0001508117,0.00018295334,0.0035938467,0.00021165071,0.00006354923,0.00051872194],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.88125205,0.09892313,0.013016671,0.0012854465,0.0044363975,0.0010862887],"domain_scores_gemma":[0.74916303,0.23427764,0.010269593,0.0033556581,0.001849307,0.0010847985],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30924115,0.00048459176,0.038215064,0.0032121604,0.00003909941,0.000012412283,0.0009137151,0.0011173693,0.0027756577],"category_scores_gemma":[0.58092874,0.00030213618,0.0038569842,0.0076649524,0.00042911782,0.000027715283,0.00045412386,0.0024279542,0.00003219456],"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":[0.000074085176,0.00005634028,0.00020151181,0.73932153,0.0019061696,0.00016912015,0.00008180833,2.89827e-7,2.1470719e-7,0.000038119633,0.00013141967,0.2580194],"study_design_scores_gemma":[0.00039333102,0.00008525438,0.000028102715,0.9116202,0.050405916,0.00007392226,0.00019694523,0.000092232265,5.4381013e-7,0.000013883301,0.036878526,0.0002111198],"about_ca_topic_score_codex":0.0054014814,"about_ca_topic_score_gemma":0.01138688,"teacher_disagreement_score":0.2716876,"about_ca_system_score_codex":0.00055605365,"about_ca_system_score_gemma":0.011124326,"threshold_uncertainty_score":0.9999431},"labels":[],"label_agreement":null},{"id":"W3005979941","doi":"10.1186/s12874-019-0876-8","title":"LEVEL (Logical Explanations & Visualizations of Estimates in Linear mixed models): recommendations for reporting multilevel data and analyses","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":127,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute; McMaster University","funders":"","keywords":"Multilevel model; Computer science; Data science; Statistics; Data mining; Mathematics; Machine learning","score_opus":0.9892096136300748,"score_gpt":0.7711307624025253,"score_spread":0.21807885122754944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005979941","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006541578,0.000089160305,0.9887838,0.0036293298,0.00003090609,0.00055304694,0.00022282971,0.00008644267,0.00006292356],"genre_scores_gemma":[0.038943388,0.00021153135,0.9600252,0.00010487522,0.00005551145,0.0002039883,0.00040555792,0.000022230457,0.000027748449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99394304,0.0028704104,0.0016050328,0.000550462,0.0006255622,0.0004054841],"domain_scores_gemma":[0.8574357,0.13972789,0.0007559563,0.00078675605,0.00084604014,0.00044763938],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018967204,0.00013480321,0.0006591917,0.00031953954,0.0001317418,0.000013181044,0.0005933032,0.00025302963,0.00018624846],"category_scores_gemma":[0.6580242,0.00011427937,0.000048292306,0.00056498195,0.0004546303,0.00020182217,0.0007912337,0.0005188256,0.0000012251234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005137393,0.0012497732,0.005670229,0.0025377607,0.00025663842,0.000039046725,0.006801959,0.0012167483,0.020307016,0.83557653,0.027941654,0.09788891],"study_design_scores_gemma":[0.00035192634,0.00009570413,0.00015141175,0.00011729355,0.000021821335,0.000008931784,0.00078254833,0.51713604,0.0017388288,0.4790523,0.0004433101,0.0000999],"about_ca_topic_score_codex":0.00014482977,"about_ca_topic_score_gemma":0.0012475887,"teacher_disagreement_score":0.639057,"about_ca_system_score_codex":0.000033951346,"about_ca_system_score_gemma":0.0005248383,"threshold_uncertainty_score":0.6573692},"labels":[],"label_agreement":null},{"id":"W3008510792","doi":"10.1186/s12874-020-0899-1","title":"A systematic survey of randomised trials that stopped early for reasons of futility","year":2020,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interim; Interim analysis; Early stopping; Sample size determination; Clinical trial; Medicine; Data monitoring committee; Protocol (science); Sample (material); Psychological intervention; Set (abstract data type); Generalizability theory; Research design; Medical physics; Statistics; Alternative medicine; Computer science; Internal medicine; Psychiatry","score_opus":0.9898736424568401,"score_gpt":0.7985629352472344,"score_spread":0.19131070720960563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008510792","genre_codex":"methods","genre_gemma":"review","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":[0.0000042077127,0.48061273,0.50444615,0.000050661274,0.00063789665,0.012810434,0.0013331894,0.00003351225,0.000071223825],"genre_scores_gemma":[0.0000026025687,0.49905446,0.49832517,0.000007992963,0.00024721038,0.0021848218,0.000022870983,0.00008837407,0.00006648602],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.16426763,0.8089391,0.01682447,0.0018856257,0.0064518135,0.0016313405],"domain_scores_gemma":[0.022849,0.9651564,0.0062523573,0.0021829766,0.0022606724,0.0012986277],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.7454215,0.000763649,0.03770428,0.00065952743,0.00010038654,0.000028134817,0.0029657986,0.0029048487,0.0010884089],"category_scores_gemma":[0.99814045,0.00048128306,0.0039168797,0.0016045338,0.0025770094,0.00003285494,0.0009457489,0.002756268,0.000023464512],"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":[0.0070809443,0.00031198032,0.000008964465,0.7011159,0.0019031769,0.000015947833,0.000075352815,8.87175e-9,0.0000011810475,0.020889958,0.0012001379,0.26739645],"study_design_scores_gemma":[0.027919473,0.002439901,0.000044840177,0.27225223,0.00991961,0.000029103352,0.00015812895,0.00014229381,0.000051101524,0.673228,0.0129198395,0.0008954736],"about_ca_topic_score_codex":0.00032835625,"about_ca_topic_score_gemma":0.00019333092,"teacher_disagreement_score":0.6523381,"about_ca_system_score_codex":0.0001687452,"about_ca_system_score_gemma":0.008487181,"threshold_uncertainty_score":0.9998247},"labels":[],"label_agreement":null},{"id":"W3011550827","doi":"10.1186/s12874-020-00945-9","title":"Incorporating sampling weights into robust estimation of Cox proportional hazards regression model, with illustration in the Multi-Ethnic Study of Atherosclerosis","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute","keywords":"Proportional hazards model; Statistics; Estimation; Regression analysis; Regression; Econometrics; Medicine; Computer science; Mathematics","score_opus":0.8839438527848583,"score_gpt":0.6241169862692942,"score_spread":0.2598268665155641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011550827","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42148754,0.000012550093,0.5775015,0.00025062842,0.000006510157,0.0006984399,0.0000011794867,0.000026254716,0.000015378384],"genre_scores_gemma":[0.48161143,0.000011041478,0.51819444,0.00001647951,0.000018424567,0.00012870402,0.0000050174813,0.000011344908,0.0000031374097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9884811,0.0077164574,0.0010176403,0.0004024742,0.0020771155,0.00030519627],"domain_scores_gemma":[0.9807526,0.017814785,0.0004960207,0.0003665178,0.00042973144,0.00014038205],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017630052,0.00015414425,0.0005361393,0.00020196971,0.00010713597,0.000009172745,0.00050209253,0.00023770066,0.00003193964],"category_scores_gemma":[0.055113465,0.00008992097,0.000040366558,0.0008216958,0.0006071536,0.00015167969,0.00019588087,0.0009311085,5.371348e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044101044,0.007952282,0.037781507,0.00550656,0.00019467185,0.000055038534,0.11550374,0.19386172,0.09690247,0.41522536,0.00017397878,0.12243257],"study_design_scores_gemma":[0.0011571236,0.0020172517,0.0021849696,0.00062429253,0.000021252677,0.00000541175,0.008570662,0.8057726,0.0070821424,0.1724372,5.6335364e-7,0.00012651364],"about_ca_topic_score_codex":0.00012898765,"about_ca_topic_score_gemma":0.0012143563,"teacher_disagreement_score":0.6119109,"about_ca_system_score_codex":0.000058560192,"about_ca_system_score_gemma":0.00083054363,"threshold_uncertainty_score":0.9528457},"labels":[],"label_agreement":null},{"id":"W3011779659","doi":"10.1186/s12874-020-00924-0","title":"Non-communicable diseases research output in the Eastern Mediterranean region: an overview of systematic reviews","year":2020,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Global Public Health Policies and Epidemiology","field":"Business, Management and Accounting","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; American University of Beirut","keywords":"Systematic review; Medicine; MEDLINE; Meta-analysis; Critical appraisal; Family medicine; Alternative medicine; Pathology; Political science","score_opus":0.9432455323954612,"score_gpt":0.6673553847965227,"score_spread":0.2758901475989385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011779659","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":[0.0000043412565,0.9763763,0.00042702063,0.013480079,0.0005216859,0.0061598034,0.000007709283,0.000033166074,0.0029899229],"genre_scores_gemma":[0.000009996531,0.9875358,0.00061794795,0.005823352,0.0034517455,0.0022365213,0.00012492557,0.000070712915,0.00012904106],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.834793,0.15069388,0.0056305784,0.0013890321,0.0045207674,0.0029727558],"domain_scores_gemma":[0.72609925,0.2612853,0.0030430825,0.006796351,0.0018282138,0.00094780105],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24475385,0.0005959041,0.008909338,0.0016414967,0.00040953027,0.00017639996,0.0076975645,0.001135295,0.00027319926],"category_scores_gemma":[0.3880828,0.00032736774,0.0008469171,0.0047830385,0.0017999776,0.00037542422,0.003161332,0.0050562136,0.00081337336],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003119041,0.00015718167,0.000036509362,0.648354,0.00004117707,0.00012758502,0.00015412326,5.1901395e-7,5.8859624e-9,0.015634438,0.13923016,0.19623312],"study_design_scores_gemma":[0.00024792648,0.0001201131,0.000013310287,0.08897874,0.00015508977,0.000056630415,0.0009123342,0.0020428898,1.3355103e-9,0.0026730052,0.90458727,0.00021270588],"about_ca_topic_score_codex":0.0146381315,"about_ca_topic_score_gemma":0.0018961123,"teacher_disagreement_score":0.7653571,"about_ca_system_score_codex":0.00020676768,"about_ca_system_score_gemma":0.002350973,"threshold_uncertainty_score":0.9999646},"labels":[],"label_agreement":null},{"id":"W3012803971","doi":"10.1186/s12874-020-00921-3","title":"Development and validation of algorithms to classify type 1 and 2 diabetes according to age at diagnosis using electronic health records","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Diabetes Management and Research","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Institute for Work & Health; Centre for Global Health Research; University of Toronto","funders":"Canadian Institutes of Health Research; Canadian Society of Endocrinology and Metabolism; Hospital Authority; University of Toronto; Royal College of Physicians and Surgeons of Canada","keywords":"Algorithm; Medicine; Confidence interval; Type 2 diabetes; Diagnosis code; Medical prescription; Cohort; Kappa; Diabetes mellitus; Cohen's kappa; Pediatrics; Machine learning; Internal medicine; Population; Mathematics; Computer science","score_opus":0.6115181868632938,"score_gpt":0.5554459890631923,"score_spread":0.05607219780010153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012803971","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":[0.9727102,0.0007754215,0.011813433,0.013594232,0.00007823646,0.00087467884,0.0000014666984,0.000022502029,0.00012984821],"genre_scores_gemma":[0.46941742,0.0014279676,0.52400875,0.0038631714,0.0004410322,0.00019396671,0.000039794213,0.00006105864,0.0005468607],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941301,0.0026563231,0.00044017605,0.0005278534,0.0012551605,0.0009904227],"domain_scores_gemma":[0.99191993,0.0061937873,0.00005705372,0.00017913154,0.00024878717,0.0014013124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016002415,0.00013061345,0.0006167259,0.00046054475,0.00016396584,0.00002268162,0.00018996756,0.00014384859,0.0002170286],"category_scores_gemma":[0.04050503,0.000107151965,0.000028743616,0.0011672277,0.00022346013,0.000041312032,0.0010212032,0.00052687066,0.000021073383],"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":[0.0006642094,0.00010439447,0.23593168,0.0018972135,0.00015153324,0.000033278404,0.0016988111,0.0000065150602,0.012418707,0.0004116704,0.0031258618,0.74355614],"study_design_scores_gemma":[0.011065421,0.030129401,0.29053488,0.004669648,0.00025595896,0.00003090629,0.010003837,0.029631143,0.22116895,0.0019980907,0.3988498,0.0016619823],"about_ca_topic_score_codex":0.000069721595,"about_ca_topic_score_gemma":0.00010793317,"teacher_disagreement_score":0.7418941,"about_ca_system_score_codex":0.00025984985,"about_ca_system_score_gemma":0.0012815064,"threshold_uncertainty_score":0.9675772},"labels":[],"label_agreement":null},{"id":"W3012860972","doi":"10.1186/s12874-020-00941-z","title":"Assessing the effect of genetic markers on drug immunogenicity from a mechanistic model-based approach","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Biosimilars and Bioanalytical Methods","field":"Immunology and Microbiology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Immunogenicity; Statistic; Population; Drug; Immune system; Computational biology; Test statistic; Computer science; Medicine; Immunology; Statistical hypothesis testing; Statistics; Biology; Pharmacology; Mathematics","score_opus":0.3227665133978012,"score_gpt":0.4872711939285132,"score_spread":0.164504680530712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012860972","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":[0.15110375,0.0019736525,0.8412599,0.0039005198,0.00024315066,0.0005944207,0.00003244677,0.000042756878,0.0008493973],"genre_scores_gemma":[0.8249549,0.000063650725,0.17315419,0.0014846516,0.00010810124,0.000084045256,0.000027539112,0.000030508325,0.00009237333],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9437523,0.053498585,0.00064745184,0.0007451109,0.00054274005,0.000813845],"domain_scores_gemma":[0.91079897,0.08812066,0.00014115556,0.0005878492,0.00013522901,0.00021613688],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026638482,0.0002704502,0.000950378,0.00013037935,0.00028344302,0.000027434431,0.001250847,0.00072331895,0.0014144892],"category_scores_gemma":[0.0736431,0.00015229433,0.00032086665,0.000525763,0.002127705,0.000026789285,0.00042739595,0.002165122,0.000056602577],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020518092,0.0008056992,0.0073182504,0.001459583,0.0015272362,0.000097602155,0.0008741852,0.0020257435,0.6793547,0.007255946,0.01119347,0.26756945],"study_design_scores_gemma":[0.008042351,0.00534005,0.0064597926,0.00033534248,0.00058041187,0.000033010027,0.00089746196,0.5030075,0.46246415,0.010157432,0.001980876,0.00070163305],"about_ca_topic_score_codex":0.00024839715,"about_ca_topic_score_gemma":0.000015014767,"teacher_disagreement_score":0.6738512,"about_ca_system_score_codex":0.00005230846,"about_ca_system_score_gemma":0.0007193472,"threshold_uncertainty_score":0.99949837},"labels":[],"label_agreement":null},{"id":"W3013921428","doi":"10.1186/s12874-020-0900-z","title":"Methods of competing risks flexible parametric modeling for estimation of the risk of the first disease among HIV infected men","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"National Institute of Allergy and Infectious Diseases; National Cancer Institute; National Institute on Deafness and Other Communication Disorders; National Institute on Drug Abuse; Northwestern University; National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Center for Advancing Translational Sciences; Johns Hopkins Bloomberg School of Public Health; University of California, Los Angeles; National Institutes of Health; Johns Hopkins University; Tehran University of Medical Sciences and Health Services; University of Pittsburgh; McMaster University","keywords":"Estimation; Human immunodeficiency virus (HIV); Disease; Parametric statistics; Medicine; Environmental health; Econometrics; Computer science; Statistics; Risk analysis (engineering); Family medicine; Mathematics; Internal medicine; Engineering","score_opus":0.6493900727292393,"score_gpt":0.595324126106831,"score_spread":0.05406594662240827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013921428","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04221869,0.000098747696,0.9555056,0.00082665676,0.00008020664,0.00096015434,0.00007630155,0.000019428846,0.00021417535],"genre_scores_gemma":[0.2740323,0.000031716518,0.725772,0.000025058573,0.00004258228,0.00007242958,0.0000016010683,0.000017058808,0.0000052710056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9721628,0.024657864,0.001106475,0.00034657388,0.0012914399,0.00043486795],"domain_scores_gemma":[0.6984957,0.29882744,0.0007284361,0.00073459704,0.0008108912,0.00040297039],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03877732,0.00015827223,0.00083678326,0.00016331463,0.0002069102,0.000009926775,0.0009938923,0.00022525204,0.0001439537],"category_scores_gemma":[0.76671344,0.00008859101,0.00029706527,0.0015128637,0.0012657802,0.00003852566,0.00065109885,0.0008537382,7.1679057e-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":[0.0015528314,0.00052224327,0.14016055,0.009532226,0.00034328032,0.0000021520827,0.002487123,0.014134867,0.00083475653,0.67641854,0.00072758185,0.15328383],"study_design_scores_gemma":[0.00038992713,0.000085694635,0.011213117,0.0002269806,0.00010088468,3.5333508e-7,0.00015582997,0.6035938,0.0024806764,0.38169023,0.000008816415,0.000053654334],"about_ca_topic_score_codex":0.0003306579,"about_ca_topic_score_gemma":0.000029009763,"teacher_disagreement_score":0.7279361,"about_ca_system_score_codex":0.000034612724,"about_ca_system_score_gemma":0.0007429435,"threshold_uncertainty_score":0.989781},"labels":[],"label_agreement":null},{"id":"W3014136929","doi":"10.1186/s12874-020-00950-y","title":"A factorial cluster-randomised controlled trial combining home-environmental and early child development interventions to improve child health and development: rationale, trial design and baseline findings","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Child Nutrition and Water Access","field":"Nursing","cited_by":32,"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":"UBS Optimus Foundation; Grand Challenges Canada","keywords":"Cluster randomised controlled trial; Psychological intervention; Randomized controlled trial; Medicine; Child development; Cluster (spacecraft); Child health; Baseline (sea); Pediatrics; Psychology; Psychiatry; Computer science","score_opus":0.27439022074984687,"score_gpt":0.447779349014191,"score_spread":0.1733891282643441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014136929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7217271,0.0006944643,0.24518688,0.020625211,0.0011412029,0.010543477,0.0000120534505,0.000052987736,0.000016628714],"genre_scores_gemma":[0.80541193,0.00030606045,0.18188463,0.006700553,0.0028674137,0.0025000994,0.00018090727,0.000088744535,0.000059638365],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.984568,0.011440439,0.0013406483,0.0008205042,0.0011466051,0.0006838315],"domain_scores_gemma":[0.9800389,0.01804354,0.00013767112,0.00013411931,0.000062077146,0.0015837408],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020409761,0.00027906115,0.0011066389,0.00038854082,0.0008670758,0.0001681165,0.00025409003,0.00026287316,0.00019961482],"category_scores_gemma":[0.028131979,0.00023637105,0.00010939971,0.00018306986,0.0003586876,0.00017289507,0.00045405971,0.0009236928,0.000010512905],"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":[0.9801057,0.00038389195,0.00029037672,0.00032650822,0.00009744832,0.0000065267186,0.0059170416,0.0000012412106,0.00011311599,0.000054985863,0.00066323485,0.0120399445],"study_design_scores_gemma":[0.9880536,0.005281588,0.001102926,0.00033496378,0.000025573438,0.000026966532,0.00033883442,0.00042822,0.0007431594,0.00013856855,0.0032427507,0.00028284302],"about_ca_topic_score_codex":0.000025292742,"about_ca_topic_score_gemma":0.000029463594,"teacher_disagreement_score":0.083684854,"about_ca_system_score_codex":0.00012844933,"about_ca_system_score_gemma":0.00047258835,"threshold_uncertainty_score":0.9800545},"labels":[],"label_agreement":null},{"id":"W3014346384","doi":"10.1186/s12874-020-00955-7","title":"When piloting health services interventions, what predicts real world behaviours? A systematic concept mapping review","year":2020,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Canadian Institutes of Health Research","keywords":"PsycINFO; MEDLINE; Scopus; Systematic review; Psychological intervention; Data extraction; Computer science; Data collection; Applied psychology; Data science; Medicine; Psychology; Nursing; Statistics","score_opus":0.9666692459324164,"score_gpt":0.8137960670466763,"score_spread":0.15287317888574015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014346384","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":[7.3612597e-7,0.9465383,0.010215892,0.023164328,0.0019066442,0.017431956,0.00016977797,0.00024470786,0.00032764272],"genre_scores_gemma":[2.791701e-7,0.94175214,0.024738036,0.022665385,0.0013829905,0.007564669,0.00026094195,0.00012832168,0.0015072488],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.6658878,0.31493992,0.009187895,0.0016268621,0.004982571,0.0033749905],"domain_scores_gemma":[0.71280974,0.2736063,0.0056383624,0.0018610719,0.0013076309,0.004776885],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.25730264,0.0007555025,0.009306083,0.0017789616,0.0019044566,0.000116036,0.0035891156,0.00093107537,0.0065796142],"category_scores_gemma":[0.1870607,0.000575041,0.0010139506,0.0038433713,0.00084180816,0.00039779526,0.0026757186,0.008140557,0.0017302942],"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":[0.000004538047,0.000024174593,0.000020020165,0.7016383,0.00006104449,0.00003016225,0.0048997956,1.1144587e-8,9.543373e-9,0.0007140378,0.018760208,0.27384773],"study_design_scores_gemma":[0.00028062865,0.00014510847,0.000008527931,0.5472782,0.00015693535,0.000025842588,0.004762313,0.000017295946,8.32638e-9,0.00012092645,0.44702357,0.00018062316],"about_ca_topic_score_codex":0.005355139,"about_ca_topic_score_gemma":0.012043879,"teacher_disagreement_score":0.42826334,"about_ca_system_score_codex":0.0024182547,"about_ca_system_score_gemma":0.036267687,"threshold_uncertainty_score":0.9996701},"labels":[],"label_agreement":null},{"id":"W3014446443","doi":"10.1186/s12874-020-00953-9","title":"Validation of an algorithm based on administrative data to detect new onset of atrial fibrillation after cardiac surgery","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hôpital Charles-Le Moyne; Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"Canadian Institutes of Health Research; Réseau de recherche portant sur les interventions en sciences infirmières du Québec; Université de Sherbrooke","keywords":"Medicine; Atrial fibrillation; Cardiac surgery; Incidence (geometry); Diagnosis code; Gold standard (test); Medical record; Complication; Positive predicative value; Likelihood ratios in diagnostic testing; Algorithm; Internal medicine; Emergency medicine; Cardiology; Predictive value; Population","score_opus":0.7468782825457505,"score_gpt":0.58114115180843,"score_spread":0.16573713073732055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014446443","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":[0.4380593,0.00028228803,0.5410387,0.017296221,0.0006329301,0.002117186,0.00032847034,0.00006310847,0.00018179911],"genre_scores_gemma":[0.5100764,0.00011114672,0.4830814,0.00050322025,0.004997852,0.0000055176192,0.0010531581,0.00003747406,0.0001338512],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9884569,0.008134075,0.0007071592,0.00050583074,0.0018870184,0.0003089914],"domain_scores_gemma":[0.9622795,0.03591881,0.00015096329,0.0006325121,0.0002693142,0.00074890454],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016153252,0.00013145889,0.0008702454,0.00039722427,0.00003453193,0.000009596062,0.00025532124,0.00022174038,0.001022101],"category_scores_gemma":[0.13190156,0.000109127606,0.00024362121,0.0007860421,0.00018420117,0.00009374864,0.00023273607,0.00026670165,0.000027313079],"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":[0.028248057,0.000016705219,0.10461875,0.00058794685,0.00025337545,0.000060283117,0.00047800626,0.00030658205,0.0017386804,0.00009819297,0.009731947,0.85386145],"study_design_scores_gemma":[0.011701592,0.021390457,0.50434554,0.0012107661,0.0011207603,0.00002171093,0.0015326693,0.1950132,0.13881086,0.0019115695,0.121766,0.0011749038],"about_ca_topic_score_codex":0.00013799936,"about_ca_topic_score_gemma":0.000022627608,"teacher_disagreement_score":0.8526866,"about_ca_system_score_codex":0.00003644004,"about_ca_system_score_gemma":0.0022379842,"threshold_uncertainty_score":0.9998911},"labels":[],"label_agreement":null},{"id":"W3016108386","doi":"10.1186/s12874-020-00967-3","title":"Correction to: Estimation of treatment preference effects in clinical trials when some participants are indifferent to treatment choice","year":2020,"lang":"en","type":"erratum","venue":"BMC Medical Research Methodology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Sentence; Preference; Section (typography); Affect (linguistics); Estimation; Clinical trial; Psychology; MEDLINE; Statistics; Medical physics; Medicine; Computer science; Natural language processing; Mathematics; Internal medicine; Political science","score_opus":0.9597185315143579,"score_gpt":0.707653335571187,"score_spread":0.2520651959431709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016108386","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22139786,0.016350742,0.36457834,0.15416919,0.19672886,0.041023225,0.0018749263,0.000314716,0.0035621573],"genre_scores_gemma":[0.14050016,0.040459417,0.39461723,0.05555734,0.07292415,0.06917634,0.005165495,0.0014368948,0.22016297],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.872626,0.10585084,0.016074387,0.002555161,0.0010398914,0.0018537443],"domain_scores_gemma":[0.6200371,0.3695631,0.0054953443,0.0015603305,0.00029794322,0.003046199],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22976448,0.00052122615,0.0072539966,0.0016701872,0.00012928415,0.000059166774,0.0008104965,0.0015427351,0.00077712076],"category_scores_gemma":[0.80050945,0.0004927877,0.00051169674,0.0006014624,0.00024255173,0.00013812659,0.0003099771,0.0016390006,0.0017190271],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011042304,0.0015952497,0.036477126,0.0032104691,0.0006239986,0.000021912165,0.006547363,0.0006318035,0.0000029237133,0.0044438047,0.8552171,0.09012405],"study_design_scores_gemma":[0.012426708,0.02458418,0.3834078,0.008124447,0.00021984216,0.00000877303,0.0014759524,0.11650669,0.000083350074,0.037970442,0.41352943,0.0016623649],"about_ca_topic_score_codex":0.010873153,"about_ca_topic_score_gemma":0.017403776,"teacher_disagreement_score":0.57074493,"about_ca_system_score_codex":0.0044261324,"about_ca_system_score_gemma":0.005365551,"threshold_uncertainty_score":0.9997535},"labels":[],"label_agreement":null},{"id":"W3016185304","doi":"10.1186/s12874-020-00958-4","title":"Telephone versus web panel National Survey for monitoring adoption of preventive behaviors to climate change in populations: a case study of Lyme disease in Québec, Canada","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Vector-borne infectious diseases","field":"Immunology and Microbiology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Public Health Agency of Canada; The Quebec Population Health Research Network; Institut National de Santé Publique du Québec; Université Laval","funders":"Institut National de Santé Publique du Québec","keywords":"Representativeness heuristic; Data collection; Population; Lyme disease; Public health; Medicine; Psychology; Environmental health; Applied psychology; Family medicine; Statistics; Social psychology; Nursing","score_opus":0.5979067778130718,"score_gpt":0.5241533606049114,"score_spread":0.07375341720816042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016185304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966189,0.00069894147,0.00016083417,0.000255758,0.00041275917,0.0014981554,0.00034150528,0.000010539187,0.000002566953],"genre_scores_gemma":[0.9984559,0.00004396881,0.0004448682,0.000027975851,0.000059772028,0.00085881556,0.000088872635,0.000015126093,0.00000474577],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9878957,0.010234586,0.0006382826,0.0004025696,0.00035354667,0.00047527815],"domain_scores_gemma":[0.9821367,0.01689905,0.00012373616,0.00016445998,0.0004679646,0.0002080817],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070891767,0.00012574255,0.00047818737,0.00041057818,0.00007556386,0.0000027242977,0.00023470045,0.00016517325,0.00014110953],"category_scores_gemma":[0.07265792,0.00012597744,0.000052957585,0.0007416165,0.00016854436,0.000052112428,0.0002222151,0.0003791782,0.000003953966],"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":[0.0054831393,0.0010054094,0.9869976,0.00015362461,0.000049665654,0.0001795992,0.0017750858,0.000115633564,0.0019701303,0.00004950492,0.00009832295,0.0021222613],"study_design_scores_gemma":[0.004371908,0.0010924147,0.99035585,0.00008064447,0.000029509149,0.000012411267,0.0035207786,0.00013383909,0.00025401145,0.000017039507,0.000026528389,0.00010508035],"about_ca_topic_score_codex":0.88395154,"about_ca_topic_score_gemma":0.98774946,"teacher_disagreement_score":0.10379792,"about_ca_system_score_codex":0.00037638095,"about_ca_system_score_gemma":0.0039677075,"threshold_uncertainty_score":0.9351535},"labels":[],"label_agreement":null},{"id":"W3020176834","doi":"10.1186/s12874-020-00975-3","title":"How are systematic reviews of prevalence conducted? A methodological study","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":356,"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":"Systematic review; Medicine; MEDLINE; Interquartile range; Meta-analysis; Family medicine; Pathology; Surgery","score_opus":0.9945339847664632,"score_gpt":0.7580766681875971,"score_spread":0.23645731657886604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020176834","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":[0.056639362,0.016495693,0.9019256,0.012030337,0.00041777114,0.011502338,0.000015770847,0.000022184951,0.0009509121],"genre_scores_gemma":[0.41814047,0.0022070499,0.563491,0.002069059,0.0008115571,0.0024624304,0.000004990253,0.00006243664,0.010751041],"study_design_codex":"systematic_review","study_design_gemma":"qualitative","domain_scores_codex":[0.076061025,0.87354106,0.018658925,0.0027960483,0.027915187,0.0010277797],"domain_scores_gemma":[0.05774934,0.9103556,0.013113216,0.00888063,0.0073453435,0.002555835],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.87299025,0.0005029082,0.017591445,0.0007095059,0.00019754258,0.00042609975,0.008294229,0.000470788,0.028328437],"category_scores_gemma":[0.9899712,0.00020865625,0.0026378294,0.00512251,0.001043155,0.0002125376,0.0015350751,0.001572345,0.0016307865],"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":[0.00095864624,0.0031148947,0.23918164,0.3600555,0.0030699726,0.0009832621,0.021160984,0.00003477736,0.00581306,0.02808451,0.2634945,0.07404824],"study_design_scores_gemma":[0.013015774,0.022057561,0.0912033,0.03252134,0.008213393,0.0011367071,0.3615171,0.08477633,0.0022811908,0.11126412,0.26674932,0.005263848],"about_ca_topic_score_codex":0.000019269566,"about_ca_topic_score_gemma":0.000086949316,"teacher_disagreement_score":0.3615011,"about_ca_system_score_codex":0.00004643364,"about_ca_system_score_gemma":0.00067039643,"threshold_uncertainty_score":0.9991466},"labels":[],"label_agreement":null},{"id":"W3021150726","doi":"10.1186/s12874-020-00991-3","title":"Feasibility and evaluation of a large-scale external validation approach for patient-level prediction in an international data network: validation of models predicting stroke in female patients newly diagnosed with atrial fibrillation","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"U.S. National Library of Medicine; Innovative Medicines Initiative; Health Promotion Administration, Ministry of Health and Welfare; Korea Health Industry Development Institute; European Commission; European Federation of Pharmaceutical Industries and Associations","keywords":"Observational study; Standardization; Atrial fibrillation; Computer science; Predictive modelling; Scale (ratio); Cross-validation; Medicine; Data mining; Internal medicine; Artificial intelligence; Machine learning","score_opus":0.6334701342418498,"score_gpt":0.5302730048634271,"score_spread":0.10319712937842274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021150726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.506096,0.000040895393,0.49258316,0.00008597719,0.00008272259,0.0010099291,0.00008045475,0.000010604491,0.000010257965],"genre_scores_gemma":[0.6496955,0.000017717039,0.34955913,0.0000111508,0.00018691202,0.000038026792,0.00048338878,0.000007716861,4.5310878e-7],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98124635,0.013685093,0.0009928038,0.00090107747,0.0027660567,0.00040858955],"domain_scores_gemma":[0.99087524,0.0068204934,0.00040737118,0.00052948674,0.0011577082,0.0002096969],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03711225,0.000120107325,0.0003713638,0.00028481105,0.000072994706,0.0000330027,0.00077234674,0.00027086714,0.000015972593],"category_scores_gemma":[0.03656566,0.0001113373,0.00003613296,0.00057169475,0.00011445743,0.0010081042,0.00063243904,0.0005611142,1.3410636e-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":[0.00079377956,0.000077546785,0.7161408,0.00015857424,0.000007718131,3.035064e-7,0.00274855,0.23515612,0.000025831694,0.00023926854,0.0000036111833,0.04464791],"study_design_scores_gemma":[0.0033697877,0.00067543867,0.26620308,0.00008536856,0.000008501925,9.55039e-7,0.00026067704,0.728455,0.000053803982,0.00083351973,0.0000018322743,0.000052002237],"about_ca_topic_score_codex":0.0004485045,"about_ca_topic_score_gemma":0.000647499,"teacher_disagreement_score":0.49329892,"about_ca_system_score_codex":0.00015366352,"about_ca_system_score_gemma":0.0009001856,"threshold_uncertainty_score":0.99149555},"labels":[],"label_agreement":null},{"id":"W3022156859","doi":"10.1186/s12874-020-00999-9","title":"An assessment of the quality of current clinical meta-analyses","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Quality (philosophy); Current (fluid); MEDLINE; Medicine; Psychology; Data science; Computer science; Political science","score_opus":0.9987362646929091,"score_gpt":0.8860861989993718,"score_spread":0.1126500656935373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022156859","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":[0.08128055,0.0030707354,0.9056362,0.006619334,0.0004516948,0.0008985088,0.00003170026,0.000003932687,0.0020073452],"genre_scores_gemma":[0.79108727,0.0001869134,0.20726651,0.00067455345,0.00032341713,0.000073599214,0.0000043173122,0.000012842523,0.0003705874],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.08871554,0.84832656,0.025391582,0.0017286387,0.035264764,0.0005728982],"domain_scores_gemma":[0.10913929,0.85181767,0.014452103,0.012594926,0.009661213,0.002334807],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8646045,0.00023902555,0.010308822,0.0003006384,0.00011556965,0.00008441972,0.0075399415,0.00026495586,0.04341832],"category_scores_gemma":[0.91874385,0.00008111006,0.0069703874,0.0031342774,0.0017239706,0.00009400857,0.0011303436,0.0013872755,0.00016520052],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021976362,0.0016020023,0.52802736,0.0013396872,0.009220147,0.0000074420177,0.0010413005,0.00024170123,0.003741843,0.14461842,0.059348915,0.2505914],"study_design_scores_gemma":[0.0016435236,0.0016107333,0.68627554,0.00009150972,0.007632063,0.000008540771,0.0043818923,0.085033454,0.0013333374,0.08670092,0.12478083,0.0005076367],"about_ca_topic_score_codex":0.00008398927,"about_ca_topic_score_gemma":0.00023134385,"teacher_disagreement_score":0.7098067,"about_ca_system_score_codex":0.000019579324,"about_ca_system_score_gemma":0.002405114,"threshold_uncertainty_score":0.99782974},"labels":[],"label_agreement":null},{"id":"W3022223070","doi":"10.1186/s12874-020-00984-2","title":"Baseline-adjusted proportional odds models for the quantification of treatment effects in trials with ordinal sum score outcomes","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cerebral Palsy and Movement Disorders","field":"Medicine","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":"International Collaboration On Repair Discoveries; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Staatssekretariat für Bildung, Forschung und Innovation; European Commission","keywords":"Medicine; Clinical trial; Randomized controlled trial; Ordinal regression; Odds; Logistic regression; Wilcoxon signed-rank test; Ordered logit; Statistics; Odds ratio; Statistical power; Baseline (sea); Physical therapy; Mathematics; Internal medicine","score_opus":0.7496213551462679,"score_gpt":0.5618478547567198,"score_spread":0.1877735003895481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022223070","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":[0.13074654,0.0006170045,0.8360045,0.028242456,0.00008741581,0.004178831,0.00001715368,0.00002045473,0.00008563075],"genre_scores_gemma":[0.9509369,0.00048375598,0.04498406,0.0012562741,0.0002654209,0.0015233896,0.00015577911,0.00003063995,0.00036377436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9905082,0.0067866915,0.0007833112,0.00041181332,0.0010887441,0.00042126307],"domain_scores_gemma":[0.92514837,0.07361869,0.00018380076,0.00031712616,0.00037851025,0.00035353142],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027490107,0.00015039787,0.0010087488,0.00018293314,0.000073971074,0.0000063374014,0.0001924207,0.00018016035,0.000298085],"category_scores_gemma":[0.11639876,0.0000725965,0.00019336188,0.00045227833,0.00048323272,0.000040342966,0.000051407806,0.00034044145,0.000003432808],"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":[0.08455181,0.003465241,0.34802932,0.0076492433,0.0018867066,0.00013272246,0.0032068868,0.004204473,0.014945154,0.165815,0.005108351,0.3610051],"study_design_scores_gemma":[0.07970817,0.032742944,0.24539688,0.001432937,0.0012591265,0.00004816791,0.0068702684,0.5867269,0.021089494,0.018942093,0.005130683,0.00065232284],"about_ca_topic_score_codex":0.00067851576,"about_ca_topic_score_gemma":0.0014253313,"teacher_disagreement_score":0.82019037,"about_ca_system_score_codex":0.000085275504,"about_ca_system_score_gemma":0.002047733,"threshold_uncertainty_score":0.9527577},"labels":[],"label_agreement":null},{"id":"W3024831471","doi":"10.1186/s12874-020-01004-z","title":"Current methods for development of rapid reviews about diagnostic tests: an international survey","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Agency for Drugs and Technologies in Health; Public Health Ontario; Queen's University; St. Michael's Hospital","funders":"Instituto de Salud Carlos III","keywords":"Scope (computer science); Diagnostic test; Test (biology); Computer science; Systematic review; Health care; Management science; Data science; MEDLINE; Risk analysis (engineering); Medicine; Medical physics; Political science; Engineering","score_opus":0.9887539574876372,"score_gpt":0.7936162784854344,"score_spread":0.1951376790022028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024831471","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":[0.0067942864,0.011745519,0.9775825,0.0010610294,0.00080427225,0.001710783,0.00002633065,0.0000050328886,0.00027022685],"genre_scores_gemma":[0.0024545758,0.0022581818,0.99364334,0.00035116164,0.00039521183,0.000561391,0.00007124894,0.000016796906,0.00024808946],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.25846615,0.6993041,0.02165917,0.0028048828,0.016629284,0.0011363821],"domain_scores_gemma":[0.042297773,0.94096524,0.0042956555,0.0034382022,0.0070225555,0.001980602],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8442201,0.00028588998,0.0049905414,0.0005932823,0.00016081826,0.00018014507,0.0057170014,0.00022120865,0.02810892],"category_scores_gemma":[0.9847536,0.0001437455,0.0010744345,0.0020192997,0.00043987797,0.00016550199,0.0007856127,0.00067702134,0.001048229],"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":[0.00006931522,0.00011558174,0.016087506,0.00032919942,0.000093119204,0.0000012526042,0.00081397715,0.0000024512722,0.00014474687,0.0019423884,0.026075482,0.95432496],"study_design_scores_gemma":[0.00040196892,0.00023349217,0.055144195,0.00015132743,0.000040226005,0.0000039356587,0.00016794591,0.009257173,0.00021246368,0.0043011047,0.9299264,0.00015977157],"about_ca_topic_score_codex":0.000025964453,"about_ca_topic_score_gemma":0.00035280542,"teacher_disagreement_score":0.9541652,"about_ca_system_score_codex":0.000060062357,"about_ca_system_score_gemma":0.0015989856,"threshold_uncertainty_score":0.9997296},"labels":[],"label_agreement":null},{"id":"W3027531952","doi":"10.1186/s12874-020-00964-6","title":"Obtaining and managing data sets for individual participant data meta-analysis: scoping review and practical guide","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":84,"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; Cancer Research UK; Marie Curie; McMaster University","keywords":"Certification; Data sharing; MEDLINE; Cochrane Library; Computer science; Meta-analysis; Knowledge management; Data science; Medicine; Alternative medicine; Political science","score_opus":0.9978150246277914,"score_gpt":0.8161935446665352,"score_spread":0.18162147996125622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027531952","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":[0.000077533645,0.21046355,0.7049721,0.081813864,0.000044862867,0.0021870257,0.00021077451,0.000009528472,0.00022074608],"genre_scores_gemma":[0.0020960355,0.013533656,0.9709202,0.012132209,0.00022336679,0.00035706055,0.00036389212,0.000029422446,0.00034415926],"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","domain_scores_codex":[0.70072156,0.26303357,0.013415593,0.005297485,0.016114753,0.0014170379],"domain_scores_gemma":[0.14163697,0.82846594,0.0048160455,0.01878997,0.002623733,0.0036673108],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.79776627,0.00035052933,0.010542854,0.00054287584,0.00036503442,0.0008317604,0.0060500368,0.00021543325,0.009761067],"category_scores_gemma":[0.93403363,0.00017382953,0.0009954419,0.002907331,0.00068184565,0.0006269592,0.009690075,0.0008584482,0.00014083604],"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":[0.00014595487,0.0001406547,0.0026685135,0.021222506,0.21611984,0.000279622,0.0019024379,0.000022652173,0.000014911283,0.01128637,0.61936444,0.1268321],"study_design_scores_gemma":[0.0006771338,0.0002681533,0.00038410316,0.0010188567,0.55883676,0.00016107727,0.0035488317,0.31341827,0.0000034704256,0.0081210695,0.11302796,0.000534352],"about_ca_topic_score_codex":0.000047318455,"about_ca_topic_score_gemma":0.0005373901,"teacher_disagreement_score":0.5654324,"about_ca_system_score_codex":0.000007089872,"about_ca_system_score_gemma":0.0013143724,"threshold_uncertainty_score":0.9993277},"labels":[],"label_agreement":null},{"id":"W3027727468","doi":"10.1186/s12874-020-00998-w","title":"Fuzzy cognitive mapping and soft models of indigenous knowledge on maternal health in Guerrero, Mexico","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cognitive Science and Mapping","field":"Computer Science","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":"McGill University","funders":"Consejo Nacional de Ciencia y Tecnología; Fundación CeiBA; Faculty of Medicine, McGill University","keywords":"Indigenous; Mental health; Thematic analysis; Ethnic group; Medicine; Health care; Anger; Cognition; Psychology; Clinical psychology; Psychiatry; Qualitative research; Sociology","score_opus":0.5907677275985771,"score_gpt":0.5191634489962841,"score_spread":0.07160427860229301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027727468","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":[0.0780525,0.0008859411,0.9113834,0.005861789,0.000120828976,0.0004152129,0.000004820406,0.000034736673,0.0032407602],"genre_scores_gemma":[0.9266075,0.00068361673,0.06947865,0.0030101342,0.00012350753,0.00004615424,0.0000022441316,0.0000109737875,0.00003722004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890601,0.0077161784,0.0005143387,0.0007366697,0.0010733405,0.00089935097],"domain_scores_gemma":[0.98059565,0.017935878,0.00011627911,0.0002130365,0.00031791828,0.0008212311],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021974668,0.00013906122,0.0005490143,0.00056406023,0.00015732042,0.000038686558,0.0009887374,0.00015017166,0.000026555097],"category_scores_gemma":[0.022208128,0.000119572505,0.000051122057,0.001277629,0.00068739214,0.0002223255,0.0011214126,0.0008454879,0.000031036256],"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":[0.0001426372,0.00013425483,0.0021541782,0.00030932238,0.000016366277,0.00007545128,0.029883495,0.000023593513,0.00043216266,0.04328405,0.0001405138,0.923404],"study_design_scores_gemma":[0.008011561,0.0074034105,0.0846346,0.0045329314,0.000009926032,0.00024927463,0.015834793,0.44359764,0.0079573775,0.42456973,0.002063481,0.0011352934],"about_ca_topic_score_codex":0.00041323365,"about_ca_topic_score_gemma":0.0003937499,"teacher_disagreement_score":0.9222687,"about_ca_system_score_codex":0.00006250345,"about_ca_system_score_gemma":0.0022774758,"threshold_uncertainty_score":0.98602825},"labels":[],"label_agreement":null},{"id":"W3028245033","doi":"10.1186/s12874-020-01014-x","title":"A randomized trial of mail and email recruitment strategies for a physician survey on clinical trial accrual","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","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 Center for Advancing Translational Sciences; National Cancer Institute; National Institutes of Health","keywords":"Medicine; Family medicine; Clinical trial; Accrual; Randomized controlled trial; Quarter (Canadian coin); Electronic mail; Internet privacy; Internal medicine","score_opus":0.9599464235452072,"score_gpt":0.7284341669249853,"score_spread":0.2315122566202219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028245033","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":[0.8857136,0.00029066316,0.09318962,0.007897838,0.002096881,0.009119777,0.000057939207,0.000055170698,0.0015785071],"genre_scores_gemma":[0.67864287,0.007597697,0.26799598,0.010802573,0.022073478,0.01014641,0.00019216324,0.00019976909,0.002349023],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.22192355,0.77205515,0.0017378872,0.0009647106,0.0022267373,0.0010919507],"domain_scores_gemma":[0.37746966,0.62095606,0.00025539068,0.00023853678,0.00038741995,0.00069291005],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7024892,0.00020891857,0.002223121,0.00020241782,0.0004044113,0.000046243633,0.00075986667,0.0009390525,0.00039133368],"category_scores_gemma":[0.904361,0.00015535727,0.00048420238,0.0006053888,0.006279915,0.000084571846,0.00023617341,0.0011838223,0.000014097177],"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":[0.9399727,0.00037026103,0.000076678094,0.0000374945,0.00015225068,0.000007481352,0.0031530953,5.0340674e-7,0.000019173985,0.022341894,0.0022883487,0.031580135],"study_design_scores_gemma":[0.9604744,0.008991627,0.001013357,0.000032229033,0.000044669356,3.0181448e-7,0.0041745487,0.00009591244,0.000052158088,0.019165516,0.005800338,0.00015497273],"about_ca_topic_score_codex":0.0018636652,"about_ca_topic_score_gemma":0.006220054,"teacher_disagreement_score":0.20707071,"about_ca_system_score_codex":0.000038143673,"about_ca_system_score_gemma":0.0067239506,"threshold_uncertainty_score":0.998907},"labels":[],"label_agreement":null},{"id":"W3028609296","doi":"10.1186/s12874-020-00962-8","title":"Translation method is validity evidence for construct equivalence: analysis of secondary data routinely collected during translations of the Health Literacy Questionnaire (HLQ)","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":106,"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 Health and Medical Research Council; Medical Research Council; Deakin University","keywords":"Equivalence (formal languages); Construct (python library); Natural language processing; Prom; Construct validity; Health literacy; Computer science; Psychology; Linguistics; Artificial intelligence; Medicine; Psychometrics; Clinical psychology","score_opus":0.8037549855598017,"score_gpt":0.630616517361185,"score_spread":0.17313846819861678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028609296","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":[0.103011295,0.0045018313,0.8615205,0.028769314,0.00017911024,0.0011718184,0.0007603156,0.000028549828,0.00005726369],"genre_scores_gemma":[0.83669066,0.0007386284,0.1613536,0.0007472247,0.00018253217,0.000062856794,0.00015634067,0.000018592667,0.000049556493],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9829686,0.013195841,0.0010928687,0.000654849,0.0016409052,0.00044688632],"domain_scores_gemma":[0.95958173,0.037252102,0.00035886344,0.0010730199,0.0011623023,0.00057200197],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020826694,0.00014389804,0.0010883384,0.00038482,0.00020791448,0.000010945064,0.0007538151,0.00023742965,0.00091621425],"category_scores_gemma":[0.056602232,0.00010805783,0.00037262394,0.0036585825,0.0006779754,0.00014449157,0.00018438838,0.0007908474,5.570132e-7],"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":[0.013421957,0.000343682,0.16731791,0.021342335,0.0027182912,0.000013724191,0.05641883,0.0001304751,0.020278977,0.0017752119,0.0021225375,0.7141161],"study_design_scores_gemma":[0.008432512,0.0028488638,0.62349844,0.00471383,0.003958327,0.00007871429,0.0037527722,0.323428,0.023507046,0.0024669787,0.002811591,0.00050294277],"about_ca_topic_score_codex":0.002068657,"about_ca_topic_score_gemma":0.004096244,"teacher_disagreement_score":0.73367935,"about_ca_system_score_codex":0.000083019695,"about_ca_system_score_gemma":0.0059261895,"threshold_uncertainty_score":0.9999971},"labels":[],"label_agreement":null},{"id":"W3029276627","doi":"10.1186/s12874-020-01023-w","title":"Summarizing the extent of visit irregularity in longitudinal data","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Systemic Lupus Erythematosus Research","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":"University of Manitoba; Children's Hospital Research Institute of Manitoba; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Public Health Ontario; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MEDLINE; Longitudinal data; Data science; Psychology; Computer science; Medicine; Data mining; Political science","score_opus":0.7691544192905426,"score_gpt":0.5812971810134152,"score_spread":0.18785723827712741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029276627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8002302,0.008108087,0.116124675,0.06886524,0.0003577229,0.0026975726,0.000034626217,0.00007732781,0.0035045282],"genre_scores_gemma":[0.94485873,0.0011951023,0.051524863,0.0007746391,0.0010073595,0.00011126263,0.0000711173,0.000059305872,0.00039760853],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9710807,0.020400533,0.0011225463,0.0010577715,0.005107623,0.0012307976],"domain_scores_gemma":[0.9249512,0.070144214,0.0001577984,0.0026833701,0.0006965738,0.0013668666],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07328503,0.00016934477,0.0010027837,0.0003356465,0.00010382113,0.000018136914,0.0022341951,0.00037180158,0.0013698881],"category_scores_gemma":[0.27784663,0.000105176696,0.00011532975,0.0014900698,0.001605999,0.000080293394,0.0031274615,0.0024039748,0.00009820405],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003272224,0.00041446503,0.92042744,0.0046368106,0.00018623729,0.0012234349,0.002434556,0.0000043196887,0.007570653,0.0066548386,0.014010967,0.03916404],"study_design_scores_gemma":[0.03293639,0.006602412,0.5795545,0.0102118105,0.00035752793,0.02250327,0.037032496,0.21889164,0.012136162,0.012634957,0.06574608,0.001392761],"about_ca_topic_score_codex":0.0011469952,"about_ca_topic_score_gemma":0.0010247662,"teacher_disagreement_score":0.34087294,"about_ca_system_score_codex":0.00013366995,"about_ca_system_score_gemma":0.003155119,"threshold_uncertainty_score":0.99989754},"labels":[],"label_agreement":null},{"id":"W3029775226","doi":"10.1186/s12874-020-01019-6","title":"Primary outcome reporting in adolescent depression clinical trials needs standardization","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"Cundill Centre for Child and Youth Depression; Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Checklist; Outcome (game theory); Medicine; Randomized controlled trial; Psychological intervention; Clinical trial; MEDLINE; Major depressive disorder; Reporting bias; Depression (economics); Family medicine; Clinical psychology; Psychology; Psychiatry; Mood; Internal medicine","score_opus":0.996080800305135,"score_gpt":0.8238819560303902,"score_spread":0.17219884427474486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029775226","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":[0.061458793,0.0012793716,0.923925,0.0083434805,0.000602708,0.0013661189,0.0000050658605,0.000013029071,0.0030064443],"genre_scores_gemma":[0.60260844,0.0007128856,0.38267896,0.008426076,0.0026576326,0.00022610488,0.000038180795,0.000060713934,0.0025909825],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.031321976,0.85958594,0.07605577,0.002310279,0.02967168,0.0010543194],"domain_scores_gemma":[0.016795356,0.93926173,0.030819802,0.005513869,0.0044836784,0.0031255768],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.96569216,0.00027211994,0.010540406,0.0010345752,0.00015701646,0.00032081627,0.0027493816,0.000645228,0.015440778],"category_scores_gemma":[0.9952305,0.00012800514,0.0026008557,0.00411161,0.00041379943,0.00015333331,0.0011227546,0.0021067467,0.0009840375],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002293924,0.000073963434,0.6971762,0.00019293114,0.00004428153,0.00008049979,0.00029125236,0.000050077517,0.00011807578,0.00053001486,0.032329947,0.26888338],"study_design_scores_gemma":[0.0036803724,0.0004802855,0.6512016,0.00056392094,0.00020213296,0.000068066896,0.0042531136,0.055282455,0.00016189554,0.013184565,0.2703915,0.000530101],"about_ca_topic_score_codex":0.000024206016,"about_ca_topic_score_gemma":0.000080953,"teacher_disagreement_score":0.54124606,"about_ca_system_score_codex":0.00010588722,"about_ca_system_score_gemma":0.0018835607,"threshold_uncertainty_score":0.9997938},"labels":[],"label_agreement":null},{"id":"W3029811621","doi":"10.1186/s12874-020-01031-w","title":"The semi-automation of title and abstract screening: a retrospective exploration of ways to leverage Abstrackr’s relevance predictions in systematic and rapid reviews","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates","keywords":"Workload; Leverage (statistics); Systematic review; Computer science; Relevance (law); Medicine; Automation; MEDLINE; Machine learning; Data mining; Medical physics; Engineering","score_opus":0.951314378397344,"score_gpt":0.6454746183789096,"score_spread":0.3058397600184344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029811621","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":[0.008056253,0.012556524,0.97228694,0.00240189,0.00007947088,0.00166542,0.0000064396145,0.0000036298734,0.0029434478],"genre_scores_gemma":[0.8723917,0.0073804418,0.118613176,0.00018666631,0.0001478115,0.0003212525,0.0000035232572,0.000015398058,0.00094002543],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9559295,0.032738622,0.005832588,0.0006330779,0.004611648,0.00025454556],"domain_scores_gemma":[0.91034174,0.085839026,0.0016190874,0.0010327016,0.0008658385,0.0003016094],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23950592,0.000084763255,0.001585877,0.00020738272,0.00006791197,0.000052095264,0.0004646987,0.000090526846,0.0010539287],"category_scores_gemma":[0.6097248,0.00003936898,0.00015490784,0.00093900796,0.00019476254,0.000109710854,0.00012498755,0.0002641435,0.00016259008],"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":[0.0005071257,0.0002921407,0.017985232,0.06277563,0.0007750763,0.000033789624,0.030372176,0.00063349266,0.006383398,0.15587284,0.22898948,0.49537963],"study_design_scores_gemma":[0.0025114808,0.0024029855,0.2705332,0.020655643,0.00061615364,0.00006831413,0.018872041,0.38487357,0.0014114866,0.16336988,0.1337967,0.0008885562],"about_ca_topic_score_codex":0.000016327693,"about_ca_topic_score_gemma":0.000096926015,"teacher_disagreement_score":0.8643355,"about_ca_system_score_codex":0.000016330285,"about_ca_system_score_gemma":0.000097180666,"threshold_uncertainty_score":0.9998592},"labels":[],"label_agreement":null},{"id":"W3029969037","doi":"10.1186/s12874-020-00983-3","title":"Database combinations to retrieve systematic reviews in overviews of reviews: a methodological study","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; University of British Columbia","funders":"","keywords":"MEDLINE; Systematic review; CINAHL; PsycINFO; Medicine; Meta-analysis; Confidence interval; Database; Computer science; Internal medicine","score_opus":0.9941658052708935,"score_gpt":0.7768281980751072,"score_spread":0.21733760719578632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029969037","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":[0.016180366,0.03371963,0.91601753,0.00814522,0.00037538752,0.023965744,0.000026765503,0.000013164252,0.0015561705],"genre_scores_gemma":[0.05429639,0.007581947,0.921723,0.006984125,0.00040585696,0.005996878,0.000028015533,0.00006478781,0.0029189866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.046742484,0.8954736,0.033330597,0.002930333,0.02041282,0.0011101596],"domain_scores_gemma":[0.05317001,0.9161891,0.010155691,0.012244254,0.0047904323,0.0034505224],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.9164807,0.0005227533,0.019558245,0.001577426,0.00015166737,0.00018791984,0.007413854,0.00035809973,0.019513],"category_scores_gemma":[0.98950547,0.00023917636,0.002188758,0.013045519,0.00040816824,0.00020363182,0.0021362347,0.0016255858,0.0055780318],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093832775,0.006142065,0.06670509,0.12230924,0.00082012353,0.0005448898,0.036980167,0.000054126267,0.0020627105,0.054836966,0.59554046,0.11306581],"study_design_scores_gemma":[0.0092819035,0.011191727,0.024465563,0.03507699,0.0018777385,0.00017578395,0.05326364,0.03689738,0.00027854985,0.04882788,0.7759546,0.0027082288],"about_ca_topic_score_codex":0.00012021604,"about_ca_topic_score_gemma":0.00080975133,"teacher_disagreement_score":0.18041413,"about_ca_system_score_codex":0.00010499836,"about_ca_system_score_gemma":0.00069943647,"threshold_uncertainty_score":0.9979565},"labels":[],"label_agreement":null},{"id":"W3033836482","doi":"10.1186/s12874-020-01037-4","title":"Towards reduction in bias in epidemic curves due to outcome misclassification through Bayesian analysis of time-series of laboratory test results: case study of COVID-19 in Alberta, Canada and Philadelphia, USA","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Coronavirus disease 2019 (COVID-19); Statistics; Sensitivity (control systems); Bayesian probability; Medicine; Confidence interval; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Receiver operating characteristic; Test (biology); Econometrics; Demography; Computer science; Mathematics; Pathology; Biology","score_opus":0.5858101104766196,"score_gpt":0.5398356436985445,"score_spread":0.04597446677807504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033836482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98166895,0.00019931307,0.0017624208,0.015548456,0.000040606,0.00068558694,0.00003940876,0.000006582246,0.000048656322],"genre_scores_gemma":[0.9916105,0.000071088776,0.00737461,0.00083734246,0.000031890126,0.000037648686,0.00001233064,0.000011201515,0.000013386149],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9883785,0.008208856,0.0016465314,0.00050954113,0.0009410481,0.00031549166],"domain_scores_gemma":[0.9618154,0.036752343,0.00032254978,0.0003706979,0.0003770779,0.00036194528],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018210134,0.00013080364,0.0012221881,0.0010635512,0.000026745218,0.0000024087299,0.00016200873,0.00018757788,0.000069152156],"category_scores_gemma":[0.50754875,0.000116798976,0.00004527244,0.0052341768,0.00038709724,0.00006304854,0.00011206505,0.0006568249,5.8320563e-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":[0.002185438,0.00060610165,0.94921476,0.0015845093,0.00015295479,0.0013849878,0.013339517,0.00018910892,0.029037343,0.000034004177,0.00044786982,0.0018234211],"study_design_scores_gemma":[0.015400207,0.0067648883,0.7858609,0.0014296056,0.00063960813,0.0011330182,0.10876963,0.028446881,0.049736258,0.0002925785,0.00091513025,0.00061128906],"about_ca_topic_score_codex":0.90008986,"about_ca_topic_score_gemma":0.97036105,"teacher_disagreement_score":0.48933864,"about_ca_system_score_codex":0.0002953209,"about_ca_system_score_gemma":0.003594235,"threshold_uncertainty_score":0.63760185},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"simulation_or_modeling","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":"high"}],"label_agreement":"split"},{"id":"W3035592618","doi":"10.1186/s12874-020-01022-x","title":"Using multiple agreement methods for continuous repeated measures data: a tutorial for practitioners","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Emory University","keywords":"Concordance; Cohen's kappa; Computer science; Concordance correlation coefficient; Data mining; Statistics; Strengths and weaknesses; Correlation coefficient; Pulmonary disease; Limits of agreement; Medical physics; Medicine; Mathematics; Machine learning; Psychology","score_opus":0.9644013985579888,"score_gpt":0.7181859517571121,"score_spread":0.2462154468008767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035592618","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":[0.0024845893,0.0004510766,0.9788967,0.012543528,0.0021252527,0.0031028646,0.00012332706,0.00005018777,0.00022247047],"genre_scores_gemma":[0.005849201,0.00007368642,0.9896866,0.0011057194,0.0024477977,0.00047534003,0.00008486683,0.000027621758,0.00024915877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9347641,0.051040456,0.0023333617,0.0024123206,0.008000678,0.001449097],"domain_scores_gemma":[0.44727448,0.53967786,0.00089552125,0.0032219994,0.0068131993,0.0021169551],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34703776,0.0002609011,0.0011267075,0.00031716868,0.000635898,0.0002511844,0.0032971671,0.00044785696,0.00080968585],"category_scores_gemma":[0.8918822,0.00018645363,0.00031351112,0.0010767526,0.0008022512,0.00034991544,0.0012073916,0.00078650087,0.00004570411],"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":[0.009065401,0.00054224493,0.002173008,0.00036202426,0.00033551024,0.000016611159,0.0016001738,0.00051658956,0.057104804,0.005255338,0.12332341,0.7997049],"study_design_scores_gemma":[0.0039503546,0.0011122961,0.000088039764,0.000056513923,0.00006757223,0.000008103986,0.0027997934,0.2378906,0.004435614,0.032240424,0.71708375,0.00026696088],"about_ca_topic_score_codex":0.0002758091,"about_ca_topic_score_gemma":0.00034063737,"teacher_disagreement_score":0.79943794,"about_ca_system_score_codex":0.0001853395,"about_ca_system_score_gemma":0.0025231843,"threshold_uncertainty_score":0.88654923},"labels":[],"label_agreement":null},{"id":"W3035611753","doi":"10.1186/s12874-020-01029-4","title":"Improving design choices in Delphi studies in medicine: the case of an exemplary physician multi-round panel study with 100% response","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":187,"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":"Newfoundland and Labrador; Achmea","keywords":"Delphi method; Delphi; Operations research; Computer science; Psychology; Medical education; Medicine; Management science; Data science; Artificial intelligence","score_opus":0.9143798360928609,"score_gpt":0.6898360383718415,"score_spread":0.2245437977210194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035611753","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9518112,0.0010385477,0.031907357,0.011942577,0.000083150815,0.0030351598,0.0000024606725,0.00006747597,0.00011210346],"genre_scores_gemma":[0.9458477,0.0002825252,0.05261456,0.00044918284,0.00030123309,0.00041859492,7.78009e-7,0.000033226766,0.000052239076],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.83581364,0.15771043,0.0009275078,0.000900183,0.0032981394,0.0013500911],"domain_scores_gemma":[0.8231097,0.17480089,0.0001776098,0.0006003765,0.00068443234,0.0006269762],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21431653,0.00021765992,0.0008887201,0.0007210181,0.00049508276,0.000034635956,0.0018855482,0.00030475573,0.00008591428],"category_scores_gemma":[0.3555852,0.00013561537,0.000045453664,0.0032582304,0.007526118,0.00025662305,0.0007180095,0.0021702612,0.0000053451345],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03073626,0.0030688767,0.018554494,0.0009053997,0.00021691431,0.049874794,0.6852881,0.00023727339,0.008375018,0.0020415415,0.0011849747,0.1995164],"study_design_scores_gemma":[0.0034442397,0.0072644646,0.007879219,0.00032385075,0.00002386674,0.00010650575,0.9717151,0.0065517016,0.0004310289,0.0017517657,0.00024450742,0.00026376126],"about_ca_topic_score_codex":0.06959035,"about_ca_topic_score_gemma":0.2055721,"teacher_disagreement_score":0.28642705,"about_ca_system_score_codex":0.00028959257,"about_ca_system_score_gemma":0.0032905845,"threshold_uncertainty_score":0.9951748},"labels":[],"label_agreement":null},{"id":"W3037194796","doi":"10.1186/s12874-020-01056-1","title":"Applying an intersectionality lens to the theoretical domains framework: a tool for thinking about how intersecting social identities and structures of power influence behaviour","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":123,"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; George & Fay Yee Centre for Healthcare Innovation; St. Michael's Hospital; Centre for Advancing Health Outcomes; University of Ottawa; Toronto Rehabilitation Institute; University of Waterloo; University of British Columbia; University of Manitoba; Research Canada; Ottawa Hospital","funders":"Research Institute for Aging, University of Waterloo; Canadian Institutes of Health Research; Toronto Rehabilitation Institute; University of Waterloo; University of Toronto; Department of Medicine, University of Toronto; University of Ottawa","keywords":"Intersectionality; Lens (geology); Through-the-lens metering; Power (physics); Sociology; Computer science; Psychology; Epistemology; Gender studies; Physics; Optics","score_opus":0.822539031507419,"score_gpt":0.7341587459265357,"score_spread":0.08838028558088329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037194796","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57607836,0.000008297434,0.3830909,0.03909302,0.0001989853,0.0013787607,0.000040002622,0.000025103913,0.000086582055],"genre_scores_gemma":[0.9032245,0.000009183666,0.07404499,0.02110328,0.0006351371,0.0009526349,0.000002618559,0.000016738688,0.000010899679],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9725562,0.023488445,0.00079656875,0.00049837434,0.0016416165,0.0010188493],"domain_scores_gemma":[0.88266313,0.11540621,0.00025524994,0.00027433565,0.00080554833,0.00059551734],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054045547,0.00013040174,0.00042117474,0.0001768558,0.0017773219,0.000050119812,0.00078366534,0.0003473429,0.0007505813],"category_scores_gemma":[0.33049262,0.000091972455,0.00006873342,0.00049185485,0.001671772,0.00020271068,0.0008730171,0.0019783415,0.0000055802784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005180322,0.000014202205,0.037414342,0.0006305402,0.000021946886,0.0000030123688,0.21002887,0.0000038969206,0.0009524111,0.74295074,0.0025199086,0.0049421266],"study_design_scores_gemma":[0.0016003791,0.0011305216,0.23231561,0.0004324893,0.0000293318,0.000018041814,0.35015178,0.0009164978,0.0003525504,0.40771547,0.0050249114,0.00031242173],"about_ca_topic_score_codex":0.00034093118,"about_ca_topic_score_gemma":0.0006414347,"teacher_disagreement_score":0.33523524,"about_ca_system_score_codex":0.0001279216,"about_ca_system_score_gemma":0.0015694834,"threshold_uncertainty_score":0.9995222},"labels":[],"label_agreement":null},{"id":"W3037840142","doi":"10.1186/s12874-020-01050-7","title":"A conceptual framework for prognostic research","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; Public Health Ontario; University of Toronto; Canadian Memorial Chiropractic College","funders":"","keywords":"Computer science; Conceptual framework; Data science; MEDLINE; Medicine; Management science; Sociology; Political science","score_opus":0.9537009219251084,"score_gpt":0.7282200696729361,"score_spread":0.2254808522521723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037840142","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007186115,0.00029856787,0.978814,0.010006688,0.00010932175,0.0020279626,0.000013282311,0.00037804322,0.0011659854],"genre_scores_gemma":[0.04223992,0.00012894672,0.9538759,0.00074875494,0.0010389435,0.0016934247,0.000007775503,0.00007305294,0.00019328856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9695448,0.023279358,0.0007715838,0.00093818974,0.0035345086,0.0019315203],"domain_scores_gemma":[0.4421055,0.5537502,0.00010803941,0.0007215974,0.0018141649,0.0015004653],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06224936,0.00021192933,0.0007753365,0.00029791344,0.00033225864,0.00004074993,0.0014638009,0.0008808991,0.0019376497],"category_scores_gemma":[0.8790135,0.00017415274,0.00014587057,0.0012112757,0.0035464615,0.00009338793,0.0009364445,0.003833684,0.0001617276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003870403,0.00009540031,0.00024249293,0.00034114724,0.000023382056,0.00004404636,0.0017225594,3.55427e-7,0.0007656477,0.9640669,0.01990509,0.012405896],"study_design_scores_gemma":[0.00043876984,0.0016582089,0.000028937831,0.00022326774,0.000008778,0.000012938573,0.0028360395,0.00081361743,0.004310206,0.97013503,0.019368334,0.0001658704],"about_ca_topic_score_codex":0.000026321131,"about_ca_topic_score_gemma":0.00005883664,"teacher_disagreement_score":0.8167641,"about_ca_system_score_codex":0.00013022296,"about_ca_system_score_gemma":0.0020402446,"threshold_uncertainty_score":0.9991653},"labels":[],"label_agreement":null},{"id":"W3037957272","doi":"10.1186/s12874-020-01036-5","title":"Explaining the variation in the attained power of a stepped-wedge trial with unequal cluster sizes","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"Servier; Bayer Canada; Vancouver Coastal Health Research Institute; Biogen; Michael Smith Health Research BC; Compute Canada; Western Canada Research Grid; Heart and Stroke Foundation of Canada","keywords":"Statistics; Intraclass correlation; Mathematics; Linear regression; Cluster (spacecraft); Power (physics); Correlation; Statistical power; Coefficient of variation; Econometrics; Computer science; Physics; Thermodynamics","score_opus":0.920380177653608,"score_gpt":0.6920578964242246,"score_spread":0.22832228122938347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037957272","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":[0.0763945,0.000041164523,0.90195423,0.018089935,0.0002791632,0.002316703,0.000011858028,0.000029360108,0.00088310626],"genre_scores_gemma":[0.17465039,0.00002180703,0.822349,0.0017189094,0.00080859306,0.00037947015,0.0000013503208,0.000034517507,0.00003593872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8165442,0.17507286,0.0022426834,0.00077532965,0.004327169,0.0010377897],"domain_scores_gemma":[0.11952629,0.87868667,0.0003594018,0.0007265626,0.00036474236,0.00033636286],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1836931,0.00019598105,0.0010849136,0.00012490894,0.00013695785,0.000034264267,0.0013930604,0.00043513183,0.0011463611],"category_scores_gemma":[0.91482174,0.00009089202,0.00014722286,0.0010862882,0.001448961,0.000047940186,0.0004469536,0.0020213604,0.000020447433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15467694,0.0008605869,0.00036868447,0.0006532761,0.00023154124,0.0001445572,0.03063131,0.000030395433,0.00042791336,0.7869696,0.008867989,0.016137213],"study_design_scores_gemma":[0.06770177,0.007926935,0.0014796329,0.00027012115,0.00012481752,0.000019966092,0.0121214595,0.007800756,0.00028272622,0.9009795,0.0009780943,0.00031420842],"about_ca_topic_score_codex":0.00007027879,"about_ca_topic_score_gemma":0.00012675513,"teacher_disagreement_score":0.73112863,"about_ca_system_score_codex":0.00004099296,"about_ca_system_score_gemma":0.0010082204,"threshold_uncertainty_score":0.9997667},"labels":[],"label_agreement":null},{"id":"W3038839399","doi":"10.1186/s12874-020-01069-w","title":"Agreement between original and Rasch-approved neck disability index","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","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":"Western University; McMaster University; St Joseph's Health Care","funders":"Canadian Institutes of Health Research","keywords":"Rasch model; Medicine; Mean difference; MEDLINE; Physical therapy; Item response theory; Confidence interval; Psychometrics; Statistics; Clinical psychology; Internal medicine; Mathematics","score_opus":0.41144905618960165,"score_gpt":0.5321857489474677,"score_spread":0.12073669275786608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038839399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88163364,0.0002765309,0.06753179,0.047552522,0.000082495935,0.00091693376,0.0000029239754,0.000051388335,0.0019517579],"genre_scores_gemma":[0.9351671,0.00014751864,0.062494166,0.0010002861,0.00093298074,0.0000637574,0.000019802148,0.00001843919,0.0001559641],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9891352,0.007315672,0.00051829667,0.0006576001,0.0017848961,0.0005883054],"domain_scores_gemma":[0.9738153,0.023783503,0.000054112075,0.00038020874,0.00023262032,0.0017342502],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01941219,0.00015552063,0.0006540886,0.00008841986,0.00011910924,0.000013372642,0.00020786347,0.0003555212,0.0024812939],"category_scores_gemma":[0.11480109,0.00011069304,0.00012829402,0.00037972952,0.0016147178,0.00004667473,0.000287771,0.0012390065,0.0000977267],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011522182,0.00018990385,0.80561996,0.003161755,0.000092597984,0.000020184625,0.00065104576,7.2941464e-7,0.0033377407,0.005073606,0.0015172858,0.17918296],"study_design_scores_gemma":[0.003106381,0.0024440256,0.95813745,0.00015976928,0.000034120316,0.000009037216,0.00084722467,0.0023779997,0.0002962931,0.004435537,0.027991638,0.00016051928],"about_ca_topic_score_codex":0.00023451509,"about_ca_topic_score_gemma":0.00008837248,"teacher_disagreement_score":0.17902243,"about_ca_system_score_codex":0.00008363056,"about_ca_system_score_gemma":0.00058554526,"threshold_uncertainty_score":0.99843055},"labels":[],"label_agreement":null},{"id":"W3039993240","doi":"10.1186/s12874-020-01065-0","title":"International severe asthma registry (ISAR): protocol for a global registry","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Asthma and respiratory diseases","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Optimum Patient Care","keywords":"Asthma; Protocol (science); Medicine; Alternative medicine; Pathology; Internal medicine","score_opus":0.4808448048602259,"score_gpt":0.5793847402209696,"score_spread":0.09853993536074374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039993240","genre_codex":"methods","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010089385,0.00027088466,0.6010865,0.11373005,0.0009293119,0.20611164,0.00029072014,0.00053996244,0.06695155],"genre_scores_gemma":[0.014021472,0.000052345316,0.45056662,0.026343148,0.01650542,0.48318183,0.00027038984,0.00017845069,0.008880317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927074,0.0030740895,0.00056411495,0.00074560975,0.00214964,0.0007591794],"domain_scores_gemma":[0.99029654,0.006498727,0.00013415783,0.0004919324,0.00066677725,0.0019118905],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0059614573,0.00020331764,0.0005762112,0.00008309571,0.00014750152,0.00003235449,0.0007510332,0.0005219324,0.0032518338],"category_scores_gemma":[0.14059779,0.00015431958,0.00028467624,0.00040180876,0.0009438182,0.000059441012,0.00041575902,0.00088511466,0.00010907323],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030693268,0.0009985167,0.041543085,0.0050182235,0.00028834803,0.0019289633,0.00025904409,0.00000930728,0.0016088807,0.011434037,0.5392792,0.3669391],"study_design_scores_gemma":[0.0064206175,0.0015407845,0.005212643,0.00028634915,0.000015816293,0.0004307336,0.0005608523,0.0014294927,0.00032843748,0.0014018265,0.98220205,0.00017042104],"about_ca_topic_score_codex":0.000027885631,"about_ca_topic_score_gemma":0.00002663132,"teacher_disagreement_score":0.4429228,"about_ca_system_score_codex":0.0001687785,"about_ca_system_score_gemma":0.0044401367,"threshold_uncertainty_score":0.9976593},"labels":[],"label_agreement":null},{"id":"W3081089509","doi":"10.1186/s12874-020-01095-8","title":"Measuring clinical uncertainty and equipoise by applying the agreement study methodology to patient management decisions","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Clinical Reasoning and Diagnostic Skills","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":"Université de Montréal; University of Alberta Hospital; Centre Hospitalier de l’Université de Montréal; Health Sciences Centre; Ottawa Hospital","funders":"","keywords":"Reliability (semiconductor); Clinical equipoise; Dilemma; Medicine; Warrant; Clinical trial; Randomized controlled trial; Inter-rater reliability; Variety (cybernetics); Portfolio; Medical physics; Computer science; Psychology; Artificial intelligence; Rating scale; Surgery; Pathology; Mathematics","score_opus":0.7981267890516146,"score_gpt":0.6120079939446796,"score_spread":0.18611879510693496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081089509","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":[0.6512899,0.001916385,0.2887691,0.048972655,0.000656707,0.0068493774,0.000012319915,0.000099956495,0.001433623],"genre_scores_gemma":[0.6480188,0.0029149526,0.31866595,0.02581617,0.0010551413,0.0030655684,0.000025735306,0.00007770939,0.00035999407],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9542947,0.037458923,0.0017804463,0.0015228016,0.0036589885,0.001284134],"domain_scores_gemma":[0.26849335,0.7245437,0.00021499985,0.0013660344,0.0006146541,0.0047672843],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08108921,0.00028002873,0.0012739332,0.00019553502,0.0003592251,0.000041324,0.0007096586,0.00035003707,0.00065285724],"category_scores_gemma":[0.8043064,0.00017256415,0.00022445957,0.0008440009,0.00091908034,0.000023141101,0.002257766,0.0020110502,0.00019626177],"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":[0.002807884,0.0011502078,0.02968855,0.00006692499,0.0003581626,0.0005387837,0.0016743797,0.000042551408,0.00007842569,0.0010086066,0.02122583,0.9413597],"study_design_scores_gemma":[0.04865035,0.07546539,0.29321924,0.006986723,0.0026088424,0.00059629633,0.12304079,0.014483036,0.0005948404,0.01549575,0.41647357,0.0023851783],"about_ca_topic_score_codex":0.00039854305,"about_ca_topic_score_gemma":0.00022561796,"teacher_disagreement_score":0.9389745,"about_ca_system_score_codex":0.000100236124,"about_ca_system_score_gemma":0.0005717848,"threshold_uncertainty_score":0.94621205},"labels":[],"label_agreement":null},{"id":"W3082392532","doi":"10.1186/s12874-020-01100-0","title":"Inference about time-dependent prognostic accuracy measures in the presence of competing risks","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"McGill University","keywords":"Estimator; Inference; Outcome (game theory); Statistics; Computer science; Causal inference; Event (particle physics); Rank (graph theory); Econometrics; Survival analysis; Medicine; Mathematics; Artificial intelligence","score_opus":0.8180778493755235,"score_gpt":0.6242850620286619,"score_spread":0.19379278734686167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082392532","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":[0.07246333,0.00036728475,0.9205726,0.0028421727,0.000078108,0.00089252525,0.000014910868,0.000040622155,0.0027284434],"genre_scores_gemma":[0.5094769,0.0001679516,0.48973438,0.00029988922,0.00015119622,0.00013330104,0.0000017009543,0.000017604294,0.000017065291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93743587,0.055962574,0.0012363082,0.0006502058,0.0037125768,0.0010024427],"domain_scores_gemma":[0.37614626,0.6219508,0.00024092989,0.0005734818,0.00059417856,0.00049432466],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.063730344,0.0001874474,0.0007626121,0.00014307372,0.00011749926,0.00003927902,0.0017208585,0.00027076763,0.0014194704],"category_scores_gemma":[0.90437216,0.000117940304,0.00008482628,0.0007923465,0.0011941036,0.00005530127,0.0006305899,0.0018980933,0.00007479405],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007984007,0.00070024794,0.053214036,0.0023705726,0.000078053105,0.0002812519,0.013116025,0.000055957087,0.0056037125,0.57134324,0.00216646,0.35027206],"study_design_scores_gemma":[0.0018842254,0.0015691075,0.04391325,0.0013418549,0.00006318228,0.00005360586,0.004757816,0.06841738,0.0032958959,0.87329304,0.00092035416,0.0004902978],"about_ca_topic_score_codex":0.0003779557,"about_ca_topic_score_gemma":0.00017325534,"teacher_disagreement_score":0.8406418,"about_ca_system_score_codex":0.000028193952,"about_ca_system_score_gemma":0.0010412773,"threshold_uncertainty_score":0.99949336},"labels":[],"label_agreement":null},{"id":"W3084046422","doi":"10.1186/s12874-020-01107-7","title":"A tutorial on methodological studies: the what, when, how and why","year":2020,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":147,"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; Population Health Research Institute; McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"","keywords":"Research design; Biostatistics; Computer science; Management science; Protocol (science); Publication; Data science; Data extraction; Quality (philosophy); External validity; Engineering ethics; MEDLINE; Medicine; Psychology; Alternative medicine; Public health; Sociology; Social science","score_opus":0.9967600144857308,"score_gpt":0.8075475698813431,"score_spread":0.1892124446043877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084046422","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":[9.1473675e-7,0.89012015,0.078417026,0.024802277,0.0032074724,0.002856828,0.000014502024,0.000014466127,0.00056636136],"genre_scores_gemma":[2.8315904e-7,0.9222741,0.067242004,0.002239595,0.0036009212,0.0008912032,0.000009491267,0.000049972066,0.0036924034],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.14960669,0.80135083,0.013275349,0.004380712,0.029925426,0.0014610077],"domain_scores_gemma":[0.026542526,0.9553625,0.005768526,0.007434067,0.0030756148,0.0018167769],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.867433,0.0011440347,0.029640933,0.0012353604,0.00067971786,0.0026646615,0.0104155885,0.001479227,0.0131514445],"category_scores_gemma":[0.9788883,0.00036732058,0.0059771403,0.003797773,0.0033249932,0.00024343106,0.003848006,0.0053724675,0.0030099342],"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":[0.000030787953,0.000024301457,0.0000025124773,0.00269123,0.0006129267,0.00012260825,0.0003700385,6.471459e-8,6.321955e-8,0.0096273385,0.28161612,0.704902],"study_design_scores_gemma":[0.0002056549,0.000323194,0.0000016344634,0.0034350606,0.00083368795,0.00021973286,0.0033618473,0.00013022343,1.1513084e-7,0.043460965,0.9477348,0.00029312502],"about_ca_topic_score_codex":0.00001605989,"about_ca_topic_score_gemma":0.000119929646,"teacher_disagreement_score":0.70460886,"about_ca_system_score_codex":0.00018705912,"about_ca_system_score_gemma":0.0027008126,"threshold_uncertainty_score":0.99987787},"labels":[],"label_agreement":null},{"id":"W3084701287","doi":"10.1186/s12874-020-01117-5","title":"Recruitment of adolescents with suicidal ideation in the emergency department: lessons from a randomized controlled pilot trial of a youth suicide prevention intervention","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Suicide and Self-Harm Studies","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Centre for Addiction and Mental Health; University of Toronto; Hospital for Sick Children","funders":"Cundill Centre for Child and Youth Depression; Hospital for Sick Children; Sick Kids Foundation; Centre for Addiction and Mental Health","keywords":"Suicidal ideation; Randomized controlled trial; Medicine; Emergency department; Mental health; Psychological intervention; Suicide prevention; Intervention (counseling); Poison control; Family medicine; Randomization; Psychiatry; Outpatient clinic; Medical emergency","score_opus":0.6451800102093039,"score_gpt":0.5684292908780336,"score_spread":0.07675071933127031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084701287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9137505,0.0019130253,0.07398694,0.0019834407,0.0004024074,0.007391533,0.000025501293,0.000017899813,0.0005287539],"genre_scores_gemma":[0.995119,0.00041931207,0.0015191069,0.00009537424,0.0002161642,0.0025021364,0.00006320662,0.000017429338,0.000048307455],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.92711985,0.067869656,0.0020289351,0.00057069736,0.0018470315,0.00056383177],"domain_scores_gemma":[0.97959065,0.01897435,0.0006077028,0.00035517718,0.00030439688,0.0001677007],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04040236,0.00020371776,0.001992377,0.00028294555,0.000068019064,0.0000072508797,0.00053539977,0.00019780485,0.001004524],"category_scores_gemma":[0.044289652,0.00011816388,0.00046298868,0.0005862263,0.00051183114,0.000046032816,0.000145975,0.0006400345,0.000014608635],"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":[0.9722115,0.0016709593,0.009257132,0.00012921999,0.0006643951,0.00001904744,0.00901683,0.000003090921,0.00023088323,0.003082847,0.000084289946,0.0036298374],"study_design_scores_gemma":[0.95472383,0.006391993,0.018971419,0.0002037937,0.00045200728,0.0000023614084,0.013344294,0.00022142938,0.00027687952,0.0052650766,0.0000102730755,0.00013664369],"about_ca_topic_score_codex":0.004616993,"about_ca_topic_score_gemma":0.0050202254,"teacher_disagreement_score":0.08136846,"about_ca_system_score_codex":0.000043171236,"about_ca_system_score_gemma":0.00026120493,"threshold_uncertainty_score":0.9999087},"labels":[],"label_agreement":null},{"id":"W3085937784","doi":"10.1186/s12874-020-01112-w","title":"Modeling socio-demographic and clinical factors influencing psychiatric inpatient service use: a comparison of models for zero-Inflated and overdispersed count data","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Schizophrenia research and treatment","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":"Saskatchewan Health Authority; Dalhousie University; University of Saskatchewan","funders":"Ministry of Health, Saskatchewan; University of Saskatchewan","keywords":"Count data; Psychiatry; Medicine; Generalized estimating equation; Psychology; Statistics; Poisson distribution","score_opus":0.7186641947034513,"score_gpt":0.5761796909298731,"score_spread":0.14248450377357824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085937784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85432404,0.0017450895,0.13935675,0.0031814915,0.0000615996,0.0012000833,0.00009001193,0.000034980174,0.000005975565],"genre_scores_gemma":[0.86938524,0.0015123175,0.12830709,0.00040734242,0.00012283295,0.00003946805,0.00019130627,0.000032067994,0.0000023345046],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915931,0.0037614459,0.0011116789,0.00096005254,0.0018127734,0.0007609432],"domain_scores_gemma":[0.9705384,0.0260716,0.00014615477,0.00068102183,0.000766304,0.0017965662],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011113517,0.00023784302,0.0012205912,0.00036091506,0.00020500051,0.000033427517,0.00044074547,0.0005047452,0.000033576955],"category_scores_gemma":[0.042732213,0.0001761661,0.00012849833,0.0007727407,0.0006287317,0.00019726614,0.00092311145,0.0013061939,0.0000018327692],"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":[0.034804694,0.0009491462,0.9272933,0.0028777074,0.0011222984,0.000039811985,0.0038765536,0.0007453267,0.0006058834,0.002536766,0.0007174958,0.024431009],"study_design_scores_gemma":[0.00827034,0.0024135625,0.028757386,0.00014775318,0.00021013092,0.000011197213,0.0018794324,0.9554008,0.000046227688,0.0026697791,0.00005022399,0.00014313984],"about_ca_topic_score_codex":0.0013383962,"about_ca_topic_score_gemma":0.00092550763,"teacher_disagreement_score":0.9546555,"about_ca_system_score_codex":0.000060315466,"about_ca_system_score_gemma":0.0020737604,"threshold_uncertainty_score":0.96533126},"labels":[],"label_agreement":null},{"id":"W3092092890","doi":"10.1186/s12874-020-01136-2","title":"Recruiting men from across the socioeconomic spectrum via GP registers and community outreach to a weight management feasibility randomised controlled trial","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Social Media in Health Education","field":"Social 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":false,"ca_institutions":"University of New Brunswick","funders":"Medical Research Council; University of Stirling; National Institute for Health and Care Research; University of Dundee; University of Aberdeen; Scottish Government; Public Health Research Programme; Scottish Government Health and Social Care Directorate","keywords":"Outreach; Disadvantaged; Medicine; Weight management; Psychological intervention; Waist; Family medicine; Socioeconomic status; Gerontology; Randomized controlled trial; Obesity; Weight loss; Physical therapy; Demography; Population; Nursing; Environmental health; Surgery; Internal medicine","score_opus":0.6917735072072287,"score_gpt":0.6027140174313876,"score_spread":0.0890594897758411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092092890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8000943,0.00020508304,0.009464475,0.17144899,0.0018013568,0.013584467,0.000006617602,0.00006354051,0.0033311439],"genre_scores_gemma":[0.9508104,0.0010220201,0.02402514,0.0057475152,0.007316506,0.010803009,0.000020193942,0.000045521934,0.00020972929],"study_design_codex":"qualitative","study_design_gemma":"randomized_trial","domain_scores_codex":[0.86654884,0.12957233,0.0008417543,0.0005574323,0.0013806534,0.0010989911],"domain_scores_gemma":[0.60260963,0.39457175,0.00028863928,0.00064066745,0.00019078796,0.0016985295],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14457645,0.00016294148,0.0009241541,0.000073793555,0.0026274428,0.00010660799,0.0011973608,0.00036507854,0.0007608446],"category_scores_gemma":[0.3608529,0.00012311182,0.00015870837,0.00036914233,0.0023060278,0.000079288584,0.000573618,0.00205748,0.00007419387],"study_design_candidate":"randomized_trial","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":[0.36169082,0.00034232796,0.0079538785,0.00018115013,0.0002491386,0.000013911253,0.4948656,8.7901395e-7,0.000038879254,0.0034408665,0.004930958,0.1262916],"study_design_scores_gemma":[0.5748979,0.0010717246,0.015948778,0.00009047886,0.00010364407,0.000001400393,0.3372165,0.00067465584,0.00004746545,0.04160993,0.027935628,0.0004019471],"about_ca_topic_score_codex":0.031831026,"about_ca_topic_score_gemma":0.023828393,"teacher_disagreement_score":0.26499942,"about_ca_system_score_codex":0.0006482616,"about_ca_system_score_gemma":0.001500286,"threshold_uncertainty_score":0.998671},"labels":[],"label_agreement":null},{"id":"W3093336514","doi":"10.1186/s12874-020-01129-1","title":"An evaluation of DistillerSR’s machine learning-based prioritization tool for title/abstract screening – impact on reviewer-relevant outcomes","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":141,"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; McGill University; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Interquartile range; Prioritization; Medicine; Recall; Computer science; Reduction (mathematics); Machine learning; Surgery; Psychology; Mathematics; Management science","score_opus":0.9578986850993956,"score_gpt":0.7245179146353774,"score_spread":0.23338077046401817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093336514","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":[0.018479843,0.00095051393,0.975691,0.0023836412,0.0001627631,0.0013829949,0.000029406214,0.0000082030565,0.00091162923],"genre_scores_gemma":[0.8540188,0.000087749904,0.14416184,0.0005056994,0.0003054648,0.00014057297,0.00011934754,0.000027702257,0.00063280977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.86680573,0.11212722,0.0046529816,0.00094709377,0.015051545,0.0004154317],"domain_scores_gemma":[0.8122507,0.17698757,0.0021128776,0.0018470504,0.006143304,0.00065853295],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4938144,0.00015982133,0.0020233842,0.00030759317,0.00010004092,0.00008803529,0.000990612,0.00015514596,0.035255566],"category_scores_gemma":[0.8683048,0.00007418382,0.0008762632,0.0007921253,0.0001319986,0.00006965977,0.000059719314,0.0004093923,0.0005637506],"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":[0.00028792318,0.00013678528,0.037068974,0.0005452848,0.00017699556,0.0000032751009,0.00019517643,0.0069442573,0.00031721455,0.0017422986,0.031097217,0.9214846],"study_design_scores_gemma":[0.0006530157,0.000559222,0.045236096,0.00011116018,0.00012210861,7.914931e-7,0.00008965871,0.9182074,0.00006352704,0.0022639544,0.032579772,0.000113270304],"about_ca_topic_score_codex":0.000022172831,"about_ca_topic_score_gemma":0.000021053389,"teacher_disagreement_score":0.92137134,"about_ca_system_score_codex":0.00004284471,"about_ca_system_score_gemma":0.00076226343,"threshold_uncertainty_score":0.96562636},"labels":[],"label_agreement":null},{"id":"W3095656533","doi":"10.1186/s12874-020-01140-6","title":"Pharmacist and patient perspectives on recruitment strategies for randomized controlled trials: a qualitative analysis","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","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":"Health Sciences Centre; University of Alberta; University of Calgary","funders":"Canadian Institutes of Health Research; Alberta Innovates; Alberta Innovates - Health Solutions; University of Calgary","keywords":"Thematic analysis; Pharmacist; Focus group; Pharmacy; Medicine; Qualitative research; Randomized controlled trial; Patient recruitment; Family medicine; Descriptive statistics; Copayment; Nursing; Health care; Surgery","score_opus":0.9679947079169486,"score_gpt":0.7964907084309147,"score_spread":0.1715039994860339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095656533","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":[0.08009136,0.011877641,0.72180635,0.15252367,0.00027244864,0.02751497,0.00008621172,0.00012528016,0.005702062],"genre_scores_gemma":[0.7297107,0.020638924,0.22411789,0.0068635494,0.0011796231,0.016483445,0.000052365678,0.00008135918,0.0008721226],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.7667082,0.22056705,0.0034412653,0.0016132295,0.0064997408,0.0011705083],"domain_scores_gemma":[0.03523046,0.9592439,0.00047818504,0.00046964752,0.002704192,0.0018735933],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.44057196,0.00029837358,0.0080027655,0.00080010947,0.00023704955,0.000088212815,0.00038482345,0.0007037967,0.001760461],"category_scores_gemma":[0.9613451,0.00017150625,0.0019502975,0.0011190681,0.003946604,0.000052553223,0.00030787228,0.0037234754,0.00002670683],"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":[0.7325464,0.0004465926,0.000022678689,0.0005527811,0.0074141943,0.00006466963,0.055962216,0.000010047905,0.00040400718,0.19243489,0.00081043533,0.00933109],"study_design_scores_gemma":[0.53584194,0.007402968,0.00001909154,0.00025772964,0.0027228538,0.000006728448,0.27890924,0.022002261,0.0004586911,0.15078205,0.0013574526,0.00023902109],"about_ca_topic_score_codex":0.0001240885,"about_ca_topic_score_gemma":0.00015477477,"teacher_disagreement_score":0.73867685,"about_ca_system_score_codex":0.00015872462,"about_ca_system_score_gemma":0.0047113555,"threshold_uncertainty_score":0.99915206},"labels":[],"label_agreement":null},{"id":"W3095785912","doi":"10.1186/s12874-020-01128-2","title":"Spie charts for quantifying treatment effectiveness and safety in multiple outcome network meta-analysis: a proof-of-concept study","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":33,"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; University of Toronto; St. Michael's Hospital; McMaster University Medical Centre; St. Joseph’s Healthcare Hamilton; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Meta-analysis; Outcome (game theory); Proof of concept; Computer science; MEDLINE; Medicine; Data science; Mathematics; Internal medicine","score_opus":0.9861603358130153,"score_gpt":0.7232262615792209,"score_spread":0.26293407423379445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095785912","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":[0.19965528,0.0067614038,0.78497857,0.0017323862,0.00011243254,0.006674159,0.000026790309,0.0000057538286,0.000053219814],"genre_scores_gemma":[0.9275108,0.000021576094,0.07063403,0.00013421079,0.00012858439,0.0013855868,0.0000068691265,0.000016398293,0.00016196084],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.6433544,0.32724464,0.013834936,0.003101644,0.011239256,0.001225144],"domain_scores_gemma":[0.53810036,0.4556573,0.0019404297,0.0022435782,0.0012580492,0.0008002426],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5988024,0.0003736854,0.013446089,0.0007908868,0.00021039299,0.00013908741,0.0016246801,0.00023503379,0.0037152807],"category_scores_gemma":[0.64106554,0.00016814939,0.0039212974,0.0046116547,0.00041034602,0.00009687833,0.00048876693,0.00044777975,0.00003079653],"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":[0.0013464462,0.00087793445,0.8325587,0.00062795024,0.067656316,0.000072290604,0.0054522473,0.004878308,0.00003514031,0.0025890109,0.00045514322,0.083450496],"study_design_scores_gemma":[0.013769008,0.009530234,0.32480308,0.00009656711,0.14464892,0.000019613703,0.017879555,0.45990872,0.0006565446,0.014160127,0.013308001,0.0012196393],"about_ca_topic_score_codex":0.00024970114,"about_ca_topic_score_gemma":0.0030641905,"teacher_disagreement_score":0.7278555,"about_ca_system_score_codex":0.000062945444,"about_ca_system_score_gemma":0.000402364,"threshold_uncertainty_score":0.9971955},"labels":[],"label_agreement":null},{"id":"W3103564249","doi":"10.1186/s12874-020-01055-2","title":"A comparison of residual diagnosis tools for diagnosing regression models for count data","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":113,"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 Saskatchewan; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Count data; Statistics; Overdispersion; Covariate; Deviance (statistics); Studentized residual; Goodness of fit; Regression analysis; Residual; Generalized linear model; Normality; Econometrics; Linear regression; Nominal level; Regression; Statistic; Computer science; Mathematics; Poisson distribution; Confidence interval","score_opus":0.9407488530482577,"score_gpt":0.6995752683244929,"score_spread":0.24117358472376482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103564249","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":[0.0016568471,0.0005159867,0.99004227,0.005337837,0.00015789975,0.0014645244,0.0006598182,0.000039653703,0.00012517799],"genre_scores_gemma":[0.00935133,0.00024272238,0.988671,0.00026341097,0.0005011158,0.00082616165,0.00009347677,0.0000405569,0.000010220055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9871814,0.008384783,0.0011394395,0.00083585386,0.0016361239,0.00082236505],"domain_scores_gemma":[0.42840466,0.5691995,0.00025530197,0.0008119632,0.0006960178,0.00063255744],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03345672,0.00019763215,0.0012710936,0.00012295802,0.00019788745,0.000052546526,0.0015011717,0.00041666644,0.00032591086],"category_scores_gemma":[0.7634403,0.00014650887,0.000113677575,0.00033021078,0.00069544214,0.00018542395,0.0009002456,0.0006571527,0.0000030510464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011435286,0.00029696253,0.00078120455,0.0024703522,0.00005131884,0.000006537278,0.0007880681,0.0000042368442,0.00031673472,0.58358836,0.07557714,0.33497554],"study_design_scores_gemma":[0.0011549382,0.0010563834,0.00007216735,0.0005192819,0.00006543269,0.0000023538676,0.000771198,0.19936383,0.0046941107,0.7878706,0.004267236,0.00016246802],"about_ca_topic_score_codex":0.00005061637,"about_ca_topic_score_gemma":0.000090746595,"teacher_disagreement_score":0.7299836,"about_ca_system_score_codex":0.00004237776,"about_ca_system_score_gemma":0.0009921106,"threshold_uncertainty_score":0.9952597},"labels":[],"label_agreement":null},{"id":"W3106640820","doi":"10.1186/s12874-020-01157-x","title":"Epistemonikos: a comprehensive database of systematic reviews for health decision-making","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Systematic review; MEDLINE; Computer science; Data science; Medicine; Management science","score_opus":0.9837697841573154,"score_gpt":0.7577131318616004,"score_spread":0.22605665229571503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106640820","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":[0.0011206822,0.030936368,0.95368254,0.006684072,0.00030025048,0.00691533,0.000054213964,0.0000074061054,0.00029913356],"genre_scores_gemma":[0.016773608,0.0020742272,0.9741816,0.0051261755,0.00036184952,0.0010207321,0.000015639373,0.000034466775,0.000411735],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.2524184,0.67245996,0.039902043,0.0033244777,0.030205105,0.0016899827],"domain_scores_gemma":[0.05664556,0.9192275,0.009937756,0.0064483234,0.005827751,0.0019131589],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.74721575,0.0003716038,0.014012881,0.0007725087,0.000286105,0.00019767716,0.005463323,0.00025022976,0.0075952355],"category_scores_gemma":[0.9705512,0.0001726443,0.0026612997,0.0033513822,0.00055519096,0.00013985655,0.0010365569,0.00074985507,0.0013830732],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005022435,0.00019351728,0.0009239916,0.21421629,0.00042753754,0.0000411155,0.0031308688,0.000040932096,0.00023929313,0.026900176,0.52684677,0.22653727],"study_design_scores_gemma":[0.0032307236,0.0029495282,0.00094061316,0.078990206,0.0006283224,0.00025546574,0.01659969,0.2425524,0.00008769412,0.09021877,0.5624757,0.0010708958],"about_ca_topic_score_codex":0.000028133543,"about_ca_topic_score_gemma":0.0001451322,"teacher_disagreement_score":0.24676746,"about_ca_system_score_codex":0.00008061958,"about_ca_system_score_gemma":0.0017653609,"threshold_uncertainty_score":0.99991757},"labels":[],"label_agreement":null},{"id":"W3109344025","doi":"10.1186/s12874-020-01159-9","title":"Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saskatchewan Health; University of Saskatchewan","funders":"University of Saskatchewan","keywords":"Autoregressive integrated moving average; Exponential smoothing; Statistics; Mean squared error; Time series; Artificial neural network; Mean absolute percentage error; Moving average; Autoregressive model; Linear regression; Econometrics; Mathematics; Computer science; Artificial intelligence","score_opus":0.3938727386782235,"score_gpt":0.5010691567098738,"score_spread":0.10719641803165036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109344025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55936545,0.00017332926,0.43885148,0.0004987815,0.00020290185,0.0006356787,0.00009277223,0.00003710139,0.00014249413],"genre_scores_gemma":[0.990381,0.00023305502,0.0088291075,0.000074423064,0.00025755176,0.00009029996,0.00009197101,0.000012288469,0.000030314597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9830125,0.013321064,0.0009019982,0.0006117407,0.0015112152,0.0006414849],"domain_scores_gemma":[0.98457026,0.013643199,0.00039626868,0.0002328514,0.0007643203,0.0003931198],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.016610894,0.00019847976,0.0011377976,0.000499478,0.00043234613,0.000058714355,0.0005002513,0.00031625887,0.00019422355],"category_scores_gemma":[0.014848949,0.00017767979,0.00030414452,0.0015031692,0.0038344278,0.000384805,0.0002852356,0.00057688757,5.1168735e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009294597,0.00078143034,0.1059501,0.001084282,0.012272515,0.00008286778,0.22848584,0.5016863,0.006089435,0.11834337,0.0018128307,0.01411643],"study_design_scores_gemma":[0.00046648,0.00033657206,0.018381622,0.000060272352,0.00034677522,3.6995695e-7,0.03087964,0.9443167,0.00039919378,0.0046237363,0.00004434338,0.00014432402],"about_ca_topic_score_codex":0.0035518978,"about_ca_topic_score_gemma":0.0073252744,"teacher_disagreement_score":0.44263038,"about_ca_system_score_codex":0.00007988882,"about_ca_system_score_gemma":0.00044135674,"threshold_uncertainty_score":0.9988766},"labels":[],"label_agreement":null},{"id":"W3110669237","doi":"10.1186/s12874-021-01214-z","title":"National surveillance of stroke quality of care and outcomes by applying post-stratification survey weights on the Get With The Guidelines-Stroke patient registry","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Acute Ischemic Stroke Management","field":"Medicine","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":"Hotchkiss Brain Institute; University of Calgary","funders":"National Center for Advancing Translational Sciences; American Heart Association","keywords":"Medicine; Percentile; Stroke (engine); Emergency medicine; Stratified sampling; Statistics","score_opus":0.36820774751843854,"score_gpt":0.5125776120744674,"score_spread":0.14436986455602885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110669237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95190257,0.0016660444,0.016998922,0.02323975,0.00008621197,0.0009968758,0.0006330482,0.0000136688195,0.0044629164],"genre_scores_gemma":[0.9630915,0.0002728382,0.033607293,0.001215114,0.000072711555,0.00018235734,0.00036260366,0.000019908037,0.001175655],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9847309,0.0105297435,0.0008122185,0.00046584048,0.0031260666,0.00033520508],"domain_scores_gemma":[0.9442225,0.051119335,0.0003572388,0.00076439,0.0033660014,0.00017051566],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026474394,0.00014864907,0.00060173706,0.0000923266,0.00012360122,0.000011018931,0.00034413548,0.0001685415,0.00014288821],"category_scores_gemma":[0.1280275,0.000075312244,0.00008962703,0.00028138416,0.001106889,0.000019989855,0.0002483,0.0006526248,0.0000019553804],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040555205,0.00047975953,0.81975776,0.0015224728,0.0009347306,0.00003510228,0.0018707268,0.0000132821815,0.039553963,0.023479333,0.07508876,0.03320857],"study_design_scores_gemma":[0.0040065274,0.0020190917,0.88898045,0.00039651632,0.0000647799,0.0000627296,0.02985201,0.00046061198,0.05122389,0.00032486336,0.022275541,0.00033300702],"about_ca_topic_score_codex":0.00076392345,"about_ca_topic_score_gemma":0.0013621011,"teacher_disagreement_score":0.10155311,"about_ca_system_score_codex":0.000078649835,"about_ca_system_score_gemma":0.0012684313,"threshold_uncertainty_score":0.917555},"labels":[],"label_agreement":null},{"id":"W3111872407","doi":"10.1186/s12874-021-01234-9","title":"LASSO type penalized spline regression for binary data","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Fonds de Recherche du Québec - Santé","keywords":"Penalty method; Mathematics; Lasso (programming language); Markov chain Monte Carlo; Spline (mechanical); Applied mathematics; Monte Carlo method; Mathematical optimization; Algorithm; Computer science; Statistics","score_opus":0.9356473127376237,"score_gpt":0.7198974010970174,"score_spread":0.2157499116406063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111872407","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006811419,0.00084421143,0.9860267,0.0030850396,0.00063549937,0.00038050406,0.000089998524,0.00005414137,0.0020724917],"genre_scores_gemma":[0.00040301654,0.0005091823,0.99444515,0.00027074813,0.0004978309,0.00005901249,0.0001500292,0.000034224136,0.003630801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9773417,0.018881386,0.00062776724,0.0008121582,0.0015150167,0.00082198007],"domain_scores_gemma":[0.66077816,0.33529454,0.0001147863,0.0017675599,0.0013419746,0.00070294586],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052083045,0.00016062702,0.0007291957,0.00013142855,0.00019327125,0.000030826115,0.0011455666,0.00040824403,0.007128687],"category_scores_gemma":[0.7751465,0.00011226325,0.00007532752,0.00059137016,0.00054339116,0.000050862913,0.0016932818,0.0009016964,0.00007223972],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012100646,0.0004309696,0.00022629397,0.0011088076,0.00007356769,0.00037611212,0.00012449487,2.0439447e-7,0.008227852,0.685239,0.12927839,0.17370422],"study_design_scores_gemma":[0.0015937929,0.00050737476,0.00030525908,0.0003888123,0.00004306336,0.00010112357,0.00028295,0.01944874,0.002801549,0.89616114,0.078165896,0.00020027286],"about_ca_topic_score_codex":0.00003519433,"about_ca_topic_score_gemma":0.00013587244,"teacher_disagreement_score":0.72306347,"about_ca_system_score_codex":0.000042324373,"about_ca_system_score_gemma":0.0022706361,"threshold_uncertainty_score":0.99377894},"labels":[],"label_agreement":null},{"id":"W3112321584","doi":"10.1186/s12874-020-01181-x","title":"Handling coarsened age information in the analysis of emergency department presentations","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Insurance, Mortality, Demography, Risk Management","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":"University of Alberta Hospital; Simon Fraser University; University of Alberta","funders":"Canadian Statistical Sciences Institute; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Alberta Health Services","keywords":"Missing data; Emergency department; Computer science; Statistics; Event (particle physics); Regression analysis; Psychology; Medicine; Medical emergency; Psychiatry; Machine learning; Mathematics","score_opus":0.5513198400258864,"score_gpt":0.5748121554512873,"score_spread":0.023492315425400867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112321584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71149266,0.00038352434,0.24750175,0.016056888,0.0004874268,0.0018179199,0.00002680061,0.000050641076,0.02218241],"genre_scores_gemma":[0.9885331,0.0014931194,0.009098052,0.000466158,0.00014053013,0.0001752122,0.000053046748,0.000003928367,0.000036881014],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9749475,0.02082934,0.000701618,0.00021520874,0.0027956523,0.00051069696],"domain_scores_gemma":[0.9847781,0.014344481,0.0001351212,0.000251602,0.00026117847,0.0002295288],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03773921,0.00007471144,0.0003361464,0.0006137298,0.00029692234,0.000031009273,0.0007984269,0.00013095835,0.000959437],"category_scores_gemma":[0.069382444,0.00005663188,0.00017998359,0.0043762634,0.0006369956,0.0001768659,0.00015807517,0.00039673536,0.000020383908],"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":[0.00026696298,0.00034924614,0.58535504,0.0003042188,0.0009185068,0.000073293246,0.14247754,0.0020336541,0.000047368823,0.19928941,0.01056422,0.05832054],"study_design_scores_gemma":[0.0008041885,0.00015794954,0.84593177,0.000019185743,0.00031892225,2.5326295e-7,0.06378484,0.011176914,0.000040089973,0.009961146,0.067616135,0.0001886361],"about_ca_topic_score_codex":0.006536569,"about_ca_topic_score_gemma":0.05029552,"teacher_disagreement_score":0.27704042,"about_ca_system_score_codex":0.000034372875,"about_ca_system_score_gemma":0.00043200332,"threshold_uncertainty_score":0.9999538},"labels":[],"label_agreement":null},{"id":"W3119569388","doi":"10.1186/s12874-020-01202-9","title":"Impact of time-varying cumulative bevacizumab exposures on survival: re-analysis of data from randomized clinical trial in patients with metastatic colo-rectal cancer","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Colorectal Cancer Treatments and Studies","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":"McGill University","funders":"McGill University","keywords":"Medicine; Bevacizumab; Hazard ratio; Confounding; Proportional hazards model; Colorectal cancer; Internal medicine; Cumulative dose; Randomized controlled trial; Oncology; Cancer; Chemotherapy; Confidence interval","score_opus":0.6734549344032265,"score_gpt":0.6406946490676309,"score_spread":0.03276028533559561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119569388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950357,0.0009904581,0.0013595879,0.00021816118,0.00015583205,0.0013626707,0.00049548637,0.000008319171,0.00037380398],"genre_scores_gemma":[0.9847578,0.00080283894,0.013143815,0.000040330677,0.00011606051,0.00017907884,0.00081975514,0.000024155674,0.000116168994],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9624825,0.032347493,0.0015336582,0.0008208669,0.0023346816,0.00048079665],"domain_scores_gemma":[0.83265895,0.16474609,0.00041296103,0.0008763074,0.0009711275,0.00033453878],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027064614,0.00022919313,0.004394398,0.00057026494,0.000054093067,0.0000072120433,0.00035664273,0.00020094444,0.004122411],"category_scores_gemma":[0.16831157,0.00013306923,0.0005962253,0.001594749,0.0011542146,0.00006043997,0.0004839801,0.0007305364,0.0000036015767],"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":[0.71710867,0.0018683926,0.25303474,0.000045063432,0.015955796,0.00008108957,0.0004268885,0.000067416324,0.00001786491,0.000012277628,0.0001367134,0.0112451],"study_design_scores_gemma":[0.5448541,0.0067992057,0.4376922,0.00025550282,0.004171821,5.23114e-7,0.00023550178,0.0056308964,0.00008244872,0.00014486947,0.000010777274,0.00012212856],"about_ca_topic_score_codex":0.011511457,"about_ca_topic_score_gemma":0.0145804705,"teacher_disagreement_score":0.18465747,"about_ca_system_score_codex":0.00024619958,"about_ca_system_score_gemma":0.0035558427,"threshold_uncertainty_score":0.99678797},"labels":[],"label_agreement":null},{"id":"W3119616871","doi":"10.1186/s12874-020-01198-2","title":"When does the use of individual patient data in network meta-analysis make a difference? A simulation study","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Centre for Advancing Health Outcomes; Impact; University of British Columbia","funders":"","keywords":"Covariate; Percentile; Meta-analysis; Statistics; Standard error; Linear regression; Mean squared error; Meta-regression; Regression analysis; Mathematics; Medicine; Internal medicine","score_opus":0.9493931596982993,"score_gpt":0.6836634658657746,"score_spread":0.26572969383252465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119616871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8628719,0.005224406,0.1183145,0.008007814,0.00078585,0.0040709814,0.00037722645,0.000037114132,0.000310231],"genre_scores_gemma":[0.9376615,0.00013270607,0.057526994,0.001153534,0.00030554272,0.00077662844,0.0003209581,0.000036250578,0.0020858322],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8590892,0.13259485,0.001365034,0.0011264601,0.004553725,0.001270759],"domain_scores_gemma":[0.8360857,0.15967788,0.00021521687,0.0030558116,0.00047943863,0.00048595975],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.070441894,0.0001991836,0.0015104322,0.0005668657,0.00018791719,0.00006171525,0.0020514133,0.00034960106,0.015430491],"category_scores_gemma":[0.102874964,0.00010847815,0.00028638082,0.0025756804,0.0007500718,0.00006993913,0.003560743,0.0019069802,0.000023663017],"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":[0.0025685413,0.007632207,0.44593313,0.00038499502,0.085542046,0.0016352528,0.035786796,0.004338261,0.000013670477,0.008019055,0.005492201,0.40265384],"study_design_scores_gemma":[0.0039064824,0.0026170907,0.83832437,0.00004970474,0.022379432,0.000033128832,0.025954306,0.065257534,0.000027816412,0.018482182,0.022427088,0.0005408826],"about_ca_topic_score_codex":0.0051807375,"about_ca_topic_score_gemma":0.078236036,"teacher_disagreement_score":0.40211296,"about_ca_system_score_codex":0.00007719557,"about_ca_system_score_gemma":0.001190384,"threshold_uncertainty_score":0.9854695},"labels":[],"label_agreement":null},{"id":"W3120269661","doi":"10.1186/s12874-020-01195-5","title":"Informing the research agenda for optimizing audit and feedback interventions: results of a prioritization exercise","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of British Columbia; Ottawa Hospital; Women's College Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; National Institute for Health and Care Research","keywords":"Psychological intervention; Audit; Prioritization; Psychology; Intervention (counseling); Control (management); Applied psychology; Medicine; Medical education; Process management; Computer science; Nursing; Business; Accounting","score_opus":0.9680407047097342,"score_gpt":0.81259401995496,"score_spread":0.1554466847547743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120269661","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.091485724,0.0026466083,0.7212646,0.16701284,0.0017383686,0.00871316,0.00026905976,0.000087934735,0.006781678],"genre_scores_gemma":[0.046474222,0.008675881,0.9232217,0.0050011217,0.0012365914,0.004127841,0.00009598777,0.00006755486,0.011099108],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94609934,0.047494337,0.0019458632,0.00053457083,0.0024060684,0.0015197991],"domain_scores_gemma":[0.5581664,0.43516684,0.00042452372,0.00077973295,0.004750862,0.0007116405],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22408794,0.00009652717,0.00043504688,0.0005292295,0.0017934641,0.000025300085,0.00059878355,0.00031877347,0.00071003777],"category_scores_gemma":[0.6685984,0.00007101692,0.00009213038,0.0017084708,0.0012700959,0.0001668379,0.001098217,0.0016877452,0.000041586183],"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":[0.0026648315,0.00020527208,0.0031950793,0.021148672,0.00007511295,0.00003849022,0.10414629,0.000023506562,0.0031306562,0.074774995,0.27427962,0.5163175],"study_design_scores_gemma":[0.016613591,0.0015671245,0.0210996,0.015895803,0.000058993086,0.000069236405,0.29475543,0.010539008,0.004792328,0.053714003,0.5804075,0.00048736014],"about_ca_topic_score_codex":0.00072404835,"about_ca_topic_score_gemma":0.00310388,"teacher_disagreement_score":0.5158301,"about_ca_system_score_codex":0.0002182262,"about_ca_system_score_gemma":0.010461745,"threshold_uncertainty_score":0.99950606},"labels":[],"label_agreement":null},{"id":"W3121025618","doi":"10.1186/s12874-021-01317-7","title":"Validity of using mobile phone surveys to evaluate community health worker program in Mali","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Mobile Health and mHealth Applications","field":"Health Professions","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":"Canadian Red Cross Society","funders":"Global Affairs Canada","keywords":"Mobile phone; Phone; Computer science; Environmental health; Data science; Applied psychology; Psychology; Medicine; Telecommunications","score_opus":0.8362476739854771,"score_gpt":0.724453004774358,"score_spread":0.11179466921111902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121025618","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":[0.8624479,0.0012170809,0.119813375,0.0050649364,0.0007248047,0.009128001,0.000055420867,0.00009810049,0.0014503888],"genre_scores_gemma":[0.40890384,0.003931469,0.5511881,0.0050707194,0.00059956627,0.029089449,0.000195493,0.00010559127,0.00091576256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6376496,0.35432947,0.0024774855,0.0007250791,0.002160121,0.0026582424],"domain_scores_gemma":[0.88943326,0.104430646,0.0003726934,0.0014715097,0.0016697092,0.0026221501],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29144466,0.00019565473,0.0012226382,0.00051306887,0.0012448033,0.000005660518,0.0007003682,0.0006672962,0.004198659],"category_scores_gemma":[0.124539845,0.00018066358,0.00009940125,0.0023975112,0.000529853,0.000043271237,0.0010221675,0.0052489117,0.00021347897],"study_design_candidate":"observational","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":[0.00046506964,0.0020785828,0.29263428,0.0052735996,0.000019993062,0.000025593417,0.0027941007,0.00010582272,0.00047246736,0.0037274882,0.006027915,0.6863751],"study_design_scores_gemma":[0.007352825,0.002572311,0.774742,0.0037958154,0.000024364594,0.00003969273,0.019017363,0.0057497034,0.00047684548,0.015690867,0.16997688,0.0005613223],"about_ca_topic_score_codex":0.031569976,"about_ca_topic_score_gemma":0.10626719,"teacher_disagreement_score":0.6858138,"about_ca_system_score_codex":0.0006919364,"about_ca_system_score_gemma":0.023555838,"threshold_uncertainty_score":0.997046},"labels":[],"label_agreement":null},{"id":"W3121736026","doi":"10.1186/s12874-021-01269-y","title":"Managing overlap of primary study results across systematic reviews: practical considerations for authors of overviews of reviews","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":254,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montfort Hospital; Cochrane; Ottawa Hospital; University of British Columbia","funders":"","keywords":"Computer science; Data extraction; Usability; Systematic review; Data science; Information retrieval; Data mining; Resource (disambiguation); MEDLINE; Biology","score_opus":0.9844134215215561,"score_gpt":0.7615619304483037,"score_spread":0.22285149107325242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121736026","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":[0.014564506,0.120889075,0.8305911,0.0045741834,0.0010410311,0.024080174,0.00017718149,0.000008777578,0.0040740175],"genre_scores_gemma":[0.026906926,0.015088288,0.9491822,0.0004829457,0.0002234332,0.0020905323,0.000030051582,0.00004444695,0.0059511834],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.18509778,0.7381988,0.05216662,0.0025861904,0.020769771,0.0011807968],"domain_scores_gemma":[0.08179337,0.8765656,0.019373748,0.009625222,0.011810656,0.0008314144],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8596493,0.00036870973,0.01653252,0.0006103158,0.00020690965,0.00013036552,0.0016323201,0.00033810706,0.0034174647],"category_scores_gemma":[0.9803037,0.00018543188,0.003089384,0.0030781582,0.0007863953,0.00020027644,0.0009940596,0.0007605164,0.00016590506],"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":[0.0010385117,0.005299697,0.007354485,0.43856767,0.002813823,0.0002660565,0.025873523,0.0000524461,0.004042008,0.07921266,0.3514602,0.08401892],"study_design_scores_gemma":[0.01477064,0.0065215454,0.013055802,0.08185232,0.007149188,0.0011779875,0.11653515,0.021915717,0.0040314137,0.31931752,0.411468,0.0022047071],"about_ca_topic_score_codex":0.00005698229,"about_ca_topic_score_gemma":0.0006480095,"teacher_disagreement_score":0.35671535,"about_ca_system_score_codex":0.000074468466,"about_ca_system_score_gemma":0.0021756694,"threshold_uncertainty_score":0.9980681},"labels":[],"label_agreement":null},{"id":"W3127746826","doi":"10.1186/s12874-020-01200-x","title":"The unintended consequences of COVID-19 mitigation measures matter: practical guidance for investigating them","year":2021,"lang":"en","type":"letter","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":59,"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; Université du Québec à Montréal","funders":"Institute of Population and Public Health; Canadian Institutes of Health Research; International Development Research Centre","keywords":"Unintended consequences; Psychological intervention; Scope (computer science); Intervention (counseling); Resource (disambiguation); Reflexivity; Psychology; Public relations; Management science; Computer science; Political science; Sociology; Engineering","score_opus":0.9664399748970323,"score_gpt":0.795021087372044,"score_spread":0.17141888752498824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127746826","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":[0.0002544204,0.00016497105,0.16187592,0.8332705,0.0009915417,0.0022099102,0.00014775472,0.0000389714,0.001046026],"genre_scores_gemma":[0.00022745554,0.00033364267,0.1867923,0.80428725,0.002624315,0.0028709327,0.000088578236,0.000048945025,0.0027265758],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7841647,0.20454913,0.002890732,0.00097613124,0.0049332273,0.0024860348],"domain_scores_gemma":[0.3903018,0.60320234,0.0013499126,0.00088754366,0.003109125,0.0011492927],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","research_integrity"],"category_scores_codex":[0.21869706,0.00030137997,0.0010990576,0.00032964934,0.0026790695,0.000046941594,0.0016355852,0.001878658,0.003742631],"category_scores_gemma":[0.9110852,0.00020496173,0.0001856206,0.0010380977,0.013126181,0.00011322325,0.0006989036,0.008028612,0.00019053435],"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":[0.0000757245,0.000006747069,0.0019750893,0.0037544286,0.00003895675,0.00003844672,0.0031606867,4.2557392e-7,0.00044995974,0.014712025,0.97479415,0.0009933871],"study_design_scores_gemma":[0.00077096076,0.00011713188,0.00018222073,0.0007054755,0.00002093109,0.00006397963,0.010606154,0.00010719243,0.00041149984,0.0751861,0.9116602,0.00016813925],"about_ca_topic_score_codex":0.0022217045,"about_ca_topic_score_gemma":0.0032617396,"teacher_disagreement_score":0.6923881,"about_ca_system_score_codex":0.0007736536,"about_ca_system_score_gemma":0.091992125,"threshold_uncertainty_score":0.9994171},"labels":[],"label_agreement":null},{"id":"W3132408111","doi":"10.1186/s12874-021-01228-7","title":"Using a distribution-based approach and systematic review methods to derive minimum clinically important differences","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":156,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; University of Toronto; St. Michael's Hospital","funders":"European Commission","keywords":"Minimal clinically important difference; Medicine; Meta-analysis; Randomized controlled trial; Internal medicine","score_opus":0.5436773323167089,"score_gpt":0.616288516678449,"score_spread":0.07261118436174008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132408111","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024700541,0.021344295,0.9473735,0.0034392707,0.00010216263,0.0025372216,0.000019031702,0.000034340203,0.00044960747],"genre_scores_gemma":[0.028109556,0.007651644,0.95740914,0.0048129046,0.00019003508,0.0009848195,0.00015245941,0.000040045485,0.0006493735],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9509325,0.042465188,0.0017108229,0.0009893673,0.0027908548,0.0011112731],"domain_scores_gemma":[0.93763226,0.057103045,0.0002264825,0.0008337128,0.0019880552,0.0022164504],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0819428,0.00024797456,0.0019445188,0.00023767796,0.00021743805,0.000053323813,0.000358171,0.00031613096,0.0009894824],"category_scores_gemma":[0.4124444,0.00017215117,0.0002526718,0.0012732188,0.00086297083,0.00003734938,0.0005702098,0.0011366772,0.000021484766],"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":[0.0019045395,0.002748387,0.11545603,0.8379571,0.0010759158,0.002453792,0.00037233555,8.109419e-7,0.0116034625,0.0034795527,0.0022302282,0.020717887],"study_design_scores_gemma":[0.021482712,0.01643922,0.12355839,0.60549915,0.008097881,0.008052475,0.015032578,0.16781005,0.018989893,0.008694695,0.0032072673,0.0031357089],"about_ca_topic_score_codex":0.00005708368,"about_ca_topic_score_gemma":0.000022712622,"teacher_disagreement_score":0.33050162,"about_ca_system_score_codex":0.00012848538,"about_ca_system_score_gemma":0.0049384595,"threshold_uncertainty_score":0.99992377},"labels":[],"label_agreement":null},{"id":"W3135317005","doi":"10.1186/s12874-021-01436-1","title":"Methods to support evidence-informed decision-making in the midst of COVID-19: creation and evolution of a rapid review service from the National Collaborating Centre for Methods and Tools","year":2021,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":46,"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; Dalhousie University; McMaster University","funders":"Public Health Agency; Public Health Agency of Canada; Johns Hopkins University","keywords":"Service (business); Evidence-based medicine; Evidence-based practice; Public health; Coronavirus disease 2019 (COVID-19); MEDLINE; Process (computing); Public relations; Medicine; Computer science; Psychology; Political science; Business; Alternative medicine; Nursing; Marketing","score_opus":0.9670685359049925,"score_gpt":0.7843943544149949,"score_spread":0.1826741814899976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135317005","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":[0.0000070031524,0.55356574,0.43971795,0.0031642092,0.00008543207,0.0032857684,0.00008662189,0.000001279534,0.0000859994],"genre_scores_gemma":[0.0000023164635,0.5043842,0.49389806,0.0010847412,0.000082727296,0.00047683637,0.000028316423,0.000009727682,0.00003305085],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.20320898,0.75291276,0.022265028,0.002621006,0.018075109,0.0009171151],"domain_scores_gemma":[0.0154211875,0.9682119,0.00595037,0.0023431312,0.0075580217,0.0005154043],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8296812,0.0004412938,0.010193207,0.0009649518,0.00028867868,0.0003828779,0.0035393424,0.0005641663,0.0039974456],"category_scores_gemma":[0.9849081,0.00018088598,0.0013028231,0.008328541,0.000501946,0.0002587858,0.0010755796,0.00084852276,0.000013665212],"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":[0.00003458151,0.000022135218,0.000075013486,0.02227401,0.00017065296,0.0000020168068,0.0011440341,0.0000032119515,0.0000026856146,0.002898465,0.014969059,0.9584041],"study_design_scores_gemma":[0.0002124448,0.00014704044,0.00015274464,0.050405234,0.0008697138,0.00005460138,0.0048866393,0.001322428,0.00000115026,0.01301717,0.9287542,0.00017665084],"about_ca_topic_score_codex":0.00017682249,"about_ca_topic_score_gemma":0.0016208483,"teacher_disagreement_score":0.95822746,"about_ca_system_score_codex":0.0003212791,"about_ca_system_score_gemma":0.013978981,"threshold_uncertainty_score":0.996913},"labels":[],"label_agreement":null},{"id":"W3137754773","doi":"10.1186/s12874-021-01242-9","title":"Waist circumference prediction for epidemiological research using gradient boosted trees","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Physical Activity and Health","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":"Canada Research Chairs; University of New Brunswick; University of Toronto","funders":"Carolina Population Center, University of North Carolina at Chapel Hill; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Diabetes and Digestive and Kidney Diseases; Fogarty International Center; China-Japan Friendship Hospital; University of North Carolina at Chapel Hill; National Institutes of Health","keywords":"Waist; Circumference; Gradient boosting; Body mass index; Statistics; Linear regression; Mean squared error; Regression analysis; Predictive modelling; Regression; Decision tree; Medicine; Linear model; Mathematics; Demography; Artificial intelligence; Machine learning; Computer science; Random forest; Internal medicine","score_opus":0.934710567356231,"score_gpt":0.687416148352609,"score_spread":0.24729441900362203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137754773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6391985,0.0011321453,0.3418073,0.0140904635,0.00045546418,0.0013082518,0.000044377266,0.00009831472,0.0018651776],"genre_scores_gemma":[0.8275908,0.0015440318,0.16494447,0.0011088119,0.0028451022,0.00050235953,0.00017778816,0.000052967724,0.0012336163],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9635244,0.030318119,0.00074307126,0.0010448958,0.002545076,0.0018244175],"domain_scores_gemma":[0.85507494,0.14038734,0.000084188,0.0007143119,0.0019725782,0.0017666445],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06631733,0.00019168272,0.0012480723,0.0004109494,0.0006784354,0.000024344416,0.00035679186,0.0007494841,0.00079268886],"category_scores_gemma":[0.38022348,0.000144569,0.00026844317,0.0012666344,0.0019323234,0.00008408347,0.000455334,0.0031483448,0.000048308786],"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":[0.014215689,0.011359868,0.05584132,0.006405942,0.0005540492,0.001791149,0.0018056867,0.000057431072,0.30532214,0.2535904,0.03665856,0.31239775],"study_design_scores_gemma":[0.013141309,0.018629035,0.23106393,0.0030126823,0.00022970083,0.0024073552,0.004426778,0.15674165,0.03477362,0.43709436,0.097638324,0.0008412773],"about_ca_topic_score_codex":0.000449677,"about_ca_topic_score_gemma":0.0006878828,"teacher_disagreement_score":0.31390616,"about_ca_system_score_codex":0.00050147396,"about_ca_system_score_gemma":0.0058745407,"threshold_uncertainty_score":0.9997612},"labels":[],"label_agreement":null},{"id":"W3144019913","doi":"10.1186/s12874-021-01254-5","title":"Comparing the use of aggregate data and various methods of integrating individual patient data to network meta-analysis and its application to first-line ART","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Centre for Advancing Health Outcomes; Impact; University of British Columbia","funders":"Canadian Institutes of Health Research; GlaxoSmithKline","keywords":"Meta-analysis; Random effects model; Multilevel model; Meta-regression; Aggregate data; Regression analysis; Statistics; Regression; Econometrics; Medicine; Mathematics; Internal medicine","score_opus":0.9871596714246437,"score_gpt":0.7170550535319948,"score_spread":0.27010461789264884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3144019913","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":[0.020142684,0.006371509,0.968415,0.0038190999,0.00005611875,0.00095646025,0.00018682552,0.0000024097535,0.000049867296],"genre_scores_gemma":[0.05075158,0.00029529425,0.9477823,0.0005368806,0.000063315405,0.00010205514,0.00019346303,0.000010881873,0.0002642671],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.6927608,0.28032207,0.010849062,0.0031766247,0.012104411,0.0007869904],"domain_scores_gemma":[0.25953048,0.70820075,0.0047870064,0.020651156,0.005372581,0.0014580507],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58052075,0.00023771105,0.0060758055,0.0006479842,0.0002193872,0.00029311623,0.0050906017,0.00015939685,0.0017328938],"category_scores_gemma":[0.7648921,0.00010622977,0.00057446794,0.006642629,0.00030548286,0.00019318004,0.010475573,0.00056152616,0.0000346144],"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":[0.00019638703,0.00030107098,0.029149828,0.00054255524,0.07237354,0.000025578125,0.004666792,0.009484367,0.0010711122,0.00812208,0.05161017,0.82245654],"study_design_scores_gemma":[0.00021242043,0.00018926126,0.0057053836,0.000060029906,0.031776946,0.000034888093,0.0012433472,0.8020373,0.00039546267,0.0037231552,0.15439804,0.00022377449],"about_ca_topic_score_codex":0.0002660203,"about_ca_topic_score_gemma":0.0102263,"teacher_disagreement_score":0.8222327,"about_ca_system_score_codex":0.000012320336,"about_ca_system_score_gemma":0.0003633741,"threshold_uncertainty_score":0.99917966},"labels":[],"label_agreement":null},{"id":"W3153887738","doi":"10.1186/s12874-021-01401-y","title":"Prevalence of evidence of inconsistency and its association with network structural characteristics in 201 published networks of interventions","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"Medical Research Council; Deutsche Forschungsgemeinschaft; European Commission; Canadian Institutes of Health Research; National Institute for Health and Care Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Consistency (knowledge bases); Statistics; Meta-analysis; Psychological intervention; Statistic; Medicine; Reliability (semiconductor); Random effects model; Econometrics; Computer science; Mathematics; Power (physics); Psychiatry; Internal medicine; Artificial intelligence","score_opus":0.692155203311666,"score_gpt":0.6244239738788419,"score_spread":0.06773122943282417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153887738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9753346,0.012215619,0.009589377,0.0013252939,0.0004955315,0.00063521776,0.000022552727,0.000007025569,0.00037477756],"genre_scores_gemma":[0.9811345,0.0024744137,0.014959972,0.00003461718,0.0001370244,0.00007065154,0.000009992051,0.000012109495,0.0011667191],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9711641,0.024743836,0.001314007,0.0004448214,0.001564124,0.00076910225],"domain_scores_gemma":[0.9507061,0.046723668,0.0005204567,0.0004183144,0.0013201346,0.0003112989],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03951528,0.0001051716,0.0007031074,0.00025623242,0.000050439532,0.000008669713,0.00043649122,0.0003946734,0.0032937927],"category_scores_gemma":[0.12889531,0.000081087695,0.0000758789,0.00096016296,0.0005724668,0.00012191238,0.00047316612,0.0011974296,0.0000021033322],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010292123,0.00020190753,0.9577201,0.007514667,0.00008390707,0.00005301315,0.0005869951,0.000012106251,0.0002428193,0.010986208,0.00036445918,0.02120459],"study_design_scores_gemma":[0.0008693377,0.0009980666,0.9903734,0.0033078033,0.000022218528,0.00003340825,0.0003608008,0.0019874575,0.00024374349,0.0017061502,0.00002408106,0.000073553994],"about_ca_topic_score_codex":0.0003945024,"about_ca_topic_score_gemma":0.0014426725,"teacher_disagreement_score":0.08938004,"about_ca_system_score_codex":0.00013073473,"about_ca_system_score_gemma":0.0012795762,"threshold_uncertainty_score":0.9976173},"labels":[],"label_agreement":null},{"id":"W3154092642","doi":"10.1186/s12874-021-01258-1","title":"Guidelines are needed for studies of pre-treatment HIV drug resistance: a methodological study","year":2021,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"HIV/AIDS Research and Interventions","field":"Medicine","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; Population Health Research Institute; McMaster University; Ontario HIV Treatment Network; Hamilton Health Sciences; St. Joseph’s Healthcare Hamilton; Impact","funders":"World Health Organization","keywords":"Generalizability theory; Medicine; Quartile; Family medicine; Transgender; MEDLINE; Demography; Psychology; Internal medicine; Confidence interval","score_opus":0.9127431928931639,"score_gpt":0.7338483980888297,"score_spread":0.17889479480433412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154092642","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":[0.000060673403,0.9520792,0.035381287,0.0037905886,0.00025317143,0.0078564575,0.00020043225,0.00006803088,0.00031016322],"genre_scores_gemma":[4.8839934e-7,0.7160019,0.1843519,0.00005497491,0.00081697013,0.005379922,0.00020093998,0.000082479084,0.09311036],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9046198,0.0842791,0.0037475459,0.0017992746,0.0038270561,0.0017271955],"domain_scores_gemma":[0.71782285,0.268893,0.0010316519,0.0024088072,0.007999494,0.0018442109],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0945597,0.0007987994,0.010697294,0.0015134047,0.00034894623,0.000036778136,0.001185636,0.0010643365,0.0015834878],"category_scores_gemma":[0.66751117,0.00047886348,0.0030310312,0.0018598008,0.0020168896,0.000052211642,0.0012272013,0.0022015783,0.000040669427],"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":[0.0011513997,0.0023715892,0.000035906487,0.05423606,0.0040269084,0.0005557458,0.00066580466,1.4417256e-7,0.0000042471147,0.000632239,0.33987552,0.5964444],"study_design_scores_gemma":[0.0028805418,0.005675736,0.000006522809,0.043089792,0.0018412818,0.0001308404,0.014786878,0.0000371496,0.000031759166,0.00063326495,0.9305761,0.0003101189],"about_ca_topic_score_codex":0.00023600012,"about_ca_topic_score_gemma":0.0033218798,"teacher_disagreement_score":0.5961343,"about_ca_system_score_codex":0.0007471567,"about_ca_system_score_gemma":0.008457183,"threshold_uncertainty_score":0.9997663},"labels":[],"label_agreement":null},{"id":"W3154127147","doi":"10.1186/s12874-021-01260-7","title":"Intention-to-treat analysis may be more conservative than per protocol analysis in antibiotic non-inferiority trials: a systematic review","year":2021,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","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 Health Network; University of Toronto; McMaster University; Mount Sinai Hospital; Juravinski Cancer Centre","funders":"","keywords":"Medicine; Intention-to-treat analysis; Relative risk; Confidence interval; Meta-analysis; Protocol (science); Randomized controlled trial; Subgroup analysis; Psychological intervention; Clinical endpoint; Internal medicine; Surgery; Alternative medicine; Psychiatry","score_opus":0.9728313334913404,"score_gpt":0.7741893391801877,"score_spread":0.1986419943111527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154127147","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":[0.0000051001703,0.7131434,0.13509636,0.0012637776,0.00013765466,0.14980195,0.00011839382,0.000011305073,0.0004220726],"genre_scores_gemma":[0.0000033523013,0.82331747,0.032677606,0.0007502102,0.00014084998,0.13421722,0.00028355874,0.000066497145,0.008543206],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.27182847,0.6525098,0.044493612,0.0048766495,0.024687722,0.0016037598],"domain_scores_gemma":[0.1095127,0.825893,0.026145112,0.020898687,0.014166605,0.0033839205],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","bibliometrics","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","bibliometrics","research_integrity","insufficient_payload"],"category_scores_codex":[0.8868218,0.0017441676,0.121109135,0.015586799,0.00033902854,0.0012136551,0.009841378,0.001757902,0.044290084],"category_scores_gemma":[0.9587519,0.00078872324,0.037165575,0.072139785,0.0010008715,0.0002180009,0.0024194245,0.0034850454,0.002725346],"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":[0.000035354456,0.00035789167,0.0027991415,0.9173063,0.026578277,0.00033458768,0.0003592387,0.0000049187815,3.0158097e-7,0.00033712192,0.011082188,0.04080465],"study_design_scores_gemma":[0.0007367542,0.00024869977,0.0005388528,0.5323799,0.19967823,0.00010915721,0.002213421,0.0025136534,8.184283e-7,0.00023628195,0.26002297,0.0013212333],"about_ca_topic_score_codex":0.0010341174,"about_ca_topic_score_gemma":0.0054808646,"teacher_disagreement_score":0.3849264,"about_ca_system_score_codex":0.00073330157,"about_ca_system_score_gemma":0.008704773,"threshold_uncertainty_score":0.99982315},"labels":[],"label_agreement":null},{"id":"W3155520879","doi":"10.1186/s12874-021-01276-z","title":"Growth mixture models: a case example of the longitudinal analysis of patient‐reported outcomes data captured by a clinical registry","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Providence Health Care Research Institute; Providence Health Care; St. Paul's Hospital; Trinity Western University; University of British Columbia; Western University","funders":"School of Nursing, University of British Columbia; Canadian Institutes of Health Research; University of British Columbia; Canadian Nurses Foundation","keywords":"Metric (unit); Population; Identification (biology); Computer science; Outcome (game theory); Longitudinal study; Econometrics; Statistics; Medicine; Mathematics","score_opus":0.7970365415584607,"score_gpt":0.6160857039973919,"score_spread":0.18095083756106878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155520879","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07281305,0.00036331094,0.924857,0.00068324554,0.00018341749,0.00024152808,0.00058231206,0.00001243263,0.00026365943],"genre_scores_gemma":[0.12698363,0.00011704691,0.8725042,0.00010421373,0.000050813214,0.000025023692,0.00008479233,0.000020537518,0.000109763234],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9631324,0.031169169,0.0019380285,0.00093222543,0.0022454183,0.0005828044],"domain_scores_gemma":[0.777188,0.21694866,0.00069223624,0.0031838077,0.0014628351,0.00052448333],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03524785,0.00020445653,0.0017703185,0.00020639882,0.00011550945,0.000016844724,0.0013360758,0.00057606946,0.0009401663],"category_scores_gemma":[0.58476156,0.00012532204,0.00041417262,0.0020493863,0.0018492893,0.00006088209,0.0017708046,0.0013808327,7.4071045e-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":[0.00071734627,0.0029057919,0.2666481,0.0017471769,0.007434353,0.0064808372,0.0013551662,0.000005787932,0.00057506026,0.632089,0.032353427,0.04768794],"study_design_scores_gemma":[0.0014124869,0.00028109908,0.016674068,0.00021417232,0.002523266,0.0010263926,0.0015299106,0.027690541,0.0014356932,0.94654244,0.00035080125,0.00031911972],"about_ca_topic_score_codex":0.003171719,"about_ca_topic_score_gemma":0.0032045264,"teacher_disagreement_score":0.5495137,"about_ca_system_score_codex":0.00003148565,"about_ca_system_score_gemma":0.0018048708,"threshold_uncertainty_score":0.9999731},"labels":[],"label_agreement":null},{"id":"W3157785707","doi":"10.1186/s12874-021-01306-w","title":"Comparison of six statistical methods for interrupted time series studies: empirical evaluation of 190 published series","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Medical Research Council; Canadian Institutes of Health Research; Monash University","keywords":"Statistics; Series (stratigraphy); Confidence interval; Autocorrelation; Pairwise comparison; Statistical significance; Sample size determination; Point estimation; Statistical hypothesis testing; Mathematics; Computer science; Econometrics","score_opus":0.9326180323716993,"score_gpt":0.7848555400066978,"score_spread":0.1477624923650015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157785707","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009407206,0.0010164756,0.98614556,0.001602622,0.00018793046,0.0008941239,0.000042047366,0.00008873657,0.0006153174],"genre_scores_gemma":[0.008021544,0.00012485858,0.9907952,0.000038658727,0.00009199267,0.00049610756,0.000061918414,0.000036617155,0.00033312896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9433912,0.050329223,0.0019614007,0.0007085279,0.0028312155,0.00077840843],"domain_scores_gemma":[0.72983086,0.2601709,0.00045202306,0.0008463223,0.008353094,0.00034681903],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10038468,0.0002281455,0.0018937878,0.00033683877,0.00010065618,0.000019779918,0.00057558174,0.000495734,0.002912541],"category_scores_gemma":[0.81620026,0.00018530949,0.00015895528,0.00078686763,0.0024717222,0.00024521726,0.0007530133,0.0008640803,0.000004528746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028333322,0.001503358,0.0020500075,0.0051970966,0.00089775596,0.000018822659,0.007609781,0.000015787624,0.050759867,0.60593766,0.045629073,0.27754748],"study_design_scores_gemma":[0.0007372991,0.0012424567,0.00015725875,0.00025626004,0.00013572439,0.000026187734,0.0052960766,0.007481461,0.16348195,0.81941926,0.0016157274,0.00015033345],"about_ca_topic_score_codex":0.000014371395,"about_ca_topic_score_gemma":0.00024371417,"teacher_disagreement_score":0.7158156,"about_ca_system_score_codex":0.0002149571,"about_ca_system_score_gemma":0.0028380037,"threshold_uncertainty_score":0.99799895},"labels":[],"label_agreement":null},{"id":"W3163221394","doi":"10.1186/s12874-021-01289-8","title":"Using random forests to model 90-day hometime in people with stroke","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Acute Ischemic Stroke Management","field":"Medicine","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":"University Health Network; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; University of Calgary","funders":"Canadian Institutes of Health Research; Government of Ontario; Heart and Stroke Foundation of Canada","keywords":"Covariate; Random forest; Statistic; Statistics; Random effects model; Linear regression; Stroke (engine); Regression analysis; Multilevel model; Regression; Medicine; Mathematics; Computer science; Machine learning; Internal medicine","score_opus":0.4412801546265416,"score_gpt":0.5318426152045134,"score_spread":0.09056246057797179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163221394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3786093,0.00027154616,0.61258703,0.0035149835,0.00007663952,0.00063273596,0.000004895137,0.000027591057,0.004275282],"genre_scores_gemma":[0.1904241,0.00015668725,0.7993259,0.0015709476,0.0003718992,0.00023551818,0.00002812987,0.00006912678,0.00781771],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98860514,0.0059047937,0.00056051346,0.0008399829,0.0028251568,0.0012644248],"domain_scores_gemma":[0.9819959,0.015473609,0.000058123485,0.0008338732,0.0005082779,0.0011302156],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023421962,0.0002181813,0.001044623,0.000790449,0.00008108624,0.00002116591,0.00040048515,0.00032899072,0.0011937359],"category_scores_gemma":[0.08363491,0.00016806653,0.00011665131,0.0014061265,0.0003487885,0.000053648575,0.00087377557,0.0012996892,0.000066213426],"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":[0.031169923,0.0026229369,0.5929316,0.003124258,0.0014011814,0.015968187,0.0074721067,0.024538364,0.11930162,0.00513981,0.09494257,0.10138744],"study_design_scores_gemma":[0.035717703,0.0016771657,0.061789792,0.0016490504,0.00028771296,0.0012951329,0.0040104254,0.8535635,0.023671394,0.0010241026,0.014505052,0.0008089628],"about_ca_topic_score_codex":0.0003792954,"about_ca_topic_score_gemma":0.005974404,"teacher_disagreement_score":0.82902515,"about_ca_system_score_codex":0.00034601826,"about_ca_system_score_gemma":0.003382866,"threshold_uncertainty_score":0.9997193},"labels":[],"label_agreement":null},{"id":"W3163596589","doi":"10.1186/s12874-021-01296-9","title":"A population‐based study to develop juvenile arthritis case definitions for administrative health data using model‐based dynamic classification","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; CancerCare Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Medical diagnosis; Population; Health care; Cohort; Cohort study; Statistics; Family medicine; Data mining; Computer science; Mathematics; Environmental health; Internal medicine","score_opus":0.8236829765893262,"score_gpt":0.62476912098243,"score_spread":0.19891385560689623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163596589","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":[0.2439207,0.001205479,0.7433226,0.008818217,0.00008197132,0.0020990565,0.00045955207,0.000053888947,0.00003851601],"genre_scores_gemma":[0.5190778,0.00031584347,0.47810778,0.00061509287,0.000049636317,0.00040541714,0.0013607834,0.000032823966,0.000034843684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98454374,0.010636887,0.0009528334,0.0010380329,0.0017838951,0.0010446326],"domain_scores_gemma":[0.97653216,0.0185508,0.00012798762,0.0013046785,0.0019952501,0.0014891461],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02281003,0.00020932873,0.0008751932,0.000596909,0.00080483383,0.000072341114,0.0004105065,0.00018309808,0.00045509738],"category_scores_gemma":[0.13823226,0.00020100924,0.000086370615,0.0015494495,0.00027113044,0.00011882769,0.00032004766,0.0007945689,0.000019440064],"study_design_candidate":"simulation_or_modeling","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":[0.012425334,0.01931362,0.032322094,0.0030525974,0.0009645272,0.01659973,0.00763055,0.0032070566,0.006987837,0.030085608,0.010581943,0.8568291],"study_design_scores_gemma":[0.008417478,0.0030152171,0.0063471855,0.0008748363,0.0000165842,0.00176897,0.009534414,0.9644498,0.00024754414,0.0038493506,0.0011610073,0.00031760024],"about_ca_topic_score_codex":0.000888762,"about_ca_topic_score_gemma":0.040387478,"teacher_disagreement_score":0.96124274,"about_ca_system_score_codex":0.00039599187,"about_ca_system_score_gemma":0.027919276,"threshold_uncertainty_score":0.9775915},"labels":[],"label_agreement":null},{"id":"W3163788934","doi":"10.1186/s12874-021-01295-w","title":"Quality assessment tools used in systematic reviews of in vitro studies: A systematic review","year":2021,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":126,"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":"Al-Azhar University; Zagazig University; McMaster University","keywords":"Systematic review; Medical physics; Protocol (science); Guideline; Scopus; Quality assessment; Medicine; Computer science; MEDLINE; Pathology; External quality assessment; Alternative medicine; Biology","score_opus":0.9945041192763169,"score_gpt":0.8198052753117314,"score_spread":0.17469884396458546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163788934","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":[0.000002628009,0.95138794,0.015179634,0.00025129673,0.00045934337,0.032209642,0.000032572967,0.000005706168,0.000471251],"genre_scores_gemma":[0.000001815443,0.947226,0.035698086,0.00023419125,0.000089087116,0.015213303,0.000051169685,0.000055516004,0.0014308146],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.021803804,0.845766,0.09581819,0.0035196648,0.031603508,0.0014888234],"domain_scores_gemma":[0.024821851,0.9162979,0.035824,0.016420325,0.0056327987,0.0010031105],"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":[0.9613585,0.0014289073,0.16688412,0.0040598945,0.00011060417,0.000367389,0.010656685,0.0013205624,0.006820119],"category_scores_gemma":[0.988098,0.00061345473,0.013921045,0.015254443,0.0007777135,0.00023152902,0.002333131,0.003926601,0.0014525205],"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":[0.0000036713425,0.00018421133,0.00001551367,0.9400328,0.000779301,0.00013133153,0.0002087565,1.82326e-7,6.114476e-7,0.0015269826,0.0022518027,0.05486484],"study_design_scores_gemma":[0.00025365214,0.0000563287,0.0000033698857,0.9377954,0.0024317298,0.000102680926,0.0017284206,0.00007081704,2.547394e-7,0.0008316234,0.056312937,0.0004127887],"about_ca_topic_score_codex":0.00008380972,"about_ca_topic_score_gemma":0.0008124691,"teacher_disagreement_score":0.15296309,"about_ca_system_score_codex":0.001177859,"about_ca_system_score_gemma":0.007898412,"threshold_uncertainty_score":0.9999759},"labels":[{"model":"gemma","categories":["metaresearch","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_broad"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3164676482","doi":"10.1186/s12874-021-01354-2","title":"Creating efficiencies in the extraction of data from randomized trials: a prospective evaluation of a machine learning and text mining tool","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta; Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"Data extraction; Interquartile range; Computer science; Upload; Artificial intelligence; Randomized controlled trial; Machine learning; Data mining; Calibration; Medicine; MEDLINE; Statistics; Mathematics; Surgery","score_opus":0.9809497216382548,"score_gpt":0.7599686211737876,"score_spread":0.22098110046446717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164676482","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":[0.65577346,0.010958838,0.32945874,0.00050958165,0.00007502322,0.0014845792,0.000014970466,0.0000014164011,0.001723398],"genre_scores_gemma":[0.8115503,0.00037962798,0.1875481,0.000021115953,0.00008747847,0.00014668,0.000023227665,0.0000052799596,0.0002381521],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.052353863,0.9162698,0.010674816,0.0012231476,0.019149695,0.00032870332],"domain_scores_gemma":[0.014252328,0.9765326,0.0037363763,0.0019621865,0.003421483,0.0000950711],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.94848156,0.00012762583,0.005377796,0.00047323626,0.00012765237,0.00014380307,0.0014124664,0.00015075925,0.009726345],"category_scores_gemma":[0.99222606,0.00005255221,0.00049423764,0.0019166982,0.00061723596,0.00015812126,0.00056040357,0.0005989382,0.000014178988],"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":[0.008951645,0.0003980829,0.06280202,0.0003164171,0.00077230204,0.000025350815,0.02557937,0.00032563772,0.009833566,0.0048352797,0.0009917316,0.8851686],"study_design_scores_gemma":[0.017727464,0.000081881946,0.01166624,0.0002456044,0.0005214386,0.000026592956,0.034396444,0.91302574,0.00039476313,0.021296624,0.0005396662,0.00007756271],"about_ca_topic_score_codex":0.00047027256,"about_ca_topic_score_gemma":0.0012744492,"teacher_disagreement_score":0.91270006,"about_ca_system_score_codex":0.000028761557,"about_ca_system_score_gemma":0.0012584446,"threshold_uncertainty_score":0.9911789},"labels":[],"label_agreement":null},{"id":"W3168520614","doi":"10.1186/s12874-021-01311-z","title":"Social media attention and citations of published outputs from re-use of clinical trial data: a matched comparison with articles published in the same journals","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"Agence Nationale de la Recherche","keywords":"Interquartile range; Randomized controlled trial; Citation; Sample size determination; Social media; MEDLINE; Medicine; Clinical trial; Computer science; Statistics; Library science; World Wide Web; Internal medicine","score_opus":0.986696572208997,"score_gpt":0.7493060614089416,"score_spread":0.23739051080005535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168520614","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":[0.88944817,0.00075302133,0.090678446,0.018002877,0.00029260843,0.00064101827,0.00005441389,0.0000022150375,0.00012724222],"genre_scores_gemma":[0.82198334,0.00017682664,0.17664175,0.0002543466,0.0005623545,0.000058378948,0.00012835803,0.000011840467,0.00018282168],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.29131424,0.6505963,0.026512515,0.0024847037,0.028214712,0.00087752216],"domain_scores_gemma":[0.045450807,0.93417984,0.007019879,0.0057651834,0.006925835,0.000658441],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7020232,0.00016927399,0.005043071,0.00068977964,0.00012937568,0.0009775328,0.003074412,0.0003714046,0.007637417],"category_scores_gemma":[0.9484779,0.00007289775,0.00059496163,0.003473905,0.0012316289,0.00072746107,0.00085465575,0.0012468382,0.000023607708],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008442282,0.0020496421,0.6179471,0.00021773715,0.0010276899,0.00009394728,0.01393494,0.000006942102,0.0005781567,0.0120411785,0.20314991,0.14051048],"study_design_scores_gemma":[0.015511066,0.0003644013,0.8460412,0.00021527987,0.00038238533,0.000017638362,0.03685838,0.01090441,0.00004284989,0.08444276,0.0050418107,0.00017784548],"about_ca_topic_score_codex":0.0003225816,"about_ca_topic_score_gemma":0.012556682,"teacher_disagreement_score":0.28358355,"about_ca_system_score_codex":0.000014431548,"about_ca_system_score_gemma":0.0016303471,"threshold_uncertainty_score":0.99326974},"labels":[],"label_agreement":null},{"id":"W3170269751","doi":"10.1186/s12874-021-01310-0","title":"Most published meta-regression analyses based on aggregate data suffer from methodological pitfalls: a meta-epidemiological study","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":179,"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; St. Michael's Hospital","funders":"Canada Research Chairs","keywords":"Meta-regression; Meta-analysis; Logistic regression; Overfitting; Regression; Regression analysis; Medicine; Confounding; Statistics; Internal medicine; Computer science; Mathematics; Machine learning","score_opus":0.9961418339580116,"score_gpt":0.7873935714980298,"score_spread":0.2087482624599818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170269751","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":[0.024073685,0.015206034,0.9311513,0.023144728,0.0008747491,0.0023032022,0.00032036848,0.000061602026,0.0028643385],"genre_scores_gemma":[0.092208214,0.00048348025,0.8897399,0.008670182,0.0009238249,0.0011754041,0.00084578025,0.00007992026,0.005873332],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.13334686,0.80425125,0.017113095,0.0081819445,0.035120342,0.0019865164],"domain_scores_gemma":[0.022242133,0.9345885,0.0053381273,0.026819536,0.0081231855,0.0028885398],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.88504416,0.0014091865,0.028948124,0.0018040959,0.0007117591,0.0016079213,0.01728588,0.0013704539,0.35709417],"category_scores_gemma":[0.9872183,0.00048089717,0.0075031416,0.009396645,0.0014966044,0.00055805617,0.007045828,0.0040901415,0.002309508],"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":[0.0019379699,0.008138814,0.05178978,0.00024054603,0.0772541,0.0054741474,0.0005365816,0.0016916788,0.0016728804,0.006444358,0.745556,0.09926317],"study_design_scores_gemma":[0.0056731296,0.00329757,0.05110065,0.00024416263,0.06140316,0.00017922849,0.008385799,0.45069548,0.0013022935,0.18541202,0.2298335,0.0024730067],"about_ca_topic_score_codex":0.0009274093,"about_ca_topic_score_gemma":0.002271944,"teacher_disagreement_score":0.51572245,"about_ca_system_score_codex":0.00011226986,"about_ca_system_score_gemma":0.0029494558,"threshold_uncertainty_score":0.999926},"labels":[],"label_agreement":null},{"id":"W3170350666","doi":"10.1186/s12874-021-01452-1","title":"Evaluating the performance of propensity score matching based approaches in individual patient data meta-analysis","year":2021,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University; McGill University Health Centre","funders":"","keywords":"Propensity score matching; Observational study; Confounding; Matching (statistics); Meta-analysis; Random effects model; Statistics; Logistic regression; Medicine; Odds ratio; Internal medicine; Mathematics","score_opus":0.9918079962204878,"score_gpt":0.7322729214567691,"score_spread":0.2595350747637186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170350666","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008313393,0.85266477,0.14391182,0.00008884885,0.000036192727,0.0022465724,0.00011093163,0.00004311447,0.000066390756],"genre_scores_gemma":[0.000126811,0.43989632,0.5585578,0.00003046419,0.0000469961,0.0009064551,0.00036121506,0.000050708044,0.000023220582],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.88493437,0.10443444,0.0027216438,0.001505319,0.0053832955,0.0010209352],"domain_scores_gemma":[0.8104118,0.18421097,0.0010563437,0.0035991417,0.0004954955,0.0002262413],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19373369,0.0004973408,0.0073343106,0.0010373284,0.00017137094,0.000047345915,0.0041459515,0.00081221136,0.00093783264],"category_scores_gemma":[0.25178897,0.00026768266,0.0011575683,0.0032038982,0.0010905877,0.00014052662,0.005057341,0.004111223,0.0000044384],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031034746,0.00027315787,0.000048942755,0.022253279,0.019761553,0.000038415485,0.00034997432,0.00006916745,9.592554e-7,0.004279953,0.000087425455,0.9528061],"study_design_scores_gemma":[0.0012977187,0.0038224347,0.00011449292,0.032105517,0.765369,0.00027814793,0.0023524615,0.06334006,0.00037521217,0.092761196,0.03472661,0.003457181],"about_ca_topic_score_codex":0.00021176443,"about_ca_topic_score_gemma":0.0009479213,"teacher_disagreement_score":0.949349,"about_ca_system_score_codex":0.00014302059,"about_ca_system_score_gemma":0.005600437,"threshold_uncertainty_score":0.9999775},"labels":[],"label_agreement":null},{"id":"W3174389136","doi":"10.1186/s12874-021-01330-w","title":"How to analyze work productivity loss due to health problems in randomized controlled trials? A simulation study","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Workplace Health and Well-being","field":"Health Professions","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":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Michael Smith Health Research BC","keywords":"Covariate; Productivity; Statistics; Mathematics; Randomized controlled trial; Econometrics; Medicine; Surgery; Economics","score_opus":0.5354543263760496,"score_gpt":0.6398807562898948,"score_spread":0.10442642991384521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174389136","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":[0.3013775,0.0016000193,0.48051047,0.17909747,0.0015894135,0.03540956,0.0000043602113,0.00009298777,0.00031818438],"genre_scores_gemma":[0.9299499,0.00029512102,0.04294364,0.005054984,0.002419389,0.014162944,0.00002306565,0.000073415045,0.005077563],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.4141673,0.57408726,0.0041849953,0.0015093151,0.0031958893,0.0028552178],"domain_scores_gemma":[0.27476257,0.71749085,0.00094672065,0.00131653,0.001969354,0.0035139846],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6124005,0.0003426309,0.00902833,0.0013787342,0.0009302343,0.000054214754,0.0005239982,0.0006353364,0.0009246397],"category_scores_gemma":[0.89051,0.00023502359,0.00043785985,0.0042352965,0.00024264124,0.00010212119,0.0007035733,0.0038760449,0.00013490074],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7088542,0.0031441606,0.10868751,0.0037037416,0.00060573494,0.0006215596,0.050734907,0.009268251,0.00007405984,0.0029653904,0.008046192,0.10329428],"study_design_scores_gemma":[0.88788694,0.0023669556,0.036230333,0.00523412,0.00016777936,0.000016512506,0.02808221,0.009715152,0.000027224747,0.017133908,0.012311281,0.0008276027],"about_ca_topic_score_codex":0.0020015982,"about_ca_topic_score_gemma":0.02830905,"teacher_disagreement_score":0.62857234,"about_ca_system_score_codex":0.0007244198,"about_ca_system_score_gemma":0.014353496,"threshold_uncertainty_score":0.9999887},"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":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3179388700","doi":"10.1186/s12874-021-01335-5","title":"Evaluating the relationship between citation set size, team size and screening methods used in systematic reviews: a cross-sectional study","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Library and Archives Canada; Health Canada; University of British Columbia; Agricultural Research Institute of Ontario; University of Toronto; McMaster University; University of Ottawa","funders":"CHEO Research Institute","keywords":"Citation; Sample size determination; Pairwise comparison; Set (abstract data type); Medicine; Workload; Statistics; Logistic regression; MEDLINE; Computer science; Information retrieval; Data science; Mathematics; World Wide Web","score_opus":0.9912808527538538,"score_gpt":0.8060137752601971,"score_spread":0.18526707749365667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179388700","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":[0.56208706,0.0036532083,0.42940214,0.000711622,0.00019084787,0.003697288,0.0000042787915,0.000006669427,0.00024689012],"genre_scores_gemma":[0.4897678,0.000042530053,0.50558877,0.00014745435,0.00022755166,0.001023924,0.0000063904563,0.000018450239,0.00317711],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.06670225,0.89536387,0.01643218,0.0020368972,0.018669235,0.00079555396],"domain_scores_gemma":[0.009997789,0.98010415,0.0031764884,0.0032352228,0.0029896304,0.0004967081],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.9375789,0.00031985104,0.005478608,0.0006483684,0.0007328036,0.00107267,0.002050709,0.00037293154,0.004661469],"category_scores_gemma":[0.99406934,0.00014726774,0.0008954657,0.005598371,0.0005336626,0.0002457544,0.00082837517,0.0017651039,0.00027726666],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023627637,0.000049115955,0.9882647,0.002010928,0.000112077854,0.000009620188,0.0021096515,0.000034435496,0.00005658592,0.0009125112,0.0002810861,0.0061356733],"study_design_scores_gemma":[0.00070294796,0.00018097273,0.9507109,0.00083575246,0.00014235945,0.00004844579,0.0075664166,0.011048808,0.000004140477,0.028442267,0.00018190866,0.00013509813],"about_ca_topic_score_codex":0.00010775518,"about_ca_topic_score_gemma":0.00070892036,"teacher_disagreement_score":0.08474027,"about_ca_system_score_codex":0.000109957095,"about_ca_system_score_gemma":0.0010757531,"threshold_uncertainty_score":0.9999643},"labels":[],"label_agreement":null},{"id":"W3181769638","doi":"10.1186/s12874-021-01332-8","title":"Survey design and analysis considerations when utilizing misclassified sampling strata","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"National Human Genome Research Institute; National Heart, Lung, and Blood Institute","keywords":"Stratified sampling; Sampling design; Sampling (signal processing); Simple random sample; Statistics; Systematic sampling; Sample size determination; Sample (material); Inference; Survey sampling; Computer science; Econometrics; Mathematics; Medicine; Artificial intelligence; Environmental health; Population","score_opus":0.9413660578017012,"score_gpt":0.6646432639260955,"score_spread":0.2767227938756057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181769638","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":[0.078930095,0.0019339919,0.91324466,0.0037309402,0.00029711385,0.0002445521,0.0000251056,0.000052817984,0.0015407118],"genre_scores_gemma":[0.13514271,0.0009978547,0.86133295,0.00059678213,0.00023694115,0.000057766447,0.00006844368,0.000018807032,0.0015477311],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.44767657,0.54877084,0.0005015497,0.0007336057,0.0013894179,0.0009280196],"domain_scores_gemma":[0.30346182,0.6943706,0.00007480809,0.00042158752,0.000901154,0.0007700241],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.5323557,0.00014974042,0.0007313291,0.0005472784,0.0014706117,0.00013378347,0.0003735698,0.0006980335,0.0075021866],"category_scores_gemma":[0.8733763,0.00013880996,0.00013158702,0.0017568982,0.002792387,0.000109047156,0.0003021614,0.0011178995,0.000021357884],"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":[0.00932559,0.0007448678,0.5236855,0.00018337747,0.003948173,0.0015102188,0.046687465,0.00025206513,0.007963184,0.2907092,0.01375913,0.101231225],"study_design_scores_gemma":[0.0010194439,0.00014253405,0.88107157,0.000048034748,0.00025551146,0.000033957887,0.01742479,0.0028715197,0.0014060638,0.089353666,0.005940913,0.00043199092],"about_ca_topic_score_codex":0.0038544894,"about_ca_topic_score_gemma":0.108511634,"teacher_disagreement_score":0.35738605,"about_ca_system_score_codex":0.00007137367,"about_ca_system_score_gemma":0.00781981,"threshold_uncertainty_score":0.99992144},"labels":[],"label_agreement":null},{"id":"W3182926934","doi":"10.1186/s12874-021-01331-9","title":"Comparing regression modeling strategies for predicting hometime","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":24,"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 Health Network; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; University of Calgary","funders":"Canadian Institutes of Health Research; Government of Ontario; Heart and Stroke Foundation of Canada","keywords":"Covariate; Metric (unit); Statistical model; Statistics; Mean squared error; Regression analysis; Sample size determination; Mathematics; Artificial intelligence; Machine learning; Data set; Sample (material); Computer science","score_opus":0.6541861622607366,"score_gpt":0.5671287890872743,"score_spread":0.0870573731734623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182926934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2481079,0.0013240519,0.73376054,0.0022445368,0.0002655771,0.00049173686,0.0000023045095,0.00009339082,0.013709946],"genre_scores_gemma":[0.4312408,0.00034664854,0.5644009,0.00041032946,0.0009577065,0.00022787307,0.00007333635,0.00004837424,0.0022940221],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99247855,0.0032743593,0.0006008592,0.0007189025,0.0019318373,0.0009955063],"domain_scores_gemma":[0.9779645,0.019820353,0.0000786474,0.00063778216,0.000841425,0.00065726525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0203879,0.00018216374,0.00079484144,0.00032771172,0.0002264573,0.000044913148,0.0003448359,0.00035713008,0.00068465807],"category_scores_gemma":[0.09000864,0.00014450264,0.00018328836,0.00051745516,0.00032238004,0.000085243875,0.00078243116,0.0011560955,0.000026486365],"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":[0.012733393,0.0023289288,0.11864673,0.018421706,0.0026462413,0.0048252023,0.006615664,0.005590612,0.20935866,0.077050075,0.22812839,0.3136544],"study_design_scores_gemma":[0.0046401327,0.00050515844,0.00082490547,0.0014890822,0.00013859266,0.00040588816,0.0146233775,0.94909847,0.008267459,0.00486932,0.014888337,0.00024926892],"about_ca_topic_score_codex":0.00009068963,"about_ca_topic_score_gemma":0.000086072774,"teacher_disagreement_score":0.94350785,"about_ca_system_score_codex":0.00015286724,"about_ca_system_score_gemma":0.0024873426,"threshold_uncertainty_score":0.9176566},"labels":[],"label_agreement":null},{"id":"W3197211443","doi":"10.1186/s12874-021-01364-0","title":"Evaluation of statistical methods used in the analysis of interrupted time series studies: a simulation study","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; Ottawa Hospital","funders":"National Health and Medical Research Council; Medical Research Council; Monash University","keywords":"Autocorrelation; Statistics; Series (stratigraphy); Ordinary least squares; Mathematics; Restricted maximum likelihood; Econometrics; Population; Confidence interval; Maximum likelihood; Demography; Biology","score_opus":0.9376995805081113,"score_gpt":0.7822997123750204,"score_spread":0.15539986813309092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197211443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21869157,0.00017700957,0.7802029,0.00012773833,0.000023172124,0.0006390743,0.000007722982,0.00001829206,0.000112501904],"genre_scores_gemma":[0.44438154,0.00002953354,0.5553709,0.0000114419645,0.00001332048,0.00015569803,0.00001005673,0.000008483943,0.000018991315],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79594135,0.19655383,0.0015387806,0.00051569357,0.005005406,0.00044496937],"domain_scores_gemma":[0.6449887,0.35028455,0.00025566499,0.00075381337,0.0036306423,0.00008660329],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22855736,0.00012456019,0.0011532047,0.00071749825,0.000043784636,0.000007314886,0.00042679088,0.0001808043,0.0013655312],"category_scores_gemma":[0.71255326,0.00008412467,0.00010535922,0.002900389,0.00079659047,0.000075533615,0.0003294905,0.00059127633,0.0000014321055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002015477,0.00901151,0.025978519,0.0017366784,0.011877075,0.00023823138,0.13118507,0.0104617,0.026018176,0.25491515,0.0005169568,0.5260455],"study_design_scores_gemma":[0.00092925155,0.0008536815,0.009751314,0.00011974012,0.0016902057,0.0000041553594,0.040325556,0.22655338,0.0050430894,0.71459806,0.000013400866,0.00011814424],"about_ca_topic_score_codex":0.00007145682,"about_ca_topic_score_gemma":0.0021441653,"teacher_disagreement_score":0.5259273,"about_ca_system_score_codex":0.00015897359,"about_ca_system_score_gemma":0.0010512241,"threshold_uncertainty_score":0.99954736},"labels":[],"label_agreement":null},{"id":"W3197313539","doi":"10.1186/s12874-021-01369-9","title":"Predicting postoperative surgical site infection with administrative data: a random forests algorithm","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Surgical site infection prevention","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Ottawa; Wilfrid Laurier University; University of British Columbia; Ottawa Hospital","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Random forest; Surgical site infection; Algorithm; Computer science; Data mining; Medicine; Surgery; Machine learning","score_opus":0.4802925906095507,"score_gpt":0.5637844322141916,"score_spread":0.0834918416046409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197313539","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52752167,0.00044126704,0.46509784,0.0025928486,0.0002923417,0.0008335307,0.000033497003,0.00013851485,0.0030484896],"genre_scores_gemma":[0.63255507,0.001719424,0.3511598,0.00084842206,0.003457804,0.000662235,0.0026374715,0.00014658389,0.006813166],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97355586,0.021526465,0.0006610406,0.0010664919,0.0023995095,0.0007906028],"domain_scores_gemma":[0.9557366,0.040728737,0.0001286052,0.00084232335,0.0014994894,0.0010642849],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026884368,0.00023838432,0.00086458056,0.0002878451,0.00032299463,0.000058676156,0.00021484733,0.0005347167,0.007135196],"category_scores_gemma":[0.06775806,0.00016976682,0.00015373669,0.0013170622,0.0008744203,0.00026909335,0.0005753761,0.0020448081,0.00012574052],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011015509,0.001631267,0.5596384,0.00036145345,0.0007344705,0.01256184,0.0006619897,0.000020877225,0.0014592104,0.0018947078,0.0007553418,0.40926492],"study_design_scores_gemma":[0.07968615,0.013548087,0.51141745,0.0029978377,0.0007607259,0.07044103,0.0021232418,0.07895701,0.02057913,0.0037637716,0.21438754,0.0013380622],"about_ca_topic_score_codex":0.0006460716,"about_ca_topic_score_gemma":0.0063003856,"teacher_disagreement_score":0.4079269,"about_ca_system_score_codex":0.00019190997,"about_ca_system_score_gemma":0.0035681021,"threshold_uncertainty_score":0.9937724},"labels":[],"label_agreement":null},{"id":"W3200920720","doi":"10.1186/s12874-021-01381-z","title":"Conducting proportional meta-analysis in different types of systematic reviews: a guide for synthesisers of evidence","year":2021,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":724,"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":"Meta-analysis; Pairwise comparison; Systematic review; Computer science; Data science; Management science; Psychology; MEDLINE; Medicine; Artificial intelligence; Engineering; Political science","score_opus":0.9978106427928172,"score_gpt":0.7994635274499049,"score_spread":0.19834711534291227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200920720","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":[0.000004974898,0.86434364,0.12787537,0.00019802478,0.00013510366,0.0073083895,0.00004482745,0.0000020259297,0.00008765139],"genre_scores_gemma":[0.000014037656,0.889511,0.10210988,0.000021499853,0.000094192466,0.004620028,0.000027200509,0.000029450914,0.003572725],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.1836095,0.7258913,0.060878057,0.003220403,0.025347989,0.001052742],"domain_scores_gemma":[0.0408083,0.91497767,0.027611211,0.008050778,0.00792683,0.000625237],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8533682,0.00080948666,0.08917446,0.004460998,0.00009497116,0.0001471527,0.006250582,0.0008293644,0.025312323],"category_scores_gemma":[0.9775119,0.00028221094,0.035505414,0.0095636295,0.0007681514,0.00012254559,0.0008921716,0.0010711685,0.00013353945],"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":[0.000013745809,0.00019748138,0.00007194315,0.7864833,0.092238076,0.00001927777,0.00016855511,0.000014178738,0.0000029940832,0.0032777456,0.0047309916,0.112781696],"study_design_scores_gemma":[0.0001664566,0.00018514879,0.000009221102,0.13113138,0.5808495,0.00006354242,0.0011324888,0.0012817914,0.000012854875,0.0023664115,0.2822391,0.0005620873],"about_ca_topic_score_codex":0.000091174545,"about_ca_topic_score_gemma":0.00057764055,"teacher_disagreement_score":0.65535194,"about_ca_system_score_codex":0.00017286408,"about_ca_system_score_gemma":0.0038860226,"threshold_uncertainty_score":0.999963},"labels":[],"label_agreement":null},{"id":"W3203491616","doi":"10.1186/s12874-021-01392-w","title":"Can the adverse childhood experiences (ACEs) checklist be utilized to predict emergency department visits among children and adolescents?","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Child Abuse and Trauma","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"Alberta Innovates; Alberta Innovates - Health Solutions; Alberta Health Services","keywords":"Medicine; Mental health; Checklist; Emergency department; Population; Logistic regression; Adolescent health; Suicidal ideation; Psychiatry; Poison control; Suicide prevention; Emergency medicine; Psychology; Environmental health; Nursing","score_opus":0.16579642485292306,"score_gpt":0.46961266539559143,"score_spread":0.30381624054266837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203491616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872541,0.0022830854,0.0010807953,0.0048891157,0.0010561781,0.0010251586,0.00003777969,0.000066301705,0.002307505],"genre_scores_gemma":[0.9939431,0.0007897873,0.0017843512,0.0010941182,0.0006971532,0.000547127,0.000049043978,0.00003701839,0.0010582899],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9833646,0.011982565,0.0006442085,0.0011383779,0.0016317817,0.001238495],"domain_scores_gemma":[0.9936766,0.0038912196,0.00009067617,0.0009432105,0.00021889183,0.0011794072],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009866709,0.00028409678,0.0005720468,0.00020773336,0.0004966754,0.000033294,0.00092263194,0.00037319204,0.01448105],"category_scores_gemma":[0.01613371,0.00019798853,0.00017146156,0.00085086597,0.0008654852,0.000059352,0.00080713467,0.001202606,0.000109715824],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011448865,0.0018108679,0.7645684,0.00010209911,0.0007228579,0.0006437841,0.08246345,0.0000029763767,0.00016052279,0.006292749,0.04834706,0.09374038],"study_design_scores_gemma":[0.0018939697,0.00027202757,0.97930944,0.00010687802,0.000038475497,0.0001696996,0.013505322,0.000015979494,0.00039456578,0.000363944,0.0037231054,0.0002065707],"about_ca_topic_score_codex":0.00093690207,"about_ca_topic_score_gemma":0.009631079,"teacher_disagreement_score":0.2147411,"about_ca_system_score_codex":0.000049998973,"about_ca_system_score_gemma":0.0006050193,"threshold_uncertainty_score":0.9921538},"labels":[],"label_agreement":null},{"id":"W3205923972","doi":"10.1186/s12874-021-01388-6","title":"Statistical reanalysis of vascular event outcomes in primary and secondary vascular prevention trials","year":2021,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","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":"Robarts Clinical Trials","funders":"Robarts Research Institute; National Health and Medical Research Council; Universität Duisburg-Essen; National Institute for Health and Care Research; Monash University; Medical Research Council; University of Texas Health Science Center at Houston; GlaxoSmithKline","keywords":"Ordered logit; Medicine; Statistics; Categorical variable; Ordinal regression; Bootstrapping (finance); Ordinal data; Event (particle physics); Psychology; Econometrics; Mathematics","score_opus":0.9665012314998981,"score_gpt":0.7504500615364047,"score_spread":0.21605116996349338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205923972","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":[0.000040922067,0.6926237,0.30490237,0.00007791487,0.00017394086,0.0017062993,0.00005494026,0.000002313399,0.00041764678],"genre_scores_gemma":[0.000003422885,0.87383926,0.12360798,0.000031499894,0.000116030504,0.00040642841,0.00019007904,0.000032790624,0.0017725362],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.11515722,0.81762165,0.03587507,0.0031248326,0.027234165,0.0009870629],"domain_scores_gemma":[0.2470706,0.7330441,0.009125769,0.0071451357,0.0025047252,0.0011097019],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.9032919,0.0007073037,0.049277004,0.0034157764,0.00011296293,0.00026859433,0.003337428,0.0012952003,0.057367716],"category_scores_gemma":[0.92933035,0.00033190649,0.0114054,0.0043646093,0.00085409713,0.00011284251,0.0016496866,0.0023300108,0.0003084196],"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":[0.000008182454,0.00018313086,0.00035005907,0.013565909,0.0027169625,0.000076242366,0.000060923758,0.0000011629551,3.3718337e-7,0.0031957673,0.0030663412,0.976775],"study_design_scores_gemma":[0.0007180849,0.00015059029,0.0014524101,0.0062830537,0.004889989,0.000044137,0.0003441668,0.00024907567,3.558242e-7,0.010369906,0.97514457,0.0003536415],"about_ca_topic_score_codex":0.00011553071,"about_ca_topic_score_gemma":0.00034965758,"teacher_disagreement_score":0.97642136,"about_ca_system_score_codex":0.00020842657,"about_ca_system_score_gemma":0.0071681426,"threshold_uncertainty_score":0.9999716},"labels":[],"label_agreement":null},{"id":"W3210129127","doi":"10.1186/s12874-021-01434-3","title":"Standardizing registry data to the OMOP Common Data Model: experience from three pulmonary hypertension databases","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Pulmonary Hypertension Research and Treatments","field":"Medicine","cited_by":86,"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":"Actelion Pharmaceuticals","keywords":"Observational study; Computer science; Missing data; Data mining; Medicine; Information retrieval; Database; Data science; Machine learning; Internal medicine","score_opus":0.8345554526349793,"score_gpt":0.5887189182897148,"score_spread":0.24583653434526453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210129127","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":[0.5611498,0.028188836,0.3276821,0.0716624,0.000843057,0.0021362586,0.006195426,0.00022138424,0.0019207613],"genre_scores_gemma":[0.44511425,0.008460587,0.51431096,0.0082996525,0.0016290749,0.00025041637,0.020156823,0.00014614078,0.0016320853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98288465,0.007741921,0.0006805545,0.0021895093,0.005112287,0.0013911056],"domain_scores_gemma":[0.9408724,0.040752463,0.00010718765,0.0144434115,0.001123367,0.002701229],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017577022,0.00030558996,0.0010070396,0.00020893995,0.00064260676,0.00006861159,0.0038646657,0.00028521832,0.001237527],"category_scores_gemma":[0.16119738,0.00019101075,0.00010771711,0.00097464095,0.0010630717,0.00035472916,0.014401301,0.0019077348,0.00018867607],"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":[0.010842906,0.0036548653,0.07804661,0.0004915498,0.0010558129,0.15846072,0.0003736687,0.000071638926,0.057029337,0.00088327395,0.32703122,0.36205837],"study_design_scores_gemma":[0.00428958,0.000658266,0.038902774,0.0018186476,0.00036521856,0.008926157,0.005200589,0.65568703,0.004093091,0.0029635897,0.27638316,0.00071191083],"about_ca_topic_score_codex":0.003372167,"about_ca_topic_score_gemma":0.0070800735,"teacher_disagreement_score":0.6556154,"about_ca_system_score_codex":0.000120285295,"about_ca_system_score_gemma":0.0051854537,"threshold_uncertainty_score":0.99967545},"labels":[],"label_agreement":null},{"id":"W3212329752","doi":"10.1186/s12874-021-01442-3","title":"Frequency and characteristics of promissory conference abstracts, i.e. abstracts without results, accepted at Cochrane Colloquia 1994-2020","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Academic Writing and Publishing","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cochrane Library; Publication; Medicine; Interquartile range; Cochrane collaboration; Library science; MEDLINE; Family medicine; Pediatrics; Alternative medicine; Political science; Computer science; Surgery; Pathology; Law","score_opus":0.3983771567913619,"score_gpt":0.4609424313927617,"score_spread":0.06256527460139982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212329752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.909578,0.0021093108,0.00029542262,0.004760096,0.00064467214,0.00034931378,0.00033179086,0.000086166096,0.08184517],"genre_scores_gemma":[0.9763996,0.0020329554,0.010628555,0.00032991907,0.0014243425,0.000034157885,0.0002490075,0.000034474335,0.00886699],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904508,0.005070362,0.0013326374,0.00066022493,0.0016657418,0.0008202496],"domain_scores_gemma":[0.9695366,0.0277135,0.00043619945,0.00045526496,0.0011309242,0.00072748045],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024767395,0.00021716286,0.0008427938,0.00016990869,0.00043041594,0.00018695054,0.00057913834,0.0005345916,0.007198498],"category_scores_gemma":[0.14977263,0.00018771103,0.00008273301,0.00015036245,0.0023310694,0.00022141293,0.00050826767,0.0019510341,0.000038424034],"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":[0.0053212517,0.0015235109,0.030251466,0.011824493,0.0007733308,0.003270935,0.11510286,0.0000074563527,0.09250728,0.42650732,0.14884435,0.16406575],"study_design_scores_gemma":[0.014868268,0.0018764348,0.31504422,0.007854961,0.00033854423,0.0016071575,0.055848893,0.0010711162,0.027619442,0.04643913,0.52472883,0.0027029726],"about_ca_topic_score_codex":0.0011810901,"about_ca_topic_score_gemma":0.0032173945,"teacher_disagreement_score":0.38006818,"about_ca_system_score_codex":0.000071508955,"about_ca_system_score_gemma":0.0020661645,"threshold_uncertainty_score":0.993709},"labels":[],"label_agreement":null},{"id":"W3212935286","doi":"10.1186/s12874-021-01409-4","title":"Advancing data science in drug development through an innovative computational framework for data sharing and statistical analysis","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Multiple Sclerosis Research Studies","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":"Children's Hospital of Eastern Ontario","funders":"","keywords":"Clinical trial; Medicine; Informatics; Data science; Drug development; Data sharing; Big data; Medical physics; Data integration; Computer science; Electronic data capture; Data mining; Alternative medicine; Pathology; Drug; Engineering","score_opus":0.8010144352143743,"score_gpt":0.6682467293530194,"score_spread":0.1327677058613549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212935286","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118054,0.00036782675,0.8782534,0.002550756,0.00006444926,0.0004710845,0.00012186575,0.000017386392,0.00009924225],"genre_scores_gemma":[0.08103795,0.0004972857,0.91635686,0.00026603925,0.00012617733,0.000078852674,0.0016005613,0.000015154878,0.000021105812],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98932815,0.0034820712,0.00074580335,0.0020309256,0.0032353636,0.0011776966],"domain_scores_gemma":[0.7845028,0.20335077,0.00020287545,0.004896093,0.005147415,0.0019000595],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07385499,0.00015582134,0.00080875435,0.0007590847,0.00045449636,0.000079447535,0.0017589326,0.00014139512,0.0003587147],"category_scores_gemma":[0.55573744,0.00013170352,0.00001846677,0.004815405,0.0025087567,0.0006000651,0.008471595,0.00126758,0.0000037462319],"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":[0.0014659015,0.0011533984,0.6046685,0.001514083,0.0010415011,0.0005012055,0.008749875,0.0002058631,0.001557214,0.1049086,0.0014461158,0.27278772],"study_design_scores_gemma":[0.0020961058,0.00016828458,0.5191978,0.0004306365,0.000074647,0.000032767897,0.0052834307,0.448791,0.0004167894,0.019607225,0.0036634267,0.00023788695],"about_ca_topic_score_codex":0.00049483933,"about_ca_topic_score_gemma":0.0062053944,"teacher_disagreement_score":0.48188248,"about_ca_system_score_codex":0.0002413051,"about_ca_system_score_gemma":0.008872371,"threshold_uncertainty_score":0.9995477},"labels":[],"label_agreement":null},{"id":"W3214219534","doi":"10.1186/s12874-021-01445-0","title":"Appraising clinical applicability of studies: mapping and synthesis of current frameworks, and proposal of the FrACAS framework and VICORT checklist","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Centre Hospitalier Universitaire Sainte-Justine; McGill University; Centre Hospitalier de l’Université de Montréal; Université de Montréal; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Scope (computer science); Checklist; Management science; Brainstorming; Originality; Relevance (law); Data science; Perspective (graphical); Process (computing); Conceptual framework; Knowledge management; Process management; Psychology; Artificial intelligence; Creativity; Engineering","score_opus":0.962558234149893,"score_gpt":0.7500185959344068,"score_spread":0.21253963821548627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214219534","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":[0.6036977,0.033628177,0.3589866,0.002430912,0.00024526747,0.00075001526,0.0000086762675,0.0000019429478,0.0002506743],"genre_scores_gemma":[0.66077656,0.004961991,0.33392632,0.00007366496,0.00013292495,0.000059217215,3.8785328e-7,0.000009584897,0.000059354254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7807707,0.19643019,0.011285543,0.0017078919,0.009284375,0.00052128034],"domain_scores_gemma":[0.09404469,0.89197606,0.0043105315,0.004297183,0.004701638,0.00066990225],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.51062226,0.00019556993,0.004967328,0.00022379012,0.0001496999,0.000057662528,0.0010993608,0.0005808856,0.0005601434],"category_scores_gemma":[0.92417186,0.000087780194,0.00063789106,0.0016418305,0.0048605255,0.00005149637,0.0018946166,0.0016965568,0.0000030980602],"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":[0.00007623272,0.00031017198,0.415464,0.00406427,0.00045329137,0.000004648328,0.0015896414,0.0000011985794,0.00025782562,0.0297576,0.0010036861,0.54701746],"study_design_scores_gemma":[0.0008429377,0.0003203461,0.4222146,0.0055211456,0.0006364086,0.00010265954,0.036713235,0.005532813,0.0021572015,0.50857407,0.016995775,0.00038882406],"about_ca_topic_score_codex":0.000016121714,"about_ca_topic_score_gemma":0.00005719516,"teacher_disagreement_score":0.69554585,"about_ca_system_score_codex":0.000014009018,"about_ca_system_score_gemma":0.0009195496,"threshold_uncertainty_score":0.9978477},"labels":[],"label_agreement":null},{"id":"W3216572326","doi":"10.1186/s12874-021-01457-w","title":"Similarities, reliability and gaps in assessing the quality of conduct of systematic reviews using AMSTAR-2 and ROBIS: systematic survey of nutrition reviews","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"McMaster University; Impact","funders":"China Academy of Chinese Medical Sciences; Uniwersytet Jagielloński Collegium Medicum","keywords":"Systematic review; Medicine; MEDLINE; Cochrane Library; Meta-analysis; Reliability (semiconductor); Publication bias; Protocol (science); Statistics; Family medicine; Alternative medicine; Pathology; Mathematics; Biology","score_opus":0.9845042905545137,"score_gpt":0.7484438442130675,"score_spread":0.23606044634144618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216572326","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":[0.5560026,0.3475514,0.08751304,0.00046876905,0.00019755804,0.0080917645,0.000033821536,0.0000021362182,0.00013888959],"genre_scores_gemma":[0.70741075,0.039904628,0.25129357,0.00016495271,0.00006680686,0.00075795903,0.000022110034,0.000031637905,0.0003475816],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.076518334,0.8836066,0.029599033,0.0012251612,0.008554142,0.0004967407],"domain_scores_gemma":[0.09669062,0.8697946,0.01689197,0.0072933943,0.008830052,0.0004993629],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.905287,0.0002805933,0.015481137,0.00052705826,0.00011421095,0.00014289882,0.0013992514,0.00030444082,0.0006772202],"category_scores_gemma":[0.9632591,0.00012204199,0.00084109546,0.0032193556,0.0013907759,0.00019923641,0.00059036806,0.0006527399,0.000006097374],"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":[0.00002469958,0.00023816021,0.029349025,0.96432287,0.00010283812,0.0000048123566,0.0009364296,0.000005701916,0.0021379974,0.0015414536,0.0005695754,0.00076642673],"study_design_scores_gemma":[0.0031672684,0.0005117047,0.1765924,0.6748631,0.0018847126,0.0004038004,0.045912057,0.04515319,0.0018696795,0.047675602,0.00094848656,0.0010179814],"about_ca_topic_score_codex":0.0013014511,"about_ca_topic_score_gemma":0.0025911364,"teacher_disagreement_score":0.30764678,"about_ca_system_score_codex":0.00006785714,"about_ca_system_score_gemma":0.00096492696,"threshold_uncertainty_score":0.9991351},"labels":[],"label_agreement":null},{"id":"W3216683616","doi":"10.1186/s12874-021-01441-4","title":"Predicting COVID-19 mortality risk in Toronto, Canada: a comparison of tree-based and regression-based machine learning methods","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada","keywords":"Brier score; Logistic regression; Statistics; Linear discriminant analysis; Receiver operating characteristic; Machine learning; Random forest; Discriminative model; Medicine; Decision tree; Generalized additive model; Artificial intelligence; Lasso (programming language); Gradient boosting; Population; Computer science; Mathematics; Environmental health","score_opus":0.8059894945389353,"score_gpt":0.6821761730198052,"score_spread":0.12381332151913016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216683616","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":[0.26646733,0.007991661,0.72046274,0.0040371944,0.00013834727,0.00045577934,0.00003425394,0.00006921575,0.00034350055],"genre_scores_gemma":[0.37924838,0.00042354278,0.6192045,0.0008054174,0.000085142085,0.00013191419,0.000021075508,0.000027463639,0.000052521897],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.87198603,0.12258698,0.0015679864,0.0009313974,0.0019350178,0.0009926016],"domain_scores_gemma":[0.49369353,0.5040942,0.00044903898,0.00053087017,0.00034335407,0.00088901096],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.122764096,0.00028466652,0.00195951,0.00014999988,0.00036877047,0.000011320296,0.0004852008,0.00049579213,0.0013691906],"category_scores_gemma":[0.9095177,0.00020892432,0.00014965705,0.00064225664,0.0010637766,0.00003297914,0.0007290934,0.0022324673,4.2122622e-7],"study_design_candidate":"observational","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":[0.00038611895,0.00025553044,0.9670565,0.0013785441,0.00007698756,0.00013813861,0.0003700468,0.00048765997,0.00025475095,0.0017722569,0.00062964484,0.027193822],"study_design_scores_gemma":[0.004639157,0.00066080276,0.26780283,0.0006322717,0.0001353473,0.000009910299,0.005358693,0.6739036,0.0029530898,0.03858202,0.0048455875,0.00047670281],"about_ca_topic_score_codex":0.82696265,"about_ca_topic_score_gemma":0.98460865,"teacher_disagreement_score":0.7867536,"about_ca_system_score_codex":0.0014447209,"about_ca_system_score_gemma":0.010128245,"threshold_uncertainty_score":0.99954367},"labels":[],"label_agreement":null},{"id":"W3217122674","doi":"10.1186/s12874-021-01446-z","title":"On clinical trial fragility due to patients lost to follow up","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"National Institutes of Health; National Institute of Allergy and Infectious Diseases; Patient-Centered Outcomes Research Institute","keywords":"Fragility; Medicine; MEDLINE; Clinical trial; Psychology; Internal medicine; Political science","score_opus":0.9626865098308511,"score_gpt":0.7740116613576609,"score_spread":0.18867484847319027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217122674","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":[0.31137505,0.000013266129,0.6708959,0.0045611467,0.007423459,0.0021600646,0.000079459525,0.00007247865,0.0034192],"genre_scores_gemma":[0.00386114,0.000032259435,0.9861766,0.0050851023,0.0024210173,0.000339268,0.000007960959,0.00007819598,0.0019984317],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82181555,0.16471924,0.003716581,0.0021242953,0.0057721306,0.001852183],"domain_scores_gemma":[0.1008938,0.89060646,0.00023955216,0.0021976882,0.0020379159,0.0040245904],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.22639984,0.0003762003,0.0027322548,0.00034612676,0.00021569207,0.00006627431,0.0015585418,0.001397213,0.01350969],"category_scores_gemma":[0.99322975,0.0003030162,0.0006322579,0.0015180358,0.0009031102,0.000036931386,0.001991822,0.0034178009,0.003046144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12405844,0.004978548,0.002626533,0.0003378787,0.00025186015,0.00075202325,0.00026504477,0.0000013282503,0.000043025517,0.31499386,0.15191804,0.39977342],"study_design_scores_gemma":[0.034747425,0.00658231,0.004368527,0.00022879666,0.000048232418,0.000007990189,0.000073439325,0.000046879108,0.0004940464,0.94368374,0.009382378,0.00033620984],"about_ca_topic_score_codex":0.00006602308,"about_ca_topic_score_gemma":0.00049729605,"teacher_disagreement_score":0.7668299,"about_ca_system_score_codex":0.0002176238,"about_ca_system_score_gemma":0.0026759582,"threshold_uncertainty_score":0.9999422},"labels":[],"label_agreement":null},{"id":"W32450810","doi":"10.1186/s12874-020-01019-6","title":"American and British English - Polish - Russian semantic analysis of automotive LSP","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Linguistics, Language Diversity, and Identity","field":"Arts and Humanities","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":"Spelling; Linguistics; Vocabulary; History; American English; Automotive industry; Computer science; Engineering; Philosophy","score_opus":0.2347875660581822,"score_gpt":0.42802922305445695,"score_spread":0.19324165699627474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W32450810","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98227197,0.0004403504,0.0016066493,0.00015320092,0.0020500175,0.00023424737,0.00008254989,0.00005863039,0.013102365],"genre_scores_gemma":[0.9893247,0.00039694403,0.0036933587,0.0002983806,0.004502541,0.000015154822,0.000033669992,0.0000141553655,0.0017211016],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99405533,0.00370666,0.000351552,0.00037382517,0.00096395466,0.0005487036],"domain_scores_gemma":[0.98708063,0.008820619,0.00012554768,0.0002849311,0.0032098158,0.00047844922],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057656285,0.00010858986,0.0006931931,0.0006446438,0.00026697374,0.00019244717,0.0004212699,0.00010454258,0.015320481],"category_scores_gemma":[0.2719531,0.00010371905,0.00015376016,0.0003778568,0.004088289,0.00012129217,0.00042083897,0.0004727189,0.000039042054],"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":[0.00012874289,0.0010108968,0.34297624,0.0009531396,0.004099064,0.00028968774,0.3215917,0.0000073680117,0.000012177424,0.156888,0.10654461,0.06549839],"study_design_scores_gemma":[0.001615315,0.00086834066,0.604426,0.0002188093,0.0014601754,0.0000045145684,0.338984,0.005016757,0.0000630502,0.026146114,0.020437833,0.0007590228],"about_ca_topic_score_codex":0.17065972,"about_ca_topic_score_gemma":0.101234086,"teacher_disagreement_score":0.26618746,"about_ca_system_score_codex":0.000036339086,"about_ca_system_score_gemma":0.00022135212,"threshold_uncertainty_score":0.998622},"labels":[],"label_agreement":null},{"id":"W4200114768","doi":"10.1186/s12874-021-01468-7","title":"Impact of limited sample size and follow-up on single event survival extrapolation for health technology assessment: a simulation study","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Hospital for Sick Children; Health Sciences Centre; Canadian Centre for Applied Research in Cancer Control; Sunnybrook Health Science Centre; Cancer Care Ontario; SickKids Foundation; University of Toronto","funders":"","keywords":"Statistics; Sample size determination; Mathematics; Percentile; Weibull distribution; Gompertz function; Survival analysis; Proportional hazards model; Population; Econometrics; Medicine","score_opus":0.8881276886981748,"score_gpt":0.6973721849853365,"score_spread":0.19075550371283834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200114768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5778908,0.00057478354,0.4067654,0.012751749,0.00042497888,0.0013340401,0.00016891325,0.000026171507,0.00006313309],"genre_scores_gemma":[0.9242699,0.00011235548,0.07454791,0.00050409365,0.00017673401,0.00020509321,0.000048330523,0.000028660601,0.000106917534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98114127,0.013377958,0.00341928,0.00084197527,0.00047621154,0.0007433241],"domain_scores_gemma":[0.8050389,0.19222163,0.0012175809,0.00060938945,0.00049072376,0.0004217584],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1283491,0.0001638361,0.0014562741,0.0007550826,0.0002503488,0.000030867886,0.000245915,0.00035075992,0.0005601044],"category_scores_gemma":[0.45669115,0.00017922085,0.0001672109,0.0006995664,0.00022303892,0.00011366978,0.00014152797,0.00047743792,0.000014207287],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012208641,0.0041461093,0.8332548,0.0016687168,0.00066477805,0.000005706591,0.004463308,0.0035170196,0.00025304762,0.12360666,0.00197224,0.02522671],"study_design_scores_gemma":[0.009603786,0.009925477,0.69445163,0.0002447677,0.000016790096,0.000008936474,0.008326165,0.15254106,0.00002655854,0.12193721,0.0025016372,0.00041596196],"about_ca_topic_score_codex":0.0014574006,"about_ca_topic_score_gemma":0.0020002655,"teacher_disagreement_score":0.34637907,"about_ca_system_score_codex":0.0008237345,"about_ca_system_score_gemma":0.0023636112,"threshold_uncertainty_score":0.897548},"labels":[],"label_agreement":null},{"id":"W4200362342","doi":"10.1186/s12874-021-01451-2","title":"Guidance for using artificial intelligence for title and abstract screening while conducting knowledge syntheses","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":101,"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 Ottawa; Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Workflow; Computer science; Cornerstone; Set (abstract data type); Systematic review; Citation; Artificial intelligence; Applications of artificial intelligence; Process (computing); Knowledge management; Data science; MEDLINE; Database; World Wide Web","score_opus":0.965880617299061,"score_gpt":0.706944635125865,"score_spread":0.258935982173196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200362342","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032550912,0.0029253524,0.9591538,0.0021136773,0.00064536283,0.0004582518,0.0000064439946,0.000021165122,0.0021250402],"genre_scores_gemma":[0.3529219,0.00018116723,0.6439746,0.00019044738,0.0019113565,0.00011537864,0.000015115459,0.0000257952,0.0006642403],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980624,0.00064366154,0.00036650378,0.00029245633,0.00025562348,0.00037939395],"domain_scores_gemma":[0.9529155,0.04562885,0.000055046363,0.00019237377,0.0009122813,0.00029596043],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009976309,0.000066765766,0.00024174157,0.0001043253,0.00020029361,0.000019030662,0.000078097175,0.00019241929,0.0009576875],"category_scores_gemma":[0.14813249,0.00005992505,0.000056250756,0.00018900461,0.00027343383,0.000033069155,0.00005426249,0.0003042901,0.00003062341],"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":[0.00018379213,0.00008059371,0.00024122334,0.0007578406,0.000018786224,0.0000074989757,0.00046554126,0.000003674895,0.0046692668,0.028074121,0.0009958518,0.9645018],"study_design_scores_gemma":[0.00015449274,0.0009608549,0.0003270084,0.0029869354,0.000117080366,0.0004296206,0.031487867,0.11464133,0.59196484,0.15935136,0.09709091,0.00048772176],"about_ca_topic_score_codex":0.00011533948,"about_ca_topic_score_gemma":0.00022536922,"teacher_disagreement_score":0.9640141,"about_ca_system_score_codex":0.000045928573,"about_ca_system_score_gemma":0.0016263542,"threshold_uncertainty_score":0.9999556},"labels":[],"label_agreement":null},{"id":"W4205390071","doi":"10.1186/s12874-021-01486-5","title":"Are there non-linear relationships between alcohol consumption and long-term health?: a systematic review of observational studies employing approaches to improve causal inference","year":2022,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Alcohol Consumption and Health Effects","field":"Medicine","cited_by":27,"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":"University of Sydney; University of New South Wales; University of Bristol","keywords":"Observational study; Causal inference; Alcohol consumption; Inference; Term (time); Consumption (sociology); Computer science; Data science; Econometrics; Medicine; Alcohol; Artificial intelligence; Mathematics; Pathology","score_opus":0.9749409399963292,"score_gpt":0.6922019589415839,"score_spread":0.2827389810547454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205390071","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":[0.00052209385,0.9799871,0.0060318103,0.0018799872,0.00018937723,0.011254095,0.00007983733,0.00004478489,0.000010937714],"genre_scores_gemma":[0.00004913081,0.98311126,0.010838786,0.0008041596,0.00027884493,0.004366277,0.00032954908,0.000066310684,0.00015566169],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.94535077,0.046978757,0.0030452474,0.0010285653,0.002730183,0.0008665099],"domain_scores_gemma":[0.76454186,0.22819144,0.002873087,0.0014619369,0.0008812477,0.0020504494],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.080239035,0.00048200437,0.007251337,0.00084409444,0.00050776755,0.000013820262,0.00047366117,0.00066120055,0.00039131244],"category_scores_gemma":[0.2698937,0.00035050523,0.00036981588,0.0009459363,0.0007447549,0.00006255299,0.0008188721,0.0038057596,0.000071400085],"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":[0.000040720413,0.00006250009,0.014098308,0.93195516,0.0004722184,0.000041563864,0.00024933595,7.1153025e-8,1.03154214e-7,0.00037519733,0.00018431508,0.052520517],"study_design_scores_gemma":[0.0007461558,0.0006741492,0.016782602,0.9744467,0.0015669356,0.00017734266,0.00030993254,0.00003249336,2.1086707e-7,0.000070717055,0.0048929704,0.00029975869],"about_ca_topic_score_codex":0.00003587111,"about_ca_topic_score_gemma":0.00014483761,"teacher_disagreement_score":0.18965468,"about_ca_system_score_codex":0.0006820054,"about_ca_system_score_gemma":0.0059228577,"threshold_uncertainty_score":0.9998947},"labels":[],"label_agreement":null},{"id":"W4205646676","doi":"10.1186/s12874-021-01411-w","title":"COVID-19 impact on mental health","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"COVID-19 and Mental Health","field":"Psychology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Mental health; MEDLINE; Medicine; Pandemic; Psychology; Psychiatry; Virology; Political science; Pathology; Outbreak","score_opus":0.7976202612181947,"score_gpt":0.73475158938297,"score_spread":0.06286867183522471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205646676","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":[0.3865726,0.011597023,0.072035216,0.46572453,0.014992696,0.007678669,0.0012229602,0.000809424,0.039366882],"genre_scores_gemma":[0.60738146,0.0014604832,0.013191288,0.3449778,0.002251629,0.0031140537,0.00070114917,0.00022312146,0.026699046],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9246932,0.06817546,0.0006999177,0.00103152,0.0032723346,0.0021275706],"domain_scores_gemma":[0.9457936,0.048666496,0.00013844842,0.0008181541,0.000048035465,0.00453524],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.07795817,0.00023248736,0.0006873169,0.00078993855,0.0014620995,0.000013118614,0.0010778892,0.00021915237,0.145062],"category_scores_gemma":[0.031917,0.0001905126,0.00023600657,0.0010001779,0.0007017258,0.000027049546,0.0009361361,0.0027661317,0.00081234856],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0070435544,0.0014757869,0.0075991214,0.00033712373,0.00009257564,0.00038424126,0.00958867,0.000034469624,0.000060299768,0.05404713,0.779097,0.14023998],"study_design_scores_gemma":[0.0038013589,0.008618232,0.008918097,0.000020330397,0.0000035898609,0.00046303592,0.008844159,0.00020150811,0.0000109304765,0.0056709186,0.96322703,0.00022081601],"about_ca_topic_score_codex":0.028743874,"about_ca_topic_score_gemma":0.0022317127,"teacher_disagreement_score":0.22080885,"about_ca_system_score_codex":0.006015935,"about_ca_system_score_gemma":0.028641049,"threshold_uncertainty_score":0.9999656},"labels":[],"label_agreement":null},{"id":"W4206031387","doi":"10.1186/s12874-021-01496-3","title":"Stacked survival models for residual lifetime data","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Health Canada; Medical Research Council; Pfizer Canada; Pfizer; Natural Sciences and Engineering Research Council of Canada; Medical Research Council Canada","keywords":"Censoring (clinical trials); Residual; Estimator; Statistics; Nonparametric statistics; Confidence interval; Parametric statistics; Survival analysis; Econometrics; Mathematics; Robustness (evolution); Survival function; Brier score; Algorithm","score_opus":0.677483171735411,"score_gpt":0.564349427297388,"score_spread":0.11313374443802293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206031387","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13564765,0.0021390072,0.84991616,0.0073096054,0.000989677,0.0009438585,0.0007749704,0.000030612166,0.0022484434],"genre_scores_gemma":[0.28450465,0.0016661636,0.6816566,0.0027920036,0.004035963,0.0017875636,0.008878915,0.00015124877,0.01452687],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97669166,0.01976048,0.00052189635,0.00097626884,0.0010650497,0.0009846267],"domain_scores_gemma":[0.98461175,0.013330421,0.00010888736,0.001283307,0.00029184177,0.00037379438],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.061186127,0.00014276944,0.00043139348,0.00012933444,0.00054233626,0.000011573201,0.0018326566,0.00034484788,0.0008064621],"category_scores_gemma":[0.08424789,0.00013637629,0.000096555785,0.00020742504,0.00041921347,0.0000032198714,0.0035671566,0.00063455856,0.000012789336],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029780052,0.0006397051,0.0111928135,0.00015710808,0.0005054425,0.000028547089,0.0003015136,0.005484334,0.017294163,0.023841888,0.895613,0.041963488],"study_design_scores_gemma":[0.003982149,0.003157995,0.0043217745,0.000010939443,0.00005580212,0.00008637201,0.0032780166,0.071205094,0.00063404517,0.05598337,0.85667986,0.00060457806],"about_ca_topic_score_codex":0.00026507114,"about_ca_topic_score_gemma":0.0006501354,"teacher_disagreement_score":0.16825955,"about_ca_system_score_codex":0.00004892265,"about_ca_system_score_gemma":0.0020741848,"threshold_uncertainty_score":0.96670645},"labels":[],"label_agreement":null},{"id":"W4206266676","doi":"10.1186/s12874-021-01482-9","title":"Reporting of abstracts in studies that used routinely collected data for exploring drug treatment effects: a cross-sectional survey","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"Peking University; Capital Medical University; Soochow University; Sichuan University; West China Hospital, Sichuan University; Guangzhou University; Guangzhou University of Chinese Medicine; National Natural Science Foundation of China","keywords":"Observational study; Medicine; Pharmacoepidemiology; MEDLINE; Descriptive statistics; Family medicine; Cross-sectional study; Medical prescription; Statistics; Pathology; Pharmacology","score_opus":0.9966038443494306,"score_gpt":0.7859026732215398,"score_spread":0.21070117112789077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206266676","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":[0.97395515,0.0018493927,0.021123784,0.00030378372,0.0006808711,0.0018474567,0.00012510364,0.0000062368586,0.00010821595],"genre_scores_gemma":[0.94082546,0.000165508,0.052785248,0.000049979764,0.00014337298,0.0022978743,0.00015424268,0.000022974718,0.0035553311],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.28451958,0.6284756,0.04546546,0.0048642843,0.034704793,0.0019702797],"domain_scores_gemma":[0.04067835,0.93792886,0.012232569,0.005505433,0.0031934136,0.00046138847],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.87184757,0.00024191571,0.0053315945,0.0011133065,0.0004925042,0.0001648035,0.0032591538,0.00010633714,0.0026212772],"category_scores_gemma":[0.9680617,0.00012942028,0.00073547236,0.0030325833,0.00041493357,0.00018408101,0.0019193266,0.0006066214,0.000026527985],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003681134,0.00025024018,0.98295295,0.00032347345,0.00043327885,0.000069123984,0.0013946425,0.00041521253,0.00012270552,0.00016574303,0.0062199794,0.0072845523],"study_design_scores_gemma":[0.0013294325,0.00033363557,0.97735375,0.000051730665,0.000035412606,0.00003417863,0.0032139914,0.007886975,0.00024369676,0.0031232594,0.006265314,0.00012863336],"about_ca_topic_score_codex":0.0015888116,"about_ca_topic_score_gemma":0.009491793,"teacher_disagreement_score":0.30945325,"about_ca_system_score_codex":0.00032985726,"about_ca_system_score_gemma":0.001979225,"threshold_uncertainty_score":0.9982905},"labels":[],"label_agreement":null},{"id":"W4206348701","doi":"10.1186/s12874-021-01448-x","title":"The impact of lookback windows on the prevalence and incidence of chronic diseases among people living with HIV: an exploration in administrative health data in Canada","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV-related health complications and treatments","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; Research Canada; AIDS Vancouver; University of British Columbia","funders":"Health Canada; Victoria General Hospital Foundation; University of British Columbia; Michael Smith Health Research BC; Canadian Institutes of Health Research; Ministry of Health, British Columbia; Public Health Agency; Public Health Agency of Canada; Canadian Foundation for AIDS Research","keywords":"Incidence (geometry); Medicine; Comparability; Demography; Population; Human immunodeficiency virus (HIV); Public health; Epidemiology; Environmental health; Family medicine; Pathology","score_opus":0.43056851996296686,"score_gpt":0.5532046081573708,"score_spread":0.12263608819440397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206348701","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931767,0.0014481631,0.0005809122,0.0036232818,0.0000117250265,0.0010410211,0.00008370367,0.0000024255285,0.000032095093],"genre_scores_gemma":[0.9979253,0.0012974126,0.00038026136,0.00003843308,0.000014669661,0.0002740281,0.000037017566,0.000006896604,0.000025981677],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9874739,0.010509436,0.00041671662,0.00030442627,0.00094616326,0.00034938118],"domain_scores_gemma":[0.9636972,0.034911886,0.00018391196,0.0007801674,0.000107765874,0.00031907333],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011233,0.000078243545,0.00031724176,0.0001176874,0.00022847985,0.0000040329182,0.0004164769,0.000031038453,0.00017703911],"category_scores_gemma":[0.0164073,0.00004122064,0.000013644306,0.0005964964,0.00041876332,0.00008713889,0.0002832378,0.00069182523,3.5597262e-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":[0.00054259744,0.0003009488,0.9910517,0.0002983405,0.000020262823,0.000017011429,0.0014993164,0.00019771428,0.000004784711,0.00042409412,0.00018035343,0.0054629017],"study_design_scores_gemma":[0.00056826684,0.0027707447,0.97584283,0.00051138765,0.000006483591,0.000015141808,0.0035520908,0.016510056,0.0000037359941,0.0001821799,0.000007804114,0.000029269839],"about_ca_topic_score_codex":0.5918079,"about_ca_topic_score_gemma":0.935925,"teacher_disagreement_score":0.34411713,"about_ca_system_score_codex":0.0008692427,"about_ca_system_score_gemma":0.026887111,"threshold_uncertainty_score":0.9918779},"labels":[],"label_agreement":null},{"id":"W4210336058","doi":"10.1186/s12874-021-01493-6","title":"Sex-specific analysis of traumatic brain injury events: applying computational and data visualization techniques to inform prevention and management","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Traumatic Brain Injury Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Brain Institute; Public Health Ontario; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Government of Ontario","keywords":"Visualization; Data science; Computer science; Traumatic brain injury; Psychology; Medicine; Data mining; Psychiatry","score_opus":0.6092069429490466,"score_gpt":0.6093537206932703,"score_spread":0.00014677774422366952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210336058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18770775,0.00025348685,0.8051599,0.0033760068,0.000041482985,0.0028419038,0.000078503996,0.000057896872,0.0004830344],"genre_scores_gemma":[0.22297052,0.00071078364,0.7706836,0.0009684825,0.000095732896,0.0019084403,0.0014775979,0.00005409776,0.0011307705],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9882562,0.0066826567,0.00081107725,0.00063199527,0.0031759678,0.00044208704],"domain_scores_gemma":[0.98589617,0.012687171,0.00011534925,0.0006809201,0.00021032,0.00041008997],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045426585,0.00012853062,0.0006695304,0.0023393717,0.0002830803,0.00001991583,0.00051654887,0.00011165307,0.0012214528],"category_scores_gemma":[0.01032473,0.00012040835,0.00005858752,0.002985556,0.00037822648,0.00010463289,0.002089753,0.0005575638,0.0000030359809],"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":[0.0011886322,0.00046986126,0.009149133,0.0018338666,0.0011462829,0.000024357687,0.0019353909,0.00006686144,0.0004844485,0.022527538,0.0060823304,0.9550913],"study_design_scores_gemma":[0.0086684935,0.01099241,0.3930214,0.0015301731,0.0016781439,0.0004402237,0.034855567,0.39129865,0.00094398885,0.049582552,0.10589115,0.0010972491],"about_ca_topic_score_codex":0.000063629224,"about_ca_topic_score_gemma":0.00006146676,"teacher_disagreement_score":0.95399404,"about_ca_system_score_codex":0.00014726224,"about_ca_system_score_gemma":0.00035575998,"threshold_uncertainty_score":0.99969155},"labels":[],"label_agreement":null},{"id":"W4211119714","doi":"10.1186/s12874-016-0256-6","title":"Erratum to: A Monte Carlo simulation study comparing linear regression, beta regression, variable-dispersion beta regression and fractional logit regression at recovering average difference measures in a two sample design","year":2016,"lang":"en","type":"erratum","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Logistic regression; Statistics; Regression analysis; Linear regression; BETA (programming language); Mathematics; Monte Carlo method; Econometrics; Regression diagnostic; Bayesian multivariate linear regression; Computer science","score_opus":0.5399558078900126,"score_gpt":0.5516702108883331,"score_spread":0.011714402998320494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211119714","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005306205,0.0015329567,0.98356515,0.00071659195,0.005055496,0.0027703654,0.00012539225,0.00016180532,0.0007660163],"genre_scores_gemma":[0.02485367,0.0021245503,0.95968807,0.00013555193,0.002122788,0.0006464257,0.00010044114,0.0002758146,0.010052713],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.93496877,0.050124183,0.0028036854,0.0031980728,0.0063495073,0.0025557657],"domain_scores_gemma":[0.8070075,0.18651012,0.0011200864,0.0019508554,0.0014184904,0.0019929379],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.049279034,0.0013392633,0.0036524136,0.0016555333,0.001201466,0.0001865577,0.001739068,0.002180183,0.0011000867],"category_scores_gemma":[0.33471325,0.0008209219,0.00026165717,0.0013560584,0.00088829047,0.0002768729,0.0034453324,0.006268048,0.000034538843],"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":[0.025834795,0.0041666194,0.0679851,0.006378873,0.00079992873,0.0019905204,0.0063701975,0.0018377667,0.0036704624,0.012284976,0.49495032,0.37373042],"study_design_scores_gemma":[0.012530357,0.00411165,0.021019034,0.07628113,0.00049539265,0.00023671382,0.001360187,0.42976737,0.0006182843,0.41880485,0.030775521,0.00399951],"about_ca_topic_score_codex":0.0034386367,"about_ca_topic_score_gemma":0.0045367233,"teacher_disagreement_score":0.4641748,"about_ca_system_score_codex":0.0012470406,"about_ca_system_score_gemma":0.0025330829,"threshold_uncertainty_score":0.99993587},"labels":[],"label_agreement":null},{"id":"W4213070302","doi":"10.1186/s12874-022-01518-8","title":"Analysis approaches to address treatment nonadherence in pragmatic trials with point-treatment settings: a simulation study","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Confounding; Statistics; Instrumental variable; Confidence interval; Nonparametric statistics; Mean squared error; Medicine; Marginal structural model; Type I and type II errors; Point estimation; Selection bias; Causal inference; Econometrics; Mathematics","score_opus":0.9212178228589814,"score_gpt":0.6612591426169402,"score_spread":0.25995868024204116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213070302","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3108664,0.000069229754,0.6811788,0.0009653579,0.000030793788,0.006306695,0.000029196164,0.00015192968,0.00040158813],"genre_scores_gemma":[0.6650106,0.0000136947465,0.32525206,0.000050201237,0.00005052288,0.009188286,0.000026029225,0.00003313256,0.00037550883],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92941344,0.064639434,0.0013658736,0.0010233097,0.0026173915,0.00094052975],"domain_scores_gemma":[0.82544446,0.17260888,0.00033446582,0.0009739296,0.00017556713,0.00046271976],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065930754,0.00031186323,0.0018627167,0.0014144644,0.00025468285,0.00003394751,0.0005799102,0.0001399772,0.0019315638],"category_scores_gemma":[0.11454531,0.00020780631,0.00017899489,0.0027813197,0.00020545529,0.00008293445,0.00046370865,0.00061605213,0.000011849664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019138591,0.045961075,0.13858664,0.00102923,0.009570846,0.0026428874,0.11412028,0.20816734,0.00071927044,0.055148564,0.00074558094,0.40416968],"study_design_scores_gemma":[0.023394933,0.099539965,0.009144852,0.0005194348,0.003750514,0.00011339055,0.15698595,0.2916821,0.0032195533,0.4066758,0.0026265548,0.0023470006],"about_ca_topic_score_codex":0.0011304315,"about_ca_topic_score_gemma":0.00868708,"teacher_disagreement_score":0.4018227,"about_ca_system_score_codex":0.001447624,"about_ca_system_score_gemma":0.0011197077,"threshold_uncertainty_score":0.9989808},"labels":[],"label_agreement":null},{"id":"W4220660709","doi":"10.1186/s12874-022-01549-1","title":"Documenting patients’ and providers’ preferences when proposing a randomized controlled trial: a qualitative exploration","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cancer survivorship and care","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":false,"ca_institutions":"University of Calgary; Alberta Children's Hospital; Alberta Health Services","funders":"Alberta Cancer Foundation","keywords":"Randomized controlled trial; Qualitative research; MEDLINE; Medicine; Family medicine; Psychology; Surgery; Sociology; Political science","score_opus":0.4616466608462584,"score_gpt":0.5466185661175107,"score_spread":0.08497190527125231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220660709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9165447,0.0021642796,0.05275231,0.009285324,0.0010638776,0.015262501,0.000004992686,0.00008659303,0.0028354665],"genre_scores_gemma":[0.95741504,0.0003542345,0.021544136,0.0008170271,0.00040845832,0.017032316,0.00008158056,0.000040842082,0.0023063822],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.90864915,0.086545154,0.0008925587,0.0005405478,0.0028295824,0.0005430261],"domain_scores_gemma":[0.89531523,0.102795176,0.00033926973,0.00029474974,0.000732231,0.0005233431],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09323596,0.00016117161,0.00171104,0.00040860334,0.00042668852,0.000054432123,0.00018683207,0.00013586762,0.0015853265],"category_scores_gemma":[0.17983188,0.00010992963,0.00023100317,0.00034030757,0.0008206187,0.00014234937,0.0003941883,0.0010555078,0.0000037941186],"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":[0.89968103,0.00022852379,0.00021858183,0.00022305262,0.00018195114,0.000012332671,0.076762535,5.0036584e-7,0.000052000534,0.0024208392,0.00050868676,0.019709986],"study_design_scores_gemma":[0.8957139,0.0022257948,0.000017021861,0.00009843992,0.00013276073,0.000008597206,0.06584143,0.000614618,0.000058937796,0.033926222,0.0012437442,0.00011853007],"about_ca_topic_score_codex":0.0015026976,"about_ca_topic_score_gemma":0.0011485392,"teacher_disagreement_score":0.08659591,"about_ca_system_score_codex":0.00016064919,"about_ca_system_score_gemma":0.0018353753,"threshold_uncertainty_score":0.99932736},"labels":[],"label_agreement":null},{"id":"W4220671932","doi":"10.1186/s12874-022-01546-4","title":"The role of analytic direction in qualitative research","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Qualitative Research Methods and Applications","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Rigour; Qualitative research; Reflexivity; Analytic element method; Coding (social sciences); Computer science; Qualitative property; Perspective (graphical); Qualitative analysis; Epistemology; Management science; Psychology; Sociology; Mathematics; Artificial intelligence; Statistics","score_opus":0.8384955483573598,"score_gpt":0.7727994887855106,"score_spread":0.06569605957184921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220671932","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":[0.45564216,0.019191934,0.0636812,0.11249718,0.000843456,0.006806283,0.00008845483,0.00015297589,0.34109637],"genre_scores_gemma":[0.93309057,0.004450558,0.049427543,0.00007092075,0.000452402,0.0039177686,0.000009781974,0.000036278285,0.008544193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.42477784,0.5631968,0.0008046228,0.0006074408,0.008887807,0.0017254993],"domain_scores_gemma":[0.5233842,0.47426692,0.00011260113,0.0004875914,0.0012521647,0.00049650576],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.57993126,0.00007871618,0.00034999262,0.0008439937,0.0034117592,0.000039092014,0.0015120527,0.00014094576,0.0016931174],"category_scores_gemma":[0.41489792,0.00006035711,0.00010417438,0.0053755306,0.006996575,0.00006759605,0.00085522485,0.0028049648,0.000029085997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017322456,0.00015776743,0.0006990333,0.000016416325,0.000015802956,0.0000036715624,0.06848855,0.0000067647156,0.0008339202,0.7974183,0.0009603056,0.13122627],"study_design_scores_gemma":[0.00015560545,0.00016449108,0.0008340219,0.000010732259,0.0000010461573,7.076112e-7,0.3986827,0.0004632302,0.00013242562,0.40906906,0.19044295,0.000043021828],"about_ca_topic_score_codex":0.02968351,"about_ca_topic_score_gemma":0.029587297,"teacher_disagreement_score":0.4774484,"about_ca_system_score_codex":0.00061507773,"about_ca_system_score_gemma":0.005039836,"threshold_uncertainty_score":0.9994956},"labels":[],"label_agreement":null},{"id":"W4220679456","doi":"10.1186/s12874-022-01542-8","title":"Using linear and natural cubic splines, SITAR, and latent trajectory models to characterise nonlinear longitudinal growth trajectories in cohort studies","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; University of Saskatchewan; Children's Hospital of Eastern Ontario","funders":"H2020 European Research Council; University of Bristol; European Commission; Medical Research Council; Royal Society; Economic and Social Research Council; Dairy Farmers of Canada; National Institute of Child Health and Human Development; Canadian Institutes of Health Research; Saskatchewan Health Research Foundation; Wellcome Trust","keywords":"Trajectory; Nonlinear system; Spline (mechanical); Econometrics; Linear model; Latent variable; Statistics; Mathematics; Computer science; Physics","score_opus":0.8894941905454349,"score_gpt":0.6241866468485189,"score_spread":0.265307543696916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220679456","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9553709,0.008628069,0.03307498,0.0011937213,0.0010664609,0.0005720379,0.000019680869,0.00003732363,0.00003685551],"genre_scores_gemma":[0.5750393,0.001569243,0.42227352,0.0003269206,0.00042810678,0.0001369277,0.0000052671744,0.000030609284,0.00019008026],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.967802,0.023679266,0.0013570853,0.0015367244,0.004449349,0.0011756064],"domain_scores_gemma":[0.69758296,0.29936752,0.00028849946,0.0007437105,0.0010969468,0.00092035317],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12467855,0.0002877746,0.0013241362,0.002174239,0.0006596072,0.00008465765,0.001048007,0.00019032361,0.00022425747],"category_scores_gemma":[0.45775685,0.00021303417,0.00010375468,0.004025867,0.0010013795,0.00023547876,0.0025638153,0.0018638443,0.0000041402823],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001664093,0.00024069764,0.91908467,0.0001822913,0.00017493853,0.00058801484,0.0047675716,0.0011938821,0.0024290434,0.0014286133,0.0005578993,0.067688294],"study_design_scores_gemma":[0.002284312,0.0013659399,0.7050354,0.00015247623,0.000054204567,0.0008120897,0.016433453,0.22668058,0.00023645512,0.045243718,0.0009702965,0.000731091],"about_ca_topic_score_codex":0.0010844264,"about_ca_topic_score_gemma":0.00063273555,"teacher_disagreement_score":0.38919854,"about_ca_system_score_codex":0.00020676186,"about_ca_system_score_gemma":0.0006676921,"threshold_uncertainty_score":0.9013276},"labels":[],"label_agreement":null},{"id":"W4220853067","doi":"10.1186/s12874-022-01562-4","title":"Developing a tool to assess the skills to perform a health technology assessment","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Norwegian Institute of Public Health","keywords":"Health technology; Resource (disambiguation); MEDLINE; Health care; Medical education; Knowledge management; Medicine; Computer science","score_opus":0.9157369298083231,"score_gpt":0.6970118538855636,"score_spread":0.21872507592275947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220853067","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":[0.09328306,0.0006313597,0.41439077,0.4881313,0.0007998337,0.0018447037,0.00006445117,0.00006191902,0.0007925791],"genre_scores_gemma":[0.0723636,0.00028446992,0.76850563,0.14946203,0.0007959443,0.0069065145,0.00003043589,0.00008209168,0.001569261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9600085,0.028709197,0.0057582436,0.001610916,0.0015065318,0.00240661],"domain_scores_gemma":[0.9428356,0.05365573,0.00089126057,0.0013672558,0.00026663308,0.0009834908],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.39401,0.00020747028,0.0014519449,0.001712274,0.0015844277,0.000073227435,0.001976427,0.0002299282,0.0048189587],"category_scores_gemma":[0.22234914,0.00020317701,0.00011814963,0.0021039536,0.00026583532,0.0001022899,0.002034845,0.0018264285,0.0014395206],"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":true,"study_design_scores_codex":[0.000045136818,0.0001547074,0.019901605,0.00033716066,0.000059551032,0.000007712526,0.0027813131,0.00023299907,0.0000043801797,0.89212304,0.061811227,0.02254117],"study_design_scores_gemma":[0.00079391757,0.0010340842,0.028927416,0.00009857655,0.0000020715413,0.00008021928,0.0153478095,0.0034865714,0.00000861608,0.0725313,0.87729543,0.0003939841],"about_ca_topic_score_codex":0.0013576216,"about_ca_topic_score_gemma":0.0012931384,"teacher_disagreement_score":0.81959176,"about_ca_system_score_codex":0.0039360663,"about_ca_system_score_gemma":0.00850263,"threshold_uncertainty_score":0.99988765},"labels":[],"label_agreement":null},{"id":"W4220951159","doi":"10.1186/s12874-022-01556-2","title":"Using a consistency check during data collection to identify invalid responding in an online cannabis screening survey","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social 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":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"Canada Research Chairs; Ontario Ministry of Health and Long-Term Care","keywords":"Medicine; Cannabis; Randomized controlled trial; Data collection; Psychiatry; Internal medicine","score_opus":0.9491251984146576,"score_gpt":0.7071481530514511,"score_spread":0.24197704536320652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220951159","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":[0.9574283,0.00022756115,0.03854145,0.001986284,0.00085038884,0.00065550435,0.000112348505,0.000058404603,0.0001397769],"genre_scores_gemma":[0.6415505,0.00013918361,0.3525376,0.0007046177,0.0007131102,0.00024914637,0.0003623266,0.00008023981,0.003663315],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.26230776,0.73003453,0.0009865471,0.0014507358,0.0034218011,0.0017986349],"domain_scores_gemma":[0.6608906,0.33452675,0.00026435687,0.0017791085,0.00082814385,0.0017110744],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6497692,0.0001846876,0.00069029053,0.0025380051,0.0029568642,0.00007271338,0.0024742302,0.0004078225,0.0025833726],"category_scores_gemma":[0.783323,0.00020284163,0.00006522541,0.006789197,0.0011668071,0.00033462458,0.0030266496,0.0022820423,0.000007648024],"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":[0.05508811,0.00082128646,0.86298364,0.00010769747,0.00010483341,0.0010544081,0.034261815,0.0006289685,0.021256933,0.0011922051,0.0023364518,0.020163627],"study_design_scores_gemma":[0.0010099618,0.00028200238,0.96304214,0.000056978763,0.000010223583,0.000048299236,0.027897023,0.0026145026,0.00018916871,0.00053874875,0.0040388736,0.0002721025],"about_ca_topic_score_codex":0.09206131,"about_ca_topic_score_gemma":0.48203206,"teacher_disagreement_score":0.39858282,"about_ca_system_score_codex":0.0007184176,"about_ca_system_score_gemma":0.007658381,"threshold_uncertainty_score":0.99834114},"labels":[],"label_agreement":null},{"id":"W4221047622","doi":"10.1186/s12874-021-01483-8","title":"What is the empirical basis for converting banded ordinal data on numbers of sex partners among MSM into a continuous scale level variable? A secondary analysis of 13 surveys across 17 countries","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Community Based Research Centre; University of Victoria","funders":"Robert Koch Institut; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Demography; Medicine; Descriptive statistics; Reproductive health; Psychology; Statistics; Population; Mathematics","score_opus":0.565227498602466,"score_gpt":0.5880312042911975,"score_spread":0.022803705688731468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221047622","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8056447,0.0008009135,0.17927639,0.008819926,0.00020008,0.0016620468,0.0024300385,0.00003182718,0.0011340793],"genre_scores_gemma":[0.9447703,0.0008177259,0.023965426,0.001975888,0.0003240683,0.0012623608,0.0019569183,0.00009720546,0.024830144],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9667884,0.026290163,0.0013100667,0.00091394293,0.0034794384,0.0012179681],"domain_scores_gemma":[0.9173746,0.078836404,0.0003174304,0.0015954967,0.0011546721,0.00072135625],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12173742,0.00022307677,0.0015804117,0.0007069856,0.00069691776,0.000057923062,0.0016248731,0.0002770721,0.01274072],"category_scores_gemma":[0.10405665,0.00016002438,0.000536877,0.0024863011,0.0034003714,0.00021901935,0.0019020194,0.0018497271,0.0000059898925],"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":[0.011297773,0.0022606472,0.46310782,0.0029267804,0.010844991,0.00014063387,0.03167692,0.000078538615,0.002518238,0.00071856385,0.33517268,0.13925642],"study_design_scores_gemma":[0.019904295,0.02540062,0.271068,0.0020689443,0.0032782978,0.00018866277,0.3020763,0.24481104,0.009010927,0.0032462631,0.1178508,0.0010958161],"about_ca_topic_score_codex":0.006598992,"about_ca_topic_score_gemma":0.011355579,"teacher_disagreement_score":0.2703994,"about_ca_system_score_codex":0.00021052497,"about_ca_system_score_gemma":0.0033139263,"threshold_uncertainty_score":0.9993118},"labels":[],"label_agreement":null},{"id":"W4221049767","doi":"10.1186/s12874-022-01515-x","title":"Development and validation of search filters to identify articles on deprescribing in Medline and Embase","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Women's College Hospital","funders":"","keywords":"MEDLINE; Deprescribing; Medicine; Intensive care medicine; Polypharmacy; Political science","score_opus":0.9719650177757563,"score_gpt":0.7161187116190901,"score_spread":0.25584630615666615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221049767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93945813,0.00026857588,0.05756343,0.0019605525,0.0000630509,0.0004917939,0.0000030530769,0.0000016676432,0.00018976435],"genre_scores_gemma":[0.8450826,0.000022372327,0.1540504,0.00023525742,0.000022291873,0.00013058094,0.0000035811656,0.000006714507,0.00044622517],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.73984087,0.23005807,0.0072782408,0.0016710622,0.020348305,0.00080345274],"domain_scores_gemma":[0.8030378,0.19279368,0.0006929138,0.0017721516,0.0008264591,0.00087694655],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58890384,0.00011323237,0.0014549724,0.0014541884,0.00019077708,0.00010409623,0.0009418744,0.00006529363,0.005829319],"category_scores_gemma":[0.4641683,0.0000664414,0.00012493675,0.001903647,0.00020438606,0.00005867793,0.0012204094,0.0004984528,0.00007432192],"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":[0.00044699755,0.0002767826,0.13694881,0.00034075914,0.00010703377,0.00010777042,0.013386756,0.00092458946,0.014733147,0.007335565,0.006230162,0.8191616],"study_design_scores_gemma":[0.004931236,0.002028008,0.6038063,0.0006957668,0.00011833301,0.00024456927,0.1003714,0.105245925,0.07904741,0.048450112,0.054031216,0.001029701],"about_ca_topic_score_codex":0.00011534229,"about_ca_topic_score_gemma":0.0003423368,"teacher_disagreement_score":0.8181319,"about_ca_system_score_codex":0.00006121622,"about_ca_system_score_gemma":0.00042137605,"threshold_uncertainty_score":0.9950795},"labels":[],"label_agreement":null},{"id":"W4223458273","doi":"10.1186/s12874-022-01545-5","title":"Methodology and experiences of rapid advice guideline development for children with COVID-19: responding to the COVID-19 outbreak quickly and efficiently","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","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":false,"ca_institutions":"McMaster University; Impact","funders":"Fundamental Research Funds for the Central Universities; Chongqing Medical University","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Outbreak; Guideline; Pandemic; Betacoronavirus; Medicine; Virology; Family medicine; Pathology; Disease; Infectious disease (medical specialty)","score_opus":0.8710481604260678,"score_gpt":0.7520035776108354,"score_spread":0.11904458281523245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223458273","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2584043,0.00025699206,0.60153687,0.1360143,0.0002817225,0.003322992,0.00007232603,0.00004537143,0.00006506689],"genre_scores_gemma":[0.030282874,0.00007477421,0.7863451,0.1740792,0.0002822573,0.008091618,0.000032664273,0.00003570926,0.00077576935],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.88206375,0.11002814,0.0020438267,0.00112832,0.0028151886,0.0019207918],"domain_scores_gemma":[0.6956937,0.29967427,0.0004929048,0.0005627615,0.00053988403,0.0030364904],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27800304,0.0001960552,0.0007143475,0.0013455036,0.004203668,0.000013255393,0.0011111533,0.0001929534,0.00276803],"category_scores_gemma":[0.52713704,0.00012924898,0.00003557575,0.002230438,0.0016017364,0.000059782258,0.0019842044,0.001135406,0.0000075748485],"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":[0.005333172,0.000082515486,0.019520525,0.0010744694,0.00007526148,0.000013649052,0.8014873,0.0001708965,0.00038840345,0.015269613,0.123953864,0.032630328],"study_design_scores_gemma":[0.0029587178,0.0014739113,0.0029488937,0.000025483949,0.000012197956,0.000115597715,0.30869782,0.00039362,0.000073685456,0.0006116514,0.6825174,0.00017099062],"about_ca_topic_score_codex":0.0021542967,"about_ca_topic_score_gemma":0.0035473316,"teacher_disagreement_score":0.5585636,"about_ca_system_score_codex":0.000567253,"about_ca_system_score_gemma":0.02671399,"threshold_uncertainty_score":0.99814355},"labels":[],"label_agreement":null},{"id":"W4224868022","doi":"10.1186/s12874-022-01605-w","title":"The reporting and handling of missing data in longitudinal studies of older adults is suboptimal: a methodological survey of geriatric journals","year":2022,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Hamilton Health Sciences; McMaster University; Impact","funders":"McMaster University","keywords":"Missing data; Longitudinal data; MEDLINE; Medicine; Psychology; Gerontology; Data science; Family medicine; Computer science; Statistics; Data mining; Mathematics; Political science","score_opus":0.978363974012901,"score_gpt":0.762147073679341,"score_spread":0.21621690033356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224868022","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":[0.0053445664,0.98525554,0.00763885,0.00021941689,0.0005435124,0.00085938466,0.00007016208,0.00000908731,0.00005945562],"genre_scores_gemma":[0.00012636496,0.9287969,0.07076269,0.000010730469,0.00014464896,0.000065218934,0.000021485717,0.000027292854,0.000044715754],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.070102185,0.91461426,0.007875844,0.0015771292,0.0042736656,0.0015569134],"domain_scores_gemma":[0.04081549,0.95009315,0.00610644,0.0013302448,0.0012592832,0.00039541422],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8972104,0.00035182282,0.005885219,0.001143221,0.0008122934,0.000024945588,0.002782175,0.0011097355,0.0007158071],"category_scores_gemma":[0.9777851,0.00022157362,0.00038515867,0.0034613165,0.007056609,0.00012017534,0.0032966093,0.0031573158,4.940506e-7],"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":[0.0025519286,0.00010809118,0.011122479,0.0083148265,0.0003438919,0.000116611176,0.0040361765,2.7778916e-7,0.0000012231841,0.00011587504,0.00013480785,0.9731538],"study_design_scores_gemma":[0.0051185973,0.0026281176,0.39734226,0.07260067,0.0022951425,0.0011121018,0.07011306,0.00027444385,0.00008056569,0.011206533,0.43488583,0.0023426749],"about_ca_topic_score_codex":0.007875239,"about_ca_topic_score_gemma":0.008833813,"teacher_disagreement_score":0.9708111,"about_ca_system_score_codex":0.00012945589,"about_ca_system_score_gemma":0.008254121,"threshold_uncertainty_score":0.99914247},"labels":[],"label_agreement":null},{"id":"W4225137714","doi":"10.1186/s12874-022-01600-1","title":"Minimal important difference and patient acceptable symptom state for the Numerical Rating Scale (NRS) for pain and the Patient-Rated Wrist/Hand Evaluation (PRWHE) for patients with osteoarthritis at the base of thumb","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Orthopedic Surgery and Rehabilitation","field":"Medicine","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":"University of British Columbia","funders":"Tays","keywords":"Receiver operating characteristic; Osteoarthritis; Medicine; Physical therapy; Thumb; Wrist; Percentile; Rating scale; Minimal clinically important difference; Splint (medicine); Wrist pain; Surgery; Psychology; Randomized controlled trial","score_opus":0.11795831715231656,"score_gpt":0.4169312454525688,"score_spread":0.29897292830025224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225137714","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9518678,0.0021244732,0.03504137,0.0031257952,0.00016149906,0.007488322,0.00017460492,0.00000763514,0.00000848583],"genre_scores_gemma":[0.9830875,0.00013852344,0.008548593,0.00044158314,0.00006501936,0.0074251695,0.00015402833,0.000028542883,0.00011105721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9849315,0.011756471,0.0007335868,0.00045985606,0.0016090932,0.00050949404],"domain_scores_gemma":[0.85356766,0.1448259,0.0002849197,0.00030212128,0.00083161163,0.00018777691],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04333677,0.000154647,0.00049969525,0.00008822203,0.0012419958,0.000025660456,0.00014605015,0.00008759358,0.00021894676],"category_scores_gemma":[0.07522135,0.00006877858,0.00011525997,0.00027353654,0.0017285419,0.00003970455,0.00025588454,0.00036597459,1.18491556e-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":[0.024239998,0.00030354614,0.07320476,0.0003854492,0.00009766153,0.0000012856265,0.006777141,0.000029925875,0.00053189724,0.00011380531,0.00061138184,0.89370316],"study_design_scores_gemma":[0.094117805,0.1049388,0.23516163,0.0008494276,0.0013060245,0.000115151,0.07472818,0.45223445,0.004625338,0.008862255,0.022157537,0.00090340566],"about_ca_topic_score_codex":0.00010580732,"about_ca_topic_score_gemma":0.00020495364,"teacher_disagreement_score":0.89279974,"about_ca_system_score_codex":0.00008020567,"about_ca_system_score_gemma":0.00075833977,"threshold_uncertainty_score":0.9850861},"labels":[],"label_agreement":null},{"id":"W4232330161","doi":"10.1186/s12874-016-0131-5","title":"Erratum to: The use of the Godin-Shephard Leisure-Time Physical Activity Questionnaire in oncology research: a systematic review","year":2016,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Physical Activity and 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":false,"ca_institutions":"Université Laval; University of Toronto","funders":"","keywords":"Physical activity; Medicine; Leisure time; MEDLINE; Physical therapy; Biology","score_opus":0.8706852141766637,"score_gpt":0.6744495101734901,"score_spread":0.19623570400317358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232330161","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":[0.00020716149,0.95929205,0.0008666543,0.026259137,0.00038748962,0.012618669,0.000042103828,0.000037188256,0.00028953873],"genre_scores_gemma":[0.0001731634,0.9933313,0.00055429223,0.00052414864,0.0009828146,0.0027738616,0.0000066587927,0.00007830366,0.0015754586],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.80208147,0.1887649,0.0014973092,0.0010983443,0.004854463,0.0017035381],"domain_scores_gemma":[0.7930119,0.20100807,0.0006687613,0.0028084605,0.0011642289,0.0013385759],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10222695,0.00055309676,0.010548559,0.0007430069,0.00034725555,0.000026636082,0.00223049,0.001281179,0.00015752338],"category_scores_gemma":[0.44588402,0.00022863285,0.0012881138,0.003701917,0.0029868884,0.00012701264,0.0019794453,0.00973829,0.00081014406],"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":[0.00022638575,0.0014532246,0.0000036292815,0.6805544,0.00016284428,0.00009125969,0.0001513535,7.22391e-8,0.000018237253,0.0013171848,0.010992783,0.30502862],"study_design_scores_gemma":[0.00033737786,0.000996644,0.000053050877,0.62434435,0.0004118735,0.00021551589,0.000010774788,0.000041771207,0.0000051671254,0.0006809184,0.3727455,0.00015701604],"about_ca_topic_score_codex":0.00058274495,"about_ca_topic_score_gemma":0.0008221851,"teacher_disagreement_score":0.36175275,"about_ca_system_score_codex":0.0016272577,"about_ca_system_score_gemma":0.018884648,"threshold_uncertainty_score":0.9999678},"labels":[],"label_agreement":null},{"id":"W4240792456","doi":"10.1186/s12874-019-0888-4","title":"Correction to: Methods for trustworthy nutritional recommendations NutriRECS (Nutritional Recommendations and accessible Evidence summaries Composed of Systematic reviews): a protocol","year":2019,"lang":"en","type":"erratum","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","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":"Impact; McMaster University; Dalhousie University","funders":"","keywords":"Protocol (science); Trustworthiness; Systematic review; Computer science; MEDLINE; Data science; Medicine; Information retrieval; Alternative medicine; Internet privacy; Political science; Pathology","score_opus":0.8917935385609758,"score_gpt":0.7412760124610566,"score_spread":0.1505175260999192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240792456","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006788309,0.0041451305,0.72230774,0.051770754,0.013770074,0.20680995,0.0004057689,0.00007150626,0.0007122816],"genre_scores_gemma":[0.0000034101677,0.011243457,0.7411429,0.0015658056,0.0021146815,0.22620302,0.003504223,0.000079137026,0.0141433375],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9417291,0.048029844,0.0056650024,0.0013775011,0.0022800765,0.0009184354],"domain_scores_gemma":[0.58796805,0.40441555,0.0017945151,0.0009488247,0.0040221447,0.0008509095],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12217164,0.0005065191,0.0034265765,0.0015070088,0.00044106293,0.0001051935,0.0007200933,0.0011423338,0.0028135618],"category_scores_gemma":[0.7463374,0.00042911095,0.0005740702,0.001535341,0.00067125756,0.00039606134,0.0006123126,0.0033232803,0.000051129555],"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":[0.0027141424,0.00063868845,0.00021101502,0.100494586,0.00020167853,0.0000025666325,0.000086106884,6.3944714e-7,0.00016521476,0.000759356,0.8406047,0.054121267],"study_design_scores_gemma":[0.0046304036,0.0026559667,0.00027697816,0.11631688,0.00064019056,0.0001815584,0.0006369833,0.0060606436,0.00017222035,0.0036856185,0.86435163,0.00039095068],"about_ca_topic_score_codex":0.00032461496,"about_ca_topic_score_gemma":0.0006196219,"teacher_disagreement_score":0.6241658,"about_ca_system_score_codex":0.000546585,"about_ca_system_score_gemma":0.0075682434,"threshold_uncertainty_score":0.99981606},"labels":[],"label_agreement":null},{"id":"W4245493252","doi":"10.1186/s12874-017-0444-z","title":"On the use of the outcome variable “small for gestational age” when gestational age is a potential mediator: a maternal asthma perspective","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Pregnancy and Medication Impact","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":"Université de Montréal; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"Perspective (graphical); Gestational age; Asthma; Medicine; Outcome (game theory); Gestation; Small for gestational age; Obstetrics; Pediatrics; Pregnancy; Psychology; Internal medicine; Computer science; Biology","score_opus":0.6766480991037988,"score_gpt":0.5555600853537666,"score_spread":0.1210880137500322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245493252","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":[0.30400968,0.00030035552,0.55205876,0.13530523,0.0016568478,0.0034952965,0.0004794538,0.000051177667,0.0026431917],"genre_scores_gemma":[0.5570215,0.0002447176,0.4095893,0.011104463,0.0019028385,0.0011561759,0.000101906975,0.00010098204,0.018778112],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9918241,0.0040764045,0.00056977634,0.00044615872,0.0024466799,0.00063691783],"domain_scores_gemma":[0.95687765,0.040225297,0.00035459312,0.0010579913,0.0009472622,0.0005371865],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015001583,0.0001754435,0.0004978056,0.0001881342,0.00063301966,0.00006748126,0.0010109842,0.00032521677,0.0026980203],"category_scores_gemma":[0.28580394,0.00009512681,0.00024282615,0.00011960713,0.00210508,0.00010293168,0.00033255812,0.0011043418,0.000030267893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0055089174,0.00088220823,0.029061744,0.00079431897,0.0007516273,0.00032349522,0.007019298,0.000044871736,0.003980936,0.86991274,0.07003374,0.011686109],"study_design_scores_gemma":[0.007901737,0.001296782,0.65537053,0.001257095,0.00018881197,0.00036991184,0.001296005,0.004638432,0.0022576086,0.30062413,0.024503507,0.00029543825],"about_ca_topic_score_codex":0.00094061997,"about_ca_topic_score_gemma":0.00026470717,"teacher_disagreement_score":0.6263088,"about_ca_system_score_codex":0.00017812547,"about_ca_system_score_gemma":0.0031120882,"threshold_uncertainty_score":0.99821365},"labels":[],"label_agreement":null},{"id":"W4256476373","doi":"10.1186/s12874-020-01028-5","title":"Correction to: Baseline-adjusted proportional odds models for the quantification of treatment effects in trials with ordinal sum score outcomes","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Spine and Intervertebral Disc Pathology","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":"International Collaboration On Repair Discoveries; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Baseline (sea); Odds; Statistics; Ordinal regression; Ordered logit; Computer science; MEDLINE; Ordinal data; Odds ratio; Medicine; Medical physics; Econometrics; Mathematics; Logistic regression; Political science","score_opus":0.7699654550366994,"score_gpt":0.5836996239781449,"score_spread":0.18626583105855454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256476373","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":[0.13919523,0.00020908845,0.8421785,0.015311671,0.0003631872,0.0026355959,0.000010533467,0.000020307052,0.0000758504],"genre_scores_gemma":[0.93914527,0.00011207243,0.056708388,0.0012776983,0.0003986365,0.0016295583,0.00009692734,0.000028327298,0.00060313864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99035585,0.007237464,0.0008002502,0.00044840132,0.00076314947,0.0003948741],"domain_scores_gemma":[0.96650124,0.031907458,0.00018434066,0.00035135404,0.00062160945,0.00043398907],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020092398,0.000148807,0.0010441832,0.00026838447,0.00006073858,0.0000059781705,0.0001922519,0.0001828565,0.00024620377],"category_scores_gemma":[0.20194902,0.00007307551,0.0002005447,0.0005690397,0.00032060378,0.000043885284,0.000060441245,0.00038838692,0.000010902879],"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":[0.05955932,0.0034342331,0.18645388,0.003946403,0.0013736079,0.0003224833,0.0039417474,0.0051489817,0.09034344,0.045292396,0.05192153,0.548262],"study_design_scores_gemma":[0.015100864,0.03322947,0.37074304,0.000830035,0.00039274,0.00014092271,0.0017343822,0.54885197,0.026627576,0.0013761668,0.0007273935,0.0002454636],"about_ca_topic_score_codex":0.0007413419,"about_ca_topic_score_gemma":0.0012629788,"teacher_disagreement_score":0.79995,"about_ca_system_score_codex":0.00012669218,"about_ca_system_score_gemma":0.0015853063,"threshold_uncertainty_score":0.80477333},"labels":[],"label_agreement":null},{"id":"W4280505624","doi":"10.1186/s12874-022-01583-z","title":"Automated medical chart review for breast cancer outcomes research: a novel natural language processing extraction system","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; Prevention of Organ Failure; University of British Columbia","funders":"University of British Columbia","keywords":"Computer science; Data extraction; Pipeline (software); Artificial intelligence; Medicine; Test (biology); Breast cancer; Medical physics; Natural language processing; Machine learning; Cancer; MEDLINE","score_opus":0.44980429708784625,"score_gpt":0.6128187548373685,"score_spread":0.16301445774952222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280505624","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16192093,0.5129563,0.18928191,0.11751825,0.006783263,0.007211662,0.0012577137,0.0016841962,0.0013857458],"genre_scores_gemma":[0.8981782,0.010201609,0.068320945,0.0059220227,0.0032683155,0.008468836,0.0006932747,0.00019040823,0.0047563706],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98375916,0.009799409,0.00064849417,0.0008848476,0.0036557147,0.0012523887],"domain_scores_gemma":[0.9906528,0.0074212933,0.0001386283,0.00049580686,0.0006503983,0.0006410949],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054195557,0.00021667333,0.00066902215,0.00028219033,0.00078185817,0.000027523776,0.0011756624,0.0005327071,0.00090341276],"category_scores_gemma":[0.072919615,0.00016333873,0.00020265453,0.00072325976,0.0011035079,0.0000065992717,0.0011092282,0.0019671512,0.000011174874],"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":[0.0012349115,0.0004877238,0.0009320667,0.007162559,0.00020949432,0.00017085504,0.00038490468,0.0000040240134,0.039622936,0.00039497155,0.09462986,0.8547657],"study_design_scores_gemma":[0.015379959,0.0046489765,0.024070496,0.0117384195,0.0002703758,0.010643205,0.03656336,0.13765103,0.007555533,0.00020638315,0.7488115,0.0024607864],"about_ca_topic_score_codex":0.00041389078,"about_ca_topic_score_gemma":0.00043045156,"teacher_disagreement_score":0.85230494,"about_ca_system_score_codex":0.00021723221,"about_ca_system_score_gemma":0.0036530797,"threshold_uncertainty_score":0.9891736},"labels":[],"label_agreement":null},{"id":"W4280588915","doi":"10.1186/s12874-022-01617-6","title":"Scoping review and characteristics of publicly available checklists for assessing clinical trial feasibility","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","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":"Kementerian Kesihatan Malaysia; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Association of Medical Research Charities; University of Bristol; National Institute for Health and Care Research; University of Wisconsin-Madison","keywords":"Clinical trial; Medicine; MEDLINE; Checklist; Reliability (semiconductor); Medical physics; Protocol (science); Alternative medicine; Psychology; Pathology","score_opus":0.9709940791625222,"score_gpt":0.7926194746728858,"score_spread":0.17837460448963638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280588915","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":[0.7400899,0.06490128,0.078375004,0.06826884,0.003968826,0.03639563,0.00020247884,0.00021710378,0.0075809485],"genre_scores_gemma":[0.12509696,0.16858615,0.663491,0.015844222,0.005047408,0.007371031,0.00038044844,0.00031314656,0.01386959],"study_design_codex":"systematic_review","study_design_gemma":"randomized_trial","domain_scores_codex":[0.91720843,0.064717904,0.005212956,0.0022831038,0.008633047,0.001944568],"domain_scores_gemma":[0.122717574,0.86705416,0.0008873603,0.0024321289,0.0044715647,0.0024372234],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.48394588,0.00018414404,0.0022887439,0.00030712562,0.00045099456,0.00004177409,0.000867055,0.00073855906,0.0065695364],"category_scores_gemma":[0.9107461,0.00015663188,0.00038051014,0.00083081616,0.0030709927,0.00009176515,0.0022837725,0.0073181326,0.000014864803],"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":[0.1393439,0.007798177,0.26270625,0.336739,0.0005889866,0.00029369598,0.00026664548,2.2760454e-7,0.00075793616,0.034941368,0.028024077,0.18853973],"study_design_scores_gemma":[0.41891292,0.082165524,0.123866454,0.15555461,0.0023496256,0.0012575611,0.0028278213,0.004511661,0.00093297916,0.15383093,0.051167775,0.0026221618],"about_ca_topic_score_codex":0.00012720964,"about_ca_topic_score_gemma":0.00020076668,"teacher_disagreement_score":0.8023362,"about_ca_system_score_codex":0.00020920174,"about_ca_system_score_gemma":0.019036159,"threshold_uncertainty_score":0.9996421},"labels":[],"label_agreement":null},{"id":"W4281255248","doi":"10.1186/s12874-022-01633-6","title":"Detecting accelerometer non-wear periods using change in acceleration combined with rate-of-change in temperature","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Physical Activity and Health","field":"Medicine","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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Ontario Brain Institute","keywords":"Cart; Accelerometer; Decision tree; Linear regression; Computer science; Regression; Change detection; Decision tree learning; Artificial intelligence; Statistics; Mathematics; Machine learning; Engineering","score_opus":0.7850775652130005,"score_gpt":0.5877844507609878,"score_spread":0.1972931144520127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281255248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99576306,0.00016888099,0.0004743299,0.0020425988,0.000120338555,0.0013529563,0.000004340358,0.00001596954,0.000057504498],"genre_scores_gemma":[0.98780704,0.00012494177,0.010184511,0.00084069226,0.00034138272,0.00063648605,0.000016701168,0.00002961543,0.000018626393],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.986498,0.010533755,0.00046085456,0.00049838057,0.0012001133,0.0008089164],"domain_scores_gemma":[0.99044913,0.008642571,0.00010163446,0.00030115893,0.00014876561,0.0003567379],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.019530375,0.0001622889,0.0009095168,0.0008784542,0.00021138508,0.00001325423,0.00026207633,0.00026298343,0.00078696007],"category_scores_gemma":[0.009004111,0.00012988964,0.00006549111,0.001903121,0.00030219078,0.00015215008,0.00041186233,0.0029845259,0.000002790606],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03372076,0.0059303395,0.3262075,0.003097935,0.00010610752,0.0014856186,0.033601172,0.000052048574,0.42005742,0.00082891725,0.00004435049,0.17486785],"study_design_scores_gemma":[0.020125607,0.023097003,0.85406893,0.0014609213,0.000034755994,0.0003086596,0.0064530713,0.051264055,0.04086346,0.0012412227,0.00046933867,0.0006129466],"about_ca_topic_score_codex":0.0074578193,"about_ca_topic_score_gemma":0.0061828247,"teacher_disagreement_score":0.5278615,"about_ca_system_score_codex":0.00036263705,"about_ca_system_score_gemma":0.0013138637,"threshold_uncertainty_score":0.99934345},"labels":[],"label_agreement":null},{"id":"W4281628421","doi":"10.1186/s12874-022-01623-8","title":"Impact of methodological choices in comparative effectiveness studies: application in natalizumab versus fingolimod comparison among patients with multiple sclerosis","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Multiple Sclerosis Research 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":"Cegep de Saint Jerome; Université de Montréal; Hôpital Notre-Dame; Centre intégré de santé et de services sociaux de Chaudière-Appalaches","funders":"National Health and Medical Research Council; Sanofi Genzyme; Agence Nationale de la Recherche; Fondation pour l'Aide à la Recherche sur la Sclérose en Plaques; Teva Pharmaceutical Industries; University of Melbourne; Biogen; Sanofi","keywords":"Fingolimod; Natalizumab; Multiple sclerosis; Medicine; MEDLINE; Comparative effectiveness research; Psychology; Alternative medicine; Psychiatry; Pathology","score_opus":0.749836127004372,"score_gpt":0.6084092258518772,"score_spread":0.1414269011524948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281628421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98967314,0.0009870104,0.005866065,0.000077609555,0.00010187025,0.0031008073,0.000045019107,0.00003177443,0.000116708696],"genre_scores_gemma":[0.98126185,0.00029055928,0.015325949,0.000011216568,0.000049687744,0.0029404105,0.00008499915,0.00002914231,0.0000061585306],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9464277,0.046599016,0.0010616182,0.0010435635,0.00366819,0.0011999181],"domain_scores_gemma":[0.7475597,0.24917705,0.00041884492,0.00087713345,0.0013214691,0.0006457874],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039605986,0.00033868826,0.002447657,0.0013411444,0.00027754492,0.000010376494,0.0006894952,0.00024861237,0.00022464144],"category_scores_gemma":[0.1351271,0.00023883159,0.00021505714,0.0027579647,0.0023611349,0.000114339186,0.0014403738,0.0025444098,0.000005381188],"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":[0.033653703,0.0022420718,0.9483105,0.0005050607,0.0004285861,0.000019075973,0.002437437,0.0016233104,0.0013234953,0.000053147134,0.00006688865,0.009336728],"study_design_scores_gemma":[0.020303113,0.006476106,0.9592491,0.0003962548,0.00002564501,0.00000211343,0.004251819,0.008336591,0.0006744248,0.00006646226,0.00003285825,0.00018552694],"about_ca_topic_score_codex":0.007846794,"about_ca_topic_score_gemma":0.010323385,"teacher_disagreement_score":0.20257804,"about_ca_system_score_codex":0.0018241627,"about_ca_system_score_gemma":0.0010955605,"threshold_uncertainty_score":0.99975675},"labels":[],"label_agreement":null},{"id":"W4281725307","doi":"10.1186/s12874-022-01634-5","title":"A framework to model global, regional, and national estimates of intimate partner violence","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Intimate Partner and Family Violence","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McGill University","funders":"Canada Research Chairs; Department for International Development; Department for International Development, UK Government; World Health Organization","keywords":"Poison control; Domestic violence; Human factors and ergonomics; Suicide prevention; Injury prevention; Occupational safety and health; Psychology; Medicine; Environmental health","score_opus":0.5401399206116029,"score_gpt":0.599624654159439,"score_spread":0.05948473354783612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281725307","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":[0.078319654,0.0016558421,0.8780304,0.0054896795,0.0004135585,0.0008265608,0.000074238305,0.00009851021,0.035091512],"genre_scores_gemma":[0.51577306,0.00082757167,0.48064464,0.0020337221,0.00016432682,0.0003690088,0.00000678156,0.000013396112,0.00016749908],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9879481,0.0069193733,0.00037542338,0.0004682552,0.0035433376,0.0007455053],"domain_scores_gemma":[0.97875535,0.01977083,0.000073821466,0.00022123713,0.00059644575,0.00058230245],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034754936,0.00010822203,0.00034095245,0.00019970199,0.0008638982,0.000026278749,0.0008560497,0.00018330617,0.0010067387],"category_scores_gemma":[0.07559864,0.00010208672,0.000060695642,0.0008646908,0.0019258505,0.000072237024,0.00094918796,0.0006802438,0.000028928278],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020525584,0.000096154276,0.003598368,0.000052205025,0.000014027134,0.000008496254,0.0022665795,0.0012322876,0.00009773353,0.97414166,0.0071693044,0.011117927],"study_design_scores_gemma":[0.0002180723,0.00019987825,0.0041128052,0.00014824347,0.000006857445,0.000014000025,0.0038491047,0.0491585,0.000047961614,0.9367796,0.0053017484,0.00016324034],"about_ca_topic_score_codex":0.001368907,"about_ca_topic_score_gemma":0.00011333362,"teacher_disagreement_score":0.4374534,"about_ca_system_score_codex":0.00018501702,"about_ca_system_score_gemma":0.0031596045,"threshold_uncertainty_score":0.9999065},"labels":[],"label_agreement":null},{"id":"W4281809175","doi":"10.1186/s12874-022-01607-8","title":"The effect of disease co-occurrence measurement on multimorbidity networks: a population-based study","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; Manitoba Health; George & Fay Yee Centre for Healthcare Innovation","funders":"Canadian Institutes of Health Research; Research Manitoba","keywords":"Jaccard index; Centrality; Medicine; Pairwise comparison; Population; Disease; Lift (data mining); Demography; Data mining; Statistics; Environmental health; Computer science; Mathematics; Internal medicine","score_opus":0.5341948394972292,"score_gpt":0.5700290636712829,"score_spread":0.035834224174053686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281809175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.968952,0.0011597226,0.019012097,0.002706674,0.00096421153,0.0063647577,0.00007164733,0.00011560621,0.0006532775],"genre_scores_gemma":[0.9980207,0.000027262797,0.00020928212,0.0001299762,0.0001620864,0.0012524915,0.00012288489,0.000016376562,0.000058921785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9551545,0.036436368,0.0005548023,0.0005758581,0.00656776,0.00071071234],"domain_scores_gemma":[0.9509319,0.047055505,0.00013563069,0.00097515044,0.00021999213,0.0006818233],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0654199,0.0001845168,0.0005384077,0.00026695093,0.0006407634,0.000020206951,0.0006389796,0.00005493124,0.0017990038],"category_scores_gemma":[0.09239069,0.00011857779,0.00018311915,0.00061081117,0.00045176898,0.00002063719,0.00040845212,0.0011365551,0.000010096978],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030352153,0.0029331266,0.8885582,0.0012594848,0.00038248516,0.00042747744,0.00010581907,0.010771341,0.000016844586,0.001583104,0.016763369,0.0468466],"study_design_scores_gemma":[0.012371666,0.015452968,0.88308126,0.0002656631,0.00034088953,0.0000029178516,0.0011912504,0.08171449,0.000051127987,0.00041113855,0.0048594307,0.00025720507],"about_ca_topic_score_codex":0.000373947,"about_ca_topic_score_gemma":0.00020499091,"teacher_disagreement_score":0.07094315,"about_ca_system_score_codex":0.00054868066,"about_ca_system_score_gemma":0.0020059058,"threshold_uncertainty_score":0.9991135},"labels":[],"label_agreement":null},{"id":"W4283123338","doi":"10.1186/s12874-022-01655-0","title":"The implementation and validation of the NoMAD during a complex primary care intervention","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","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":true,"ca_institutions":"McMaster University; McMaster University Medical Centre; Health Sciences Centre","funders":"Ontario Ministry of Health and Long-Term Care","keywords":"Psychological intervention; Normalization (sociology); Health care; Data collection; Psychology; Intervention (counseling); Internal consistency; Medicine; Medical education; Applied psychology; Nursing; Family medicine; Psychometrics; Clinical psychology; Statistics; Mathematics","score_opus":0.9183746440107116,"score_gpt":0.7969143748822352,"score_spread":0.1214602691284764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283123338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98061025,0.00011208438,0.004801454,0.011912341,0.00046669206,0.0014252674,0.00004700517,0.00001525479,0.00060963875],"genre_scores_gemma":[0.9935234,0.00008517628,0.003283761,0.0015012595,0.00014829067,0.0010886372,0.000033604963,0.000011947556,0.00032391225],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9192005,0.076838516,0.00094521866,0.0002679768,0.0020569153,0.0006908711],"domain_scores_gemma":[0.9519052,0.04683039,0.00034699545,0.0003474061,0.00037506048,0.00019495394],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057501737,0.00006502419,0.00018960708,0.00015934525,0.003927768,0.0000085450765,0.0006081111,0.00006470892,0.002367277],"category_scores_gemma":[0.024972463,0.000041199713,0.000050769955,0.000634141,0.0005782885,0.00006182918,0.001639155,0.0010417696,0.000009010499],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011110224,0.0000997444,0.4689267,0.00627591,0.00006178287,0.000005723865,0.14120685,0.000018414077,0.021277044,0.03873978,0.017553113,0.30472392],"study_design_scores_gemma":[0.002450215,0.00025366168,0.7727036,0.00007732314,0.000008285429,0.000012383459,0.17941992,0.000114649745,0.0009900136,0.002167928,0.04172842,0.00007358625],"about_ca_topic_score_codex":0.0016509619,"about_ca_topic_score_gemma":0.00316691,"teacher_disagreement_score":0.30465034,"about_ca_system_score_codex":0.0005330904,"about_ca_system_score_gemma":0.0023664166,"threshold_uncertainty_score":0.9985447},"labels":[],"label_agreement":null},{"id":"W4285391282","doi":"10.1186/s12874-022-01622-9","title":"Does group-based trajectory modeling estimate spurious trajectories?","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","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":"Institut National de la Recherche Scientifique; Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"Spurious relationship; Trajectory; Group (periodic table); Computer science; Statistics; Data mining; Econometrics; Machine learning; Mathematics; Physics","score_opus":0.2969045554887873,"score_gpt":0.4814858611530845,"score_spread":0.1845813056642972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285391282","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063332487,0.00059720676,0.9871492,0.0026497687,0.001873902,0.0004250135,0.000008317417,0.00028454477,0.0006788381],"genre_scores_gemma":[0.0689428,0.000041481715,0.9290143,0.0009164156,0.00034297904,0.00042851528,0.0000087825,0.000038418933,0.0002662965],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9560808,0.03689243,0.00067014026,0.0012915835,0.0035296872,0.0015353413],"domain_scores_gemma":[0.97142154,0.026022242,0.00010166266,0.0013134386,0.0002326207,0.0009085155],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06369945,0.00028009573,0.000701327,0.00065796764,0.0009644847,0.00010108361,0.0034734674,0.00028497892,0.0009789652],"category_scores_gemma":[0.019445995,0.00019071814,0.0002399442,0.0013706571,0.00046963146,0.00018552352,0.0016127077,0.0025888612,0.00001924991],"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":[0.00047970522,0.0006103415,0.00035912337,0.00032818966,0.00006985704,0.0009321039,0.0019797457,0.009021951,0.0032729553,0.4216443,0.0017761455,0.5595256],"study_design_scores_gemma":[0.00084034126,0.0004450204,0.00006278621,0.000023111274,0.0000071517907,0.00007309267,0.00009546171,0.84223056,0.00046383214,0.15191922,0.0035735,0.00026593084],"about_ca_topic_score_codex":0.00050671183,"about_ca_topic_score_gemma":0.000342809,"teacher_disagreement_score":0.8332086,"about_ca_system_score_codex":0.00025086175,"about_ca_system_score_gemma":0.0026931062,"threshold_uncertainty_score":0.99993426},"labels":[],"label_agreement":null},{"id":"W4285727872","doi":"10.1186/s12874-022-01671-0","title":"The effect of high prevalence of missing data on estimation of the coefficients of a logistic regression model when using multiple imputation","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Imputation (statistics); Missing data; Logistic regression; Statistics; Sample size determination; Standard error; Confidence interval; Odds ratio; Standard deviation; Regression analysis; Regression; Mathematics; Econometrics; Computer science","score_opus":0.6698292803895878,"score_gpt":0.6058880685071995,"score_spread":0.06394121188238833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285727872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12358761,0.00007886732,0.8755365,0.00009537364,0.00010416253,0.00045481714,0.00012317646,0.000004076267,0.000015419871],"genre_scores_gemma":[0.4769685,0.000007758658,0.5229844,0.0000028836578,0.0000071834934,0.000012390116,0.000003709184,0.000006991283,0.000006183712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9675858,0.028542843,0.0008865661,0.0003246916,0.0023590554,0.00030104126],"domain_scores_gemma":[0.76621413,0.23189244,0.0006111344,0.0009373021,0.00026448342,0.0000805268],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043075133,0.00010098441,0.0005142501,0.0001202107,0.00023024077,0.0000044872677,0.0012079853,0.00010140765,0.00008210119],"category_scores_gemma":[0.46269643,0.00005302326,0.00006217004,0.000366848,0.0012630068,0.000027757456,0.0011449333,0.000516303,1.5149197e-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":[0.0034475517,0.000515435,0.002067113,0.009433311,0.00007689449,0.000005522563,0.0012020144,0.02675656,0.015604379,0.15853539,0.00029758152,0.78205824],"study_design_scores_gemma":[0.00038230963,0.00043959057,0.00041442522,0.00046221857,0.000037950398,0.000004209525,0.000050972994,0.6871997,0.008083245,0.30289495,6.6982614e-7,0.00002975277],"about_ca_topic_score_codex":0.00021086272,"about_ca_topic_score_gemma":0.0000094873385,"teacher_disagreement_score":0.7820285,"about_ca_system_score_codex":0.0000545993,"about_ca_system_score_gemma":0.00060665124,"threshold_uncertainty_score":0.9853555},"labels":[],"label_agreement":null},{"id":"W4289837592","doi":"10.1186/s12874-022-01682-x","title":"Selecting implementation models, theories, and frameworks in which to integrate intersectional approaches","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"George & Fay Yee Centre for Healthcare Innovation; University of Toronto; University of Manitoba; University of Calgary; University of British Columbia; Université Laval; University of Ottawa; McGill University; University of Waterloo; Public Health Ontario; York University; McMaster University; Research Institute for Aging; St. Michael's Hospital; Ottawa Public Health; Ottawa Hospital","funders":"Research Institute for Aging, University of Waterloo; Canadian Institutes of Health Research","keywords":"Computer science; Usability; Process (computing); Delphi method; Management science; Artificial intelligence; Human–computer interaction","score_opus":0.9470808733350917,"score_gpt":0.7797845680641502,"score_spread":0.16729630527094153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289837592","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":[0.44682252,0.000041027084,0.5112575,0.037940033,0.0005942768,0.0015662209,0.00003068677,0.000045569046,0.0017021489],"genre_scores_gemma":[0.9009733,0.000036924772,0.083390206,0.011692052,0.00031120132,0.0033284489,0.000023663868,0.000023550054,0.00022060155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9269114,0.068107,0.0010169778,0.00063837564,0.0019027628,0.0014234706],"domain_scores_gemma":[0.907605,0.090881914,0.00014861904,0.00025527633,0.00037704917,0.000732173],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13013795,0.00012013461,0.0003421634,0.0009121641,0.0015880944,0.000015274481,0.00049727847,0.00027145472,0.0059251715],"category_scores_gemma":[0.101338446,0.0001095716,0.000021537402,0.002599913,0.00021985506,0.00014502395,0.0013232869,0.005505227,0.000027641006],"study_design_candidate":"qualitative","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":[0.00095124333,0.00009620932,0.10352298,0.000460948,0.000025684765,0.0000138828655,0.23060815,0.00079475093,0.00025427717,0.5162838,0.012377515,0.13461056],"study_design_scores_gemma":[0.0027586627,0.000999667,0.026686758,0.00015216519,0.0000056748277,0.000047887454,0.6137153,0.048501298,0.000048360525,0.27335355,0.033387955,0.00034271376],"about_ca_topic_score_codex":0.006430494,"about_ca_topic_score_gemma":0.05300502,"teacher_disagreement_score":0.45415083,"about_ca_system_score_codex":0.00086088787,"about_ca_system_score_gemma":0.0060697254,"threshold_uncertainty_score":0.9997117},"labels":[],"label_agreement":null},{"id":"W4290851618","doi":"10.1186/s12874-022-01700-y","title":"Predicting the presence of depressive symptoms in the HIV-HCV co-infected population in Canada using supervised machine learning","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Food Security and Health in Diverse Populations","field":"Health Professions","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto General Hospital; Centre hospitalier de l'Université Laval; Vancouver Infectious Diseases Centre; HIV Legal Network; St. Paul's Hospital; University of Ottawa; University of Regina; Centre Hospitalier de l’Université de Montréal; McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Human immunodeficiency virus (HIV); Population; Depressive symptoms; Medicine; Psychology; Psychiatry; Artificial intelligence; Clinical psychology; Virology; Computer science; Environmental health; Anxiety","score_opus":0.5941933774055752,"score_gpt":0.5920993857028686,"score_spread":0.0020939917027066324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290851618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935677,0.00042403367,0.0011245441,0.0026953032,0.0003606506,0.0013846608,0.000070000126,0.000014746449,0.0003583704],"genre_scores_gemma":[0.9979553,0.000063875494,0.0008430915,0.00046565288,0.00012254948,0.00038290131,0.0001169766,0.000014652696,0.00003496594],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9012482,0.09453288,0.00095623935,0.00031291659,0.0020501567,0.00089961995],"domain_scores_gemma":[0.89506316,0.10388136,0.00028672037,0.0003931715,0.00019033796,0.00018527747],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04308407,0.00011415217,0.0004129307,0.0003562934,0.0020661575,0.0000050748104,0.000864682,0.00018278726,0.0017968676],"category_scores_gemma":[0.08694323,0.00007867648,0.00004170398,0.0013215306,0.00023389976,0.00006654128,0.0006879959,0.0055565005,0.0000034649336],"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":[0.0002037062,0.000037649537,0.9726043,0.00024526613,0.000008509577,0.000025958783,0.011844303,0.012125529,0.000027439275,0.0018304331,0.00023055304,0.0008163561],"study_design_scores_gemma":[0.0011095442,0.000105434665,0.57121116,0.00019307788,0.0000074559857,0.00000903892,0.027349796,0.3981651,0.000002942494,0.0008321506,0.0009388686,0.00007542282],"about_ca_topic_score_codex":0.96022415,"about_ca_topic_score_gemma":0.9644405,"teacher_disagreement_score":0.40139312,"about_ca_system_score_codex":0.0011471673,"about_ca_system_score_gemma":0.009150273,"threshold_uncertainty_score":0.999233},"labels":[],"label_agreement":null},{"id":"W4293716275","doi":"10.1186/s12874-022-01716-4","title":"Estimating effects of health policy interventions using interrupted time-series analyses: a simulation study","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"Canada Research Chairs; Mental Health Research Canada; University of Toronto; Public Health Ontario; Centre for Addiction and Mental Health","funders":"National Institute on Alcohol Abuse and Alcoholism; National Institutes of Health","keywords":"Interrupted Time Series Analysis; Robustness (evolution); Econometrics; Autoregressive model; Interrupted time series; Statistics; Series (stratigraphy); Sample size determination; Time series; Psychological intervention; Mathematics; Computer science; Medicine","score_opus":0.945396719550643,"score_gpt":0.746644376024478,"score_spread":0.198752343526165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293716275","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":[0.20743982,0.0018922186,0.78077877,0.0076993406,0.00049706415,0.0014843617,0.00005003035,0.000039088318,0.00011930587],"genre_scores_gemma":[0.7535382,0.00001218873,0.24401394,0.0012450295,0.00037469523,0.00038103803,0.00003835728,0.000043324755,0.00035323144],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.93533885,0.056083657,0.006329334,0.0007596004,0.00067544146,0.0008131365],"domain_scores_gemma":[0.91671216,0.07806727,0.003498349,0.000928801,0.00026038798,0.0005330136],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23484394,0.00014996614,0.0016933477,0.0018504619,0.0006576843,0.000029740062,0.0006094855,0.00011242905,0.002083426],"category_scores_gemma":[0.35875893,0.00018398519,0.0002445314,0.0012055617,0.00029406254,0.00020252858,0.0006914568,0.00070799264,0.0001024659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009743389,0.009568132,0.18569186,0.029545065,0.0024384279,0.00005917412,0.09729327,0.4363878,0.00023592557,0.20649552,0.00797305,0.023337405],"study_design_scores_gemma":[0.0018842376,0.002363532,0.010861829,0.0004630114,0.000015105932,0.000017458375,0.010579116,0.935683,0.0000075914545,0.037128884,0.000743139,0.0002530607],"about_ca_topic_score_codex":0.012463697,"about_ca_topic_score_gemma":0.00046418404,"teacher_disagreement_score":0.54609835,"about_ca_system_score_codex":0.001258328,"about_ca_system_score_gemma":0.0019354055,"threshold_uncertainty_score":0.9988288},"labels":[],"label_agreement":null},{"id":"W4294193234","doi":"10.1186/s12874-022-01713-7","title":"“We’re already doing this work”: ethical research with community-based organizations","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"Centre for Drug Research and Development","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Allergy and Infectious Diseases; National Institute of Mental Health","keywords":"Beneficence; Respect for persons; Public relations; Oppression; Qualitative research; Research ethics; Public health; Ethical code; Sociology; Autonomy; Political science; Medicine; Nursing; Social science; Law; Politics","score_opus":0.9704857685276944,"score_gpt":0.8161102478594268,"score_spread":0.15437552066826765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294193234","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":[0.10745309,0.00010551013,0.30700955,0.5545721,0.0010087736,0.004905238,0.00016587804,0.0004258016,0.024354022],"genre_scores_gemma":[0.3818522,0.00021659932,0.43103525,0.15996613,0.001478429,0.0093202125,0.00035710257,0.00028109414,0.015492987],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.5824107,0.40550107,0.0011428858,0.00060674676,0.0075696823,0.0027689522],"domain_scores_gemma":[0.4279812,0.5649749,0.0002512252,0.0015649825,0.0031809234,0.002046733],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","insufficient_payload"],"category_scores_codex":[0.39514828,0.00021102442,0.00067846687,0.00160159,0.016812073,0.00003624593,0.0027674702,0.0007795191,0.058143314],"category_scores_gemma":[0.34394145,0.00017325698,0.000051794785,0.010449333,0.0030753762,0.00009679424,0.0032912341,0.034888063,0.0012109966],"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":[0.0024231984,0.0008543898,0.07075943,0.0028921254,0.00007705381,0.00023485241,0.21483806,0.0003150542,0.0007595588,0.07159994,0.61857295,0.016673375],"study_design_scores_gemma":[0.0029930302,0.001660165,0.0018524072,0.00040166333,0.000009556326,0.00002143759,0.09898487,0.0007801312,0.00008535508,0.0038025738,0.8891326,0.0002761927],"about_ca_topic_score_codex":0.0063607274,"about_ca_topic_score_gemma":0.010113316,"teacher_disagreement_score":0.394606,"about_ca_system_score_codex":0.0014029905,"about_ca_system_score_gemma":0.038675286,"threshold_uncertainty_score":0.99963766},"labels":[],"label_agreement":null},{"id":"W4297235845","doi":"10.1186/s12874-022-01726-2","title":"Prospective sampling bias in COVID-19 recruitment methods: experimental evidence from a national randomized survey testing recruitment materials","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social 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":"University of Guelph; York University","funders":"","keywords":"Odds; Coronavirus disease 2019 (COVID-19); Context (archaeology); Odds ratio; Psychology; Pandemic; Non-response bias; Medicine; Public health; Survey data collection; Family medicine; Nursing; Logistic regression; Geography","score_opus":0.9749191716954034,"score_gpt":0.7367932862011374,"score_spread":0.23812588549426605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297235845","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":[0.7069563,0.006966831,0.2671184,0.0040263357,0.0032309708,0.010440404,0.00017780234,0.00018530655,0.0008976253],"genre_scores_gemma":[0.13809094,0.00064520125,0.83808786,0.0014659078,0.00066587183,0.020499453,0.00010266237,0.00004971439,0.00039236905],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.072319336,0.9183311,0.0015536804,0.0014672568,0.0048424555,0.0014862001],"domain_scores_gemma":[0.18821578,0.80957615,0.00036330795,0.0003793525,0.0005768926,0.000888503],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.8642145,0.00030155238,0.0016393146,0.0008986464,0.0019126211,0.00010358981,0.0014293314,0.00046055648,0.015226872],"category_scores_gemma":[0.9708612,0.0002703314,0.00018530003,0.0022830265,0.0029968016,0.00021194991,0.0014391744,0.0016961648,0.000030458166],"study_design_candidate":"randomized_trial","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":[0.77217245,0.0014241755,0.064654976,0.00009171303,0.00042411365,0.00032658028,0.08361441,0.00036496855,0.034552526,0.016959932,0.0013655996,0.02404854],"study_design_scores_gemma":[0.17737214,0.0028531924,0.20828244,0.0010490202,0.000121166064,0.00011747306,0.13541295,0.0017367861,0.04278003,0.40580866,0.021858033,0.002608126],"about_ca_topic_score_codex":0.095344104,"about_ca_topic_score_gemma":0.020527234,"teacher_disagreement_score":0.59480035,"about_ca_system_score_codex":0.0034717952,"about_ca_system_score_gemma":0.017480116,"threshold_uncertainty_score":0.9999749},"labels":[],"label_agreement":null},{"id":"W4298003174","doi":"10.1186/s12874-022-01698-3","title":"Item response theory and differential test functioning analysis of the HBSC-Symptom-Checklist across 46 countries","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Mental Health Research Topics","field":"Psychology","cited_by":47,"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; Brock University","funders":"Agencia Estatal de Investigación; Canadian Institutes of Health Research; Ministerstvo Školství, Mládeže a Tělovýchovy; Public Health Agency; Public Health Agency of Canada","keywords":"Differential item functioning; Item response theory; Psychology; Measurement invariance; Clinical psychology; Psychometrics; Feeling; Population; Mental health; Structural equation modeling; Psychiatry; Medicine; Social psychology; Statistics; Confirmatory factor analysis; Mathematics; Environmental health","score_opus":0.37797663509744767,"score_gpt":0.5991301560652694,"score_spread":0.22115352096782176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298003174","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9829769,0.0010421291,0.010565419,0.0027858778,0.0009313863,0.0005886816,0.00019594067,0.000032612235,0.0008810523],"genre_scores_gemma":[0.9833701,0.00011526329,0.0007726209,0.0006394435,0.00021685788,0.0005282842,0.000026957066,0.000033918648,0.014296536],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8818007,0.11185538,0.00081228244,0.0007497113,0.0033826297,0.0013992896],"domain_scores_gemma":[0.7602105,0.2377572,0.00019549899,0.000989763,0.00028305897,0.00056396355],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.123499945,0.0001847275,0.0007382222,0.0006813222,0.0015480592,0.000039821934,0.0011948249,0.000294692,0.030008623],"category_scores_gemma":[0.16255374,0.00013437445,0.00022177173,0.0024087827,0.0033799328,0.000043023923,0.0025022512,0.0024391273,0.000027083792],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.049683765,0.0013318604,0.70231485,0.00067134027,0.0022043358,0.00023331113,0.026050348,0.000035279038,0.0038383063,0.14980175,0.009374831,0.054460037],"study_design_scores_gemma":[0.0018613563,0.0011981388,0.9511934,0.000035130168,0.00015741166,0.000089143294,0.016566213,0.0010664143,0.00026873348,0.0033478935,0.02403669,0.00017947656],"about_ca_topic_score_codex":0.0008843034,"about_ca_topic_score_gemma":0.0011648037,"teacher_disagreement_score":0.24887857,"about_ca_system_score_codex":0.0003123332,"about_ca_system_score_gemma":0.001243273,"threshold_uncertainty_score":0.9998623},"labels":[],"label_agreement":null},{"id":"W4306163964","doi":"10.1186/s12874-022-01739-x","title":"The failure of four bootstrap procedures for estimating confidence intervals for predicted-to-expected ratios for hospital profiling","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Confidence interval; Statistics; Percentile; Medicine; Logistic regression; Intraclass correlation; Econometrics; Mathematics","score_opus":0.6109030780082313,"score_gpt":0.5756935993115068,"score_spread":0.03520947869672453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306163964","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1338693,0.0005904297,0.8284973,0.024096569,0.00051403354,0.01215159,0.00019881962,0.000057317724,0.000024625893],"genre_scores_gemma":[0.27448168,0.000020883639,0.69404775,0.00032572646,0.00046405755,0.030293189,0.00010659835,0.000042987936,0.00021710906],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945744,0.0019847448,0.0007686669,0.000567554,0.0013011509,0.00080345303],"domain_scores_gemma":[0.89934313,0.09839277,0.00020866591,0.00040194517,0.0012357495,0.0004177651],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018060455,0.00017375492,0.00067265227,0.00021536522,0.0006712224,0.000025995225,0.0004903884,0.00015095806,0.00012678863],"category_scores_gemma":[0.30877036,0.00011600303,0.00029209594,0.0003459235,0.00036089894,0.00003406836,0.00025724838,0.00043589924,8.6779653e-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":[0.043585286,0.007418239,0.0725856,0.022192692,0.004992372,0.00013220483,0.016578404,0.0012624018,0.048880737,0.15451668,0.36073145,0.2671239],"study_design_scores_gemma":[0.052131932,0.12875687,0.019707644,0.0040711802,0.0015922127,0.0005472574,0.05781938,0.35422507,0.23130724,0.102833696,0.0454939,0.0015136339],"about_ca_topic_score_codex":0.00003985392,"about_ca_topic_score_gemma":0.0001777235,"teacher_disagreement_score":0.35296267,"about_ca_system_score_codex":0.00015038605,"about_ca_system_score_gemma":0.0024514755,"threshold_uncertainty_score":0.6970522},"labels":[],"label_agreement":null},{"id":"W4306292107","doi":"10.1186/s12874-022-01745-z","title":"Structured expert elicitation to inform long-term survival extrapolations using alternative parametric distributions: a case study of CAR T therapy for relapsed/ refractory multiple myeloma","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MD Precision (Canada)","funders":"Bristol-Myers Squibb","keywords":"Medicine; Survival analysis; Multiple myeloma; Parametric statistics; Expert opinion; Relative survival; Clinical trial; Oncology; Cancer; Statistics; Internal medicine; Intensive care medicine; Mathematics; Cancer registry","score_opus":0.8626325259645461,"score_gpt":0.640686392300954,"score_spread":0.22194613366359206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306292107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7124063,0.0008353611,0.28175968,0.0011618244,0.0006539856,0.0027090698,0.0004330395,0.000019185818,0.000021591339],"genre_scores_gemma":[0.94643486,0.000088728906,0.050677545,0.0004893761,0.00031010213,0.0018031338,0.000119651646,0.000037342943,0.00003927187],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9815291,0.012618575,0.0035720412,0.0007704085,0.0007796845,0.0007301553],"domain_scores_gemma":[0.9169938,0.07999058,0.001274746,0.0006962923,0.0005365356,0.000508018],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08991113,0.00020001075,0.0011622064,0.0016569302,0.0010510489,0.00003763377,0.0006087838,0.00020212581,0.0007870887],"category_scores_gemma":[0.18467765,0.00023140032,0.00016140545,0.0015196457,0.0002272222,0.00024134904,0.00028656787,0.00069654116,0.00001550597],"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":[0.0045826766,0.0058376635,0.65426457,0.0011163286,0.0015257823,0.00029082445,0.17460983,0.0102004,0.0005122912,0.06888396,0.003107336,0.075068325],"study_design_scores_gemma":[0.030912431,0.015521777,0.42344344,0.00018947246,0.00005520692,0.0007503462,0.2825088,0.19413802,0.00021962135,0.035170462,0.015139759,0.0019506721],"about_ca_topic_score_codex":0.011648879,"about_ca_topic_score_gemma":0.004931985,"teacher_disagreement_score":0.2340286,"about_ca_system_score_codex":0.0013131333,"about_ca_system_score_gemma":0.0011648958,"threshold_uncertainty_score":0.99493265},"labels":[],"label_agreement":null},{"id":"W4307560953","doi":"10.1186/s12874-022-01750-2","title":"How can clinicians choose between conflicting and discordant systematic reviews? A replication study of the Jadad algorithm","year":2022,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; McGill University Health Centre; University of Toronto; Ottawa Hospital; University of British Columbia; Nova Scotia Health Authority; Cochrane; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Jadad scale; Replicate; Systematic review; Algorithm; Computer science; Replication (statistics); MEDLINE; Medicine; Data science; Meta-analysis; Mathematics; Statistics; Pathology; Biology","score_opus":0.9851295895639681,"score_gpt":0.7600797078702005,"score_spread":0.2250498816937676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307560953","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":[0.000077142555,0.94819367,0.033124134,0.00059571245,0.0004506984,0.017332658,0.000056460318,0.000006021778,0.00016347936],"genre_scores_gemma":[0.000024668421,0.97651654,0.013370049,0.000061770465,0.0003634244,0.004213157,0.000021473996,0.000050624258,0.0053782943],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.15808973,0.785682,0.027785584,0.0035857868,0.02391986,0.0009370383],"domain_scores_gemma":[0.08181158,0.8622867,0.03091855,0.021814385,0.0020338127,0.0011349783],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8519099,0.00073552056,0.030197857,0.0012444968,0.0006853262,0.00056998536,0.008955227,0.0004487861,0.001974887],"category_scores_gemma":[0.93775105,0.0002734831,0.0041565034,0.0054736473,0.00076063717,0.00008905658,0.0034882617,0.003167944,0.000089992805],"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":[0.0000017518967,0.00009591302,0.00030766998,0.077622,0.00048141243,0.000010191565,0.000641411,5.027409e-8,5.1795702e-8,0.00019679243,0.0011510986,0.91949165],"study_design_scores_gemma":[0.0002249424,0.0002888895,0.000117712436,0.020896712,0.002894444,0.000119986405,0.007312973,0.00022271671,9.63304e-8,0.0006953893,0.9669728,0.00025331674],"about_ca_topic_score_codex":0.00029432078,"about_ca_topic_score_gemma":0.0005625202,"teacher_disagreement_score":0.96582174,"about_ca_system_score_codex":0.00019321057,"about_ca_system_score_gemma":0.0019851262,"threshold_uncertainty_score":0.99997175},"labels":[],"label_agreement":null},{"id":"W4307869843","doi":"10.1186/s12874-022-01754-y","title":"Dementia risk prediction in individuals with mild cognitive impairment: a comparison of Cox regression and machine learning models","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institute on Aging; University of Calgary; Cumming School of Medicine, University of Calgary; Alberta Innovates; Hotchkiss Brain Institute, University of Calgary; National Institutes of Health","keywords":"Proportional hazards model; Random forest; Regression; Artificial intelligence; Machine learning; Statistics; Lasso (programming language); Regression analysis; Support vector machine; Computer science; Gradient boosting; Mathematics","score_opus":0.34836705672947715,"score_gpt":0.50259677529482,"score_spread":0.1542297185653429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307869843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9613433,0.0035011156,0.032173548,0.00039999827,0.00004380846,0.0014913088,0.00007527456,0.000032791515,0.00093884225],"genre_scores_gemma":[0.9888164,0.0009406872,0.009015905,0.000066502216,0.000044478136,0.00055993604,0.00017879576,0.000030445628,0.00034686943],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97261405,0.021358443,0.0007256274,0.00066149916,0.0037921038,0.00084826356],"domain_scores_gemma":[0.98536706,0.013234652,0.0002332711,0.00020922058,0.00040579683,0.0005499773],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03341626,0.00020265205,0.0008061596,0.0011285263,0.00044835976,0.000015918014,0.00022727963,0.00017557305,0.0028347308],"category_scores_gemma":[0.011301234,0.0001524602,0.000076104974,0.001065239,0.00091569516,0.00010118611,0.0009013784,0.0030626373,0.0000042630827],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005109359,0.0011791668,0.96263933,0.00031540103,0.00026222522,0.0000835701,0.0021552288,0.00009406596,0.00024942137,0.0001458524,0.00023970213,0.02752669],"study_design_scores_gemma":[0.019902842,0.018257618,0.8333399,0.0010994523,0.00033361276,0.00021808619,0.018052546,0.103282996,0.0025325431,0.0020730572,0.0006699747,0.0002373385],"about_ca_topic_score_codex":0.00086244027,"about_ca_topic_score_gemma":0.0003287298,"teacher_disagreement_score":0.12929939,"about_ca_system_score_codex":0.00012430362,"about_ca_system_score_gemma":0.0010337158,"threshold_uncertainty_score":0.99923736},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","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":"W4308713184","doi":"10.1186/s12874-022-01776-6","title":"Minimal important difference and patient acceptable symptom state for common outcome instruments in patients with a closed humeral shaft fracture - analysis of the FISH randomised clinical trial data","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Bone fractures and treatments","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Dash; Medicine; Physical therapy; Minimal clinically important difference; Receiver operating characteristic; Patient satisfaction; Percentile; Randomized controlled trial; Physical medicine and rehabilitation; Surgery; Internal medicine","score_opus":0.3783926968726709,"score_gpt":0.5371623056971896,"score_spread":0.15876960882451868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308713184","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99444216,0.00007323761,0.0002749957,0.0010497151,0.00018305605,0.003389714,0.0005691003,0.000007556348,0.000010460855],"genre_scores_gemma":[0.99398476,0.00004257362,0.0037282312,0.0010534159,0.000036258993,0.00036846226,0.00069910474,0.00002173071,0.00006544223],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98681575,0.008218732,0.0015188996,0.0007456302,0.0020828187,0.00061814644],"domain_scores_gemma":[0.980236,0.01756441,0.000494825,0.0011261031,0.00016131779,0.00041736718],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012303009,0.00021113013,0.0016447427,0.0003536075,0.0002112067,0.000016557224,0.0006956388,0.00020089641,0.0005621972],"category_scores_gemma":[0.020155488,0.00011643102,0.000245846,0.0007826994,0.00054028106,0.0000521996,0.001301818,0.0013009048,1.9230488e-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":[0.21496728,0.0014803088,0.7614612,0.000043751905,0.0009535836,0.000016459962,0.00021374763,0.0000064955357,0.0000029305277,0.0000058877217,0.00026553092,0.020582844],"study_design_scores_gemma":[0.18426254,0.004283603,0.80716765,0.000028932407,0.00062672165,0.000002261087,0.00013741263,0.0027112423,0.000010595627,0.00010949143,0.00057234603,0.000087199216],"about_ca_topic_score_codex":0.0009907784,"about_ca_topic_score_gemma":0.0018861766,"teacher_disagreement_score":0.045706477,"about_ca_system_score_codex":0.00010522452,"about_ca_system_score_gemma":0.00087902776,"threshold_uncertainty_score":0.98809814},"labels":[],"label_agreement":null},{"id":"W4309562528","doi":"10.1186/s12874-022-01747-x","title":"A systematic review and psychometric evaluation of resilience measurement scales for people living with dementia and their carers","year":2022,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Resilience and Mental Health","field":"Psychology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"Economic and Social Research Council; Bangor University; University College London; Department of Health and Social Care; UK Research and Innovation; National Institute for Health and Care Research; Nipissing University","keywords":"Dementia; Checklist; Scale (ratio); Psychological intervention; Psychology; Clinical psychology; Construct validity; MEDLINE; Psychometrics; Gerontology; Reliability (semiconductor); Medicine; Psychiatry","score_opus":0.7100605968917391,"score_gpt":0.6367539961900424,"score_spread":0.0733066007016967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309562528","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":[0.00006939001,0.9833392,0.0067600966,0.00006277395,0.000187597,0.009244944,0.000021413203,0.000011587621,0.00030300856],"genre_scores_gemma":[0.00018523673,0.98822623,0.0024449364,0.00007545686,0.000042249158,0.008915823,0.000014610642,0.000038930535,0.00005651168],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9287932,0.063553415,0.0016354256,0.0011326998,0.003975736,0.0009095348],"domain_scores_gemma":[0.93913364,0.05814594,0.00071808475,0.0008256226,0.0006657056,0.00051097927],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18042086,0.00033994656,0.003609547,0.0009800153,0.00026984987,0.000016713673,0.00070706115,0.00031328146,0.00086500717],"category_scores_gemma":[0.09232605,0.00020611228,0.00020897597,0.0017629632,0.0006146985,0.000046185658,0.0003234483,0.00082181284,0.0000045774723],"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":[0.000021513599,0.000069751295,0.000053276355,0.5833501,0.00023871561,5.560311e-7,0.00037670115,4.3173873e-8,1.468405e-7,0.0001938913,0.00019445055,0.41550085],"study_design_scores_gemma":[0.0016184606,0.0036589135,0.00074175914,0.937271,0.008867663,0.0008019019,0.010195063,0.000080044774,6.843203e-7,0.00038608967,0.03572002,0.0006584009],"about_ca_topic_score_codex":0.00026013737,"about_ca_topic_score_gemma":0.0010503172,"teacher_disagreement_score":0.41484243,"about_ca_system_score_codex":0.00034825032,"about_ca_system_score_gemma":0.002789223,"threshold_uncertainty_score":0.9471222},"labels":[],"label_agreement":null},{"id":"W4312065798","doi":"10.1186/s12874-022-01814-3","title":"Personalized prediction of incident hospitalization for cardiovascular disease in patients with hypertension using machine learning","year":2022,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"","keywords":"Brier score; Medicine; Logistic regression; Random forest; Proportional hazards model; Hazard ratio; Concordance; Stroke (engine); Cohort; Time point; Population; Internal medicine; Statistics; Machine learning; Confidence interval; Computer science; Mathematics","score_opus":0.2933902624515831,"score_gpt":0.43473393662328214,"score_spread":0.14134367417169902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312065798","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":[0.40634307,0.0007071573,0.5919786,0.0002212569,0.00014408873,0.00056644325,0.000009102433,0.00002804453,0.0000022293577],"genre_scores_gemma":[0.82079375,0.00003994886,0.17870525,0.00006643858,0.000053493433,0.00021010016,0.00008846181,0.000022598217,0.000019942347],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.977139,0.018458048,0.00040878265,0.0005750826,0.0029519452,0.00046712265],"domain_scores_gemma":[0.9921647,0.00637717,0.00012997951,0.00048437144,0.00054261624,0.00030120893],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024055177,0.000112802925,0.00042500542,0.00050945266,0.00037202748,0.000014184755,0.0006406393,0.00011149065,0.00006884004],"category_scores_gemma":[0.038312778,0.00009738024,0.00014999139,0.0009216327,0.00018146248,0.00011450716,0.00076569756,0.0011599226,4.5503592e-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":[0.0007485738,0.00017104825,0.905215,0.00032603994,0.000054104075,0.000026331958,0.00066844263,0.0795262,0.000021324018,0.0028373485,0.000012098994,0.010393442],"study_design_scores_gemma":[0.0021601054,0.0008875824,0.1711026,0.00006497366,0.000015661408,0.00000661246,0.00008596213,0.82416046,0.0000060422235,0.00062994997,0.00080057484,0.00007946248],"about_ca_topic_score_codex":0.002123045,"about_ca_topic_score_gemma":0.000053091804,"teacher_disagreement_score":0.7446343,"about_ca_system_score_codex":0.00028220756,"about_ca_system_score_gemma":0.0010603013,"threshold_uncertainty_score":0.9697879},"labels":[],"label_agreement":null},{"id":"W4313703179","doi":"10.1186/s12874-022-01831-2","title":"Estimation of marginal structural models under irregular visits and unmeasured confounder: calibrated inverse probability weights","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Confounding; Observational study; Marginal structural model; Estimator; Glycemic; Medicine; Statistics; Inverse probability; Longitudinal study; Monte Carlo method; Calibration; Inverse probability weighting; Randomized controlled trial; Econometrics; Computer science; Mathematics; Diabetes mellitus; Bayesian probability; Internal medicine","score_opus":0.7798766947382557,"score_gpt":0.5947207635660053,"score_spread":0.18515593117225038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313703179","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3753149,0.000037254977,0.6232016,0.00044195002,0.000049018883,0.0005284,0.0000067809956,0.00022323716,0.000196883],"genre_scores_gemma":[0.4297306,0.00006712979,0.5698603,0.000040296447,0.000037865837,0.00008142485,0.000021571512,0.000027666001,0.00013315916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9877417,0.008761687,0.00063662935,0.00049859064,0.0016888002,0.0006725595],"domain_scores_gemma":[0.96807706,0.030363316,0.00014633597,0.00050878845,0.0004985335,0.00040597952],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020320874,0.00019161166,0.00063646014,0.00038242977,0.00013573172,0.000020278481,0.0003872199,0.0004698354,0.0002839224],"category_scores_gemma":[0.054469276,0.00015233355,0.00006313368,0.00082882465,0.001466495,0.0002478535,0.00040339553,0.0007541001,0.000008911481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026516482,0.000040366027,0.00035300964,0.0007649652,0.000044923232,0.00002184898,0.00042446697,0.00051009696,0.002336495,0.9833229,0.0005682032,0.011347547],"study_design_scores_gemma":[0.000367619,0.00012963655,0.0011053269,0.00009193949,0.000010633757,0.000019876108,0.0001708076,0.26761204,0.0036501857,0.72673416,0.000010464099,0.000097298216],"about_ca_topic_score_codex":0.00014548127,"about_ca_topic_score_gemma":0.0003149979,"teacher_disagreement_score":0.26710194,"about_ca_system_score_codex":0.00012604364,"about_ca_system_score_gemma":0.000912244,"threshold_uncertainty_score":0.9534953},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4315652506","doi":"10.1186/s12874-023-01832-9","title":"The reporting of prognostic prediction models for obstetric care was poor: a cross-sectional survey of 10-year publications","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Maternal and fetal healthcare","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":"McMaster University; St. Joseph’s Healthcare Hamilton","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; China Medical Board","keywords":"Cross-sectional study; Medicine; MEDLINE; Family medicine; Environmental health; Political science; Pathology","score_opus":0.7874685010241187,"score_gpt":0.6172829596447352,"score_spread":0.17018554137938346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315652506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96765125,0.0012211868,0.026147025,0.0010215979,0.0005610962,0.0018088893,0.00029954212,0.00009538596,0.0011940086],"genre_scores_gemma":[0.9886618,0.00027865465,0.0071888813,0.000017278307,0.0002128482,0.0004295095,0.0003925756,0.000022030648,0.0027964164],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99189806,0.0035477804,0.0018036679,0.00037800835,0.0017997507,0.00057273515],"domain_scores_gemma":[0.9240084,0.069020316,0.00068416947,0.00046742958,0.005387409,0.0004322479],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04812237,0.00008983393,0.00046603064,0.00045665048,0.00027703997,0.000014647784,0.00028980756,0.0003016336,0.000135437],"category_scores_gemma":[0.4974531,0.000058234353,0.00014213652,0.001574326,0.00065359985,0.000041742587,0.00018915723,0.0005068929,0.0000099541985],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011627667,0.00006591154,0.97715,0.0023801646,0.00005099443,0.0000060037823,0.00022528604,0.00004092978,0.00028939173,0.00354327,0.0006656777,0.014419609],"study_design_scores_gemma":[0.000739235,0.0006853239,0.9775117,0.00011883542,0.000010121081,0.000044278408,0.00054608315,0.015946548,0.00042307304,0.00334653,0.00058791274,0.000040327945],"about_ca_topic_score_codex":0.0011842729,"about_ca_topic_score_gemma":0.0007170835,"teacher_disagreement_score":0.44933072,"about_ca_system_score_codex":0.00008876258,"about_ca_system_score_gemma":0.0025254847,"threshold_uncertainty_score":0.9801583},"labels":[],"label_agreement":null},{"id":"W4317606040","doi":"10.1186/s12874-022-01789-1","title":"A cross-sectional study of the endorsement proportion of reporting guidelines in 1039 Chinese medical journals","year":2023,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","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":"Ottawa Hospital","funders":"Key Technologies Research and Development Program","keywords":"Cross-sectional study; Medicine; MEDLINE; Family medicine; Environmental health; Psychology; Political science; Pathology","score_opus":0.991251187517015,"score_gpt":0.8243993395495102,"score_spread":0.16685184796750485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317606040","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":[0.029928705,0.9524243,0.009283975,0.00038622838,0.0017260915,0.005892733,0.000018220528,0.000007765376,0.00033196737],"genre_scores_gemma":[0.00071962224,0.98409474,0.00827412,0.000039051905,0.0009726522,0.0009225578,0.000011563082,0.00005678896,0.004908907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.075502194,0.6445603,0.15495855,0.003577757,0.11989103,0.0015101894],"domain_scores_gemma":[0.1231055,0.70751584,0.1288003,0.013520313,0.025207845,0.0018502135],"candidate_categories":["metaresearch","metaepi_broad","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.930966,0.00052666845,0.017576247,0.0029309588,0.00021360516,0.00019874501,0.007534545,0.0010667029,0.025423927],"category_scores_gemma":[0.9883575,0.00018613948,0.0049351235,0.009971048,0.000939706,0.000088005836,0.0027642874,0.0030248482,0.00022100715],"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":[0.000024016586,0.00045475524,0.35947445,0.011266132,0.0006530508,0.00016492578,0.00024008904,0.000017316206,0.0000013671838,0.00019765344,0.0023118097,0.62519443],"study_design_scores_gemma":[0.002527096,0.0011250277,0.32082137,0.052682873,0.0013171007,0.0018494551,0.003042247,0.004670788,0.0000027358153,0.020002658,0.5909973,0.0009613637],"about_ca_topic_score_codex":0.0007547074,"about_ca_topic_score_gemma":0.004571254,"teacher_disagreement_score":0.62423307,"about_ca_system_score_codex":0.00015856492,"about_ca_system_score_gemma":0.00827414,"threshold_uncertainty_score":0.9992752},"labels":[],"label_agreement":null},{"id":"W4317907993","doi":"10.1186/s12874-022-01829-w","title":"Comparison of State-of-the-Art Neural Network Survival Models with the Pooled Cohort Equations for Cardiovascular Disease Risk Prediction","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"U.S. National Library of Medicine; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Proportional hazards model; Cohort; Pooling; Survival analysis; Artificial neural network; Medicine; Nomogram; Framingham Risk Score; Disease; Statistics; Computer science; Artificial intelligence; Internal medicine; Mathematics","score_opus":0.7636271820778228,"score_gpt":0.6357989451054679,"score_spread":0.1278282369723549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317907993","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":[0.2280747,0.0007949421,0.76142573,0.0040293685,0.0012539225,0.0040900856,0.00017336656,0.000068797206,0.00008910667],"genre_scores_gemma":[0.98900324,0.00041347716,0.0067716492,0.00010384206,0.00075634144,0.0023060571,0.00008150855,0.000051598574,0.0005122823],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.94468313,0.049989372,0.0011352584,0.00045220894,0.0026556945,0.0010843137],"domain_scores_gemma":[0.86498404,0.1317859,0.0003204928,0.0010230661,0.0014346237,0.0004519161],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07599111,0.00014649659,0.0007827501,0.00015405829,0.0014795113,0.0000048278766,0.00078060676,0.00026901273,0.00010753298],"category_scores_gemma":[0.0966256,0.00008313239,0.00036449733,0.0013936507,0.0012904775,0.00006222606,0.00044682415,0.0019292324,0.000030701758],"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":[0.0016057213,0.000070545735,0.5436463,0.00079842727,0.0004693371,0.0000027618185,0.002844412,0.41350234,0.000011509376,0.010406365,0.01002935,0.016612979],"study_design_scores_gemma":[0.00033942814,0.00027532308,0.04640828,0.0002421615,0.00022007833,3.2275645e-7,0.00403111,0.9108672,0.000034394172,0.035580404,0.0019202634,0.00008101523],"about_ca_topic_score_codex":0.0031064693,"about_ca_topic_score_gemma":0.010017792,"teacher_disagreement_score":0.7609285,"about_ca_system_score_codex":0.00011557081,"about_ca_system_score_gemma":0.0033526942,"threshold_uncertainty_score":0.9998204},"labels":[],"label_agreement":null},{"id":"W4318215161","doi":"10.1186/s12874-023-01840-9","title":"Towards full clinical trial registration and results publication: longitudinal meta-research study in Northwestern and Central Switzerland","year":2023,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","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; Impact","funders":"Northwestern University","keywords":"Clinical trial; Medicine; Trial registration; MEDLINE; Family medicine; Physical therapy; Internal medicine","score_opus":0.9847166086486041,"score_gpt":0.7969415423985603,"score_spread":0.1877750662500438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318215161","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":[0.0050331173,0.96467036,0.0007823836,0.010322551,0.0010790143,0.01632635,0.00011240275,0.00014402099,0.0015297774],"genre_scores_gemma":[0.0002487523,0.98370767,0.005914029,0.00006748619,0.0028253146,0.002438472,0.00027736637,0.00014126678,0.0043796524],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.63166475,0.30003467,0.019185353,0.009746493,0.032349646,0.0070190607],"domain_scores_gemma":[0.101266794,0.88189244,0.0013238267,0.004153765,0.0058348994,0.005528269],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.55686057,0.00073912495,0.0074577276,0.0029608572,0.0004283323,0.00035658805,0.0017842609,0.004942576,0.00043897465],"category_scores_gemma":[0.8589649,0.0005066556,0.00091197167,0.004048714,0.00634958,0.00016621384,0.0035303354,0.02823665,0.00016463963],"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":[0.045011133,0.00308527,0.0044202744,0.031404063,0.0029583196,0.002765162,0.0006371751,7.925409e-8,1.6489457e-7,0.0043205745,0.0031106838,0.9022871],"study_design_scores_gemma":[0.13519546,0.05260094,0.036331795,0.022632895,0.0063353945,0.001353336,0.0027860831,0.00023473505,4.8670285e-7,0.021521416,0.71936667,0.0016408033],"about_ca_topic_score_codex":0.0036781821,"about_ca_topic_score_gemma":0.07092176,"teacher_disagreement_score":0.90064627,"about_ca_system_score_codex":0.00048312452,"about_ca_system_score_gemma":0.026802944,"threshold_uncertainty_score":0.9997385},"labels":[],"label_agreement":null},{"id":"W4319295079","doi":"10.1186/s12874-023-01857-0","title":"The empirical estimate of the survival and variance using a weighted composite endpoint","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; Alberta Health; University of Alberta; Alberta Health Services","funders":"","keywords":"Confidence interval; Statistics; Variance (accounting); Estimator; Sample size determination; Medicine; Event (particle physics); Clinical endpoint; Survival analysis; Point estimation; Treatment effect; Delta method; Proportional hazards model; Clinical trial; Mathematics; Econometrics; Internal medicine","score_opus":0.9708732306564802,"score_gpt":0.7604618313884888,"score_spread":0.21041139926799146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319295079","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":[0.16823545,0.00015366173,0.82220864,0.0066461167,0.0013226193,0.0007428986,0.000034244007,0.00008243121,0.00057394843],"genre_scores_gemma":[0.0068236035,0.00023112915,0.9922109,0.00009487886,0.0003259696,0.000051298965,6.518591e-7,0.00003684752,0.0002246748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9039505,0.09013951,0.0014327919,0.00059224904,0.0028267356,0.0010581759],"domain_scores_gemma":[0.32571745,0.672659,0.0002052191,0.0007393601,0.0003174675,0.0003614952],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16124527,0.0001763382,0.00093803176,0.00012338332,0.00051599863,0.00003772916,0.0011355747,0.00044820568,0.00023160534],"category_scores_gemma":[0.83763784,0.000088812114,0.00016863825,0.0012975839,0.004029886,0.000024031679,0.0017054159,0.0016379332,0.000020584344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016215269,0.00023689169,0.012352036,0.00089113583,0.0002609105,0.00011043684,0.0006798725,0.000008954174,0.0038554464,0.9103391,0.00456429,0.06507937],"study_design_scores_gemma":[0.00074431166,0.000107878055,0.012482116,0.00015823291,0.00004049398,0.000025114876,0.00026296437,0.0301245,0.0007322822,0.95451665,0.00070844655,0.00009698262],"about_ca_topic_score_codex":0.000073152834,"about_ca_topic_score_gemma":0.000080621256,"teacher_disagreement_score":0.67639256,"about_ca_system_score_codex":0.000051461593,"about_ca_system_score_gemma":0.00082622626,"threshold_uncertainty_score":0.9986806},"labels":[],"label_agreement":null},{"id":"W4321236346","doi":"10.1186/s12874-023-01836-5","title":"The iterative bisection procedure: a useful tool for determining parameter values in data-generating processes in Monte Carlo simulations","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Monte Carlo method; Bisection method; Statistic; Computer science; Binary data; Statistics; Covariate; Outcome (game theory); Range (aeronautics); Population; Binary number; Algorithm; Mathematics; Medicine","score_opus":0.8555054034787316,"score_gpt":0.6606382105781666,"score_spread":0.19486719290056498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321236346","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5783565,0.000109629786,0.4190492,0.00060926296,0.00008751546,0.0015658645,0.000027102562,0.00017656104,0.000018331673],"genre_scores_gemma":[0.4185896,0.00020842861,0.5782978,0.0000770868,0.00022067512,0.0022542467,0.000035626355,0.00004987934,0.0002666761],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908614,0.0060142796,0.0007909164,0.000623996,0.0008719446,0.0008374363],"domain_scores_gemma":[0.7321366,0.2664387,0.00014315035,0.00065070984,0.00051164086,0.00011917811],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03070352,0.00016625876,0.0004273785,0.00049659424,0.0003117763,0.000080671,0.0007357278,0.00027433806,0.000017285738],"category_scores_gemma":[0.6500702,0.0001166856,0.000035499077,0.0015643189,0.00038586243,0.00031511724,0.0005344006,0.00084933254,0.0000031509953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004582591,0.0016834002,0.17523198,0.015504413,0.0004466696,0.0005946833,0.08355367,0.025599549,0.025734518,0.07116593,0.022701852,0.57320076],"study_design_scores_gemma":[0.000637349,0.00027026315,0.00087369944,0.00049965776,0.000009275948,0.000012507534,0.001830683,0.621897,0.0029162902,0.37038344,0.00046393307,0.00020592149],"about_ca_topic_score_codex":0.000058892812,"about_ca_topic_score_gemma":0.013644459,"teacher_disagreement_score":0.6193667,"about_ca_system_score_codex":0.00013269972,"about_ca_system_score_gemma":0.0012410516,"threshold_uncertainty_score":0.9980947},"labels":[],"label_agreement":null},{"id":"W4322741260","doi":"10.1186/s12874-023-01875-y","title":"Exploring data reduction strategies in the analysis of continuous pressure imaging technology","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Pressure Ulcer Prevention and Management","field":"Health Professions","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 Alberta; Alberta Health Services; Alberta Health; Foothills Medical Centre; Libin Cardiovascular Institute of Alberta; University of Calgary","funders":"Alberta Innovates; Alberta Innovates - Health Solutions","keywords":"Computer science; Reduction (mathematics); Medicine; Data science; Medical physics; Data mining; Mathematics","score_opus":0.8783758602578795,"score_gpt":0.6749957086587656,"score_spread":0.20338015159911393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322741260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44299978,0.004463622,0.42563355,0.08432322,0.004135864,0.007068947,0.00013636735,0.0010478197,0.030190835],"genre_scores_gemma":[0.98425597,0.0027343398,0.009540916,0.00017892344,0.00030230355,0.0012307192,0.00018544866,0.000023481929,0.0015479218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9655172,0.031109205,0.0007635972,0.0005328514,0.0012682455,0.0008088943],"domain_scores_gemma":[0.9767681,0.021385094,0.00015697558,0.0013485395,0.00024093024,0.00010037079],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08732774,0.000096071046,0.00053641037,0.002577127,0.00028570037,0.0000105414265,0.0017684456,0.00020031657,0.00084881164],"category_scores_gemma":[0.04242916,0.00006764686,0.00006685707,0.005569364,0.00052555953,0.00027909878,0.0018674603,0.0015903723,0.000057644724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065820426,0.0004958398,0.08173959,0.003321059,0.002659309,0.00028528395,0.02757005,0.0009347386,0.0033082515,0.4704537,0.07249812,0.33607584],"study_design_scores_gemma":[0.0018937197,0.000110469045,0.23858607,0.00046954214,0.0008692383,0.000008617581,0.44763172,0.03774036,0.0000742542,0.036500797,0.23584709,0.00026811846],"about_ca_topic_score_codex":0.0015566075,"about_ca_topic_score_gemma":0.003247805,"teacher_disagreement_score":0.5412562,"about_ca_system_score_codex":0.000027214814,"about_ca_system_score_gemma":0.00069828815,"threshold_uncertainty_score":0.96563685},"labels":[],"label_agreement":null},{"id":"W4324019806","doi":"10.1186/s12874-023-01884-x","title":"Measuring the impact of zero-cases studies in evidence synthesis practice using the harms index and benefits index (Hi-Bi)","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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 Alberta","funders":"Medical Research Council; Anhui Medical University; National Health and Medical Research Council; National Natural Science Foundation of China","keywords":"Meta-analysis; Index (typography); Measure (data warehouse); Computer science; Statistics; Medicine; Sensitivity (control systems); Systematic review; MEDLINE; Mathematics; Data mining; Pathology","score_opus":0.9903611485543717,"score_gpt":0.7623216590357637,"score_spread":0.22803948951860809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324019806","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":[0.9409059,0.024064967,0.028711932,0.0049524144,0.00019248316,0.0010020245,0.0000048350516,0.000006630895,0.0001587756],"genre_scores_gemma":[0.9882629,0.0055792867,0.005599418,0.00010057349,0.00011175386,0.00013843566,1.7777846e-7,0.000013816918,0.00019361747],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.37977383,0.5778868,0.010664054,0.0021251447,0.027908638,0.001641523],"domain_scores_gemma":[0.027151614,0.96411866,0.002157132,0.0030155017,0.0031914872,0.00036558145],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7699918,0.0002572579,0.0031092663,0.0010969851,0.00041655885,0.00026550074,0.0030803042,0.00021157722,0.00110458],"category_scores_gemma":[0.9801254,0.00008580275,0.000753708,0.005717074,0.0018088226,0.00033719325,0.0016346413,0.0010214671,0.00012024419],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088545214,0.00018311646,0.67118603,0.00089846895,0.0020927242,0.00031489687,0.012602785,0.01015544,0.00060451106,0.002403986,0.018131783,0.28054082],"study_design_scores_gemma":[0.0009602337,0.00050023856,0.58432144,0.0036440426,0.00063977315,0.0009528124,0.09778817,0.26243293,0.00049769715,0.045650218,0.002056619,0.0005557994],"about_ca_topic_score_codex":0.0017589254,"about_ca_topic_score_gemma":0.0010617205,"teacher_disagreement_score":0.38623187,"about_ca_system_score_codex":0.00010908812,"about_ca_system_score_gemma":0.0011064156,"threshold_uncertainty_score":0.99980855},"labels":[],"label_agreement":null},{"id":"W4327680206","doi":"10.1186/s12874-023-01880-1","title":"Correction to: A tutorial on pilot studies: the what, why and how","year":2023,"lang":"en","type":"erratum","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","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":"GlaxoSmithKline (Canada); St. Joseph’s Healthcare Hamilton; University of Waterloo; McMaster University","funders":"","keywords":"Data science; Computer science; MEDLINE; Information retrieval; Medicine; Medical education; Psychology; Medical physics; Chemistry","score_opus":0.9722560890743455,"score_gpt":0.8181243184953788,"score_spread":0.15413177057896665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327680206","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033310778,0.00087551697,0.008177029,0.5045506,0.4767003,0.0046482603,0.00005143654,0.00020960302,0.0044541713],"genre_scores_gemma":[0.000061220664,0.03400151,0.004758109,0.13869399,0.0630076,0.007624262,0.00006404321,0.00018629034,0.751603],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8417327,0.14792979,0.0011196829,0.0012306446,0.0053776954,0.0026094932],"domain_scores_gemma":[0.35855123,0.6362936,0.00045359414,0.0011073612,0.0017363692,0.0018578388],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.2147877,0.00034583043,0.0011661407,0.0010873394,0.002821073,0.00010129977,0.0013565599,0.0010153839,0.0010219235],"category_scores_gemma":[0.83798015,0.00021725318,0.000082076214,0.0022168844,0.0016567615,0.0001609608,0.0018505444,0.011115169,0.0015816469],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031419925,0.000014310401,0.000035748773,0.00078950747,0.000036769205,0.000016913535,0.009786725,2.730341e-7,0.000005666174,0.0010970004,0.9709134,0.01698945],"study_design_scores_gemma":[0.0007280001,0.0016762763,0.0005839087,0.0021879757,0.000012594106,0.000006325365,0.03697581,0.00012204098,0.000001621152,0.0019417749,0.95560324,0.00016045624],"about_ca_topic_score_codex":0.0026814945,"about_ca_topic_score_gemma":0.042115226,"teacher_disagreement_score":0.7471488,"about_ca_system_score_codex":0.0009943323,"about_ca_system_score_gemma":0.01734952,"threshold_uncertainty_score":0.9998913},"labels":[],"label_agreement":null},{"id":"W4327738676","doi":"10.1186/s12874-023-01871-2","title":"Accounting for complex intracluster correlations in longitudinal cluster randomized trials: a case study in malaria vector control","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Public Health; Ottawa Hospital","funders":"Medical Research Council","keywords":"Statistics; Correlation; Estimator; Generalized least squares; Cluster randomised controlled trial; Econometrics; Cluster (spacecraft); Generalized estimating equation; Mathematics; Computer science; Medicine; Randomized controlled trial; Surgery","score_opus":0.802471853529521,"score_gpt":0.6469527604550042,"score_spread":0.15551909307451683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327738676","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":[0.068728976,0.000025913578,0.9229624,0.0019702984,0.0003684193,0.005757551,0.000034836492,0.000055247743,0.000096348784],"genre_scores_gemma":[0.3584766,0.0000094964025,0.63862085,0.00009430549,0.00029343093,0.0024121152,0.000007834968,0.000032014283,0.00005332108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85433984,0.13869224,0.0030585132,0.00089062506,0.0015495868,0.0014692119],"domain_scores_gemma":[0.34429255,0.6545409,0.0002241834,0.00034057672,0.00033720228,0.0002645617],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3306481,0.0002403896,0.0028233053,0.0010828661,0.00018700575,0.0000739678,0.0004339905,0.00042353183,0.0012446307],"category_scores_gemma":[0.8623795,0.00017610673,0.0002530208,0.0013076471,0.0006610781,0.00008255622,0.00030122747,0.0013984961,0.00003597981],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14260946,0.0024567784,0.05125694,0.0016875064,0.0005618384,0.0116104465,0.008350207,0.000057304063,0.00014687028,0.6697592,0.006489732,0.10501373],"study_design_scores_gemma":[0.14788704,0.0003243323,0.010612024,0.00017404047,0.0001100865,0.00027524246,0.0039252187,0.32688063,0.000002274877,0.5095675,0.00003357096,0.00020802591],"about_ca_topic_score_codex":0.0012461737,"about_ca_topic_score_gemma":0.010400758,"teacher_disagreement_score":0.53173137,"about_ca_system_score_codex":0.00013154508,"about_ca_system_score_gemma":0.00072320324,"threshold_uncertainty_score":0.99966836},"labels":[],"label_agreement":null},{"id":"W4360615590","doi":"10.1186/s12874-023-01869-w","title":"A method for generating synthetic longitudinal health data","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":40,"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 Alberta; Institute of Health Economics; University of Ottawa; Alberta Health Services; Children's Hospital of Eastern Ontario","funders":"Alberta Innovates; Canadian Institutes of Health Research; Mitacs; University of Alberta; Natural Sciences and Engineering Research Council of Canada; Bill and Melinda Gates Foundation; Alberta Health Services; Government of Alberta; Canada Research Chairs","keywords":"Computer science; Data science; MEDLINE; Longitudinal data; Medicine; Data mining; Political science","score_opus":0.7741157892627596,"score_gpt":0.6289102418895228,"score_spread":0.14520554737323677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360615590","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017265687,0.00017731418,0.9689737,0.011362255,0.00020647414,0.0011562649,0.000053311927,0.00011200303,0.00069301814],"genre_scores_gemma":[0.006265098,0.00063899707,0.9889646,0.0020650458,0.00044985436,0.000450028,0.00015172736,0.000063035004,0.00095159595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.965765,0.026992163,0.00075084675,0.001917642,0.0024034672,0.0021708652],"domain_scores_gemma":[0.9182864,0.07887688,0.00014022787,0.0014561345,0.000030061588,0.0012103011],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.18072572,0.0001998558,0.0005699456,0.00023699329,0.0007612493,0.000032811746,0.0016197154,0.00025718258,0.0037310536],"category_scores_gemma":[0.13145694,0.00017650258,0.00007813685,0.0010198832,0.000927912,0.00015882598,0.0031564329,0.0010600989,0.0015349515],"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":[0.00009088717,0.000099274715,0.0077884854,0.00026106794,0.000027132735,0.000064300235,0.00058248127,0.00041586003,0.002538879,0.0006881816,0.03377832,0.95366514],"study_design_scores_gemma":[0.0015744937,0.0007079173,0.031232897,0.00020217925,0.000022232194,0.00014307228,0.001576325,0.7780334,0.0007040044,0.010015486,0.17529011,0.0004979204],"about_ca_topic_score_codex":0.0024484228,"about_ca_topic_score_gemma":0.002681086,"teacher_disagreement_score":0.9531672,"about_ca_system_score_codex":0.00039163107,"about_ca_system_score_gemma":0.0009931108,"threshold_uncertainty_score":0.9992425},"labels":[],"label_agreement":null},{"id":"W4362609558","doi":"10.1186/s12874-023-01902-y","title":"Development of a risk-tailored approach and dashboard for efficient management and monitoring of investigator-initiated trials","year":2023,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","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":"McMaster University; Impact","funders":"Universität Basel","keywords":"Clinical trial; Randomized controlled trial; Dashboard; Risk management; Medicine; Risk assessment; Risk analysis (engineering); Computer science; Process management; Data science; Business; Computer security; Surgery","score_opus":0.981968931630785,"score_gpt":0.7645835342758958,"score_spread":0.21738539735488926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362609558","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":[0.0016378902,0.9578722,0.032676883,0.00014251932,0.00032545277,0.006979846,0.00007216106,0.000058699625,0.00023435694],"genre_scores_gemma":[0.000011352713,0.5936398,0.40490952,0.0000074459545,0.00018274697,0.0009856602,0.000045403678,0.00006519008,0.00015291308],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.94702435,0.038798016,0.005245301,0.0016261659,0.0059847427,0.0013214223],"domain_scores_gemma":[0.16623935,0.8263247,0.0016998617,0.0013322629,0.0018096836,0.0025941401],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.36271712,0.0004403744,0.006665378,0.0017079893,0.00019023323,0.000021136808,0.00079231994,0.0021723777,0.000028067014],"category_scores_gemma":[0.8368319,0.00030635443,0.00052512955,0.001385163,0.003372547,0.000015715039,0.0020847572,0.0046830294,0.0000069196476],"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":[0.0007048226,0.0002629455,0.00025837557,0.29139104,0.0014241808,0.000035641555,0.00055100746,6.099292e-7,0.0000072270714,0.008253801,0.00008571033,0.69702464],"study_design_scores_gemma":[0.027825063,0.0049217553,0.0036081732,0.45225692,0.010567154,0.00023597706,0.011145835,0.0025543303,0.00091497926,0.052646704,0.43099955,0.0023235593],"about_ca_topic_score_codex":0.00004857529,"about_ca_topic_score_gemma":0.000028365921,"teacher_disagreement_score":0.78752667,"about_ca_system_score_codex":0.00018684965,"about_ca_system_score_gemma":0.0098115085,"threshold_uncertainty_score":0.99993885},"labels":[],"label_agreement":null},{"id":"W4366502877","doi":"10.1186/s12874-023-01904-w","title":"The relationship of publication language, study population, risk of bias, and treatment effects in acupuncture related systematic reviews: a meta-epidemiologic study","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Hamilton Health Sciences; McMaster University; Impact","funders":"National Social Science Fund of China; National Office for Philosophy and Social Sciences","keywords":"Meta-analysis; Medicine; Acupuncture; Publication bias; Systematic review; MEDLINE; Alternative medicine; Population; Research design; Environmental health; Pathology; Statistics","score_opus":0.9776181336638249,"score_gpt":0.7287011632252482,"score_spread":0.24891697043857663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366502877","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":[0.9655029,0.016331581,0.004209582,0.00079606386,0.0001200829,0.012944021,0.0000053073213,0.00001056504,0.00007990176],"genre_scores_gemma":[0.9906704,0.0010388225,0.0038002017,0.000016786395,0.000022809458,0.0025148198,0.000012308033,0.000011097179,0.00191277],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.12063141,0.8531161,0.016400408,0.001243617,0.008083623,0.00052486977],"domain_scores_gemma":[0.12604229,0.86174047,0.0065714624,0.0039445693,0.0014351642,0.00026602944],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86133534,0.0003166932,0.008953824,0.0014156578,0.00025045153,0.000095600175,0.0015438746,0.00024717866,0.0004929401],"category_scores_gemma":[0.9816713,0.000092567796,0.001198828,0.006745591,0.00028998105,0.000094163806,0.00034214405,0.0005903014,0.00016527335],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029962195,0.00029580828,0.9814963,0.0016878393,0.0011286282,0.000008155822,0.0042860094,0.000036198668,0.000003762661,0.0021552132,0.0010314239,0.007840716],"study_design_scores_gemma":[0.0006376469,0.0007515755,0.9621397,0.0003182701,0.0016465037,0.00000557537,0.012805151,0.0044125305,0.0000013724359,0.017091375,0.000112698406,0.00007757228],"about_ca_topic_score_codex":0.0010864205,"about_ca_topic_score_gemma":0.005455926,"teacher_disagreement_score":0.120335974,"about_ca_system_score_codex":0.00006994818,"about_ca_system_score_gemma":0.00019024397,"threshold_uncertainty_score":0.6120655},"labels":[],"label_agreement":null},{"id":"W4366590256","doi":"10.1186/s12874-023-01922-8","title":"Data source profile reporting by studies that use routinely collected health data to explore the effects of drug treatment","year":2023,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"West China Hospital, Sichuan University; National Key Research and Development Program of China; Sichuan University; National Natural Science Foundation of China","keywords":"Medicine; Credibility; Observational study; MEDLINE; Data source; Database; Record linkage; Family medicine; Internal medicine; Computer science; Environmental health; Population","score_opus":0.987954653323306,"score_gpt":0.7701015603537543,"score_spread":0.2178530929695517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366590256","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003919493,0.86389923,0.12598114,0.0007651169,0.00026255436,0.0078746155,0.0007316702,0.0004309041,0.000015595024],"genre_scores_gemma":[3.2814157e-7,0.74172705,0.25153825,0.000058050442,0.0001669782,0.0020235034,0.0011958019,0.000140149,0.003149898],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92147934,0.06524752,0.0050245314,0.0025217899,0.0037508141,0.001976012],"domain_scores_gemma":[0.28923878,0.6931995,0.0049479464,0.010868008,0.0007632508,0.0009825149],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.10371807,0.0006533454,0.005928603,0.00051760394,0.00038432633,0.000050832277,0.005395372,0.00052940677,0.00005174378],"category_scores_gemma":[0.8575815,0.00035803256,0.00022815866,0.0019340472,0.0010546399,0.0001674651,0.01143648,0.0019926853,0.000028299064],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004032986,0.00017756794,0.000007921044,0.055917148,0.00071154936,0.000101683276,0.0014313287,4.496787e-8,0.00000386026,0.0004804738,0.33340853,0.60771954],"study_design_scores_gemma":[0.00035822706,0.00097082404,0.0000026085438,0.044293232,0.0005103992,0.000106493346,0.0028340386,0.000096293144,0.00007904817,0.0069954908,0.943315,0.0004383237],"about_ca_topic_score_codex":0.0009468112,"about_ca_topic_score_gemma":0.0020636066,"teacher_disagreement_score":0.7538634,"about_ca_system_score_codex":0.00067641714,"about_ca_system_score_gemma":0.0063806,"threshold_uncertainty_score":0.99998593},"labels":[],"label_agreement":null},{"id":"W4366768311","doi":"10.1186/s12874-023-01897-6","title":"Lived experience-centred word clouds may improve research uncertainty gathering in priority setting partnerships","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Vancouver General Hospital; University of British Columbia; University Health Network; Toronto Rehabilitation Institute; University of Toronto","funders":"National Institute for Health and Care Research; Wellcome Trust","keywords":"General partnership; Alliance; Psychology; Medicine; Stakeholder; Health care; Computer science; Public relations; Business; Political science","score_opus":0.9277101138583762,"score_gpt":0.7044244858165806,"score_spread":0.22328562804179564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366768311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96437734,0.00021327786,0.0023553637,0.02964566,0.0006517562,0.0018328433,0.000005076592,0.00018153213,0.00073713507],"genre_scores_gemma":[0.9494186,0.0009260952,0.044565096,0.00074465014,0.0016467398,0.000727095,0.0000873592,0.000076286444,0.0018080557],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9387826,0.04833143,0.0023882503,0.0014917654,0.005922669,0.0030833401],"domain_scores_gemma":[0.7297749,0.26580164,0.00023017611,0.001152172,0.001426235,0.0016149104],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17727178,0.0002417466,0.00086328055,0.001029039,0.00035096082,0.000059704977,0.00073305896,0.00066730846,0.0022171373],"category_scores_gemma":[0.70085937,0.00020933285,0.00016830197,0.0035568231,0.00152831,0.0001619883,0.0012968516,0.004864967,0.00049740006],"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":[0.0096728075,0.0009673264,0.19770809,0.001265903,0.00013798913,0.002609246,0.023949157,0.00005929163,0.03599194,0.002442969,0.012210741,0.71298456],"study_design_scores_gemma":[0.028351752,0.004380419,0.25367326,0.0025539624,0.00010710024,0.0003014986,0.41438636,0.12733936,0.008177251,0.02576856,0.13361374,0.0013467426],"about_ca_topic_score_codex":0.0028214445,"about_ca_topic_score_gemma":0.0045400234,"teacher_disagreement_score":0.7116378,"about_ca_system_score_codex":0.0007138404,"about_ca_system_score_gemma":0.004737134,"threshold_uncertainty_score":0.99869496},"labels":[],"label_agreement":null},{"id":"W4367369250","doi":"10.1186/s12874-023-01931-7","title":"Bayesian regularization to predict neuropsychiatric adverse events in smoking cessation with pharmacotherapy","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Smoking Behavior and Cessation","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":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"Campbell Family Mental Health Research Institute; University of Toronto; Canada Research Chairs","keywords":"Odds ratio; Odds; Medicine; Smoking cessation; Varenicline; Confidence interval; Logistic regression; Internal medicine; Physical therapy","score_opus":0.2815871815676587,"score_gpt":0.5149127848495286,"score_spread":0.2333256032818699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367369250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84554464,0.000015681746,0.15020953,0.0025786173,0.00036248725,0.0008101312,0.0000020808534,0.00013622185,0.00034061875],"genre_scores_gemma":[0.9907989,0.0001717568,0.0070747705,0.0005217206,0.00038063002,0.00024121515,0.000096935866,0.00004941637,0.0006646778],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9909027,0.005145345,0.0004142534,0.00053233164,0.0023634473,0.00064192805],"domain_scores_gemma":[0.99543566,0.0034385796,0.00006577608,0.00033487432,0.00023839927,0.00048671302],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015519376,0.0001413755,0.0003367744,0.0016014542,0.00011700625,0.0000053817744,0.00022935357,0.00026875848,0.00062370277],"category_scores_gemma":[0.009684602,0.00011431494,0.000052478466,0.0038312862,0.00012284469,0.000088179324,0.00007902636,0.00082142354,0.000023128077],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013117119,0.00014933711,0.9642837,0.00013465296,0.00002149942,0.00013079726,0.0006089167,0.00025137802,0.0026594282,0.00025310225,0.0005599335,0.029635519],"study_design_scores_gemma":[0.003921831,0.00070950924,0.9871895,0.00026100915,0.000035045025,0.000053651416,0.00041070126,0.0047752196,0.0011777944,0.0007530756,0.0005931947,0.000119496704],"about_ca_topic_score_codex":0.00018936954,"about_ca_topic_score_gemma":0.00017484432,"teacher_disagreement_score":0.14525425,"about_ca_system_score_codex":0.00017647474,"about_ca_system_score_gemma":0.0008825233,"threshold_uncertainty_score":0.9986572},"labels":[],"label_agreement":null},{"id":"W4376115852","doi":"10.1186/s12874-023-01909-5","title":"Multiple imputation methods for missing multilevel ordinal outcomes","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Veterans Affairs","keywords":"Missing data; Imputation (statistics); Ordinal data; Multilevel model; Ordinal regression; Statistics; Computer science; Data science; Psychology; Data mining; Econometrics; Mathematics","score_opus":0.8069585171997071,"score_gpt":0.7009638253751819,"score_spread":0.10599469182452526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376115852","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018558528,0.000043483495,0.9940849,0.0021039308,0.00057622226,0.0007866938,0.00003130461,0.00023097939,0.00028661604],"genre_scores_gemma":[0.0011929473,0.000029784911,0.9972872,0.0001608597,0.00026311402,0.00046056043,0.000020227586,0.000056074554,0.00052922877],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97149944,0.024292545,0.0008849252,0.0007192444,0.0012760632,0.0013277613],"domain_scores_gemma":[0.549618,0.44893548,0.00010306411,0.00035307146,0.00047548758,0.0005148916],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08852159,0.00023634634,0.0009237213,0.00055192556,0.00039604265,0.000056998448,0.0006372883,0.00047894608,0.0006928625],"category_scores_gemma":[0.79266477,0.00017826242,0.00022368823,0.0008118722,0.00066197856,0.00007101697,0.00037908883,0.0008435663,0.000085534244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014828784,0.0000652131,0.0013229873,0.0004198406,0.00003927948,0.000017704448,0.0002723638,7.1579313e-7,0.0012810143,0.23935814,0.002614038,0.7544604],"study_design_scores_gemma":[0.0010752704,0.00018241811,0.0059765438,0.00008500897,0.000022498414,0.000014894951,0.00031734345,0.14465724,0.0011554243,0.84415907,0.0021797228,0.00017454562],"about_ca_topic_score_codex":0.0001231518,"about_ca_topic_score_gemma":0.00007722643,"teacher_disagreement_score":0.7542859,"about_ca_system_score_codex":0.00008887033,"about_ca_system_score_gemma":0.0008819751,"threshold_uncertainty_score":0.9385588},"labels":[],"label_agreement":null},{"id":"W4376223952","doi":"10.1186/s12874-023-01942-4","title":"Exploring flexible polynomial regression as a method to align routine clinical outcomes with daily data capture through remote technologies","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Digital Mental Health Interventions","field":"Psychology","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":"Dalhousie University","funders":"National Institute for Health and Care Research","keywords":"Polynomial regression; Polynomial; Medicine; Regression analysis; Regression; Population; Health records; Statistics; Mathematics; Health care","score_opus":0.9063888535997108,"score_gpt":0.7072837288354171,"score_spread":0.19910512476429365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376223952","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15747179,0.0009762785,0.68048924,0.123017564,0.00767404,0.0035162522,0.00030240303,0.0034868186,0.023065617],"genre_scores_gemma":[0.062456638,0.00028645163,0.9100904,0.0021570746,0.0006804078,0.0007839943,0.00027454377,0.000185824,0.023084657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9695525,0.021688787,0.0017162465,0.0022141098,0.0025086843,0.0023196517],"domain_scores_gemma":[0.9358379,0.05923094,0.00025551274,0.003391634,0.00029371495,0.0009902488],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.06246384,0.0004091482,0.0013212892,0.00092452473,0.00037125117,0.00007278454,0.0035223693,0.00087978167,0.00092620106],"category_scores_gemma":[0.1199143,0.00028029038,0.00023140002,0.002744811,0.0012346131,0.00044417538,0.004959487,0.0027330425,0.0036842346],"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":[0.0038283388,0.00052575686,0.008115757,0.00023160559,0.0003109687,0.0010985413,0.0012482322,0.000002783321,0.000042379237,0.017970493,0.11782029,0.84880483],"study_design_scores_gemma":[0.016333034,0.018005954,0.12819932,0.005505478,0.00025294,0.001864735,0.07650058,0.0010832197,0.0038429091,0.07706913,0.66886896,0.0024737092],"about_ca_topic_score_codex":0.006459171,"about_ca_topic_score_gemma":0.0017471942,"teacher_disagreement_score":0.8463311,"about_ca_system_score_codex":0.00017029402,"about_ca_system_score_gemma":0.0010587107,"threshold_uncertainty_score":0.99998707},"labels":[],"label_agreement":null},{"id":"W4376226302","doi":"10.1186/s12874-023-01933-5","title":"Research recruitment and consent methods in a pandemic: a qualitative study of COVID-19 patients’ perspectives","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; Simon Fraser University; Vancouver General Hospital; Provincial Health Services Authority; Université Laval; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; University of British Columbia; Centre Intégré de Santé et Services Sociaux de Chaudière-Appalache; Queen's University; Vancouver Coastal Health Research Institute; Vancouver Coastal Health","funders":"Canadian Institutes of Health Research; Fondation CHU de Québec; Genome British Columbia; Saskatchewan Health Research Foundation","keywords":"Thematic analysis; Focus group; Informed consent; Autonomy; Data collection; Exploratory research; Psychology; Pandemic; Qualitative research; Coronavirus disease 2019 (COVID-19); Biobank; Medical education; Medicine; Family medicine; Alternative medicine; Sociology; Political science","score_opus":0.9879824596544354,"score_gpt":0.8560172394637351,"score_spread":0.13196522019070034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376226302","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":[0.97385585,0.0011290641,0.0069436287,0.010712243,0.00013183503,0.0053347917,0.000013687159,0.00008203332,0.0017968677],"genre_scores_gemma":[0.79160756,0.021575985,0.17441607,0.0008087441,0.0003307694,0.00458513,0.00004579613,0.00013536194,0.0064945947],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.54977256,0.42377007,0.0031526873,0.0029392114,0.017105285,0.0032601873],"domain_scores_gemma":[0.11616053,0.87606764,0.00017431073,0.0011981349,0.0038536768,0.0025457104],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5778972,0.0002476816,0.0015905041,0.0033474232,0.00031405923,0.000025199926,0.0008399791,0.0011051334,0.0008464571],"category_scores_gemma":[0.91054314,0.00019286665,0.00014057878,0.0050444533,0.00752334,0.000053314616,0.002603288,0.009658535,0.00006026789],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011161271,0.00804666,0.24209319,0.005270121,0.00045415462,0.00086014945,0.64867085,0.0000059323866,0.0014649075,0.035473693,0.004056524,0.042442568],"study_design_scores_gemma":[0.009884889,0.0094202785,0.06699307,0.0005076669,0.000023030423,0.000022809198,0.7813292,0.00023682119,0.00008144267,0.13010076,0.0012284153,0.00017160908],"about_ca_topic_score_codex":0.0055744676,"about_ca_topic_score_gemma":0.013977286,"teacher_disagreement_score":0.45229757,"about_ca_system_score_codex":0.0010663839,"about_ca_system_score_gemma":0.014026434,"threshold_uncertainty_score":0.9951776},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"medium"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4378176766","doi":"10.1186/s12874-023-01944-2","title":"Development of the global inflammatory bowel disease visualization of epidemiology studies in the 21st century (GIVES-21)","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Manitoba","funders":"Canadian Institutes of Health Research; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Epidemiology; Medicine; Inflammatory bowel disease; Incidence (geometry); Disease; Population; Crohn's disease; Ulcerative colitis; Cohort study; Cohort; Environmental health; Developed country; Family medicine; Internal medicine","score_opus":0.3527061321712894,"score_gpt":0.5316630410264684,"score_spread":0.17895690885517906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378176766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99319977,0.00289609,0.0021910586,0.00051224953,0.00034785882,0.0005680245,0.000019537003,0.000011206701,0.00025423698],"genre_scores_gemma":[0.98405707,0.0066084783,0.007493967,0.0007213573,0.00038999924,0.000422976,0.00014631552,0.00003393479,0.00012592216],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9740665,0.022965636,0.000920967,0.00043547797,0.0009677816,0.0006436173],"domain_scores_gemma":[0.9918313,0.0066837114,0.00021654027,0.0006802809,0.00034610808,0.00024202895],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036639504,0.00015267706,0.00034552824,0.00013375547,0.00013859246,0.0000026609944,0.0009762449,0.00026381802,0.000034451976],"category_scores_gemma":[0.1531828,0.000092076276,0.00014635584,0.00056083273,0.0019861264,0.0000042826005,0.00097287836,0.00027201857,0.000012215925],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022274358,0.0003069293,0.87386256,0.0022034103,0.0002752788,0.00015376398,0.0030638545,0.00027808239,0.0067613525,0.08977674,0.0031765657,0.017913997],"study_design_scores_gemma":[0.00077069947,0.00006790423,0.9752689,0.0001769017,0.00001846231,0.0000065187437,0.0055632917,0.00029339423,0.0012465508,0.00444693,0.0120054,0.0001350304],"about_ca_topic_score_codex":0.000012483286,"about_ca_topic_score_gemma":0.0003650307,"teacher_disagreement_score":0.1165433,"about_ca_system_score_codex":0.00006850519,"about_ca_system_score_gemma":0.002453524,"threshold_uncertainty_score":0.99198234},"labels":[],"label_agreement":null},{"id":"W4380090386","doi":"10.1186/s12874-023-01886-9","title":"Examining differential success in recruitment using respondent driven sampling (RDS) in a multi-site study of gay, bisexual and other men who have sex with men","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; McGill University Health Centre; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; University of Toronto; Toronto Metropolitan University; University of Victoria; Institut National de Santé Publique du Québec; Simon Fraser University; Community Based Research Centre; AIDS Vancouver","funders":"Canadian HIV Trials Network, Canadian Institutes of Health Research; Michael Smith Health Research BC; Public Health Agency of Canada; Ontario HIV Treatment Network; Canadian Foundation for AIDS Research; Canadian Institutes of Health Research; Ryerson University","keywords":"Homophily; Demography; Respondent; Longitudinal study; Psychology; Cohort; Gerontology; Medicine; Social psychology; Sociology; Political science","score_opus":0.8202273471632331,"score_gpt":0.6302184357761627,"score_spread":0.19000891138707043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380090386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97256076,0.00011584619,0.024289023,0.00016903049,0.000014130599,0.002165691,0.000013876072,0.000024592642,0.0006470679],"genre_scores_gemma":[0.9771232,0.00015872913,0.014285178,0.00002260128,0.00012250374,0.0006404775,0.000021744008,0.00006734834,0.007558217],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9806758,0.014230811,0.00089027185,0.00079792633,0.0022730036,0.0011321835],"domain_scores_gemma":[0.9868957,0.011696015,0.000103399296,0.0004573496,0.00020702957,0.00064052705],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022559498,0.00020895118,0.0009626925,0.0022830814,0.00011352264,0.000030937532,0.0003438061,0.0002468767,0.0005752933],"category_scores_gemma":[0.020626815,0.00015681406,0.000049947586,0.0012618063,0.00063222455,0.000075541146,0.0007840769,0.0013031132,0.000008196677],"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":[0.0038682844,0.0015016767,0.9340223,0.00051985757,0.00019156425,0.0006871315,0.016362915,0.0000840705,0.02158653,0.000037248516,0.00038500852,0.020753384],"study_design_scores_gemma":[0.016540427,0.012563183,0.6070978,0.0019642226,0.00004787817,0.000057569297,0.080786794,0.2796087,0.0008735351,0.00006470352,0.00015483143,0.00024034057],"about_ca_topic_score_codex":0.010051134,"about_ca_topic_score_gemma":0.027065309,"teacher_disagreement_score":0.3269245,"about_ca_system_score_codex":0.00024345556,"about_ca_system_score_gemma":0.0007814975,"threshold_uncertainty_score":0.996541},"labels":[],"label_agreement":null},{"id":"W4380682159","doi":"10.1186/s12874-023-01963-z","title":"Use of days alive without life support and similar count outcomes in randomised clinical trials – an overview and comparison of methodological choices and analysis methods","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Novo Nordisk Fonden","keywords":"Medicine; Clinical trial; MEDLINE; Internal medicine","score_opus":0.9704218560795618,"score_gpt":0.7709543359675487,"score_spread":0.19946752011201307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380682159","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":[0.97544724,0.0067030075,0.013951643,0.0021414466,0.000103787184,0.0015532225,0.0000433493,0.00002978328,0.000026547581],"genre_scores_gemma":[0.29018265,0.054539774,0.65379083,0.000839718,0.000115759656,0.00032345793,0.000107264765,0.000037802096,0.000062751824],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8324823,0.16060126,0.0034789362,0.0010878748,0.0016488766,0.00070078135],"domain_scores_gemma":[0.41208684,0.58460534,0.0007193973,0.00069634913,0.00043230003,0.0014597656],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2956599,0.0002948873,0.007007253,0.0011916549,0.0000710063,0.00002505889,0.00020608265,0.00070407015,0.00040115434],"category_scores_gemma":[0.5720898,0.00018185898,0.00046010417,0.0012759882,0.0019464253,0.00007988917,0.00043830212,0.0008233522,0.000001310689],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0059082108,0.0008090517,0.9161567,0.00044601804,0.002092477,0.000051287112,0.00055705255,0.000005808817,0.00031529774,0.0006629311,0.00013253065,0.07286262],"study_design_scores_gemma":[0.018261837,0.0024439339,0.96308416,0.00015032169,0.0022058885,0.000012722956,0.0010769992,0.010402203,0.0006540819,0.00091561157,0.00064292504,0.00014930013],"about_ca_topic_score_codex":0.0010104914,"about_ca_topic_score_gemma":0.0010118862,"teacher_disagreement_score":0.6852645,"about_ca_system_score_codex":0.000031286258,"about_ca_system_score_gemma":0.00063242886,"threshold_uncertainty_score":0.74159944},"labels":[],"label_agreement":null},{"id":"W4382776735","doi":"10.1186/s12874-023-01964-y","title":"Use of electronic health data to identify patients with moderate-to-severe osteoarthritis of the hip and/or knee and inadequate response to pain medications","year":2023,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Machine Learning in Healthcare","field":"Computer Science","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":"Duchesnay (Canada)","funders":"Pfizer; Eli Lilly and Company","keywords":"Medicine; Logistic regression; Osteoarthritis; Chart; Machine learning; Medical record; Random forest; Physical therapy; Decision tree; Electronic health record; Artificial intelligence; Algorithm; Health care; Computer science; Internal medicine; Statistics; Alternative medicine; Pathology","score_opus":0.6439431080429259,"score_gpt":0.588650156425966,"score_spread":0.05529295161695991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382776735","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":[0.003243027,0.4712657,0.4830005,0.033199776,0.0003413671,0.008439922,0.0004058734,0.00010094516,0.0000029265905],"genre_scores_gemma":[0.0004058834,0.7252909,0.2702647,0.002189782,0.00011792349,0.0010380553,0.0001239228,0.00012219186,0.00044666012],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88835347,0.10451416,0.0014158462,0.0014829789,0.002947893,0.0012856757],"domain_scores_gemma":[0.8578685,0.13623783,0.00046450866,0.0032082764,0.0006328019,0.0015880634],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09768548,0.00029925987,0.0017966211,0.0010366009,0.00030168396,0.00006666762,0.0036846572,0.0004671512,0.000027649336],"category_scores_gemma":[0.33000666,0.00018443813,0.000065587075,0.0032760564,0.0004888236,0.00012757917,0.006455269,0.0024999944,0.000014830078],"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":[0.0004983993,0.0000320782,0.00015940961,0.007470706,0.00004215941,0.000007808547,0.00065554667,0.000009372363,2.8626988e-7,0.001163281,0.0010791644,0.98888177],"study_design_scores_gemma":[0.0020200126,0.015793875,0.013605812,0.058651067,0.00011421153,0.00017442476,0.00022110078,0.006986831,0.0000015702769,0.0017363152,0.8997685,0.0009263138],"about_ca_topic_score_codex":0.0018982887,"about_ca_topic_score_gemma":0.005874458,"teacher_disagreement_score":0.98795545,"about_ca_system_score_codex":0.00021460581,"about_ca_system_score_gemma":0.013676503,"threshold_uncertainty_score":0.9998013},"labels":[],"label_agreement":null},{"id":"W4383186980","doi":"10.1186/s12874-023-01978-6","title":"Effect of alcohol consumption on breast cancer: probabilistic bias analysis for adjustment of exposure misclassification bias and confounders","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cancer Risks and Factors","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Confounding; Medicine; Breast cancer; Odds ratio; Population; Logistic regression; Information bias; Statistics; Attributable risk; Alcohol consumption; Cancer; Selection bias; Mathematics; Alcohol; Internal medicine; Environmental health; Pathology; Biology","score_opus":0.6737063483700801,"score_gpt":0.5808430157274987,"score_spread":0.0928633326425814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383186980","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902783,0.00063017925,0.0062093884,0.0011450787,0.00014863408,0.0014030067,0.00011767663,0.000025721194,0.000041987332],"genre_scores_gemma":[0.99518,0.0029712121,0.00096633774,0.000040906594,0.0001144767,0.00046140383,0.00009989166,0.000015936366,0.00014982616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99312186,0.004491617,0.00051332614,0.00040703584,0.0010948463,0.00037131374],"domain_scores_gemma":[0.9551652,0.043680713,0.0001694342,0.00031514847,0.0003542786,0.00031522158],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019415403,0.00012912093,0.00085357844,0.00077150925,0.000055581786,0.0000047667445,0.00011799377,0.00025017437,0.00038513917],"category_scores_gemma":[0.031705335,0.00008934896,0.0001991672,0.00092519255,0.0009241974,0.000017151215,0.000055395416,0.00030618676,0.0000045131255],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0126646925,0.00024085659,0.74414635,0.008299478,0.0013632615,0.000009351241,0.0005751341,0.0002551037,0.009652544,0.0028127157,0.0015134689,0.21846701],"study_design_scores_gemma":[0.004935618,0.0040600374,0.9748297,0.00047621274,0.00097576133,0.000014284944,0.00027928644,0.009191739,0.004473638,0.00035359408,0.00030340863,0.00010674607],"about_ca_topic_score_codex":0.0014474661,"about_ca_topic_score_gemma":0.0010448797,"teacher_disagreement_score":0.2306833,"about_ca_system_score_codex":0.00013927062,"about_ca_system_score_gemma":0.00067073223,"threshold_uncertainty_score":0.97645104},"labels":[],"label_agreement":null},{"id":"W4385551930","doi":"10.1186/s12874-023-01956-y","title":"Power and sample size calculation for incremental net benefit in cost effectiveness analyses with applications to trials conducted by the Canadian Cancer Trials Group","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Sunnybrook Hospital; Health Sciences Centre; Canadian Centre for Applied Research in Cancer Control; University of Toronto; Cancer Care Ontario; Queen's University; Sunnybrook Health Science Centre","funders":"National Cancer Institute; Canadian Cancer Society Research Institute; Canadian Centre for Applied Research in Cancer Control","keywords":"Sample size determination; Cost effectiveness; Clinical trial; Statistics; Sample (material); Willingness to pay; Statistical power; Randomized controlled trial; Medicine; Variance (accounting); Econometrics; Computer science; Actuarial science; Mathematics; Economics; Accounting","score_opus":0.9320511847664241,"score_gpt":0.7003904723078794,"score_spread":0.2316607124585447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385551930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5285408,0.0025966743,0.36153775,0.08206566,0.00048902776,0.019116169,0.0053899405,0.000056876637,0.00020708372],"genre_scores_gemma":[0.86773455,0.00073494844,0.076669626,0.010482823,0.0009506233,0.042210165,0.0007700782,0.00010972881,0.0003374822],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9670163,0.027514806,0.0034142092,0.0007915954,0.00038326465,0.0008798534],"domain_scores_gemma":[0.5297207,0.46813786,0.00076742563,0.00040611083,0.00021827834,0.00074960326],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4085971,0.00014965725,0.0017607524,0.0007495998,0.0004349269,0.00008194506,0.00034562632,0.00028014102,0.00074131996],"category_scores_gemma":[0.52981097,0.00012144797,0.000093856164,0.0010981307,0.00028202543,0.000101442005,0.00008079916,0.0003278447,0.0000621181],"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":[0.0045151818,0.00039372544,0.4106929,0.0024626767,0.0016203743,0.000006854377,0.006301067,0.0032306148,0.0020076765,0.39345697,0.13935338,0.03595861],"study_design_scores_gemma":[0.015288985,0.0011231523,0.5874481,0.0004594027,0.00008152585,0.000010528385,0.0054043643,0.018458996,0.0003299283,0.14332618,0.22707312,0.0009957138],"about_ca_topic_score_codex":0.4004523,"about_ca_topic_score_gemma":0.68789524,"teacher_disagreement_score":0.44062307,"about_ca_system_score_codex":0.0010012578,"about_ca_system_score_gemma":0.0015013553,"threshold_uncertainty_score":0.8116934},"labels":[],"label_agreement":null},{"id":"W4385698578","doi":"10.1186/s12874-023-01995-5","title":"Genetic matching for time-dependent treatments: a longitudinal extension and simulation study","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canadian Centre for Applied Research in Cancer Control","funders":"Terry Fox Research Institute; Health Innovation Network South London; Genome British Columbia; Genome Canada","keywords":"Covariate; Propensity score matching; Matching (statistics); Statistics; Confounding; Baseline (sea); Computer science; Mathematics; Econometrics; Biology","score_opus":0.39280247786356043,"score_gpt":0.5465209185638702,"score_spread":0.15371844070030977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385698578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8027096,0.000265174,0.19595353,0.00027090378,0.00009677001,0.00065187545,0.0000075346666,0.000019592217,0.000025027588],"genre_scores_gemma":[0.9620461,0.0003340074,0.035654604,0.00008307027,0.0003434803,0.00029025905,0.00007388636,0.000026973748,0.001147627],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9925459,0.0053497897,0.00037227783,0.0006678082,0.00047066313,0.00059354235],"domain_scores_gemma":[0.9905929,0.00853255,0.000070514536,0.00033273222,0.00023322222,0.00023805701],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0153401,0.0001335748,0.00033289858,0.00017851415,0.00026252522,0.000014776039,0.00019232788,0.00031760885,0.000066400054],"category_scores_gemma":[0.03196527,0.000111617825,0.00007074881,0.00019696107,0.00016833773,0.0000024911174,0.00036616673,0.00018243435,0.000045575915],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002074498,0.0013231155,0.6658695,0.00023400878,0.00089667476,0.0001253303,0.0015876819,0.028590962,0.12557049,0.00016444646,0.007901119,0.16566217],"study_design_scores_gemma":[0.0029422215,0.0031286627,0.9155143,0.000022181157,0.00006971101,0.000036920672,0.0020014874,0.06872434,0.00019595675,0.0061904006,0.0009344236,0.00023938602],"about_ca_topic_score_codex":0.0001705705,"about_ca_topic_score_gemma":0.00026872475,"teacher_disagreement_score":0.2496448,"about_ca_system_score_codex":0.000029513929,"about_ca_system_score_gemma":0.0002448749,"threshold_uncertainty_score":0.9761889},"labels":[],"label_agreement":null},{"id":"W4386497584","doi":"10.1186/s12874-023-02011-6","title":"Ascertaining asthma status in epidemiologic studies: a comparison between administrative health data and self-report","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Asthma and respiratory diseases","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; Institut National de la Recherche Scientifique; Institut National de Santé Publique du Québec; Université de Montréal; McGill University; Université du Québec","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Institut de la statistique du Québec","keywords":"Asthma; Medicine; Logistic regression; Family medicine; Epidemiology; Cohort; Public health; Confidence interval; Demography; Environmental health; Nursing","score_opus":0.8628162645183522,"score_gpt":0.6964912847060375,"score_spread":0.16632497981231475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386497584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9642112,0.013721268,0.007913899,0.012043716,0.00020406922,0.0011990647,0.00006972019,0.00024028968,0.00039674938],"genre_scores_gemma":[0.90229577,0.010703499,0.08256671,0.0018149032,0.0010931048,0.00024451388,0.0008446406,0.00006198073,0.00037489636],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9602444,0.03322274,0.0015828806,0.0013181723,0.0018013966,0.0018303985],"domain_scores_gemma":[0.82209843,0.17296952,0.00037104764,0.0013938391,0.00039791106,0.0027692602],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09337095,0.00022240556,0.001771457,0.0006176788,0.00023464194,0.000011690731,0.00043288656,0.0003409965,0.00011450109],"category_scores_gemma":[0.35539088,0.00015774189,0.00006685455,0.0011875058,0.0012745422,0.00006738735,0.0012802883,0.0015155147,0.0000495921],"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":[0.0003472213,0.000219605,0.85096735,0.000858465,0.00017053758,0.0023919402,0.002209461,0.000002742733,0.000008573825,0.00023336824,0.012472894,0.13011783],"study_design_scores_gemma":[0.0024116456,0.0032105322,0.8861101,0.0006667257,0.000035040153,0.00022745179,0.033542193,0.0044289595,0.000012956388,0.0015773933,0.06756524,0.0002117023],"about_ca_topic_score_codex":0.00041693996,"about_ca_topic_score_gemma":0.0012993024,"teacher_disagreement_score":0.2620199,"about_ca_system_score_codex":0.00020084834,"about_ca_system_score_gemma":0.006710657,"threshold_uncertainty_score":0.9989204},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"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":"W4386688562","doi":"10.1186/s12874-023-02027-y","title":"Comparing analytical strategies for balancing site-level characteristics in stepped-wedge cluster randomized trials: a simulation study","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"Canadian Institutes of Health Research; Cundill Centre for Child and Youth Depression; University of Toronto; Centre for Addiction and Mental Health","keywords":"Statistics; Sample size determination; Cluster (spacecraft); Mathematics; Correlation; Cluster randomised controlled trial; Rank correlation; Randomized controlled trial; Medicine; Computer science; Surgery","score_opus":0.8717879191602349,"score_gpt":0.6638658868105302,"score_spread":0.20792203234970474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386688562","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":[0.15358634,0.000017031043,0.8422418,0.00025809061,0.00028940596,0.003326715,0.00003291667,0.000083483996,0.00016421068],"genre_scores_gemma":[0.44481304,0.000019436233,0.5538655,0.000048350907,0.0003542347,0.00073968974,0.000023973416,0.000035115896,0.00010067314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.88755506,0.10453014,0.0032600488,0.0009232207,0.0022247133,0.0015068315],"domain_scores_gemma":[0.39220452,0.60644025,0.0002441801,0.0003631791,0.0004032046,0.0003446498],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27547386,0.0002657609,0.0034189033,0.0008078678,0.00017738443,0.00013386259,0.0004778698,0.00040012758,0.00036205808],"category_scores_gemma":[0.81878114,0.00019443562,0.0002777247,0.00096437015,0.00060013414,0.00009864098,0.0003911182,0.0010783311,0.000042751293],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.11364463,0.0014222915,0.023492018,0.002459408,0.00042524448,0.00028182022,0.006165102,0.00023676074,0.00014435436,0.7551703,0.0016911856,0.09486689],"study_design_scores_gemma":[0.039605357,0.00019338643,0.0056120125,0.00014604736,0.000074556985,0.0000023300067,0.002032759,0.56284565,0.000003861267,0.38931882,0.000025580797,0.00013962135],"about_ca_topic_score_codex":0.000156133,"about_ca_topic_score_gemma":0.0008346299,"teacher_disagreement_score":0.5626089,"about_ca_system_score_codex":0.0001172845,"about_ca_system_score_gemma":0.0010143773,"threshold_uncertainty_score":0.7928855},"labels":[],"label_agreement":null},{"id":"W4387408123","doi":"10.1186/s12874-023-02051-y","title":"Asynchronous online focus groups for research with people living with amyotrophic lateral sclerosis and family caregivers: usefulness, acceptability and lessons learned","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Focus Groups and Qualitative Methods","field":"Social 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":"Inuit Tapiriit Kanatami; Simon Fraser University; University of Alberta","funders":"","keywords":"Focus group; Amyotrophic lateral sclerosis; Context (archaeology); Psychology; Moderation; Online discussion; Confidentiality; Medical education; Online research methods; Grounded theory; Qualitative research; Asynchronous communication; Data collection; Applied psychology; Internet privacy; Medicine; Computer science; World Wide Web; Social psychology","score_opus":0.6998250111289526,"score_gpt":0.5809055774301132,"score_spread":0.1189194336988394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387408123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9023096,0.0006758064,0.08363567,0.011789463,0.00009819018,0.0010158923,0.00004369745,0.000111330206,0.00032036353],"genre_scores_gemma":[0.85002506,0.0025578937,0.14601779,0.000052956057,0.0004331465,0.00048225195,0.000013573095,0.000054011514,0.00036334104],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9410208,0.05284076,0.00039682994,0.0011456669,0.0026938294,0.0019021325],"domain_scores_gemma":[0.85353696,0.14389783,0.00008546906,0.00041570558,0.0011050553,0.00095894985],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.12223987,0.00023821963,0.0007911122,0.0006166328,0.002122931,0.0001988,0.0006443189,0.00045254224,0.00025919196],"category_scores_gemma":[0.1160651,0.0001708859,0.00007451869,0.0023772372,0.0073527903,0.00026259338,0.00069910625,0.0015269319,0.000008419333],"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":[0.0028300819,0.00046453995,0.11776189,0.0013544591,0.00022786364,0.0000723931,0.15922298,0.000013488947,0.00086596067,0.11430657,0.0010633968,0.60181636],"study_design_scores_gemma":[0.0030705058,0.0038139964,0.6631083,0.0005335671,0.000047437563,0.000013349952,0.2714968,0.0011992578,0.000078370926,0.05148137,0.004599238,0.0005578321],"about_ca_topic_score_codex":0.02185599,"about_ca_topic_score_gemma":0.12407453,"teacher_disagreement_score":0.6012586,"about_ca_system_score_codex":0.00022686964,"about_ca_system_score_gemma":0.0023429943,"threshold_uncertainty_score":0.99917614},"labels":[],"label_agreement":null},{"id":"W4387503967","doi":"10.1186/s12874-023-02044-x","title":"Adjusting for Berkson error in exposure in ordinary and conditional logistic regression and in Poisson regression","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Occupational and environmental lung diseases","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":"University of Ottawa; BC Cancer Agency; Centre Hospitalier de l’Université de Montréal","funders":"National Cancer Institute; National Institutes of Health","keywords":"Statistics; Job-exposure matrix; Logistic regression; Poisson regression; Regression; Poisson distribution; Regression analysis; Econometrics; Mathematics; Medicine; Population; Environmental health; Confidence interval","score_opus":0.5829241814341569,"score_gpt":0.5801489863611682,"score_spread":0.0027751950729887342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387503967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99425894,0.0014939514,0.0004651482,0.0031238713,0.000058944166,0.0004925892,0.000018839819,0.000015585636,0.00007215388],"genre_scores_gemma":[0.98655945,0.00075995974,0.011575223,0.00015248502,0.00012699423,0.00021765332,0.000261533,0.000015039747,0.00033165282],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9960314,0.0020974546,0.00034489026,0.00041307745,0.00066959404,0.00044355428],"domain_scores_gemma":[0.98128754,0.01823706,0.000038986404,0.00010811457,0.000030477,0.00029782348],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008197061,0.00010935554,0.00036892926,0.00058762415,0.000064959626,0.0000049312525,0.000072881136,0.00025971603,0.00016773194],"category_scores_gemma":[0.034917407,0.000079488564,0.000027693055,0.00042220915,0.00047081514,0.000052510124,0.0002143322,0.0005264707,0.0000066840867],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042413203,0.00020701389,0.9598449,0.00086370116,0.0000062991835,0.0005770618,0.00019106251,0.000027930528,0.0023878918,0.00047923988,0.0011103656,0.030063229],"study_design_scores_gemma":[0.0029606116,0.0004870475,0.97780216,0.0012904686,0.000007607553,0.00005236461,0.000798604,0.007537948,0.000079340745,0.008722231,0.00018842384,0.00007319249],"about_ca_topic_score_codex":0.00020600414,"about_ca_topic_score_gemma":0.0006435087,"teacher_disagreement_score":0.029990036,"about_ca_system_score_codex":0.00010775892,"about_ca_system_score_gemma":0.00024584122,"threshold_uncertainty_score":0.9732119},"labels":[],"label_agreement":null},{"id":"W4387514073","doi":"10.1186/s12874-023-02031-2","title":"Methodology for the adolopment of recommendations for the treatment of rheumatoid arthritis in the Kingdom of Saudi Arabia","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Rheumatoid arthritis; Medicine; Alternative medicine; MEDLINE; Family medicine; Internal medicine; Pathology; Political science","score_opus":0.9081137191485839,"score_gpt":0.7024296982285319,"score_spread":0.205684020920052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387514073","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":[0.0944781,0.0029061425,0.64240956,0.25199378,0.0008865701,0.0071196733,0.00013111907,0.000021730624,0.000053330055],"genre_scores_gemma":[0.191696,0.10011739,0.698568,0.002022892,0.0006325996,0.0063864924,0.0002954669,0.000066371525,0.00021483022],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97619885,0.018818678,0.002561679,0.00042344746,0.001322913,0.00067442516],"domain_scores_gemma":[0.46496227,0.5333528,0.00041558367,0.00057140196,0.0006093624,0.00008854535],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.118185416,0.00013317548,0.00087072054,0.00030591298,0.00016612178,0.0000049863215,0.0005339135,0.00021312379,0.0004130429],"category_scores_gemma":[0.4000214,0.00006409697,0.00031458348,0.0008750916,0.0011106962,0.00003116608,0.00012737329,0.0004258697,0.00000413727],"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":[0.004339115,0.0008094549,0.0036753751,0.00035296072,0.0004154848,0.0000048055254,0.004436826,0.000051544746,0.0021482727,0.012959193,0.024459612,0.94634736],"study_design_scores_gemma":[0.03160947,0.018351575,0.075903304,0.0010509533,0.00047466203,0.00017577935,0.069964975,0.018693725,0.015152799,0.067895606,0.70041996,0.00030716433],"about_ca_topic_score_codex":0.002138495,"about_ca_topic_score_gemma":0.004580775,"teacher_disagreement_score":0.9460402,"about_ca_system_score_codex":0.00008254013,"about_ca_system_score_gemma":0.0013372262,"threshold_uncertainty_score":0.9080137},"labels":[],"label_agreement":null},{"id":"W4387615037","doi":"10.1186/s12874-023-02045-w","title":"New approaches and technical considerations in detecting outlier measurements and trajectories in longitudinal children growth data","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Body Composition Measurement Techniques","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto; SickKids Foundation; Institute for Clinical Evaluative Sciences; Hospital for Sick Children; Public Health Ontario","funders":"Medical Research Council; Canadian Institutes of Health Research; Peterborough K. M. Hunter Charitable Foundation; Wellcome Trust; Alexander S. Onassis Public Benefit Foundation; Bill and Melinda Gates Foundation","keywords":"Outlier; Anomaly detection; Computer science; Cluster analysis; Artificial intelligence; Statistics; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.816385859309493,"score_gpt":0.5449894079597122,"score_spread":0.27139645134978085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387615037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8860848,0.0016251488,0.09617913,0.012800286,0.000103572,0.0021076947,0.000010672303,0.00036891055,0.0007197926],"genre_scores_gemma":[0.8011443,0.00020695213,0.19827083,0.00007657832,0.00014149283,0.00007967092,0.000037467944,0.000020465055,0.000022232785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99164766,0.004841603,0.0005602837,0.00078852597,0.001538918,0.00062302244],"domain_scores_gemma":[0.98858917,0.010297103,0.00004561441,0.00049389084,0.00011608039,0.00045815873],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036878478,0.00015386658,0.00052988506,0.0008903532,0.00012591558,0.000037731057,0.00025314098,0.00032770575,0.0001061604],"category_scores_gemma":[0.0945333,0.00013527139,0.000023767441,0.0008591336,0.00059601414,0.00013281577,0.0007110223,0.0012978498,0.0000048278393],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018443177,0.00009056505,0.9826523,0.00013424509,0.00003206468,0.00009258642,0.00018850726,6.213961e-7,0.0041788644,0.0015255576,0.0016504453,0.009269777],"study_design_scores_gemma":[0.0019522192,0.00026294426,0.98417825,0.00030440773,0.000022869048,0.00046443456,0.00015356806,0.0005088338,0.0021495773,0.009857354,0.000017139577,0.00012843414],"about_ca_topic_score_codex":0.0009236361,"about_ca_topic_score_gemma":0.005958142,"teacher_disagreement_score":0.10209171,"about_ca_system_score_codex":0.00011164379,"about_ca_system_score_gemma":0.0011003992,"threshold_uncertainty_score":0.9917363},"labels":[],"label_agreement":null},{"id":"W4387736567","doi":"10.1186/s12874-023-02062-9","title":"Longitudinal plasmode algorithms to evaluate statistical methods in realistic scenarios: an illustration applied to occupational epidemiology","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Quebec Population Health Research Network; Université Laval","funders":"Medical Research Council; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Medical Research Council Canada; Canadian Institutes of Health Research; Université Laval","keywords":"Covariate; Marginal structural model; Estimator; Statistics; Confidence interval; Nonparametric statistics; Coverage probability; Weighting; Computer science; Algorithm; Inverse probability; Inverse probability weighting; Mathematics; Medicine; Bayesian probability","score_opus":0.9221876644056204,"score_gpt":0.7397021868237371,"score_spread":0.18248547758188327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387736567","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016508283,0.000009371537,0.97900546,0.0021095797,0.0001803495,0.0012931477,0.000049915034,0.00034590677,0.00049797766],"genre_scores_gemma":[0.010606172,0.00002824249,0.9867672,0.0005235863,0.0002881592,0.0014455497,0.00015453559,0.000054941527,0.00013164886],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9418135,0.049878333,0.0019591565,0.0016672503,0.0024270518,0.0022546747],"domain_scores_gemma":[0.75794554,0.23926508,0.00013008008,0.0007706655,0.0005414371,0.0013471707],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15162396,0.00030872968,0.0012018967,0.0013928362,0.00017864878,0.000022399157,0.0008854395,0.00065864733,0.0010757901],"category_scores_gemma":[0.5813287,0.00027285778,0.00006298727,0.00198039,0.0006962246,0.00010267201,0.0006733701,0.0015436256,0.0002728173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001006623,0.00017340052,0.0015426229,0.0001590946,0.000024143414,0.0001012025,0.00058121356,0.0020404845,0.0018716342,0.85029966,0.005397524,0.13680238],"study_design_scores_gemma":[0.00048121443,0.00084785774,0.022612022,0.00009542462,0.000013812563,0.000031801177,0.0003516716,0.076512784,0.00051016966,0.8977638,0.00049258815,0.00028686126],"about_ca_topic_score_codex":0.0007366828,"about_ca_topic_score_gemma":0.0043624714,"teacher_disagreement_score":0.42970473,"about_ca_system_score_codex":0.00046193597,"about_ca_system_score_gemma":0.0015744241,"threshold_uncertainty_score":0.99997234},"labels":[],"label_agreement":null},{"id":"W4387736624","doi":"10.1186/s12874-023-02060-x","title":"Advancements in predicting and modeling rare event outcomes for enhanced decision-making","year":2023,"lang":"en","type":"editorial","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Saskatchewan Health Authority; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Rare events; Computer science; Task (project management); Event (particle physics); Data science; Machine learning; Artificial intelligence; Data mining","score_opus":0.6326234789922852,"score_gpt":0.6646749732385197,"score_spread":0.032051494246234435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387736624","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":[0.0011649622,0.00018340789,0.7575507,0.00006817115,0.23996365,0.00083218876,0.000116100164,0.000056515437,0.000064289554],"genre_scores_gemma":[0.00040669795,0.0007596355,0.90236497,0.000020683598,0.095212586,0.0009269833,0.00003098045,0.00010835808,0.00016910689],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98140186,0.009930961,0.0017531483,0.0012943909,0.004058414,0.0015612291],"domain_scores_gemma":[0.32994613,0.668173,0.00022173322,0.0004942589,0.00075735996,0.0004075137],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.07201509,0.00039126628,0.0017611047,0.00067169376,0.00022606451,0.00005514093,0.0008648529,0.0016381352,0.00021921727],"category_scores_gemma":[0.94234055,0.0003133584,0.00016467717,0.00048468917,0.00033986493,0.000059149606,0.001115921,0.0029365562,0.000010158786],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017546016,0.00025053395,0.00053629203,0.006213027,0.00019330761,0.00012869606,0.0009147837,0.00012838202,0.000046405177,0.023714706,0.2150243,0.75109494],"study_design_scores_gemma":[0.0015592712,0.0003391912,0.00004208051,0.004523295,0.00003668459,0.0000012495655,0.00047222164,0.1194742,0.0000106121715,0.8678265,0.005399899,0.00031476986],"about_ca_topic_score_codex":0.00011830852,"about_ca_topic_score_gemma":0.0010199371,"teacher_disagreement_score":0.8703255,"about_ca_system_score_codex":0.00024840626,"about_ca_system_score_gemma":0.0017958866,"threshold_uncertainty_score":0.9999319},"labels":[],"label_agreement":null},{"id":"W4387999820","doi":"10.1186/s12874-023-02048-7","title":"Can peer effects explain prescribing appropriateness? a social network analysis","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Healthcare Systems and Technology","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"HORIZON EUROPE European Research Council; Universität Hamburg","keywords":"MEDLINE; Social network analysis; Psychology; Medicine; Computer science; Social media; World Wide Web; Political science","score_opus":0.42088403544095593,"score_gpt":0.4889693409148566,"score_spread":0.06808530547390068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387999820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80886376,0.0003848912,0.11921644,0.060033318,0.0025893275,0.001691674,0.0000055852743,0.0015469441,0.0056680436],"genre_scores_gemma":[0.9853419,0.000038635586,0.004080024,0.0013013897,0.0073488364,0.000570727,0.0001099541,0.00006248354,0.0011460137],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98953456,0.004721895,0.0006360907,0.0007772445,0.002440417,0.0018898168],"domain_scores_gemma":[0.9855167,0.012997761,0.0001686989,0.0004783952,0.0007105735,0.00012785816],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062121272,0.00021953942,0.0009636306,0.0018919157,0.0007716602,0.00012636594,0.0008956845,0.00081707124,0.00042398577],"category_scores_gemma":[0.08038443,0.00018208829,0.00026274257,0.008307122,0.00046789215,0.00014328636,0.0011497475,0.0012816202,0.0005181421],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003189014,0.00013725791,0.13849115,0.0040231277,0.0010513068,0.0010740046,0.0007407919,0.00020771712,0.00034686312,0.4078617,0.11505561,0.33069155],"study_design_scores_gemma":[0.0033697202,0.0001797602,0.22062285,0.00040115835,0.0005540793,0.00002502333,0.004858259,0.075888254,0.000073861935,0.24417548,0.4486514,0.0012001649],"about_ca_topic_score_codex":0.017986564,"about_ca_topic_score_gemma":0.025169536,"teacher_disagreement_score":0.33359578,"about_ca_system_score_codex":0.000086464235,"about_ca_system_score_gemma":0.0004889715,"threshold_uncertainty_score":0.99261856},"labels":[],"label_agreement":null},{"id":"W4388522390","doi":"10.1186/s12874-023-02083-4","title":"Developing the intersectionality supplemented Consolidated Framework for Implementation Research (CFIR) and tools for intersectionality considerations","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","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":"University of Toronto; University of Waterloo; University of Calgary; York University; University of British Columbia; Ottawa Hospital; University of Ottawa; McMaster University; Research Institute for Aging; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Intersectionality; Implementation research; Psychological intervention; Privilege (computing); Computer science; Oppression; Medicine; Sociology; Political science; Gender studies; Nursing","score_opus":0.9881782786978075,"score_gpt":0.8610000526475824,"score_spread":0.1271782260502251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388522390","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":[0.14966126,0.0000137873785,0.6711808,0.17150861,0.0010213255,0.005884634,0.0005198363,0.00010901849,0.00010074555],"genre_scores_gemma":[0.45542145,0.00027490893,0.48301157,0.02557413,0.0020090118,0.03236363,0.0007867132,0.00007960426,0.00047899288],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9472598,0.046585415,0.0015074229,0.0007473234,0.0019247576,0.0019752823],"domain_scores_gemma":[0.47322837,0.5227193,0.00021123825,0.00038696543,0.0029649374,0.00048917386],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19449931,0.00015746987,0.00041432382,0.00072152156,0.00553484,0.000120618846,0.00046274692,0.00038118786,0.003785418],"category_scores_gemma":[0.48127848,0.00012139328,0.00008011275,0.0017636251,0.001565008,0.00029929078,0.0007049913,0.0018466372,0.00010329616],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041209126,0.00001866613,0.0068390574,0.00077496504,0.000068799935,0.0000018889707,0.016202867,8.556405e-7,0.00031234673,0.81393313,0.15222517,0.009210159],"study_design_scores_gemma":[0.0019717251,0.00029714618,0.027292334,0.00015999483,0.000009672782,0.000010359934,0.13489142,0.00061714614,0.00031620942,0.6798442,0.15445027,0.00013951294],"about_ca_topic_score_codex":0.0020613258,"about_ca_topic_score_gemma":0.019858122,"teacher_disagreement_score":0.4761339,"about_ca_system_score_codex":0.0007035869,"about_ca_system_score_gemma":0.009968962,"threshold_uncertainty_score":0.9980269},"labels":[],"label_agreement":null},{"id":"W4389192903","doi":"10.1186/s12874-023-02101-5","title":"Advancing guideline quality through country-wide and regional quality assessment of CPGs using AGREE: a scoping review","year":2023,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","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":false,"ca_institutions":"McMaster University","funders":"","keywords":"Grading (engineering); MEDLINE; Guideline; Quality (philosophy); Medicine; Family medicine; Political science; Pathology","score_opus":0.9711081800009462,"score_gpt":0.8268163643059345,"score_spread":0.1442918156950117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389192903","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":[0.000016779455,0.7982037,0.19334483,0.0038342671,0.0003275196,0.0040483023,0.000057150693,0.000059176204,0.00010826276],"genre_scores_gemma":[2.2329449e-7,0.6748995,0.32135293,0.0023521325,0.00060243765,0.00018944843,0.00047058685,0.000078488716,0.000054241937],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.87375134,0.09823813,0.015618555,0.00220223,0.008408804,0.001780966],"domain_scores_gemma":[0.35214677,0.63416827,0.005544302,0.0025494958,0.003974139,0.0016170101],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29850718,0.0005894143,0.008022976,0.00049110607,0.00021404264,0.000024086386,0.0006533396,0.0010836369,0.001157758],"category_scores_gemma":[0.75642693,0.00045921357,0.00076669944,0.0019078599,0.0014250558,0.00020644168,0.0013876532,0.0037184798,0.00002194547],"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":[0.00012327333,0.00015296818,0.00022474804,0.5199969,0.00034505007,0.00008558834,0.000028321767,7.8681137e-7,0.000008695496,0.0012473586,0.0062171584,0.47156915],"study_design_scores_gemma":[0.0015982225,0.0003757301,0.00013334093,0.5915346,0.0015665785,0.00037939122,0.00034688,0.00027193202,7.980257e-7,0.001321295,0.40204975,0.00042148645],"about_ca_topic_score_codex":0.0052598994,"about_ca_topic_score_gemma":0.0029345225,"teacher_disagreement_score":0.53593016,"about_ca_system_score_codex":0.0007516141,"about_ca_system_score_gemma":0.02797176,"threshold_uncertainty_score":0.99978596},"labels":[],"label_agreement":null},{"id":"W4389734370","doi":"10.1186/s12874-023-02121-1","title":"Developing non-response weights to account for attrition-related bias in a longitudinal pregnancy cohort","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Birth, Development, and 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":false,"ca_institutions":"South Health Campus; University of Ottawa; Provincial Laboratory of Public Health; Children's Hospital of Eastern Ontario; University of Calgary; McGill University; Alberta Health Services","funders":"Canadian Institutes of Health Research; Alberta Innovates; Children's Hospital Foundation; Alberta Children's Hospital Foundation; University of Pittsburgh","keywords":"Statistics; Logistic regression; Receiver operating characteristic; Confidence interval; Lasso (programming language); Calibration; Medicine; Cohort; Inverse probability; Mathematics; Cohort study; Computer science; Posterior probability","score_opus":0.6974635528471733,"score_gpt":0.5880876595631711,"score_spread":0.10937589328400221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389734370","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":[0.9026511,0.00043947663,0.06602112,0.026157817,0.0006027321,0.0035467541,0.000012329542,0.00014380371,0.00042491694],"genre_scores_gemma":[0.29891253,0.035492774,0.6514277,0.003726684,0.00086224865,0.006036332,0.00030838477,0.00019457247,0.0030387796],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98860437,0.0058446866,0.0010288467,0.0008968787,0.0019195621,0.0017056314],"domain_scores_gemma":[0.9517633,0.04583796,0.000086229695,0.00045428483,0.0006921462,0.0011660807],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059397522,0.00023057032,0.000963225,0.0019221213,0.00028096346,0.000020564685,0.00040455398,0.0006625928,0.00049788924],"category_scores_gemma":[0.1368874,0.00019068326,0.00012683864,0.0028299796,0.0003426088,0.00006143093,0.0003164445,0.0011889832,0.0005580778],"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":[0.017028492,0.00053864165,0.78896874,0.00455703,0.00031163398,0.002231474,0.004607647,0.000006306969,0.0027065822,0.11152439,0.018794112,0.048724983],"study_design_scores_gemma":[0.004321485,0.00085568556,0.9524005,0.0030685747,0.000018322284,0.00013598567,0.00046820316,0.0009355401,0.00086790987,0.033041734,0.003648652,0.00023741505],"about_ca_topic_score_codex":0.0005247511,"about_ca_topic_score_gemma":0.002278634,"teacher_disagreement_score":0.60373855,"about_ca_system_score_codex":0.0006595604,"about_ca_system_score_gemma":0.010245225,"threshold_uncertainty_score":0.99536574},"labels":[],"label_agreement":null},{"id":"W4390639388","doi":"10.1186/s12874-023-02125-x","title":"Studying missingness in spinal cord injury data: challenges and impact of data imputation","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Spinal Cord Injury 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":false,"ca_institutions":"Praxis Spinal Cord Institute; University of Saskatchewan","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Missing data; Imputation (statistics); Computer science; Data collection; Data mining; Statistics; Mathematics; Machine learning","score_opus":0.884341340141484,"score_gpt":0.7130124636285713,"score_spread":0.17132887651291273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390639388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8968256,0.07909693,0.017846754,0.004220749,0.00026748187,0.0010244069,0.00008894977,0.00006618161,0.00056295865],"genre_scores_gemma":[0.9240531,0.014871885,0.060117457,0.00003591125,0.0005512044,0.000037659083,0.00018517306,0.000050970557,0.00009667827],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9862676,0.0084500555,0.00070273294,0.0012241604,0.0024915268,0.0008639232],"domain_scores_gemma":[0.9744127,0.022433283,0.000062383966,0.0019234385,0.00039911558,0.0007691181],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06586223,0.0001831299,0.0007865948,0.0012987328,0.00006395137,0.000041495547,0.0013049808,0.0003280258,0.00033714643],"category_scores_gemma":[0.1051636,0.0001355743,0.000054156437,0.0010472302,0.001108469,0.00040379545,0.0031398907,0.0019465997,0.000021121452],"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":[0.014611097,0.00017504007,0.0033710888,0.0023813257,0.00011223378,0.0005756265,0.00014315822,1.6521268e-7,0.0029662258,0.00084409636,0.0008802506,0.9739397],"study_design_scores_gemma":[0.005697694,0.0804999,0.7624252,0.009644139,0.00024274677,0.0023262217,0.007103416,0.108047985,0.0010702485,0.014000956,0.008205265,0.0007362224],"about_ca_topic_score_codex":0.0011808616,"about_ca_topic_score_gemma":0.00051680696,"teacher_disagreement_score":0.9732035,"about_ca_system_score_codex":0.0001824851,"about_ca_system_score_gemma":0.0049365265,"threshold_uncertainty_score":0.9618914},"labels":[],"label_agreement":null},{"id":"W4391440615","doi":"10.1186/s12874-023-02134-w","title":"An empirical comparison of statistical methods for multiple cut-off diagnostic test accuracy meta-analysis of the Edinburgh postnatal depression scale (EPDS) depression screening tool using published results vs individual participant data","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Maternal Mental Health During Pregnancy and Postpartum","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":"McGill University Health Centre; McGill University; Jewish General Hospital; University of Waterloo","funders":"Division of Materials Research; National Health and Medical Research Council; Medical Research Council; TrygFonden; Harry Crossley Foundation; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; China Medical University; University of Oxford; Wellcome Trust","keywords":"Bivariate analysis; Meta-analysis; Receiver operating characteristic; Statistics; Depression (economics); Confidence interval; Scale (ratio); Cut-off; Medicine; Computer science; Psychology; Mathematics; Cartography","score_opus":0.8727257486382738,"score_gpt":0.6989856733222872,"score_spread":0.17374007531598656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391440615","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097264297,0.814681,0.17302763,0.0002517915,0.00061713695,0.0036071641,0.0067905486,0.000043702217,0.000008404598],"genre_scores_gemma":[0.0058810683,0.37724733,0.60845506,0.00012816192,0.0006380726,0.0010142218,0.0063901693,0.0001615646,0.00008433599],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.95304614,0.03471318,0.004793663,0.002143284,0.0037940834,0.0015096652],"domain_scores_gemma":[0.53871965,0.45457214,0.0014636262,0.0033179878,0.00066859834,0.0012579997],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.07366975,0.0007067565,0.008723706,0.0012567183,0.000362465,0.00009811374,0.0029660491,0.0013751282,0.00068864285],"category_scores_gemma":[0.59575915,0.00038348112,0.0016924943,0.0021778427,0.0012542965,0.00026497745,0.00389719,0.0034946545,0.000002862141],"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":[0.0056833127,0.0029263136,0.013690764,0.13009247,0.051459294,0.00022097421,0.001152745,0.00005713474,0.000047712223,0.00004920366,0.0037075845,0.7909125],"study_design_scores_gemma":[0.0029799787,0.0021171533,0.0043754997,0.056171544,0.66884285,0.00040525693,0.0003425979,0.20848656,0.00095695385,0.00021286344,0.054247916,0.00086083286],"about_ca_topic_score_codex":0.0006710405,"about_ca_topic_score_gemma":0.0002704992,"teacher_disagreement_score":0.79005164,"about_ca_system_score_codex":0.000101510705,"about_ca_system_score_gemma":0.00350537,"threshold_uncertainty_score":0.9999213},"labels":[],"label_agreement":null},{"id":"W4391716692","doi":"10.1186/s12874-024-02157-x","title":"Model-based standardization using multiple imputation","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Public Health Ontario; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Covariate; Parametric statistics; Computer science; Statistics; Outcome (game theory); Econometrics; Imputation (statistics); Nonparametric statistics; Standardization; Missing data; Data mining; Mathematics; Machine learning","score_opus":0.7575667403630337,"score_gpt":0.646695353916137,"score_spread":0.11087138644689676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391716692","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003215256,0.0001894233,0.9949682,0.00037965277,0.0003120401,0.0002983344,0.00003069146,0.00014340626,0.00046303996],"genre_scores_gemma":[0.070022054,0.000021991724,0.9295338,0.00007240692,0.00020882998,0.00004354056,0.000009079916,0.00003500558,0.00005331449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9860013,0.0106958905,0.00050547917,0.00048686404,0.0017111028,0.0005993596],"domain_scores_gemma":[0.8644107,0.13453357,0.00003961056,0.0002669766,0.00039198718,0.00035717236],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03280723,0.00014060036,0.0003898491,0.00038047234,0.00016520254,0.00008490039,0.00027550122,0.00032959896,0.0008866124],"category_scores_gemma":[0.28792208,0.00011012552,0.00009218387,0.00068800396,0.000490719,0.00007575224,0.00011981187,0.00078280544,0.00002725592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121645026,0.000055393266,0.00013838359,0.00089394924,0.000021648311,0.0000667552,0.00021640965,0.0006492554,0.0016368324,0.7107979,0.0009822551,0.28441957],"study_design_scores_gemma":[0.00016186148,0.00005214232,0.000012745161,0.00014997131,0.000011059048,0.0000075866596,0.000035171717,0.526058,0.0005102889,0.47277597,0.00016375096,0.00006144765],"about_ca_topic_score_codex":0.00006115591,"about_ca_topic_score_gemma":0.000102338665,"teacher_disagreement_score":0.52540874,"about_ca_system_score_codex":0.00017789748,"about_ca_system_score_gemma":0.0026644282,"threshold_uncertainty_score":0.99592847},"labels":[],"label_agreement":null},{"id":"W4391716914","doi":"10.1186/s12874-024-02147-z","title":"Comparison of statistical methods used to meta-analyse results from interrupted time series studies: an empirical study","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Monash University; Medical Research Council; Australian Government","keywords":"Interrupted time series; Interrupted Time Series Analysis; Series (stratigraphy); Meta-analysis; Time series; Computer science; Psychological intervention; Research design; Statistical analysis; Econometrics; Statistics; Data mining; Medicine; Machine learning; Mathematics","score_opus":0.9784031228965239,"score_gpt":0.81904854844297,"score_spread":0.15935457445355383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391716914","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002780316,0.4921082,0.5040647,0.00018703964,0.00019971763,0.00245861,0.00059652724,0.00028912877,0.00006829985],"genre_scores_gemma":[0.0000059744784,0.26852596,0.72919494,0.000032448334,0.00023193056,0.0012831762,0.00017170867,0.00016008671,0.00039376906],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78412867,0.19989277,0.006857774,0.0028644367,0.0047093714,0.0015469897],"domain_scores_gemma":[0.6232934,0.37112746,0.00077610795,0.0024382344,0.0011829934,0.0011817871],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.13498779,0.001169153,0.01756354,0.0018579965,0.00014565473,0.00008082485,0.002896521,0.001545893,0.0021931147],"category_scores_gemma":[0.6552001,0.00071874016,0.0012327669,0.0026155475,0.0020635019,0.00015139038,0.003602706,0.00538307,0.00024589812],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014238638,0.002606505,0.000009655024,0.016538016,0.029601617,0.0005402082,0.014854008,0.000001001151,0.000022116348,0.0055968245,0.043996725,0.88480943],"study_design_scores_gemma":[0.001191757,0.012907038,0.00000493029,0.011783907,0.07060119,0.00006957822,0.01873358,0.0006462292,0.00023981022,0.47522372,0.40667707,0.0019212017],"about_ca_topic_score_codex":0.0002931237,"about_ca_topic_score_gemma":0.0016900896,"teacher_disagreement_score":0.88288826,"about_ca_system_score_codex":0.00057323935,"about_ca_system_score_gemma":0.00299694,"threshold_uncertainty_score":0.9997503},"labels":[],"label_agreement":null},{"id":"W4391843538","doi":"10.1186/s12874-024-02161-1","title":"Identifying biologically implausible values in big longitudinal data: an example applied to child growth data from the Brazilian food and nutrition surveillance system","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Obesity, Physical Activity, Diet","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Agencia Estatal de Investigación; Secretaría de Ciencia y Técnica, Universidad de Buenos Aires; Ministério da Saúde; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Generalitat de Catalunya; Michael Smith Health Research BC; Centres de Recerca de Catalunya; Ministerio de Ciencia e Innovación; Wellcome Trust; Bill and Melinda Gates Foundation","keywords":"Outlier; Anthropometry; Longitudinal study; Population; Longitudinal data; Statistics; Medicine; Demography; Standard score; Mathematics; Environmental health","score_opus":0.6424941625340375,"score_gpt":0.5195192967659227,"score_spread":0.12297486576811478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391843538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95541036,0.0025023886,0.035298713,0.0037437072,0.00046658606,0.0014966378,0.0005237612,0.00018133895,0.000376486],"genre_scores_gemma":[0.97854525,0.00047370538,0.017434152,0.00019803608,0.0019624813,0.00012882201,0.0012107685,0.000035445613,0.000011312252],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9863169,0.008722565,0.00054971577,0.0019598573,0.0015664948,0.00088442274],"domain_scores_gemma":[0.95948946,0.037449386,0.000050665192,0.0021332924,0.0001491265,0.00072807947],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03360306,0.00024607425,0.0008723712,0.000306191,0.00025364404,0.00016741129,0.0018925684,0.00035071108,0.00010666416],"category_scores_gemma":[0.02339148,0.00016001817,0.000045585835,0.0011430739,0.0007403535,0.00024462744,0.0040845806,0.0016849776,0.00008558992],"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":[0.006383686,0.01306716,0.65156084,0.015470143,0.0013218643,0.0021288474,0.0023936364,0.0000028255872,0.027082589,0.11895621,0.021986503,0.13964568],"study_design_scores_gemma":[0.0017907626,0.0015614595,0.96760637,0.001449643,0.00006612546,0.0002219658,0.0018613243,0.0041235737,0.00062714453,0.018312065,0.0020623766,0.0003171982],"about_ca_topic_score_codex":0.0067648673,"about_ca_topic_score_gemma":0.022213759,"teacher_disagreement_score":0.3160455,"about_ca_system_score_codex":0.00013110618,"about_ca_system_score_gemma":0.0005030735,"threshold_uncertainty_score":0.9998492},"labels":[],"label_agreement":null},{"id":"W4392589283","doi":"10.1186/s12874-024-02188-4","title":"The minimal important difference of patient-reported outcome measures related to female urinary incontinence: a systematic review","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Pelvic floor disorders treatments","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 Alberta","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Urinary incontinence; CINAHL; Medicine; Context (archaeology); MEDLINE; Data extraction; Minimal clinically important difference; Metric (unit); Systematic review; Meta-analysis; Physical therapy; Surgery; Internal medicine; Randomized controlled trial; Nursing; Psychological intervention","score_opus":0.4709880894199534,"score_gpt":0.5589640709861257,"score_spread":0.08797598156617226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392589283","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":[0.00020854855,0.9877426,0.000104292005,0.00087230466,0.000544991,0.0099808425,0.000025964893,0.00008668362,0.0004337441],"genre_scores_gemma":[0.00005662687,0.99017906,0.0027749785,0.00018250057,0.000056858145,0.003553546,0.00007025337,0.00011787081,0.0030083254],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9571199,0.027986778,0.0067096413,0.0013773689,0.0054140687,0.001392232],"domain_scores_gemma":[0.9442698,0.049140263,0.0014672568,0.002722787,0.0009828976,0.0014170245],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049924172,0.0007945269,0.009075365,0.0008542119,0.00018033035,0.000029463179,0.0014277251,0.0010628705,0.00031849154],"category_scores_gemma":[0.3853919,0.0003833446,0.001468769,0.0024398172,0.0011432276,0.000026147009,0.0012530778,0.00309666,0.00031145968],"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":[0.00015301147,0.00034173694,0.0002709024,0.8750292,0.0017582608,0.0021745237,0.0001763273,7.638729e-9,0.0000012035944,0.00018141209,0.0010898104,0.118823625],"study_design_scores_gemma":[0.00074956135,0.0019838964,0.000072259754,0.937105,0.010264259,0.0035876925,0.00030825092,0.000013244974,0.0000011204969,0.00034606803,0.045196343,0.00037228866],"about_ca_topic_score_codex":0.00014240152,"about_ca_topic_score_gemma":0.00007776148,"teacher_disagreement_score":0.3354677,"about_ca_system_score_codex":0.00042190796,"about_ca_system_score_gemma":0.0066387756,"threshold_uncertainty_score":0.99986184},"labels":[],"label_agreement":null},{"id":"W4392656250","doi":"10.1186/s12874-024-02192-8","title":"Text analysis framework for identifying mutations among non-small cell lung cancer patients from laboratory data","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Lexical analysis; Natural language processing; Artificial intelligence; Information extraction; Syntax; Context (archaeology); Population; Information retrieval; Medicine","score_opus":0.35480033034478203,"score_gpt":0.5470634171707748,"score_spread":0.19226308682599275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392656250","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34034356,0.0069747,0.6508814,0.00029328736,0.00058422325,0.00024764714,0.0006030305,0.000028919423,0.00004320733],"genre_scores_gemma":[0.43780947,0.0017103476,0.5536845,0.00034893223,0.0015936184,0.0005343574,0.003670315,0.00006403657,0.0005844233],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944894,0.0026022126,0.00043229514,0.0010689407,0.0007377514,0.0006693996],"domain_scores_gemma":[0.9840954,0.014192118,0.0000705738,0.0008666943,0.00034750276,0.0004277422],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008110223,0.00017686567,0.00041891035,0.00032306003,0.00019765533,0.000085254374,0.0012114913,0.0008554631,0.00043765042],"category_scores_gemma":[0.044936374,0.00014627713,0.00016584745,0.0009987368,0.0007718177,0.00000843697,0.0009207528,0.0007664572,0.000015162317],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008063516,0.0009111928,0.5090109,0.0030697896,0.006898306,0.00014582276,0.0028532126,0.00013148504,0.038867336,0.0010435117,0.14041549,0.2958466],"study_design_scores_gemma":[0.006230558,0.0021881,0.35908094,0.0025440322,0.0055212453,0.0000043817186,0.00715178,0.271979,0.07596464,0.021649875,0.2447876,0.0028978596],"about_ca_topic_score_codex":0.0008112251,"about_ca_topic_score_gemma":0.0026629146,"teacher_disagreement_score":0.29294875,"about_ca_system_score_codex":0.00004180392,"about_ca_system_score_gemma":0.0013984283,"threshold_uncertainty_score":0.96310854},"labels":[],"label_agreement":null},{"id":"W4393008884","doi":"10.1186/s12874-024-02156-y","title":"An empirical evaluation of approximate and exact regression-based causal mediation approaches for a binary outcome and a continuous or a binary mediator for case-control study designs","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre; Université de Montréal; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Outcome (game theory); Estimator; Context (archaeology); Mediation; Logistic regression; Causal inference; Statistics; Binary number; Regression analysis; Parametric statistics; Regression; Computer science; Econometrics; Mathematics","score_opus":0.8753729356200297,"score_gpt":0.6686037868933843,"score_spread":0.20676914872664542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393008884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38238388,0.00040026344,0.61186725,0.00038457641,0.000072568444,0.0046891663,0.00007731073,0.00012164977,0.000003341555],"genre_scores_gemma":[0.5899888,0.000017719887,0.40540534,0.000027702556,0.0001384321,0.0043398403,0.0000227106,0.000048948656,0.000010477089],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97958297,0.016219204,0.0009958225,0.0008522554,0.0017041528,0.00064562215],"domain_scores_gemma":[0.84567976,0.15268336,0.00017645684,0.00040238243,0.0006438909,0.00041413525],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0906725,0.0002863589,0.0010418494,0.0006614878,0.00018614152,0.00004810103,0.00027051865,0.0005131958,0.000121583296],"category_scores_gemma":[0.21931003,0.00018605673,0.00009321883,0.0003984308,0.0007234795,0.00018788243,0.0001233611,0.0005852776,3.712569e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028044162,0.0068088863,0.061602447,0.021651007,0.0011091353,0.0017398184,0.017264966,0.00011474491,0.017395206,0.03139863,0.0037224276,0.80914855],"study_design_scores_gemma":[0.0047132056,0.008311931,0.0009586082,0.00025291782,0.0004051929,0.00017802321,0.0050798533,0.8613454,0.0007751282,0.11770263,0.000019133633,0.0002579667],"about_ca_topic_score_codex":0.000022759046,"about_ca_topic_score_gemma":0.00026472917,"teacher_disagreement_score":0.8612307,"about_ca_system_score_codex":0.00014865721,"about_ca_system_score_gemma":0.0018514836,"threshold_uncertainty_score":0.936344},"labels":[],"label_agreement":null},{"id":"W4393043563","doi":"10.1186/s12874-024-02199-1","title":"Development of the multivariate administrative data cystectomy model and its impact on misclassification bias","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Bladder and Urothelial Cancer Treatments","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":"Carleton University; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Cystectomy; Medicine; Bladder cancer; Logistic regression; Multivariate analysis; Multivariate statistics; Covariate; Statistics; Urinary diversion; Urology; Internal medicine; Mathematics; Cancer","score_opus":0.837076198824331,"score_gpt":0.637161082707123,"score_spread":0.19991511611720802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393043563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92434937,0.0033522143,0.059960064,0.005833237,0.00035318063,0.0018911834,0.00020619125,0.00006771635,0.0039868173],"genre_scores_gemma":[0.95510536,0.00014897335,0.043591402,0.000083699655,0.00009953739,0.00007833442,0.000037399288,0.00001841588,0.0008368736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99494684,0.0027400164,0.00034791947,0.00048495343,0.0011575522,0.0003227115],"domain_scores_gemma":[0.98944896,0.009429357,0.00004536526,0.0005771189,0.00015769147,0.00034147486],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009371131,0.00013179946,0.0003381117,0.00015602598,0.000100950325,0.000014390215,0.00036332468,0.00018554358,0.00023941873],"category_scores_gemma":[0.01771842,0.00006560307,0.000055957593,0.0003313861,0.00029374514,0.00004439965,0.00031893537,0.0006164536,0.000023756535],"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":[0.013388937,0.0022381651,0.0055363644,0.005442748,0.0032075862,0.00035957625,0.02061649,0.00006809069,0.1295994,0.039376136,0.008679149,0.77148736],"study_design_scores_gemma":[0.009927363,0.0034841462,0.19133453,0.0049814293,0.0004791623,0.00048351887,0.0021920216,0.65280735,0.112331875,0.007341324,0.014055295,0.0005819758],"about_ca_topic_score_codex":0.00008158127,"about_ca_topic_score_gemma":0.00014289263,"teacher_disagreement_score":0.7709054,"about_ca_system_score_codex":0.00013271751,"about_ca_system_score_gemma":0.006603432,"threshold_uncertainty_score":0.9990282},"labels":[],"label_agreement":null},{"id":"W4393223594","doi":"10.1186/s12874-024-02189-3","title":"Evaluating methods for risk prediction of Covid-19 mortality in nursing home residents before and after vaccine availability: a retrospective cohort study","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Geriatric Care and Nursing Homes","field":"Health Professions","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":"Ministry of Health and Long Term Care; University of Toronto; McMaster University; Impact","funders":"Canadian Institutes of Health Research; Public Health Agency; Public Health Agency of Canada; McMaster University","keywords":"Logistic regression; Medicine; Receiver operating characteristic; Random forest; Retrospective cohort study; Coronavirus disease 2019 (COVID-19); Cohort; Cart; Lasso (programming language); Cohort study; Discriminative model; Regression analysis; Regression; Machine learning; Statistics; Emergency medicine; Computer science; Internal medicine; Geography; Mathematics","score_opus":0.4959599838740073,"score_gpt":0.6939486744791862,"score_spread":0.19798869060517887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393223594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82457244,0.0017051747,0.16716821,0.00077294227,0.0014138309,0.0041628066,0.000082680264,0.00006866663,0.000053236654],"genre_scores_gemma":[0.87033296,0.0003847314,0.12555952,0.000050154697,0.0007798362,0.0025475866,0.000031495747,0.00004804292,0.00026564905],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9097207,0.08513027,0.0014636905,0.0011138174,0.0016310412,0.00094046775],"domain_scores_gemma":[0.9050194,0.09293912,0.00019317027,0.00058541284,0.0006762648,0.00058665115],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24841145,0.00019234432,0.0010663965,0.0008419637,0.0004285608,0.000016544594,0.0002565838,0.00057976745,0.0006743635],"category_scores_gemma":[0.3175456,0.00015474783,0.00011835339,0.001197203,0.00047294825,0.00010017295,0.00028344648,0.0021421423,0.000004400552],"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":[0.0015799834,0.00019870538,0.92972946,0.00165245,0.000101987935,0.000014903551,0.019390179,0.0000014921181,0.00006156477,0.00022664794,0.00069043355,0.046352185],"study_design_scores_gemma":[0.0018760565,0.0016592151,0.8984486,0.00060352526,0.00017776522,0.0000052910636,0.01097902,0.005306956,0.000007868684,0.08079791,0.00005499904,0.00008277544],"about_ca_topic_score_codex":0.008568752,"about_ca_topic_score_gemma":0.012217593,"teacher_disagreement_score":0.080571264,"about_ca_system_score_codex":0.0013741216,"about_ca_system_score_gemma":0.0036566039,"threshold_uncertainty_score":0.9980333},"labels":[],"label_agreement":null},{"id":"W4394575910","doi":"10.1186/s12874-024-02185-7","title":"Segmentation of patients with small cell lung cancer into responders and non-responders using the optimal cross-validation technique","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Michael Smith Health Research BC","keywords":"Cutoff; Medicine; Hazard ratio; Proportional hazards model; Segmentation; Statistics; Oncology; Internal medicine; Artificial intelligence; Computer science; Mathematics; Confidence interval","score_opus":0.24529009745935876,"score_gpt":0.5452051262053038,"score_spread":0.29991502874594506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394575910","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4249702,0.00031707648,0.5731718,0.0008413809,0.00012277359,0.0005280173,0.0000015479814,0.000029197521,0.000017973847],"genre_scores_gemma":[0.35958096,0.000061253384,0.63993645,0.0001009853,0.000059326434,0.00016676963,0.000005561307,0.000018794548,0.00006988099],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98722297,0.010003568,0.00037728884,0.00056458154,0.0013729163,0.00045866796],"domain_scores_gemma":[0.981699,0.017133763,0.000099695935,0.00041238827,0.00043624037,0.00021890737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021519426,0.0001304431,0.00022854413,0.0004593655,0.00025778197,0.00012610767,0.0007670873,0.00028091288,0.00007916463],"category_scores_gemma":[0.007430182,0.000085186766,0.00003617532,0.00097300636,0.00066331105,0.00020420807,0.00053459377,0.0013140613,0.0000012293028],"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":[0.0029526195,0.00022329246,0.6695442,0.010311928,0.0001900914,0.00013230999,0.037911627,0.019190436,0.03309381,0.010464891,0.00064909237,0.21533565],"study_design_scores_gemma":[0.0012910627,0.0010064641,0.060509034,0.00077104714,0.000029510347,0.000021448319,0.0008850466,0.9037773,0.029088266,0.0018576409,0.00044625165,0.00031693652],"about_ca_topic_score_codex":0.0022047155,"about_ca_topic_score_gemma":0.00024311608,"teacher_disagreement_score":0.8845869,"about_ca_system_score_codex":0.00019843185,"about_ca_system_score_gemma":0.0022088746,"threshold_uncertainty_score":0.8895158},"labels":[],"label_agreement":null},{"id":"W4394576834","doi":"10.1186/s12874-024-02195-5","title":"Describing the content of trial recruitment interventions using the TIDieR reporting checklist: a systematic methodology review","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Ethics in Clinical Research","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":"University of Ottawa; Ottawa Hospital","funders":"Medical Research Council; Canadian Institutes of Health Research","keywords":"Checklist; Psychological intervention; Systematic review; Fidelity; Randomized controlled trial; Categorical variable; MEDLINE; Research design; Intervention (counseling); Descriptive statistics; Clinical trial; Computer science; Medicine; Psychology; Statistics; Nursing; Pathology","score_opus":0.9960468044529112,"score_gpt":0.7979322032940379,"score_spread":0.19811460115887325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394576834","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":[0.025214793,0.2917085,0.5755866,0.08207637,0.0034532757,0.019892113,0.000009931865,0.00013926729,0.0019191236],"genre_scores_gemma":[0.09375904,0.14196227,0.7110744,0.010150743,0.005291256,0.013501554,0.00004917665,0.00040785797,0.023803711],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.71423596,0.25081345,0.015532567,0.00237779,0.014108595,0.002931661],"domain_scores_gemma":[0.053295832,0.9367305,0.0019116532,0.0032276525,0.0036724727,0.001161909],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.62277377,0.00026369648,0.0023883756,0.0004131609,0.00040125227,0.00006232194,0.0013446282,0.000775507,0.0015295309],"category_scores_gemma":[0.9520773,0.00012294625,0.001433678,0.0015903421,0.003558862,0.000058531354,0.0014519738,0.007966826,0.000043690932],"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":[0.009555572,0.00082192034,0.00031551663,0.7261618,0.002605086,0.001393873,0.0028814215,0.0000055532823,0.008069979,0.20998524,0.004601268,0.03360279],"study_design_scores_gemma":[0.012253804,0.004860692,0.00020145405,0.8896285,0.003120362,0.003938929,0.010978219,0.009179696,0.0029169954,0.058995534,0.0034693591,0.0004564449],"about_ca_topic_score_codex":0.00065207464,"about_ca_topic_score_gemma":0.00054043136,"teacher_disagreement_score":0.685917,"about_ca_system_score_codex":0.00041784617,"about_ca_system_score_gemma":0.0076461774,"threshold_uncertainty_score":0.9993832},"labels":[],"label_agreement":null},{"id":"W4394958256","doi":"10.1186/s12874-024-02210-9","title":"Application of causal inference methods in individual-participant data meta-analyses in medicine: addressing data handling and reporting gaps with new proposed reporting guidelines","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Institute of Genetics; National Institute on Alcohol Abuse and Alcoholism; Universitätsklinikum Heidelberg; Canadian Institutes of Health Research; European Commission","keywords":"Causal inference; Inference; MEDLINE; Meta-analysis; Data science; Computer science; Medicine; Psychology; Data mining; Artificial intelligence","score_opus":0.9950486106954662,"score_gpt":0.8322164748674158,"score_spread":0.16283213582805045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394958256","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000078617195,0.51387644,0.48457366,0.00019607638,0.0000373722,0.0011789558,0.000027515716,0.000072054754,0.000030039904],"genre_scores_gemma":[0.00001574113,0.4071996,0.5919271,0.000014663951,0.00017660267,0.0002376635,0.00032355465,0.00007550068,0.000029560375],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9055645,0.04879054,0.031557504,0.0055107926,0.0061618746,0.002414777],"domain_scores_gemma":[0.39232743,0.5349138,0.04785432,0.01951433,0.0032423832,0.002147754],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33174077,0.0007644609,0.009966109,0.0020330527,0.0000967391,0.00008062248,0.0033581357,0.0010299422,0.0001023519],"category_scores_gemma":[0.89496875,0.0004392756,0.0001955549,0.0030624892,0.0014829874,0.0003970282,0.0068161907,0.0040823002,0.0000013989803],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003788037,0.00007412397,0.0001170925,0.038651254,0.0019913423,0.00042985004,0.00050435524,0.000004901753,0.0001837941,0.0027477778,0.0006714506,0.95458615],"study_design_scores_gemma":[0.0017069118,0.0010718121,0.0000705219,0.2623882,0.10037695,0.0026136488,0.004059404,0.040384274,0.0008069925,0.4948292,0.088761695,0.0029303757],"about_ca_topic_score_codex":0.004615001,"about_ca_topic_score_gemma":0.008151507,"teacher_disagreement_score":0.9516558,"about_ca_system_score_codex":0.00011248483,"about_ca_system_score_gemma":0.008537846,"threshold_uncertainty_score":0.9998059},"labels":[],"label_agreement":null},{"id":"W4395695382","doi":"10.1186/s12874-024-02220-7","title":"Ascertaining the Francophone population in Ontario: validating the language variable in health data","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":10,"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 Ottawa; Ottawa Hospital; University of Manitoba; Statistics Canada; Université de Moncton; Élisabeth Bruyère Hospital; Institut du Savoir Montfort","funders":"Ontario Ministry of Health and Long-Term Care","keywords":"Concordance; Kappa; Medicine; Cohen's kappa; Population; Health care; Demography; Gerontology; Family medicine; Statistics; Environmental health; Mathematics","score_opus":0.7409255953201449,"score_gpt":0.6843500919442113,"score_spread":0.056575503375933645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395695382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66524386,0.024370719,0.07564544,0.19606379,0.008030745,0.005511914,0.000053526623,0.00036917406,0.024710853],"genre_scores_gemma":[0.9597101,0.00036671513,0.03279029,0.0037216833,0.0005590296,0.0005905001,0.00020063166,0.00003606712,0.0020249481],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.88532704,0.11047474,0.0013460099,0.00054386654,0.0011512308,0.0011570943],"domain_scores_gemma":[0.7791566,0.21842524,0.00014649681,0.0019365225,0.00013193647,0.00020320498],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1899516,0.00010225022,0.00034589518,0.00026267057,0.00091239833,0.000025447902,0.0017933643,0.00032485143,0.0024437108],"category_scores_gemma":[0.11527353,0.00005886604,0.000026990689,0.00117376,0.00019444885,0.000077278564,0.0014229795,0.0074911797,0.00010657098],"study_design_candidate":"qualitative","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":[0.00035523254,0.0000947202,0.4192131,0.0032005794,0.000035574758,0.00005275522,0.3141821,0.00021655206,0.00006246134,0.082263954,0.016053108,0.16426988],"study_design_scores_gemma":[0.0012497368,0.0002911047,0.24484017,0.016933668,0.0000068196364,0.00003669001,0.357997,0.22931208,0.000005116716,0.03782205,0.11116722,0.00033836113],"about_ca_topic_score_codex":0.8311553,"about_ca_topic_score_gemma":0.88827187,"teacher_disagreement_score":0.2944663,"about_ca_system_score_codex":0.00073393557,"about_ca_system_score_gemma":0.008223437,"threshold_uncertainty_score":0.9984682},"labels":[],"label_agreement":null},{"id":"W4396636695","doi":"10.1186/s12874-024-02233-2","title":"Protocol implementation during the COVID-19 pandemic: experiences from a randomized trial of stress ulcer prophylaxis","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Nosocomial Infections in ICU","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; St. Joseph’s Healthcare Hamilton; Impact; Université Laval; Dalhousie University; University of Toronto; Queen's University; McMaster University","funders":"Canadian Institutes of Health Research; Physicians' Services Incorporated Foundation; Intensive Care Society; McMaster University","keywords":"Interquartile range; Medicine; Pandemic; Informed consent; Randomized controlled trial; Protocol (science); Stress ulcer; Coronavirus disease 2019 (COVID-19); Clinical trial; Emergency medicine; Internal medicine; Alternative medicine; Pathology","score_opus":0.5536666683700735,"score_gpt":0.6466324006324278,"score_spread":0.09296573226235427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396636695","genre_codex":"empirical","genre_gemma":"protocol","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":[0.8315252,0.00021209869,0.04178974,0.0020804205,0.00084722874,0.12301758,0.000022874592,0.00013919394,0.00036563727],"genre_scores_gemma":[0.3132025,0.00023504975,0.019526845,0.00035155477,0.0028447504,0.6632678,0.000031880052,0.000050352584,0.0004892612],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9679155,0.027917247,0.001005882,0.00054044614,0.0021016763,0.0005192935],"domain_scores_gemma":[0.9024325,0.09626393,0.00012308003,0.0004720484,0.00023817491,0.00047027698],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04265031,0.00015894324,0.0008901398,0.00040414536,0.00022818749,0.000042814085,0.0003840239,0.00032841958,0.009684495],"category_scores_gemma":[0.16694112,0.0000853151,0.00028308816,0.0007494115,0.0024810198,0.000067606416,0.0002919589,0.0012399491,0.000023868646],"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":[0.9284642,0.00027845538,0.0051267254,0.001867905,0.00040685455,0.00012345306,0.014514842,0.0000036172505,0.011331711,0.0016417467,0.0024254485,0.03381506],"study_design_scores_gemma":[0.92362547,0.0024144822,0.00036148663,0.00036906224,0.00012212008,0.00018413064,0.01673878,0.0002993569,0.028168652,0.009245706,0.018267274,0.00020348415],"about_ca_topic_score_codex":0.004242661,"about_ca_topic_score_gemma":0.0011529514,"teacher_disagreement_score":0.54025024,"about_ca_system_score_codex":0.0002942653,"about_ca_system_score_gemma":0.0039061853,"threshold_uncertainty_score":0.9912208},"labels":[],"label_agreement":null},{"id":"W4396803002","doi":"10.1186/s12874-024-02217-2","title":"An evaluation of computational methods for aggregate data meta-analyses of diagnostic test accuracy studies","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo","keywords":"Laplace's method; Generalized linear mixed model; Confidence interval; Statistics; Sensitivity (control systems); Algorithm; Computer science; Context (archaeology); Mathematics; Mean squared error; Bayesian probability","score_opus":0.9966886755845052,"score_gpt":0.8547950724739578,"score_spread":0.14189360311054744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396803002","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":[0.0034423377,0.0878211,0.9050691,0.0015905012,0.000327938,0.0014285379,0.00018350504,0.0000063248367,0.00013060991],"genre_scores_gemma":[0.06673297,0.0009122665,0.9312292,0.00006845039,0.00017895004,0.00043448704,0.0001265156,0.000018781615,0.00029837736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.23346932,0.7073126,0.01926971,0.0033283997,0.035768084,0.0008519165],"domain_scores_gemma":[0.00411485,0.9734258,0.002653365,0.0050880937,0.014331337,0.00038654165],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90476435,0.00028313033,0.006772812,0.0014081319,0.00014252677,0.00021018242,0.0051927143,0.00020988676,0.012979648],"category_scores_gemma":[0.99476427,0.00012521914,0.001892509,0.0031627736,0.0011231749,0.0004022864,0.0009458951,0.00043064586,0.0001272872],"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":[0.0000376657,0.0002362828,0.00031627688,0.0012934261,0.011469126,0.0000055602623,0.0007385001,0.0028810967,0.0012329975,0.008660562,0.029597804,0.9435307],"study_design_scores_gemma":[0.00024534416,0.00024297442,0.0003603321,0.000111497124,0.010433854,0.000012520869,0.0012044675,0.6903214,0.0008817626,0.28628215,0.009802739,0.000100968915],"about_ca_topic_score_codex":0.000072415314,"about_ca_topic_score_gemma":0.00017539173,"teacher_disagreement_score":0.9434297,"about_ca_system_score_codex":0.000046193225,"about_ca_system_score_gemma":0.0028335138,"threshold_uncertainty_score":0.9879226},"labels":[],"label_agreement":null},{"id":"W4396959522","doi":"10.1186/s12874-024-02243-0","title":"Multimorbidity prevalence and health outcome prediction: assessing the impact of lookback periods, disease count, and definition criteria in health administrative data at the population-based level","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Chronic Disease Management Strategies","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":true,"ca_institutions":"Université Laval; Institut National de Santé Publique du Québec; McGill University Health Centre; Centre hospitalier universitaire de Québec","funders":"Fonds de Recherche du Québec - Santé","keywords":"Medicine; Polypharmacy; Population; Chronic disease; Demography; Chronic condition; Disease; Emergency medicine; Family medicine; Pediatrics; Environmental health; Gerontology; Internal medicine","score_opus":0.8830429518742547,"score_gpt":0.6921976952203602,"score_spread":0.1908452566538945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396959522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8752004,0.025466172,0.027767627,0.06593742,0.00032030098,0.003185606,0.0017874136,0.00007734688,0.00025770592],"genre_scores_gemma":[0.9923475,0.0020682372,0.004315037,0.0003809656,0.00014991827,0.00007453089,0.0005408923,0.000016669463,0.0001062933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9892666,0.007884078,0.0006870768,0.0005953431,0.0011001403,0.0004668028],"domain_scores_gemma":[0.98371136,0.014804681,0.00012262046,0.00072553457,0.00009719153,0.00053863705],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029008321,0.00015614105,0.00044178727,0.00017743338,0.00028585922,0.00009678253,0.00027745988,0.00008186069,0.0007875587],"category_scores_gemma":[0.016966756,0.00008721264,0.00005764991,0.0003595617,0.0012190407,0.00017530039,0.00043963155,0.00064084824,0.0000024793578],"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":[0.00058338855,0.00021715279,0.96862495,0.011277857,0.00008409205,0.00007447483,0.00044662287,0.000023338438,0.000010284171,0.002222933,0.0053344276,0.011100464],"study_design_scores_gemma":[0.00078959554,0.00036977333,0.92087805,0.0011352898,0.000030818173,0.00002492403,0.000456672,0.07504261,7.4410434e-7,0.0010627368,0.00015551374,0.000053259817],"about_ca_topic_score_codex":0.005341461,"about_ca_topic_score_gemma":0.002171569,"teacher_disagreement_score":0.11714705,"about_ca_system_score_codex":0.0005249888,"about_ca_system_score_gemma":0.007523342,"threshold_uncertainty_score":0.99984026},"labels":[],"label_agreement":null},{"id":"W4399892012","doi":"10.1186/s12874-024-02246-x","title":"Features of databases that supported searching for rapid evidence synthesis during COVID-19: implications for future public health emergencies","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University Medical Centre; McMaster University","funders":"Public Health Agency; Public Health Agency of Canada; McMaster University","keywords":"Context (archaeology); Usability; Evidence-based practice; Data science; Evidence-based medicine; Computer science; Dissemination; Public health; Pandemic; MEDLINE; Coronavirus disease 2019 (COVID-19); Database; World Wide Web; Medicine; Political science; Alternative medicine; Geography; Nursing","score_opus":0.9831789350032875,"score_gpt":0.7533658826954909,"score_spread":0.22981305230779658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399892012","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":[0.006385644,0.025889684,0.85208327,0.112178095,0.00046180724,0.0024279412,0.00045102875,0.00002438099,0.00009814146],"genre_scores_gemma":[0.26202497,0.012295969,0.71212804,0.0016174229,0.0016715344,0.0054841866,0.00017048174,0.00008377972,0.0045236233],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6476835,0.31483912,0.012548864,0.004090606,0.018065294,0.0027725967],"domain_scores_gemma":[0.10435136,0.88276476,0.0019389266,0.0049995636,0.00322438,0.0027210186],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.71999735,0.00028498465,0.0033475498,0.0018488318,0.00089099264,0.00044558558,0.0036380826,0.00021402034,0.011253397],"category_scores_gemma":[0.932092,0.00014774123,0.0017138169,0.0029550036,0.0006894578,0.00039172222,0.00064209435,0.0006472939,0.00005937971],"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":[0.00013077562,0.00010973068,0.006542558,0.010228309,0.0005671191,0.0000069133766,0.0027835856,0.000008505607,0.0014271573,0.09639926,0.3156872,0.5661089],"study_design_scores_gemma":[0.000547484,0.00047006115,0.08339183,0.0009952576,0.00029949128,0.00019873728,0.024106279,0.0059559136,0.0014013816,0.043554507,0.8385512,0.00052783266],"about_ca_topic_score_codex":0.00018469062,"about_ca_topic_score_gemma":0.001244493,"teacher_disagreement_score":0.56792563,"about_ca_system_score_codex":0.0001642972,"about_ca_system_score_gemma":0.007935189,"threshold_uncertainty_score":0.9976889},"labels":[],"label_agreement":null},{"id":"W4400599257","doi":"10.1186/s12874-024-02273-8","title":"SurvdigitizeR: an algorithm for automated survival curve digitization","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; York University; Hospital for Sick Children; Public Health Ontario","funders":"","keywords":"Digitization; Algorithm; Computer science; Censoring (clinical trials); Mean squared error; Artificial intelligence; Statistics; Mathematics; Pattern recognition (psychology); Computer vision","score_opus":0.8083186803653117,"score_gpt":0.6766793295584699,"score_spread":0.13163935080684186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400599257","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017886498,0.00020746284,0.99128157,0.00040922186,0.00054657256,0.0008651672,0.00008050799,0.003373927,0.0014469215],"genre_scores_gemma":[0.0043328907,0.00020131591,0.9929213,0.00006572774,0.0006270848,0.0005948836,0.0001728805,0.00010407567,0.0009798422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9856981,0.010178166,0.0006779403,0.0007490044,0.0016734408,0.0010233416],"domain_scores_gemma":[0.8689452,0.12919284,0.000058481066,0.0005194496,0.00073212414,0.0005519119],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043371756,0.00022924933,0.0006207895,0.00048782738,0.000162032,0.00014634038,0.0006642517,0.0005715738,0.0005433795],"category_scores_gemma":[0.16955072,0.000189426,0.00013066421,0.000797667,0.000713791,0.0003632659,0.00026247627,0.0008846831,0.000048791586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055320554,0.00013036496,0.000046903217,0.00050392386,0.00004759922,0.00007276624,0.00022598039,0.0000019227853,0.0005456158,0.49552447,0.008954152,0.493891],"study_design_scores_gemma":[0.0002886463,0.00049971935,0.000040889998,0.00019923935,0.000013448807,0.0000407652,0.00020839543,0.22746615,0.0026539704,0.7586538,0.009729596,0.00020536479],"about_ca_topic_score_codex":0.00008487943,"about_ca_topic_score_gemma":0.000352981,"teacher_disagreement_score":0.49368563,"about_ca_system_score_codex":0.00018265758,"about_ca_system_score_gemma":0.0015125653,"threshold_uncertainty_score":0.9850501},"labels":[],"label_agreement":null},{"id":"W4401273264","doi":"10.1186/s12874-024-02284-5","title":"Can supervised deep learning architecture outperform autoencoders in building propensity score models for matching?","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoencoder; Propensity score matching; Artificial intelligence; Computer science; Machine learning; Deep learning; Supervised learning; Matching (statistics); Unsupervised learning; Observational study; Variance (accounting); Statistics; Artificial neural network; Mathematics","score_opus":0.7400976786095773,"score_gpt":0.5810570523530081,"score_spread":0.15904062625656923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401273264","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12551333,0.0003384064,0.8703568,0.0015580694,0.00013667243,0.0011815708,0.0000046146233,0.00047217504,0.00043834004],"genre_scores_gemma":[0.21901543,0.00013593417,0.7796817,0.0001024626,0.00017432657,0.00053625857,0.000009674103,0.000080471924,0.0002637372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9897632,0.0059753386,0.0006849127,0.0008344821,0.0013984818,0.0013435608],"domain_scores_gemma":[0.93853605,0.060290914,0.000057843274,0.00042522902,0.00026396985,0.00042597673],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036705654,0.0002852754,0.000807647,0.0007947055,0.00022905214,0.00007876803,0.00079070736,0.00056519447,0.00020066327],"category_scores_gemma":[0.09709975,0.00022257063,0.00015989845,0.0007049383,0.0005977142,0.00017507178,0.0005622273,0.0035368386,0.000005454438],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000516354,0.00012963648,0.00079969113,0.004294736,0.000073920986,0.00029129972,0.009550062,0.0062731113,0.005440981,0.739445,0.00030242628,0.23288283],"study_design_scores_gemma":[0.00028732728,0.00025061317,0.000034491353,0.0006747518,0.000009880229,0.00004994519,0.00056415354,0.2363728,0.001360049,0.7599655,0.00024846816,0.0001820368],"about_ca_topic_score_codex":0.0005268015,"about_ca_topic_score_gemma":0.004681815,"teacher_disagreement_score":0.2327008,"about_ca_system_score_codex":0.0003835712,"about_ca_system_score_gemma":0.0013110093,"threshold_uncertainty_score":0.9987621},"labels":[],"label_agreement":null},{"id":"W4402487736","doi":"10.1186/s12874-024-02300-8","title":"Adaptation and psychometric assessment of a sexual and reproductive empowerment scale in Arabic among refugee and non-refugee adolescent girls","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Adolescent Sexual and Reproductive Health","field":"Health Professions","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":"International Development Research Centre","keywords":"Refugee; Empowerment; Scale (ratio); Arabic; Adaptation (eye); Psychology; Psychometrics; Reproductive health; Clinical psychology; Medicine; Population; Political science; Geography; Environmental health; Cartography","score_opus":0.5119172553154959,"score_gpt":0.6224932999255126,"score_spread":0.11057604461001669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402487736","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97007275,0.0052125216,0.01869211,0.0031116095,0.00073548005,0.0019276752,0.000010319338,0.000036146197,0.00020138062],"genre_scores_gemma":[0.97584766,0.0029971967,0.01924936,0.00016017279,0.00058886665,0.00027197,0.000010573668,0.00003532382,0.00083886756],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9799063,0.015267649,0.0010459367,0.001524735,0.0013182538,0.0009371122],"domain_scores_gemma":[0.9875615,0.010789035,0.00016767395,0.00049598515,0.00033716383,0.0006486103],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045367997,0.00022622712,0.000785217,0.0013274786,0.00032510702,0.0000157904,0.00017656513,0.00048640295,0.000110243105],"category_scores_gemma":[0.018146705,0.00016672233,0.000026199663,0.0014249308,0.0015383207,0.00014377385,0.00055011216,0.0028077548,0.000007637813],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061919395,0.0005444781,0.83058196,0.010035886,0.00005235718,0.000029990866,0.007796695,0.000003935062,0.0020763858,0.0027656641,0.0008274589,0.144666],"study_design_scores_gemma":[0.0012081695,0.0009245022,0.98256236,0.0011723174,0.000018944522,0.00001910854,0.0073432084,0.0028019238,0.00003386421,0.0024059527,0.0013562446,0.00015339324],"about_ca_topic_score_codex":0.00068142376,"about_ca_topic_score_gemma":0.0010828468,"teacher_disagreement_score":0.15198041,"about_ca_system_score_codex":0.00027116644,"about_ca_system_score_gemma":0.0018316415,"threshold_uncertainty_score":0.9994928},"labels":[],"label_agreement":null},{"id":"W4402596020","doi":"10.1186/s12874-024-02320-4","title":"An exploration of available methods and tools to improve the efficiency of systematic review production: a scoping review","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Public Health Ontario","funders":"Masarykova Univerzita; Care and Public Health Research Institute, Universiteit Maastricht; Trakya Üniversitesi; Universidad de Granada; Lékařská fakulta, Masarykova univerzita; Università di Bologna; Università Cattolica del Sacro Cuore; University of Toronto; Centro de Investigação em Tecnologias e Serviços de Saúde; Universiteit Maastricht; RTI International; Gesellschaft für Forschungsförderung Niederösterreich; Amsterdam University Medical Centers; McMaster University; Ben-Gurion University of the Negev; Universiteit van Amsterdam; Universiteit Utrecht; Universidade de Aveiro","keywords":"Production (economics); Computer science; Systematic review; Data science; Management science; MEDLINE; Risk analysis (engineering); Process management; Medicine; Business; Engineering; Political science","score_opus":0.9848696628343485,"score_gpt":0.7803256948354731,"score_spread":0.20454396799887542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402596020","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":[1.8882095e-7,0.8140009,0.16504443,0.00097591407,0.00050786365,0.01917582,0.000012155564,0.0000065007166,0.00027625577],"genre_scores_gemma":[8.92871e-8,0.886235,0.107424036,0.0002355025,0.00017835462,0.0040082247,0.000009833824,0.00003530429,0.0018736436],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.21959466,0.7188938,0.03742541,0.0036041879,0.019558322,0.00092359923],"domain_scores_gemma":[0.29057762,0.64843285,0.022606911,0.024706813,0.011961371,0.0017144107],"candidate_categories":["metaresearch","metaepi_broad","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8808245,0.00066358683,0.030241208,0.0013016819,0.00018143016,0.00038786614,0.005960022,0.00045471656,0.005275914],"category_scores_gemma":[0.9335799,0.0002401644,0.0031927133,0.008724361,0.00076891744,0.0005054552,0.001181812,0.0013830502,0.0013257333],"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":[0.0000016957468,0.000025925767,7.4955786e-8,0.70149267,0.00015357402,0.0000021680357,0.000082094484,1.0510165e-7,0.0000026276514,0.0006962746,0.0074420646,0.29010072],"study_design_scores_gemma":[0.000026529966,0.00022107414,2.944195e-8,0.9218795,0.005084588,0.00008274423,0.00018841069,0.00008174934,0.000006847317,0.0009785108,0.07127275,0.00017730579],"about_ca_topic_score_codex":0.000018113182,"about_ca_topic_score_gemma":0.000041393527,"teacher_disagreement_score":0.2899234,"about_ca_system_score_codex":0.00007947361,"about_ca_system_score_gemma":0.004204002,"threshold_uncertainty_score":0.9994519},"labels":[],"label_agreement":null},{"id":"W4403112191","doi":"10.1186/s12874-024-02272-9","title":"Adaptive designs in clinical trials: a systematic review-part I","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","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":"Children's Hospital Research Institute of Manitoba; Robarts Clinical Trials; Institute for Clinical Evaluative Sciences; University of Calgary; University of Manitoba; University of Toronto; George & Fay Yee Centre for Healthcare Innovation; Hospital for Sick Children; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Research Manitoba","keywords":"Clinical trial; MEDLINE; Medicine; Research design; Computer science; Adaptive design; Medical physics; Data science; Pathology; Statistics; Mathematics; Biology","score_opus":0.9961486734106785,"score_gpt":0.8582480544456738,"score_spread":0.13790061896500472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403112191","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":[1.2694775e-8,0.74205035,0.24067293,0.00025631065,0.0030853688,0.012873145,0.00013270204,0.00014395868,0.00078523054],"genre_scores_gemma":[3.7077983e-9,0.5624415,0.42959547,0.00021863198,0.0017874801,0.0048699277,0.000008602727,0.00017487591,0.0009035047],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.10308693,0.85403585,0.030223975,0.0032833642,0.006814051,0.002555802],"domain_scores_gemma":[0.009351381,0.98082,0.0034881865,0.0033056694,0.0008135106,0.0022212504],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.88251334,0.001327629,0.04695457,0.0016711823,0.00011967502,0.00010411217,0.0041761557,0.0054325117,0.004055193],"category_scores_gemma":[0.99757975,0.00077521295,0.0058910907,0.003745652,0.0028226816,0.000060436774,0.0022647139,0.016234795,0.003007709],"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":[0.00008013692,0.00024692653,1.0965693e-7,0.61556804,0.00068753655,0.00061992777,0.000014440787,4.339095e-9,4.7827085e-9,0.05357938,0.032547574,0.2966559],"study_design_scores_gemma":[0.0004294347,0.00039435143,3.308493e-8,0.5541704,0.0065943007,0.00012161363,0.000037849,0.000057809808,4.4685976e-8,0.36546746,0.07233884,0.00038784818],"about_ca_topic_score_codex":0.000034061206,"about_ca_topic_score_gemma":0.00014574487,"teacher_disagreement_score":0.31188807,"about_ca_system_score_codex":0.0006873711,"about_ca_system_score_gemma":0.012473065,"threshold_uncertainty_score":0.9999475},"labels":[],"label_agreement":null},{"id":"W4403228773","doi":"10.1186/s12874-024-02349-5","title":"Do authors of systematic reviews of epidemiological observational studies assess the methodologies of the included primary studies? An empirical examination of methodological tool use in the literature","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Observational study; Systematic review; Data extraction; Scopus; MEDLINE; Medicine; Strengthening the reporting of observational studies in epidemiology; Descriptive statistics; Meta-analysis; Statistics; Pathology; Mathematics","score_opus":0.9969178312483066,"score_gpt":0.8001490210117719,"score_spread":0.1967688102365347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403228773","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":[0.65483457,0.13688572,0.19138876,0.008169396,0.001164992,0.007284813,0.000050828974,0.000011233935,0.00020968294],"genre_scores_gemma":[0.28845584,0.014252668,0.6942067,0.00092560996,0.00029283037,0.0012508264,0.000016670545,0.000025788915,0.0005730323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.055112265,0.9089481,0.020282596,0.0014283953,0.013617731,0.000610901],"domain_scores_gemma":[0.029964048,0.9530942,0.0063587357,0.004610213,0.0058380472,0.00013479701],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.92138904,0.00044164152,0.011938008,0.00083962077,0.00017413202,0.00012864152,0.006575868,0.0006690334,0.00044748437],"category_scores_gemma":[0.9840694,0.000118269716,0.0024561898,0.007285896,0.004062059,0.00031360568,0.0018864551,0.0018924633,0.000009071321],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007294459,0.0013130888,0.11108936,0.2025071,0.004671374,0.00007300057,0.09132575,0.00059505325,0.005753623,0.45458612,0.045561187,0.0817949],"study_design_scores_gemma":[0.0005085791,0.001172077,0.5348501,0.018473906,0.0011590555,0.00014204626,0.05365893,0.0062158788,0.00046721348,0.38030654,0.002672793,0.0003728872],"about_ca_topic_score_codex":0.000016421445,"about_ca_topic_score_gemma":0.00008104422,"teacher_disagreement_score":0.502818,"about_ca_system_score_codex":0.00010526776,"about_ca_system_score_gemma":0.00074323843,"threshold_uncertainty_score":0.998799},"labels":[],"label_agreement":null},{"id":"W4403514345","doi":"10.1186/s12874-024-02352-w","title":"A study of implementation factors for a novel approach to clinical trials: constructs for consideration in the coordination of direct-to-patient online-based medical research","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Mount Sinai Hospital","funders":"National Center for Advancing Translational Sciences; National Center for Research Resources; National Heart, Lung, and Blood Institute; Rare Diseases Clinical Research Network","keywords":"Clinical trial; Computer science; Medical research; MEDLINE; Medicine; Data science; Psychology; Medical physics; Pathology","score_opus":0.9765398374141137,"score_gpt":0.8000934324712444,"score_spread":0.17644640494286923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403514345","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8124251,0.00009855856,0.1603275,0.0037302778,0.0011031445,0.0217933,0.00038751942,0.000016098655,0.00011850419],"genre_scores_gemma":[0.9283567,0.00001823249,0.061261658,0.0010338725,0.00041096227,0.008302792,0.00056609185,0.000026214202,0.000023486815],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8533899,0.13344108,0.0053294026,0.0009898035,0.0054392787,0.0014105425],"domain_scores_gemma":[0.61520743,0.38233238,0.00026028865,0.0003218635,0.0012753753,0.0006026734],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32710308,0.00016389553,0.001109006,0.0011979843,0.00044452684,0.000012556701,0.00052328594,0.0004917824,0.00020318165],"category_scores_gemma":[0.3592449,0.000103505925,0.00015773546,0.0013692849,0.0003763099,0.00004422808,0.00023747166,0.001514049,0.0000044405524],"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":[0.021129373,0.021581564,0.17610928,0.028180072,0.00042480198,0.000014681483,0.17783348,0.000104019164,0.0009411148,0.08642488,0.047986116,0.4392706],"study_design_scores_gemma":[0.032165207,0.053686477,0.024412815,0.0050550005,0.00014886216,0.0000035982262,0.8065659,0.049869552,0.0014356449,0.00672316,0.019463783,0.00046999176],"about_ca_topic_score_codex":0.0027232862,"about_ca_topic_score_gemma":0.016958859,"teacher_disagreement_score":0.62873244,"about_ca_system_score_codex":0.00030983626,"about_ca_system_score_gemma":0.010385266,"threshold_uncertainty_score":0.99522495},"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":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4403875864","doi":"10.1186/s12874-024-02366-4","title":"Interpretation of statistical findings in randomised trials: a survey of statisticians using thematic analysis of open-ended questions","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"Ottawa Hospital; University of Ottawa","funders":"Statistical Society of Australia; Department of Health and Social Care; National Institute for Health and Care Research; United Kingdom Clinical Research Collaboration","keywords":"Thematic analysis; Interpretation (philosophy); Clinical trial; Descriptive statistics; Psychology; Medical education; Medicine; Qualitative research; Computer science; Statistics; Pathology; Sociology; Social science; Mathematics","score_opus":0.9732457615044802,"score_gpt":0.7657554605446573,"score_spread":0.2074903009598229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403875864","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":[0.13087605,0.00073677994,0.8664378,0.00008275315,0.00012866237,0.0011218464,0.0002879144,0.0000016791323,0.00032649803],"genre_scores_gemma":[0.74428296,0.00006717565,0.25537854,0.000010163147,0.000010824305,0.00006447126,0.00003915376,0.000008818511,0.0001379043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.17825527,0.77621996,0.029041879,0.0014747591,0.014377783,0.0006303635],"domain_scores_gemma":[0.112415746,0.8795839,0.002930118,0.001724021,0.003052799,0.00029344228],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.85534114,0.00018997586,0.010353115,0.0043863775,0.00004420649,0.00018847555,0.002417782,0.00021804689,0.016141055],"category_scores_gemma":[0.9651953,0.000097359014,0.001122142,0.010531106,0.0008369048,0.00013825134,0.00044004756,0.00049496046,0.00002995181],"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":[0.01214907,0.0017768021,0.08623441,0.008205648,0.020165602,0.00014747704,0.020965941,0.006724435,0.012100412,0.43060502,0.013011956,0.38791323],"study_design_scores_gemma":[0.0015468692,0.00013348596,0.038466975,0.00061350444,0.0014647364,0.000003325148,0.0012913956,0.9121779,0.00009450997,0.04409654,0.000024819568,0.000085920045],"about_ca_topic_score_codex":0.0042796484,"about_ca_topic_score_gemma":0.008020255,"teacher_disagreement_score":0.9054535,"about_ca_system_score_codex":0.000071261224,"about_ca_system_score_gemma":0.0021631953,"threshold_uncertainty_score":0.9847583},"labels":[],"label_agreement":null},{"id":"W4403990124","doi":"10.1186/s12874-024-02376-2","title":"Bayesian additive regression trees for predicting childhood asthma in the CHILD cohort study","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Asthma and respiratory diseases","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Public Health Ontario; University of Toronto; Queen's University","funders":"Institute of Circulatory and Respiratory Health; Natural Sciences and Engineering Research Council of Canada; AstraZeneca Canada; Canadian Institutes of Health Research; Canadian Lung Association; Canadian Allergy, Asthma and Immunology Foundation; AstraZeneca","keywords":"Asthma; Cohort; Bayesian probability; Regression; Regression analysis; Medicine; Cohort study; Statistics; Psychology; Mathematics; Internal medicine","score_opus":0.17940431814905222,"score_gpt":0.5069084557539918,"score_spread":0.32750413760493957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403990124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8884751,0.009407303,0.073481284,0.010485065,0.0009941203,0.010392935,0.00009926906,0.00028854463,0.006376339],"genre_scores_gemma":[0.99220663,0.00021999386,0.0029977744,0.0006653388,0.0019732204,0.0015420179,0.000064002656,0.0000504411,0.00028055639],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9816295,0.013710895,0.0005937374,0.000833589,0.0023673165,0.00086499203],"domain_scores_gemma":[0.9541404,0.044480532,0.000051909137,0.0005561426,0.00019947029,0.0005715146],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035373528,0.00022187713,0.0006529428,0.00057827216,0.00033804282,0.00004793565,0.00047788376,0.0003270449,0.0007855659],"category_scores_gemma":[0.08615673,0.00011656627,0.000228782,0.0008851338,0.0006054921,0.00006978439,0.0002048051,0.0017957034,0.000025086989],"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":[0.001995051,0.0029168616,0.45967072,0.00072308566,0.00031403283,0.0026892414,0.008223644,0.00000530891,0.000069408205,0.0014227411,0.01691069,0.5050592],"study_design_scores_gemma":[0.002862012,0.0040050405,0.93928707,0.0019301453,0.00010451207,0.00035619,0.02052978,0.004865063,0.00008536363,0.0011484257,0.0246444,0.00018200831],"about_ca_topic_score_codex":0.00009993576,"about_ca_topic_score_gemma":0.0008569925,"teacher_disagreement_score":0.5048772,"about_ca_system_score_codex":0.000093496295,"about_ca_system_score_gemma":0.001739374,"threshold_uncertainty_score":0.99328595},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","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":"W4404073559","doi":"10.1186/s12874-024-02394-0","title":"Motivations for enrollment in a COVID-19 ring-based post-exposure prophylaxis trial: qualitative examination of participant experiences","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"St. Michael's Hospital; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; St. Michael's Hospital Foundation","keywords":"Medicine; Psychological intervention; Novelty; Research design; Clinical trial; Qualitative research; Coronavirus disease 2019 (COVID-19); Family medicine; Psychology; Nursing; Social psychology; Pathology; Infectious disease (medical specialty); Disease","score_opus":0.9440115813951744,"score_gpt":0.7603019439461679,"score_spread":0.18370963744900648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404073559","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":[0.7847817,0.0012212235,0.19053887,0.018937636,0.00035205742,0.0038767222,0.0000233868,0.00005927841,0.00020914276],"genre_scores_gemma":[0.94100887,0.00023721073,0.052463,0.00044667764,0.00022225702,0.005137223,0.000046492914,0.0000298059,0.00040846938],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9519006,0.038271267,0.0019439566,0.0011091916,0.005636383,0.0011385841],"domain_scores_gemma":[0.26300892,0.7328848,0.00014175595,0.0006569947,0.0020466172,0.0012609094],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2455614,0.00016807139,0.00084903324,0.0012218301,0.00013478979,0.00003537226,0.00048941054,0.0008563952,0.0010137939],"category_scores_gemma":[0.8943827,0.00012413909,0.00022897642,0.0015958591,0.002611758,0.00009618395,0.0002171557,0.0027338937,0.000012203335],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12790936,0.0055629057,0.0024841623,0.030563718,0.0004662427,0.00047237746,0.43199593,0.00016188138,0.010812717,0.30948776,0.0005342527,0.07954871],"study_design_scores_gemma":[0.11960549,0.09209719,0.01008706,0.007592123,0.00017329455,0.000035074627,0.5259335,0.04761377,0.01952944,0.17231646,0.0042104637,0.00080610166],"about_ca_topic_score_codex":0.0005320046,"about_ca_topic_score_gemma":0.0019173794,"teacher_disagreement_score":0.6946135,"about_ca_system_score_codex":0.00042909654,"about_ca_system_score_gemma":0.01806193,"threshold_uncertainty_score":0.9998994},"labels":[],"label_agreement":null},{"id":"W4404184484","doi":"10.1186/s12874-024-02384-2","title":"The optimal approach for retrieving systematic reviews was achieved when searching MEDLINE and Epistemonikos in addition to reference checking: a methodological validation study","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"University of British Columbia; Cochrane; St. Michael's Hospital","funders":"","keywords":"MEDLINE; Systematic review; Medicine; Research design; Computer science; Medical physics; Information retrieval; Statistics","score_opus":0.9826355418614335,"score_gpt":0.7286096551981484,"score_spread":0.2540258866632852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404184484","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":[0.025312234,0.0073262667,0.9518094,0.002948608,0.0002270322,0.011795491,0.000010055551,0.000018887078,0.0005520243],"genre_scores_gemma":[0.11800542,0.0007623898,0.8702592,0.00017739579,0.0003800431,0.006692997,0.00003497073,0.0000407072,0.0036468306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.19645995,0.76517844,0.016883,0.003655472,0.01622571,0.0015974188],"domain_scores_gemma":[0.17022617,0.8212724,0.0017896355,0.0038524014,0.0018662455,0.0009931428],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.90138745,0.00041042984,0.005852677,0.001228781,0.00060435385,0.0015743632,0.003176059,0.00037187187,0.0008313557],"category_scores_gemma":[0.93880546,0.00016650684,0.0007917463,0.0032309012,0.00038796657,0.00023680567,0.0010602617,0.0016414808,0.00015934288],"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":[0.0018347452,0.00096878945,0.00541138,0.07184557,0.0012101807,0.00017123595,0.027903888,0.00052621675,0.0014582453,0.07636821,0.045270994,0.76703054],"study_design_scores_gemma":[0.001724792,0.003183884,0.003753325,0.011146648,0.00070176285,0.00029558694,0.03846982,0.8258579,0.00014589072,0.051113937,0.062595665,0.0010108019],"about_ca_topic_score_codex":0.000052987256,"about_ca_topic_score_gemma":0.00023213244,"teacher_disagreement_score":0.8253317,"about_ca_system_score_codex":0.00015077154,"about_ca_system_score_gemma":0.00056316407,"threshold_uncertainty_score":0.9994621},"labels":[],"label_agreement":null},{"id":"W4404247756","doi":"10.1186/s12874-024-02387-z","title":"Evidence pointing toward invalidity of the SF-8 physical and mental scales: a fusion validity assessment","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Geriatric Care and Nursing Homes","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":"York University; University of Alberta","funders":"University of Alberta","keywords":"Psychology; Mental health; Psychometrics; Test validity; Clinical psychology; Applied psychology; Psychiatry","score_opus":0.7846350592512534,"score_gpt":0.663055238900969,"score_spread":0.12157982035028447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404247756","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96262836,0.002023634,0.013574153,0.017643422,0.0025501514,0.0008146708,0.000015063015,0.00006139382,0.00068914524],"genre_scores_gemma":[0.98683476,0.0016288806,0.009988306,0.0001514631,0.0009280141,0.0000962258,0.0000053446197,0.000019854495,0.00034715622],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9603918,0.035856538,0.0005403745,0.0005023211,0.001990233,0.00071873434],"domain_scores_gemma":[0.90202594,0.09688958,0.00009473456,0.0003912416,0.00025301077,0.00034549754],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04220158,0.00013684155,0.00052749447,0.00018041291,0.0006055174,0.000019541723,0.00048891146,0.00032731448,0.00064252666],"category_scores_gemma":[0.0622824,0.00008203363,0.00016597947,0.000749942,0.0010264548,0.00009694816,0.0013780572,0.0023260063,0.000033169912],"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":[0.001105164,0.0007078313,0.22811475,0.021998381,0.00018846816,0.00011861176,0.0756682,0.0000017361594,0.042653408,0.02752271,0.19591865,0.40600207],"study_design_scores_gemma":[0.0036450664,0.0029360782,0.677917,0.02591752,0.00027909983,0.0001765073,0.089012876,0.020090628,0.0076167365,0.12034074,0.05109366,0.0009740772],"about_ca_topic_score_codex":0.0012054743,"about_ca_topic_score_gemma":0.0005113246,"teacher_disagreement_score":0.44980225,"about_ca_system_score_codex":0.0002390427,"about_ca_system_score_gemma":0.0028015962,"threshold_uncertainty_score":0.9999757},"labels":[],"label_agreement":null},{"id":"W4404366521","doi":"10.1186/s12874-024-02359-3","title":"A Bayesian analysis integrating expert beliefs to better understand how new evidence ought to update what we believe: a use case of chiropractic care and acute lumbar disc herniation with early surgery","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Spine and Intervertebral Disc Pathology","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":false,"ca_institutions":"University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Chiropractic; Medicine; Lumbar; MEDLINE; Physical therapy; Physical medicine and rehabilitation; Alternative medicine; Surgery; Pathology","score_opus":0.42778475047497055,"score_gpt":0.526303834022109,"score_spread":0.09851908354713845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404366521","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5535652,0.006474046,0.3918415,0.047508582,0.000115311115,0.0004459659,0.00000926891,0.000030508661,0.000009584803],"genre_scores_gemma":[0.7488869,0.0063369735,0.24068585,0.0028614672,0.00041034055,0.00012261393,0.000038333124,0.000060790077,0.0005967583],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99269444,0.0039934237,0.00054921384,0.00090048014,0.0011566709,0.0007057939],"domain_scores_gemma":[0.99162966,0.0060901023,0.00008663837,0.0005802058,0.00040923027,0.0012041661],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005937495,0.0002650149,0.0010844823,0.0013918078,0.000111121575,0.00023509678,0.00020074232,0.00030594168,0.00041491602],"category_scores_gemma":[0.035814025,0.0001769992,0.00022234207,0.0021939564,0.0003518368,0.0007815238,0.00031567074,0.00093806576,0.000019816078],"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":[0.0026108867,0.00022141146,0.04106545,0.002635753,0.0043413,0.036699444,0.060929444,0.000008579597,0.02259198,0.0011119558,0.01978123,0.8080026],"study_design_scores_gemma":[0.010364521,0.054079693,0.4071752,0.085087344,0.014524386,0.045777723,0.30872598,0.023785,0.028078897,0.003935293,0.013572482,0.004893468],"about_ca_topic_score_codex":0.0027602206,"about_ca_topic_score_gemma":0.012305291,"teacher_disagreement_score":0.8031091,"about_ca_system_score_codex":0.0001804126,"about_ca_system_score_gemma":0.0012288804,"threshold_uncertainty_score":0.97230774},"labels":[],"label_agreement":null},{"id":"W4404651529","doi":"10.1186/s12874-024-02408-x","title":"The role of the estimand framework in the analysis of patient-reported outcomes in single-arm trials: a case study in oncology","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Health Canada; European Society for Medical Oncology; European Commission; National Institute for Health and Care Research; European Federation of Pharmaceutical Industries and Associations; American Society of Clinical Oncology","keywords":"Discontinuation; Clinical trial; Quality of life (healthcare); Medicine; Psychology; Internal medicine; Psychotherapist","score_opus":0.5499835850344746,"score_gpt":0.6124147951859896,"score_spread":0.06243121015151498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404651529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897603,0.0037958252,0.00060421537,0.0038289141,0.0003888212,0.0013038545,0.000005068288,0.000006939965,0.00030605515],"genre_scores_gemma":[0.99858576,0.0001357388,0.0007383133,0.00014792377,0.000055097124,0.00029381452,0.000002027579,0.000011433048,0.000029912077],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.94078827,0.054650832,0.0017183304,0.00043591936,0.0018755727,0.0005310716],"domain_scores_gemma":[0.6991345,0.29925495,0.00023589788,0.0009900383,0.0002304421,0.00015417069],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09923824,0.0001354741,0.0014720622,0.0010065042,0.000059157665,0.000015278067,0.00049958046,0.00035726142,0.00018758132],"category_scores_gemma":[0.28046635,0.000058131474,0.0003340675,0.00482988,0.00087123166,0.000019622448,0.0002900226,0.0020249153,7.9458357e-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":[0.0015217086,0.0019119144,0.6836333,0.00010908556,0.0007445114,0.0044858954,0.0417789,0.00003768842,0.00009089362,0.0010023601,0.00003040795,0.2646533],"study_design_scores_gemma":[0.0052718436,0.006294875,0.42378852,0.000895525,0.0019219519,0.00081205496,0.52722377,0.0074473997,0.00044457332,0.020747127,0.004917355,0.00023500586],"about_ca_topic_score_codex":0.030184956,"about_ca_topic_score_gemma":0.3962739,"teacher_disagreement_score":0.48544487,"about_ca_system_score_codex":0.00022339476,"about_ca_system_score_gemma":0.0019619882,"threshold_uncertainty_score":0.9762731},"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":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4404725899","doi":"10.1186/s12874-024-02402-3","title":"Non-collapsibility and built-in selection bias of period-specific and conventional hazard ratio in randomized controlled trials","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; McGill University; McGill University Health Centre","funders":"","keywords":"Hazard ratio; Marginal structural model; Statistics; Weighting; Proportional hazards model; Inverse probability weighting; Hazard; Covariate; Econometrics; Confounding; Mathematics; Confidence interval; Medicine; Chemistry; Propensity score matching","score_opus":0.7400147912349078,"score_gpt":0.6258450755790635,"score_spread":0.11416971565584422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404725899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38905182,0.002948902,0.603291,0.00096594065,0.00014298299,0.0032577566,0.0000049141067,0.00005574668,0.00028098744],"genre_scores_gemma":[0.69581205,0.0029710033,0.29939938,0.00001772974,0.00012801403,0.0013610113,0.000004860211,0.000023593848,0.0002823956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9382921,0.056660175,0.0026691474,0.00064024696,0.0012358791,0.0005024934],"domain_scores_gemma":[0.6409687,0.35809532,0.0002255114,0.00021755823,0.00030746462,0.00018549299],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27228534,0.00016657806,0.003640863,0.0008719248,0.000042273397,0.00004165006,0.00015711613,0.00038937406,0.00078077684],"category_scores_gemma":[0.5429326,0.000111480804,0.00023126895,0.0005753588,0.0013677052,0.00009526097,0.00015537096,0.00088409486,0.0000020523162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13681266,0.00032171188,0.0032834725,0.0019777897,0.00023965834,0.00008799338,0.0015282487,0.0000039610895,0.022393985,0.8142864,0.00095777685,0.01810634],"study_design_scores_gemma":[0.090781696,0.0002509209,0.00087927637,0.00062469096,0.00003664382,0.000038805196,0.00036190718,0.020112813,0.0040358156,0.88264525,0.00010783803,0.0001243339],"about_ca_topic_score_codex":0.00011532081,"about_ca_topic_score_gemma":0.0013606062,"teacher_disagreement_score":0.3067602,"about_ca_system_score_codex":0.00011825537,"about_ca_system_score_gemma":0.0010484717,"threshold_uncertainty_score":0.8548959},"labels":[],"label_agreement":null},{"id":"W4405553788","doi":"10.1186/s12874-024-02414-z","title":"A PubMed search filter for efficiently retrieving exercise training studies","year":2024,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Cardiovascular and exercise physiology","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":"Simon Fraser University; Burnaby Hospital","funders":"","keywords":"Filter (signal processing); Computer science; Set (abstract data type); Recall; Information retrieval; Gold standard (test); MEDLINE; Medicine; Psychology; Cognitive psychology; Computer vision","score_opus":0.7735205552770625,"score_gpt":0.585494665163672,"score_spread":0.18802589011339055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405553788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40954304,0.1574351,0.40612772,0.011123604,0.0048036133,0.0069220676,0.00004289517,0.00068434037,0.0033176371],"genre_scores_gemma":[0.8287465,0.019093614,0.12936708,0.0010071475,0.0061762817,0.0053328215,0.00013445037,0.0002660255,0.009876056],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98975116,0.0048106313,0.00058726844,0.001017292,0.0020516647,0.0017819948],"domain_scores_gemma":[0.9453187,0.05232157,0.000023229031,0.00065822015,0.0007228244,0.00095546606],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06117783,0.0002393216,0.0015723291,0.00086564705,0.00024182045,0.0000480636,0.00037273057,0.000474811,0.0003677616],"category_scores_gemma":[0.11183952,0.00017500065,0.0007727466,0.0011820252,0.0012822795,0.000065390705,0.00047757046,0.0015567873,0.00011621397],"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":[0.0046745753,0.00012524998,0.00005634035,0.005478867,0.0010098444,0.00079617667,0.005958519,0.000023691267,0.0026498649,0.0036107954,0.020953264,0.9546628],"study_design_scores_gemma":[0.03670925,0.011365684,0.021459578,0.03159169,0.0051918766,0.009308023,0.100096084,0.107399166,0.092283696,0.06964251,0.51079774,0.0041546924],"about_ca_topic_score_codex":0.00004924014,"about_ca_topic_score_gemma":0.000028735154,"teacher_disagreement_score":0.9505081,"about_ca_system_score_codex":0.00023182158,"about_ca_system_score_gemma":0.0021793398,"threshold_uncertainty_score":0.966715},"labels":[],"label_agreement":null},{"id":"W4406354046","doi":"10.1186/s12874-025-02464-x","title":"Recruiting participants for focus groups in health research: a meta-research study","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Focus Groups and Qualitative Methods","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Otto von Guericke University Magdeburg; Universität Regensburg; Medizinischen Hochschule Hannover; Deutsche Forschungsgemeinschaft","keywords":"Focus group; MEDLINE; Medicine; Mental health; Psychology; Medical education; Political science; Psychiatry; Sociology","score_opus":0.9765873219534961,"score_gpt":0.7863944746839577,"score_spread":0.19019284726953833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406354046","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":[0.21441104,0.019345995,0.55655885,0.15327264,0.0018524053,0.022089908,0.00004107814,0.00025381058,0.03217427],"genre_scores_gemma":[0.70277846,0.001552379,0.26897234,0.0006620023,0.0012737603,0.01337472,0.0000072905505,0.00008551647,0.011293569],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.2608766,0.7159688,0.002413805,0.0021105653,0.010864982,0.0077652796],"domain_scores_gemma":[0.42746127,0.5666,0.00015728857,0.00092040905,0.003183928,0.0016770925],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.8254348,0.00025895433,0.001716923,0.0032105476,0.003447927,0.0001949034,0.0022348843,0.0005855591,0.0011589039],"category_scores_gemma":[0.7853708,0.00020765868,0.00031403085,0.008207334,0.0061519095,0.00018603461,0.0012767405,0.004857832,0.000049098],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008643725,0.001335057,0.0048354147,0.0004609168,0.00035242084,0.0000580835,0.0939836,0.000003411071,0.000072427625,0.6761994,0.00818303,0.21365187],"study_design_scores_gemma":[0.0024147988,0.002402593,0.0032476736,0.00030274797,0.000038355483,9.199768e-7,0.38805944,0.0005968462,0.00013465057,0.51215136,0.09041509,0.00023551875],"about_ca_topic_score_codex":0.067319356,"about_ca_topic_score_gemma":0.24715126,"teacher_disagreement_score":0.4883674,"about_ca_system_score_codex":0.0011622858,"about_ca_system_score_gemma":0.01334577,"threshold_uncertainty_score":0.9997542},"labels":[],"label_agreement":null},{"id":"W4406803011","doi":"10.1186/s12874-025-02475-8","title":"Framework for types of metainferences in mixed methods research","year":2025,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Holland Bloorview Kids Rehabilitation Hospital; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Data science; Scopus; Causal inference; Systematic review; Multimethodology; Inference; Management science; Psychology; MEDLINE; Artificial intelligence; Medicine","score_opus":0.9934433432975058,"score_gpt":0.9147727941146665,"score_spread":0.07867054918283933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406803011","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":[0.0000023923533,0.6017406,0.3876502,0.0023909924,0.0012053099,0.0051507447,0.00009825768,0.0000242248,0.0017372784],"genre_scores_gemma":[4.4607748e-7,0.5436785,0.44872758,0.00033025534,0.00035260431,0.0057071424,0.000017832172,0.000027112832,0.0011585169],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.46276942,0.5229879,0.0048778523,0.0014113839,0.004113818,0.0038396248],"domain_scores_gemma":[0.093454026,0.90057546,0.00082182436,0.0013181502,0.002776215,0.0010543341],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5864676,0.0003782159,0.004898687,0.005161383,0.0008804117,0.000015870157,0.003284396,0.0030576165,0.0037463864],"category_scores_gemma":[0.9212196,0.0002748,0.00042593607,0.007895663,0.0023384676,0.000076734956,0.0020811863,0.010224698,0.0001888124],"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":[0.000050838036,0.000032469376,0.000038760492,0.09614626,0.000038066482,0.0000030322365,0.0011250207,7.932923e-8,4.5169784e-7,0.15317002,0.005848438,0.74354655],"study_design_scores_gemma":[0.0003657361,0.00021661301,0.000034647965,0.029139016,0.00004432697,0.0000013587355,0.002739108,0.000028716177,0.0000029406146,0.12999508,0.83728653,0.00014592583],"about_ca_topic_score_codex":0.001822432,"about_ca_topic_score_gemma":0.004454523,"teacher_disagreement_score":0.8314381,"about_ca_system_score_codex":0.0007771701,"about_ca_system_score_gemma":0.08636673,"threshold_uncertainty_score":0.99997044},"labels":[],"label_agreement":null},{"id":"W4407548396","doi":"10.1186/s12874-025-02461-0","title":"The reliance on conceptual frameworks in qualitative research – a way forward","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Qualitative Research Methods and Applications","field":"Social 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":"Institute for Work & Health; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Rigour; Qualitative research; Conceptual framework; Engineering ethics; Management science; The Conceptual Framework; Conceptual model; Epistemology; Computer science; Sociology; Data science; Social science; Engineering","score_opus":0.8008111189144518,"score_gpt":0.76875603955336,"score_spread":0.032055079361091754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407548396","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":[0.029992145,0.0044220216,0.4579684,0.3105594,0.00067618716,0.00339151,0.000019482522,0.000104852195,0.192866],"genre_scores_gemma":[0.4085373,0.032992993,0.44299296,0.0047419295,0.0023738616,0.011636472,0.000020586544,0.000116991665,0.09658691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5863785,0.40160742,0.0009511098,0.0010833995,0.00698784,0.002991736],"domain_scores_gemma":[0.30118352,0.6951665,0.00008142042,0.00083189516,0.0019674904,0.00076912733],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.48068482,0.00016368585,0.00052169204,0.0008872697,0.0031934762,0.00015893513,0.0023693086,0.0010229805,0.0006107735],"category_scores_gemma":[0.73295546,0.000112939335,0.00013813197,0.005733546,0.021066876,0.00009680923,0.0006277153,0.008069094,0.0002755213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003047557,0.0001141371,0.00014007224,0.000025531888,0.000018251483,0.000009317028,0.0418569,0.0000018849935,0.000055833752,0.83194697,0.019915506,0.105610825],"study_design_scores_gemma":[0.0003429762,0.00016817269,0.00056537485,0.00020385301,0.0000010861744,1.8255199e-7,0.21244621,0.00012734423,0.00008973364,0.49231592,0.29366416,0.00007498106],"about_ca_topic_score_codex":0.0067636697,"about_ca_topic_score_gemma":0.025344659,"teacher_disagreement_score":0.37854514,"about_ca_system_score_codex":0.00067345315,"about_ca_system_score_gemma":0.0069632046,"threshold_uncertainty_score":0.9998504},"labels":[],"label_agreement":null},{"id":"W4408072300","doi":"10.1186/s12874-025-02510-8","title":"Handling missing values in patient-reported outcome data in the presence of intercurrent events","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Health Canada; American Society of Clinical Oncology","keywords":"Missing data; Imputation (statistics); Leverage (statistics); Covariate; Statistics; Data quality; Medicine; Data mining; Computer science; Mathematics; Operations management; Engineering","score_opus":0.8508464498930282,"score_gpt":0.6712143987581608,"score_spread":0.17963205113486735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408072300","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22082314,0.00035108445,0.77614456,0.0011381069,0.00031740678,0.00045789342,0.000009575281,0.000009251517,0.0007489729],"genre_scores_gemma":[0.31722257,0.000089610556,0.68241477,0.00012255722,0.000033237957,0.00005742121,0.0000064701712,0.000008791542,0.00004460319],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9597009,0.035448603,0.0016881848,0.0006168727,0.0018419903,0.00070347305],"domain_scores_gemma":[0.65001845,0.34778532,0.00021438413,0.001533768,0.00027619998,0.00017184697],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.078524716,0.00012276234,0.00062539673,0.00041725198,0.00005923985,0.000015587775,0.0016258267,0.00019355834,0.00019729846],"category_scores_gemma":[0.7407067,0.000077663186,0.000045375866,0.0008871756,0.0005681112,0.000054177537,0.0012415046,0.0012161662,0.0000021461055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038185128,0.0008922224,0.16862978,0.0017018846,0.000049103543,0.00018291616,0.0035512052,0.0000030003328,0.0004139963,0.15859842,0.0011405114,0.6644551],"study_design_scores_gemma":[0.0007691025,0.0001454016,0.032207634,0.0016350977,0.000018113582,0.000014302565,0.002030373,0.020791996,0.0003714871,0.9416445,0.0002695373,0.00010248253],"about_ca_topic_score_codex":0.0006288794,"about_ca_topic_score_gemma":0.00060040154,"teacher_disagreement_score":0.78304607,"about_ca_system_score_codex":0.000054520442,"about_ca_system_score_gemma":0.0007654843,"threshold_uncertainty_score":0.9488527},"labels":[],"label_agreement":null},{"id":"W4408072393","doi":"10.1186/s12874-025-02516-2","title":"The reporting quality and methodological quality of dynamic prediction models for cancer prognosis","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"AI in cancer detection","field":"Computer Science","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":"Impact; McMaster University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Quality (philosophy); Medicine; Computer science; Data science","score_opus":0.8402655165870867,"score_gpt":0.6765423709087541,"score_spread":0.16372314567833257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408072393","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028567888,0.0018804311,0.9585141,0.009164685,0.00074363366,0.0007976836,0.000007701981,0.00008447428,0.0002394101],"genre_scores_gemma":[0.17161728,0.0018599142,0.82443726,0.00021794187,0.0001105613,0.0014906547,0.0000019398208,0.000009653531,0.00025479234],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95685273,0.037345298,0.0024470177,0.00096963445,0.0016289987,0.0007563019],"domain_scores_gemma":[0.75800556,0.23786607,0.0013333602,0.0010791325,0.0014176,0.0002982798],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23567729,0.00013206537,0.0006723541,0.00019990069,0.00051628385,0.000054158525,0.001043637,0.0003934761,0.000009790073],"category_scores_gemma":[0.33534938,0.000087647764,0.0001513119,0.0008503282,0.0011701627,0.00016667004,0.0009004363,0.00077392027,2.631845e-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":[0.00042849535,0.000051981053,0.0049346043,0.0005770432,0.00007468965,0.0000010175961,0.00025369012,0.00011207023,0.0028575591,0.1932534,0.00031396112,0.7971415],"study_design_scores_gemma":[0.0006220438,0.0002737577,0.05880402,0.00013313873,0.000014058394,0.000008214977,0.00030086405,0.386795,0.0034284992,0.5485188,0.0009901715,0.00011145837],"about_ca_topic_score_codex":0.0012027198,"about_ca_topic_score_gemma":0.0019090478,"teacher_disagreement_score":0.79703003,"about_ca_system_score_codex":0.00022329148,"about_ca_system_score_gemma":0.0016976588,"threshold_uncertainty_score":0.78703105},"labels":[],"label_agreement":null},{"id":"W4408298481","doi":"10.1186/s12874-025-02499-0","title":"Ranking of treatments in network meta-analysis: incorporating minimally important differences","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","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":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Statistics; Bayesian network; Mathematics; Computer science; Medicine; Machine learning","score_opus":0.9728456260694304,"score_gpt":0.7115555423479419,"score_spread":0.26129008372148843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408298481","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":[0.32055917,0.029019166,0.63102144,0.0033638806,0.00041590552,0.0020481597,0.000018075949,0.00001135007,0.013542829],"genre_scores_gemma":[0.7503509,0.00017968079,0.2428867,0.00026029695,0.00007900367,0.00030730318,0.000008682111,0.000009817787,0.005917641],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.44981262,0.49255985,0.028617138,0.002949669,0.024554696,0.0015060087],"domain_scores_gemma":[0.4145862,0.56832945,0.0073417462,0.0059007434,0.0031703576,0.0006714995],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7238237,0.00034876703,0.013366775,0.0029334824,0.00017886233,0.00020521128,0.0037817385,0.00036773662,0.019322842],"category_scores_gemma":[0.6338161,0.00015457568,0.0051881527,0.013494301,0.00066629826,0.00010354515,0.0007935247,0.0007560559,0.000099957935],"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":[0.00012092716,0.00022302175,0.8751851,0.00015446208,0.06866177,0.00007479009,0.0003967324,0.00031416139,0.000077984056,0.035473403,0.0034467394,0.015870936],"study_design_scores_gemma":[0.0014273098,0.00040055564,0.3215086,0.00015858762,0.095032096,0.000010984263,0.0037587117,0.08052804,0.00011918594,0.4940895,0.002496807,0.00046959583],"about_ca_topic_score_codex":0.0004964844,"about_ca_topic_score_gemma":0.008358,"teacher_disagreement_score":0.5536765,"about_ca_system_score_codex":0.000061132465,"about_ca_system_score_gemma":0.001492526,"threshold_uncertainty_score":0.98157364},"labels":[],"label_agreement":null},{"id":"W4408546352","doi":"10.1186/s12874-025-02531-3","title":"Evaluating methods to define place of residence in Canadian administrative data and the impact on observed associations with all-cause mortality in type 2 diabetes","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Diabetes Management and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; University of Alberta","funders":"","keywords":"Residence; Gerontology; Type 2 diabetes; Medicine; Demography; Diabetes mellitus; Sociology","score_opus":0.8412516278183337,"score_gpt":0.6940008955014625,"score_spread":0.14725073231687125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408546352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98586696,0.000408888,0.0004909042,0.010707794,0.000058704798,0.00094719173,0.000013284495,0.000005092839,0.0015011876],"genre_scores_gemma":[0.91120166,0.000118953714,0.08752338,0.00064366235,0.000035203844,0.00011382507,0.000093358314,0.000008843608,0.00026114358],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98147595,0.016264021,0.00045193365,0.00043238228,0.0007504123,0.00062531926],"domain_scores_gemma":[0.91124827,0.086785555,0.00011005145,0.0009532038,0.00038347757,0.0005194516],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08339524,0.000101724,0.00049134437,0.0005605939,0.000056045454,0.000017500539,0.00040123297,0.00012409095,0.00011309132],"category_scores_gemma":[0.32979596,0.00006186733,0.000020135722,0.0014705538,0.00038778727,0.000055467834,0.00023900848,0.00060272764,0.0000023501964],"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":[0.0012176273,0.00012518803,0.97598773,0.00014881467,0.00028467205,0.000009783838,0.0009587447,0.00006303812,0.00015931185,0.005635106,0.0013776836,0.014032283],"study_design_scores_gemma":[0.0014679249,0.0006464258,0.9809316,0.0004162343,0.00008681471,3.5071977e-7,0.0009351435,0.012105798,0.00017646137,0.0031083054,0.00007215795,0.000052783525],"about_ca_topic_score_codex":0.108232655,"about_ca_topic_score_gemma":0.4857593,"teacher_disagreement_score":0.37752664,"about_ca_system_score_codex":0.00031348967,"about_ca_system_score_gemma":0.005603399,"threshold_uncertainty_score":0.9940189},"labels":[],"label_agreement":null},{"id":"W4408546444","doi":"10.1186/s12874-025-02528-y","title":"Using artificial intelligence for systematic review: the example of elicit","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","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":"Université de Montréal; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal","funders":"","keywords":"MEDLINE; Computer science; Data science; Medicine; Artificial intelligence; Psychology; Biology","score_opus":0.9149833792834483,"score_gpt":0.7109676948478502,"score_spread":0.20401568443559814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408546444","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065679043,0.015231931,0.9583202,0.014976652,0.00049740844,0.0040875594,0.000002347174,0.000018202889,0.0002977786],"genre_scores_gemma":[0.39887783,0.03518693,0.52411485,0.029380323,0.0032987336,0.0062188366,0.00008710382,0.00013034744,0.002705031],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9898877,0.0068549872,0.0014201559,0.0003360129,0.00097336806,0.0005277434],"domain_scores_gemma":[0.86643904,0.12976074,0.00026004552,0.0010631817,0.0021363792,0.00034059343],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051094074,0.00010442226,0.0008353471,0.0002794349,0.0002195139,0.000009266055,0.00042429808,0.00023278773,0.00024751746],"category_scores_gemma":[0.31106806,0.00006341675,0.00016855916,0.0009752819,0.00070920645,0.000025206291,0.00011226804,0.0005789307,0.000020498594],"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":[0.0006029104,0.00030096478,0.00029928156,0.5936326,0.00012918598,0.000005601683,0.001015846,0.000012190153,0.0016959154,0.32572493,0.0041562277,0.07242438],"study_design_scores_gemma":[0.00011467166,0.0014482073,0.00010149284,0.30677566,0.0009006958,0.00014175278,0.0127066625,0.051314846,0.08837067,0.53342897,0.004392973,0.00030336823],"about_ca_topic_score_codex":0.0034740346,"about_ca_topic_score_gemma":0.0005388916,"teacher_disagreement_score":0.43420535,"about_ca_system_score_codex":0.00011935064,"about_ca_system_score_gemma":0.0029875052,"threshold_uncertainty_score":0.97709835},"labels":[],"label_agreement":null},{"id":"W4409372846","doi":"10.1186/s12874-025-02539-9","title":"Exploring the use of the aboriginal and Torres Strait Islander quality appraisal tool in Indigenous health research","year":2025,"lang":"en","type":"letter","venue":"BMC Medical Research Methodology","topic":"Indigenous Health, Education, and Rights","field":"Social 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":"McMaster University; Alberta Health Services; Assembly of First Nations; University of Alberta; University of Calgary; Trent University; Alberta Health","funders":"Alberta Health Services","keywords":"Indigenous; Critical appraisal; Medicine; Quality (philosophy); MEDLINE; Family medicine; Psychology; Medical education; Alternative medicine; Geography; Political science; Biology","score_opus":0.8240650767844817,"score_gpt":0.6460140904862818,"score_spread":0.17805098629819993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409372846","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":[0.25130698,0.0015636187,0.0012972282,0.73193055,0.0049810875,0.004612316,0.000078810415,0.00004122701,0.004188203],"genre_scores_gemma":[0.016708462,0.50531083,0.046286143,0.22418743,0.07621684,0.0023136016,0.00037893772,0.0003997907,0.12819792],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.7892109,0.19914286,0.0013063793,0.0008946803,0.0065847603,0.0028603931],"domain_scores_gemma":[0.72074234,0.27612254,0.000342292,0.0011639826,0.0012468453,0.00038198204],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.1834837,0.00023270331,0.0008736183,0.00082835107,0.006779833,0.00013539927,0.0019871749,0.0011729322,0.00020741018],"category_scores_gemma":[0.032361556,0.00012973463,0.00013460834,0.0019023428,0.0063941525,0.00018571297,0.00007089273,0.009758108,0.0000071525305],"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":[0.00019211973,0.00021205394,0.0044595306,0.0024335142,0.00006616407,0.000040887724,0.63950026,0.0000021523776,7.0312814e-7,0.15849894,0.17449775,0.020095915],"study_design_scores_gemma":[0.00021456617,0.00011550142,0.011708077,0.00037430914,0.000004811166,0.000004618152,0.008067146,0.0000025438671,0.0000037596271,0.004857555,0.974526,0.00012113796],"about_ca_topic_score_codex":0.6629783,"about_ca_topic_score_gemma":0.90852404,"teacher_disagreement_score":0.8000282,"about_ca_system_score_codex":0.0007603207,"about_ca_system_score_gemma":0.19452573,"threshold_uncertainty_score":0.9963099},"labels":[],"label_agreement":null},{"id":"W4410214727","doi":"10.1186/s12874-025-02547-9","title":"Spin Bias in randomized controlled trials of botulinum toxin for bruxism management: a meta-epidemiologic study","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Temporomandibular Joint Disorders","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Randomized controlled trial; Meta-analysis; Botulinum toxin; Medicine; MEDLINE; Physical therapy; Internal medicine; Surgery; Biology","score_opus":0.8796501178182825,"score_gpt":0.7192512938865604,"score_spread":0.1603988239317221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410214727","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":[0.054641493,0.014333238,0.8144498,0.034117717,0.0018203581,0.07222988,0.000040340634,0.00013365035,0.008233525],"genre_scores_gemma":[0.24276146,0.005785923,0.59286004,0.005436014,0.0005504702,0.1294208,0.000092021466,0.00012831354,0.022964984],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.31737494,0.6674991,0.010161853,0.0011489931,0.001901439,0.0019136382],"domain_scores_gemma":[0.19551171,0.80113894,0.001513463,0.0009192817,0.0005740192,0.00034255517],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7815618,0.00037308442,0.017919665,0.00228758,0.0003720173,0.000007500244,0.0010455596,0.0009259671,0.003097104],"category_scores_gemma":[0.92199826,0.00021052241,0.002284799,0.0012184681,0.00094512437,0.000046437723,0.00082414574,0.002144192,0.000031149633],"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":[0.69345385,0.0021957955,0.010743605,0.00432834,0.016022427,0.00009026939,0.00274828,0.000031024643,0.0001255482,0.20975542,0.05120232,0.00930314],"study_design_scores_gemma":[0.7587097,0.00065258937,0.001969243,0.000596183,0.0024523267,6.796957e-7,0.013916619,0.002132229,0.00002167433,0.21360886,0.0057373405,0.00020252353],"about_ca_topic_score_codex":0.0020692172,"about_ca_topic_score_gemma":0.005439156,"teacher_disagreement_score":0.22158979,"about_ca_system_score_codex":0.00016683948,"about_ca_system_score_gemma":0.0024665948,"threshold_uncertainty_score":0.9978142},"labels":[],"label_agreement":null},{"id":"W4410250207","doi":"10.1186/s12874-025-02581-7","title":"Critically appraising the cass report: methodological flaws and unsupported claims","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Sex and Gender in Healthcare","field":"Medicine","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 Alberta","funders":"","keywords":"MEDLINE; Medicine; Computer science; Data science; Psychology; Actuarial science; Political science; Law; Business","score_opus":0.8157749592780283,"score_gpt":0.6809390048541768,"score_spread":0.13483595442385155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410250207","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16309883,0.00638859,0.6238983,0.18419978,0.001643218,0.0017630669,0.000005513325,0.00021130989,0.01879135],"genre_scores_gemma":[0.3588415,0.0020224093,0.6010165,0.026756072,0.0022683043,0.00049399375,0.000069105954,0.0000722438,0.00845987],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95794016,0.03628965,0.0011121097,0.0011650797,0.0021199214,0.0013730738],"domain_scores_gemma":[0.759724,0.23559418,0.00010379992,0.0015765288,0.0015666904,0.0014347602],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10765198,0.00023434838,0.0010120544,0.0003984373,0.00053784583,0.00004306054,0.00047856668,0.0009178251,0.00084074086],"category_scores_gemma":[0.45917112,0.00013896805,0.00016861536,0.0010494571,0.0028844175,0.00003745051,0.0006429349,0.0030373815,0.000023501596],"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":[0.0023445864,0.00035200926,0.04834314,0.0024205323,0.00037707205,0.009457012,0.0012544958,0.0000010342295,0.0034590268,0.13113494,0.029547287,0.77130884],"study_design_scores_gemma":[0.0058826776,0.0023146525,0.29978293,0.0011623403,0.00039375247,0.026032714,0.017718554,0.0046926755,0.0033580156,0.31519136,0.32280546,0.000664878],"about_ca_topic_score_codex":0.0004062245,"about_ca_topic_score_gemma":0.00033581757,"teacher_disagreement_score":0.770644,"about_ca_system_score_codex":0.00009996869,"about_ca_system_score_gemma":0.0035567207,"threshold_uncertainty_score":0.9998292},"labels":[],"label_agreement":null},{"id":"W4410406004","doi":"10.1186/s12874-025-02561-x","title":"Comparison of methods for tuning machine learning model hyper-parameters: with application to predicting high-need high-cost health care users","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Machine learning; Bayesian optimization; Computer science; Artificial intelligence; Random forest; Gradient boosting; Overfitting; Boosting (machine learning); Extreme learning machine; Cross-validation; Calibration; Statistics; Mathematics; Artificial neural network","score_opus":0.38504065731138276,"score_gpt":0.6055089837650878,"score_spread":0.220468326453705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410406004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016852299,0.0008637549,0.9679337,0.011707979,0.00024234438,0.0020953517,0.0000087993685,0.00022108764,0.00007463997],"genre_scores_gemma":[0.2004635,0.000029420968,0.7978571,0.00074573245,0.000056132863,0.00070374314,0.00004449058,0.000031687814,0.00006819339],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9727648,0.022043219,0.0011812302,0.0012927342,0.0013716609,0.0013463411],"domain_scores_gemma":[0.9415341,0.055115234,0.0003982564,0.001087627,0.0010697197,0.000795037],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038245864,0.00028416194,0.0012402664,0.0010681674,0.0006589972,0.00006596764,0.0021278097,0.00046953358,0.000009213492],"category_scores_gemma":[0.06924054,0.00024484828,0.00010436536,0.002007387,0.0003318152,0.00013621562,0.0010948277,0.00291172,0.0000033522253],"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":[0.00056421454,0.00008870003,0.038704693,0.0017973516,0.000057626152,0.0000010510706,0.0057803444,0.15591058,0.0007397057,0.037681375,0.00022571957,0.75844866],"study_design_scores_gemma":[0.0010050442,0.0013560178,0.0013253608,0.00036558893,0.00001270449,0.0000049634896,0.0013254958,0.9893616,0.0012406098,0.0018313582,0.001993087,0.00017821114],"about_ca_topic_score_codex":0.006197397,"about_ca_topic_score_gemma":0.0016528874,"teacher_disagreement_score":0.833451,"about_ca_system_score_codex":0.00044547516,"about_ca_system_score_gemma":0.0033194001,"threshold_uncertainty_score":0.9993886},"labels":[],"label_agreement":null},{"id":"W4410784164","doi":"10.1186/s12874-025-02594-2","title":"Comparison of methods to handle missing values in a continuous index test in a diagnostic accuracy study – a simulation study","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Universitätsklinikum Hamburg-Eppendorf; Deutsche Forschungsgemeinschaft","keywords":"Missing data; Statistics; Covariate; Imputation (statistics); Sample size determination; Inverse probability weighting; Weighting; Correlation; Mathematics; Medicine; Estimator","score_opus":0.6339960035583913,"score_gpt":0.6978124382894738,"score_spread":0.06381643473108256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410784164","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":[0.28025356,0.00010794587,0.71705705,0.00019249444,0.00010361596,0.002081278,0.0000027012866,0.000019537158,0.00018185074],"genre_scores_gemma":[0.5030883,0.0000035006778,0.4966041,0.000025511856,0.000021662321,0.0002250324,4.1424872e-7,0.00001081269,0.000020672762],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91752756,0.07635962,0.0025823128,0.00092514127,0.0016003781,0.0010050039],"domain_scores_gemma":[0.1991512,0.7992402,0.00020933812,0.00061568344,0.00046115235,0.00032243566],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08979559,0.0002255853,0.001748348,0.0013804277,0.00009895935,0.00004361089,0.0007084263,0.00027985245,0.00022805134],"category_scores_gemma":[0.93665874,0.00018792812,0.000065547974,0.0024387236,0.00035716072,0.000054703836,0.0006543457,0.0012903856,0.000003983588],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038366858,0.0061220177,0.6494406,0.00028483706,0.000029956751,0.00006131909,0.006400825,0.00007303779,0.00019562148,0.004954449,0.00006507392,0.33198857],"study_design_scores_gemma":[0.0032291696,0.0025369078,0.44653866,0.00088842557,0.000046163197,0.0000016310487,0.017677814,0.086499,0.00035625338,0.44198978,0.00003459156,0.00020160152],"about_ca_topic_score_codex":0.0015066998,"about_ca_topic_score_gemma":0.0040626978,"teacher_disagreement_score":0.84686315,"about_ca_system_score_codex":0.00015656212,"about_ca_system_score_gemma":0.0009849728,"threshold_uncertainty_score":0.937247},"labels":[],"label_agreement":null},{"id":"W4411133310","doi":"10.1186/s12874-025-02593-3","title":"Comparison of total event analysis and first event analysis in relation to heterogeneity in cardiovascular trials","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Impact; McMaster University; Population Health Research Institute","funders":"","keywords":"Event (particle physics); Cardiovascular event; Clinical trial; Medicine; Statistics; Internal medicine; Mathematics; Myocardial infarction","score_opus":0.8918162979523403,"score_gpt":0.7417101097785189,"score_spread":0.15010618817382138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411133310","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":[0.35205215,0.0005996645,0.64595324,0.0004905792,0.0001179248,0.0007015859,0.000015517506,0.00000879506,0.00006051185],"genre_scores_gemma":[0.48997986,0.00011638127,0.50965774,0.00002227096,0.00004374997,0.00014216448,0.0000035000774,0.000007987918,0.000026311618],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.853228,0.1373876,0.0047453907,0.0011171546,0.0027291693,0.0007927273],"domain_scores_gemma":[0.48311284,0.51512617,0.00027797322,0.00084269914,0.00027024248,0.00037006845],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31925398,0.00020651631,0.005450489,0.0034361351,0.00006566943,0.000017099537,0.00044131256,0.00064101035,0.00040995085],"category_scores_gemma":[0.8924835,0.0001705852,0.0012248445,0.008335308,0.00046095075,0.000029178356,0.00063074945,0.0010269923,0.0000038400726],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020879686,0.0012311368,0.84699917,0.0009892848,0.012831553,0.000047716636,0.0008023259,0.010882496,0.00016920737,0.028190067,0.00017964486,0.09558944],"study_design_scores_gemma":[0.0026312303,0.00032737636,0.7121949,0.00028899076,0.0044542486,0.0000011289972,0.0003600953,0.043406602,0.0014995836,0.23453513,0.00008512888,0.0002155793],"about_ca_topic_score_codex":0.0013597156,"about_ca_topic_score_gemma":0.011894126,"teacher_disagreement_score":0.5732295,"about_ca_system_score_codex":0.00024277087,"about_ca_system_score_gemma":0.00043342597,"threshold_uncertainty_score":0.7009713},"labels":[],"label_agreement":null},{"id":"W4411902950","doi":"10.1186/s12874-025-02602-5","title":"Identifying hospitalization episodes of care among people with and without HIV in British Columbia, Canada","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"HIV-related health complications and treatments","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":"University of British Columbia; Simon Fraser University; AIDS Vancouver","funders":"National Institute on Drug Abuse; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Medicine; Human immunodeficiency virus (HIV); Family medicine; MEDLINE; Gerontology; Demography; Political science; Sociology","score_opus":0.109087369630352,"score_gpt":0.4625828952242853,"score_spread":0.3534955255939333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411902950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9813173,0.001975322,0.014509019,0.0006609041,0.000043574655,0.000653481,0.00000870072,0.000011080925,0.0008206191],"genre_scores_gemma":[0.98135656,0.00053566694,0.016709544,0.00007276967,0.000013864672,0.0001455597,0.000050424158,0.00001067162,0.0011049503],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9966446,0.0016669687,0.00035926412,0.00031677357,0.00065717596,0.0003552206],"domain_scores_gemma":[0.99588406,0.0031331675,0.000055856268,0.000227868,0.00042674877,0.0002723175],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024554557,0.00006037553,0.00044716563,0.00017800539,0.00013888764,0.000019745663,0.000106469684,0.00016546536,0.00013572484],"category_scores_gemma":[0.008927819,0.00007054186,0.000018020097,0.00074244966,0.00035107226,0.000032497726,0.0000909686,0.00041957002,8.019684e-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":[0.000059333448,0.000058063644,0.9872319,0.000976717,0.00003131407,0.00004204176,0.00039345524,0.0000017331731,0.000006614707,0.00015851978,0.0005544652,0.010485835],"study_design_scores_gemma":[0.0017832294,0.00018376022,0.9928318,0.0015813414,0.000027522186,0.00003450062,0.002513774,0.0004778233,0.000020305677,0.00032498388,0.00017443902,0.000046467405],"about_ca_topic_score_codex":0.93024105,"about_ca_topic_score_gemma":0.99829,"teacher_disagreement_score":0.06804896,"about_ca_system_score_codex":0.0002419787,"about_ca_system_score_gemma":0.004355065,"threshold_uncertainty_score":0.9994204},"labels":[],"label_agreement":null},{"id":"W4412151422","doi":"10.1186/s12874-025-02616-z","title":"A framework for clinical care pathway renewal: an example from inflammatory bowel disease","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Clinical practice guidelines implementation","field":"Medicine","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":"Alberta Health Services; Alberta Health; University of Calgary; University of Alberta","funders":"Crohn's and Colitis Canada; University of Alberta; Alberta Health Services","keywords":"Inflammatory bowel disease; Medicine; Intensive care medicine; Inflammatory Bowel Diseases; MEDLINE; Disease; Internal medicine; Political science","score_opus":0.8780862472448779,"score_gpt":0.7198018972619796,"score_spread":0.1582843499828983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412151422","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2803877,0.0017783402,0.7033298,0.010558455,0.0014638968,0.0019929395,0.00006486031,0.00013969725,0.00028431206],"genre_scores_gemma":[0.11059423,0.0013871705,0.8704112,0.01086599,0.0042294175,0.00093171943,0.0009948056,0.00008201229,0.0005034471],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9734175,0.020156201,0.0023689677,0.0012713197,0.0018479904,0.00093798817],"domain_scores_gemma":[0.57501674,0.4179375,0.00033224974,0.002014093,0.0019438341,0.002755611],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056299128,0.00023964651,0.0009265503,0.00035585611,0.00025434225,0.00004076506,0.0006539929,0.0009394848,0.0015693626],"category_scores_gemma":[0.649491,0.00020419956,0.00038060255,0.00044108354,0.0010013905,0.00013175778,0.0005424138,0.002282199,0.00005376313],"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":[0.027753536,0.001213236,0.26554772,0.0013920061,0.00039324944,0.00035800828,0.0013509438,0.0000048956085,0.00032712767,0.066971645,0.024654644,0.610033],"study_design_scores_gemma":[0.01816049,0.0029310521,0.22658452,0.0015080518,0.00059971027,0.000010914975,0.016073981,0.00525224,0.00045966456,0.46241465,0.26546517,0.0005395772],"about_ca_topic_score_codex":0.0029029073,"about_ca_topic_score_gemma":0.003739834,"teacher_disagreement_score":0.60949343,"about_ca_system_score_codex":0.00020247727,"about_ca_system_score_gemma":0.010658651,"threshold_uncertainty_score":0.99934334},"labels":[],"label_agreement":null},{"id":"W4412763292","doi":"10.1186/s12874-025-02626-x","title":"Comparing randomized trial designs to estimate treatment effect in rare diseases with longitudinal models: a simulation study showcased by Autosomal Recessive Cerebellar Ataxias using the SARA score","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean","funders":"","keywords":"Randomized controlled trial; Medicine; Cerebellar ataxia; Physical medicine and rehabilitation; Pediatrics; Physical therapy; Ataxia; Internal medicine; Psychiatry","score_opus":0.9042634351777981,"score_gpt":0.7046481815688531,"score_spread":0.19961525360894494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412763292","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":[0.40244654,0.00013096086,0.5895118,0.00022363677,0.00019448948,0.007381266,0.000020083779,0.000047103087,0.000044091747],"genre_scores_gemma":[0.49848372,0.000013765116,0.4995522,0.0000473023,0.0001725948,0.0016349709,0.000006683492,0.000040339237,0.000048434977],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8401385,0.15332493,0.0019284191,0.0011979014,0.0023129939,0.0010972695],"domain_scores_gemma":[0.22694728,0.77091926,0.00030509685,0.00089491525,0.00035748878,0.0005759459],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08501869,0.00046438805,0.0034148002,0.00046789265,0.00039616085,0.000115240975,0.00081055524,0.00036773938,0.00015192266],"category_scores_gemma":[0.7214521,0.00024662557,0.0002786121,0.0013106064,0.0011692628,0.00008372789,0.0005095638,0.0010417206,0.0000040781283],"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":[0.9468915,0.0020331144,0.0085285995,0.00035981278,0.000615553,0.0002778784,0.000680179,0.022787062,0.000032798336,0.005649701,0.0001227835,0.012021022],"study_design_scores_gemma":[0.38784403,0.0029683434,0.00027457447,0.0006478675,0.00059304066,0.000003988229,0.00027976328,0.4316381,0.00015044112,0.17538485,0.0000032752341,0.00021175807],"about_ca_topic_score_codex":0.00059546187,"about_ca_topic_score_gemma":0.00079960603,"teacher_disagreement_score":0.6364334,"about_ca_system_score_codex":0.0005664428,"about_ca_system_score_gemma":0.0015069672,"threshold_uncertainty_score":0.9999986},"labels":[],"label_agreement":null},{"id":"W4412806735","doi":"10.1186/s12874-025-02631-0","title":"Using a large language model (ChatGPT) to assess risk of bias in randomized controlled trials of medical interventions: protocol for a pilot study of interrater agreement with human reviewers","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Norwegian Institute of Public Health","keywords":"Inter-rater reliability; Psychological intervention; Randomized controlled trial; Systematic review; Protocol (science); MEDLINE; Medicine; Clinical trial; Psychology; Medical physics; Family medicine; Physical therapy; Rating scale; Nursing; Alternative medicine; Pathology","score_opus":0.9568881869498969,"score_gpt":0.7730588343050259,"score_spread":0.183829352644871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412806735","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":[0.36867163,0.00019972642,0.46974123,0.0007428211,0.00007877324,0.16050233,0.0000063870234,0.0000050021113,0.000052116895],"genre_scores_gemma":[0.6799417,0.00008973158,0.05179708,0.00016323304,0.000112082205,0.2676779,0.000008916209,0.000019185145,0.00019017604],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9149309,0.074136645,0.006890054,0.00055073306,0.0028643147,0.00062735076],"domain_scores_gemma":[0.84375745,0.15030214,0.0018594845,0.00086132163,0.002682519,0.0005371014],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32805088,0.00015789563,0.004959648,0.0012659754,0.000059652924,0.000006346855,0.000363147,0.00019471139,0.0006527906],"category_scores_gemma":[0.58774304,0.00008977206,0.00049061765,0.0006965634,0.00041925348,0.000030083558,0.00018857376,0.0006164501,6.5536886e-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":[0.90051085,0.014986454,0.014311199,0.020690568,0.0017779246,0.000018777682,0.016351702,0.00017326993,0.0027604843,0.0049364003,0.00058422517,0.022898147],"study_design_scores_gemma":[0.6029182,0.043432243,0.00062523107,0.070620276,0.002169534,0.000010907473,0.10074969,0.15212671,0.0155363185,0.01136149,0.00008271348,0.0003666961],"about_ca_topic_score_codex":0.0065681525,"about_ca_topic_score_gemma":0.013288666,"teacher_disagreement_score":0.41794413,"about_ca_system_score_codex":0.00012097938,"about_ca_system_score_gemma":0.0033323886,"threshold_uncertainty_score":0.9929126},"labels":[],"label_agreement":null},{"id":"W4413805698","doi":"10.1186/s12874-025-02652-9","title":"Development of a protocol complexity tool: a framework designed to stimulate discussion and simplify study design","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"AstraZeneca","keywords":"Clinical trial; Protocol (science); Medicine; Computer science; Research design; Medical physics; Statistics; Internal medicine; Alternative medicine; Pathology; Mathematics","score_opus":0.9486650995424512,"score_gpt":0.7577932577158293,"score_spread":0.19087184182662187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413805698","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":[0.008653373,0.0000040822842,0.9242758,0.0008634668,0.00013535755,0.065896526,0.0000046955092,0.000057998535,0.000108707565],"genre_scores_gemma":[0.0020242038,0.0000012617651,0.95314467,0.00017050093,0.0000762759,0.044414625,2.9768256e-7,0.00002834154,0.00013984733],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90686,0.08543395,0.0027913672,0.0011146886,0.0027307582,0.0010692235],"domain_scores_gemma":[0.34077075,0.6567873,0.00023514513,0.0008992712,0.000576068,0.00073150726],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17337136,0.0002758893,0.0016435984,0.00045857157,0.00028462207,0.000036266076,0.00090921175,0.00058222155,0.00081251905],"category_scores_gemma":[0.8965813,0.00016672067,0.000089935354,0.0011746127,0.0011032845,0.000029751687,0.0016923631,0.0013280765,0.0000168447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012480471,0.0034923498,0.0025347925,0.0028454803,0.00036662948,0.00006998755,0.0042249663,0.000009640113,0.0020381524,0.33702838,0.002107842,0.6328013],"study_design_scores_gemma":[0.0025200457,0.0012720778,0.005026473,0.000813333,0.000038503,0.0000020374011,0.0007494422,0.00080336165,0.0019046521,0.98610723,0.0005760961,0.00018674663],"about_ca_topic_score_codex":0.000020268313,"about_ca_topic_score_gemma":0.000068332665,"teacher_disagreement_score":0.7232099,"about_ca_system_score_codex":0.00011786363,"about_ca_system_score_gemma":0.0022480665,"threshold_uncertainty_score":0.88965136},"labels":[],"label_agreement":null},{"id":"W4414852885","doi":"10.1186/s12874-025-02679-y","title":"What actually happens in partnered health research? A concordance analysis of agreement on partnership practices in funded Canadian projects between academic and knowledge user investigators","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Health Policy Implementation Science","field":"Health Professions","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":"University of Ottawa; University of Manitoba; Ottawa Hospital; George & Fay Yee Centre for Healthcare Innovation","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Concordance; Documentation; General partnership; Agreement; MEDLINE; Qualitative research; Health care; Research design","score_opus":0.979728446650643,"score_gpt":0.8302594962687775,"score_spread":0.14946895038186547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414852885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.874106,0.00057399395,0.0003255452,0.119073875,0.00022666015,0.003182567,0.000030067367,0.0000146117645,0.0024666688],"genre_scores_gemma":[0.9781017,0.0029864956,0.0036043127,0.012797929,0.00013750595,0.001155754,0.00002940207,0.000018022045,0.0011688886],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.81290346,0.17752105,0.002524043,0.0011155963,0.0025695434,0.0033662803],"domain_scores_gemma":[0.6640383,0.33082417,0.0007575822,0.0007520782,0.0007296203,0.0028982533],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26953626,0.00020429034,0.0012868105,0.008147219,0.00067941204,0.000030222149,0.0010343634,0.0007085134,0.0003888097],"category_scores_gemma":[0.50642174,0.00017967414,0.00005309997,0.011448546,0.0019394177,0.00033823817,0.00062566076,0.00562699,0.000041585114],"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":[0.00027045206,0.000056603993,0.8967538,0.0013209381,0.00008844952,0.000014381501,0.05544739,0.0000053877625,0.000043280197,0.023500297,0.0100233555,0.012475704],"study_design_scores_gemma":[0.0023836882,0.0005917346,0.8497246,0.0027634883,0.000027584518,5.048259e-7,0.08255243,0.0009295367,0.00009629732,0.0034179909,0.057337318,0.00017484432],"about_ca_topic_score_codex":0.32951117,"about_ca_topic_score_gemma":0.96269715,"teacher_disagreement_score":0.633186,"about_ca_system_score_codex":0.0018295725,"about_ca_system_score_gemma":0.08159962,"threshold_uncertainty_score":0.9966671},"labels":[],"label_agreement":null},{"id":"W4416993465","doi":"10.1186/s12874-025-02721-z","title":"Omitting patients with no follow-up leads to bias when using inverse-intensity weighted GEEs to handle irregular and informative assessment times","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Medication Adherence and Compliance","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":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network; Institute for Clinical Evaluative Sciences; Hospital for Sick Children; Public Health Ontario","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MEDLINE; Task (project management); Reliability (semiconductor); R package","score_opus":0.38931730034138007,"score_gpt":0.5139301561461168,"score_spread":0.12461285580473674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416993465","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":[0.7630567,0.000047377824,0.22752737,0.004171381,0.00026747747,0.0010663542,0.0000033248277,0.000038571143,0.0038214752],"genre_scores_gemma":[0.15987042,0.000050572733,0.8144388,0.011777493,0.00022704502,0.00023659322,0.000052834017,0.000029953037,0.01331624],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9943977,0.002311065,0.0005095995,0.00049079704,0.0016394984,0.00065132295],"domain_scores_gemma":[0.9902061,0.006662513,0.00010468347,0.0005014887,0.0014196158,0.0011055552],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009386797,0.00018718666,0.0007011916,0.00054994744,0.00024619565,0.000033734337,0.00030610885,0.00021798276,0.000986173],"category_scores_gemma":[0.040944047,0.00013250661,0.000052199928,0.00077248574,0.0004921349,0.00010329297,0.00049849466,0.0007691415,0.00024743055],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00627729,0.00041591696,0.8051511,0.0011020723,0.00039807486,0.00006159441,0.0046294173,0.000006048551,0.0019767333,0.0023513383,0.083099596,0.094530806],"study_design_scores_gemma":[0.024376893,0.0074328044,0.7967935,0.0091706235,0.00030019807,0.00007948371,0.010632221,0.046558365,0.01035714,0.0049791755,0.08822633,0.0010932578],"about_ca_topic_score_codex":0.00029398504,"about_ca_topic_score_gemma":0.00011451622,"teacher_disagreement_score":0.60318625,"about_ca_system_score_codex":0.00019438055,"about_ca_system_score_gemma":0.0021446317,"threshold_uncertainty_score":0.99992704},"labels":[],"label_agreement":null},{"id":"W4417212516","doi":"10.1186/s12874-025-02722-y","title":"Qualitative dyadic analysis in care partnership research: a scoping review","year":2025,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Geriatric Care and Nursing Homes","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Sunnybrook Hospital; University of Toronto; Public Health Ontario; Sunnybrook Health Science Centre","funders":"Fondation Brain Canada; ALS Society of Canada","keywords":"Conceptualization; General partnership; Qualitative research; Health services research; MEDLINE; Primary care; Health care; Qualitative analysis","score_opus":0.9489960834848165,"score_gpt":0.8267580538993532,"score_spread":0.12223802958546326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417212516","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":[0.0000012893838,0.9793241,0.0016356055,0.0013307829,0.0006828942,0.0075566377,0.00003969906,0.00006727813,0.0093617225],"genre_scores_gemma":[8.6782615e-7,0.98350406,0.004658395,0.0002740471,0.00069605646,0.0061013363,0.0004917437,0.000063349784,0.0042101624],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.58329916,0.4060077,0.002845661,0.0014440095,0.0037403237,0.0026631786],"domain_scores_gemma":[0.4527499,0.5415147,0.00055302103,0.0017408589,0.0023167992,0.0011247323],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3083725,0.0005792147,0.008909726,0.008358514,0.0010420014,0.000024040712,0.0022238875,0.0028995494,0.005094781],"category_scores_gemma":[0.5611196,0.00043869688,0.0014401088,0.021525946,0.0015355054,0.00006244064,0.0017043313,0.014489894,0.0006929351],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044796674,0.000036284284,0.000018446757,0.54703635,0.00023940159,0.0000906582,0.010825025,4.394871e-8,6.587039e-9,0.0010163658,0.021751504,0.4189411],"study_design_scores_gemma":[0.0003035869,0.00011459069,0.000005814325,0.5988933,0.0009167076,0.0000024312385,0.030824719,0.0000010492447,2.7888447e-8,0.00075699907,0.3679484,0.00023235315],"about_ca_topic_score_codex":0.0035688772,"about_ca_topic_score_gemma":0.033002093,"teacher_disagreement_score":0.41870874,"about_ca_system_score_codex":0.0020301563,"about_ca_system_score_gemma":0.06118171,"threshold_uncertainty_score":0.99980646},"labels":[],"label_agreement":null},{"id":"W7117729834","doi":"10.1186/s12874-025-02703-1","title":"Machine learning models explanations as interpretations of evidence: a theoretical framework of explainability and its implications on high-stakes biomedical decision-making","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer 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":"University of British Columbia","funders":"European Commission","keywords":"Operationalization; Terminology; Soundness; Interpretation (philosophy); Interpretability; Raising (metalworking)","score_opus":0.4858301340420024,"score_gpt":0.5662124117095355,"score_spread":0.08038227766753309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117729834","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":[0.04846303,0.0008387243,0.9404163,0.009049136,0.00016522766,0.00041828337,0.0000071062905,0.000052648276,0.00058957445],"genre_scores_gemma":[0.7317074,0.00042054697,0.26754233,0.00015195232,0.000022824792,0.00012338077,0.0000020398406,0.000006981054,0.000022540824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9870662,0.008970654,0.0010052249,0.0007684891,0.0016067524,0.0005826573],"domain_scores_gemma":[0.6945377,0.30244738,0.00019885116,0.0010135912,0.0013807189,0.0004217743],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023198903,0.00016599263,0.00055269833,0.001060914,0.00036958922,0.000049989274,0.0017327173,0.00039844352,0.00035228924],"category_scores_gemma":[0.4507954,0.00012701312,0.00010509005,0.0022237727,0.0020735785,0.00031947307,0.0010860423,0.0013190936,0.000013633746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015435115,0.00018365162,0.00033778115,0.000118191696,0.000023902176,0.0000062289328,0.001796502,0.00065402477,0.0003957548,0.89374006,0.00003828951,0.10255124],"study_design_scores_gemma":[0.0000784679,0.00037924448,0.00043182363,0.0009786666,0.000007962699,0.000008254433,0.0007406287,0.27346864,0.0017226476,0.72206026,0.000052560332,0.000070819646],"about_ca_topic_score_codex":0.0001669313,"about_ca_topic_score_gemma":0.00009066329,"teacher_disagreement_score":0.68324435,"about_ca_system_score_codex":0.00011350292,"about_ca_system_score_gemma":0.0016634752,"threshold_uncertainty_score":0.80403227},"labels":[],"label_agreement":null}]}