{"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":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023644522,0.10883349,0.4921921,0.06797207,0.06703199,0.1977934,0.036282163,0.012322644,0.015207795],"genre_scores_gemma":[0.008174057,0.03805184,0.56033134,0.010768714,0.005870379,0.35610634,0.013902022,0.0032457982,0.00354957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.23435614,0.6043737,0.120274596,0.009015155,0.029578323,0.0024021047],"domain_scores_gemma":[0.13441075,0.61801726,0.0969284,0.0343109,0.111866504,0.0044662594],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4845528,0.0067571336,0.014351586,0.033647873,0.004891123,0.01654211,0.013093588,0.013782565,0.023708435],"category_scores_gemma":[0.7530512,0.008193507,0.028958598,0.03386367,0.0102624595,0.010647627,0.010986689,0.034138784,0.017559072],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034069135,0.00029620292,0.0024731245,0.21266295,0.010872987,0.00038264008,0.0038776023,0.0032079704,0.0010534297,0.03979798,0.49169445,0.23027375],"study_design_scores_gemma":[0.010761366,0.0009429199,0.0069412636,0.30607352,0.011806353,0.0011962705,0.0012283225,0.007971628,0.00244209,0.076394804,0.5729185,0.0013229289],"about_ca_topic_score_codex":0.005244438,"about_ca_topic_score_gemma":0.004810216,"teacher_disagreement_score":0.5154472,"about_ca_system_score_codex":0.01810674,"about_ca_system_score_gemma":0.051403128,"threshold_uncertainty_score":0.63563824},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013338195,0.00018952298,0.99771464,0.00014116048,0.0000255948,0.00012873515,0.000024204586,0.0000733059,0.00036896963],"genre_scores_gemma":[0.08156623,0.0005092877,0.9146209,0.00018132094,0.00012190843,0.002446897,0.00013632761,0.00009479021,0.0003223339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8535418,0.12672232,0.0027715676,0.007214248,0.00884768,0.0009023979],"domain_scores_gemma":[0.64732265,0.3166615,0.010870548,0.01481361,0.009513999,0.0008176246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09091135,0.0015509186,0.003148476,0.0036083094,0.00072434795,0.0026111421,0.0036841403,0.0033015984,0.003791737],"category_scores_gemma":[0.33842576,0.0012848508,0.0022207175,0.002850026,0.005020288,0.0032458848,0.003152885,0.004155358,0.0009473428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009122289,0.00023694815,0.004050142,0.001172042,0.000521643,0.00022240629,0.0011991727,0.117399774,0.0025362514,0.6230724,0.002233216,0.24644387],"study_design_scores_gemma":[0.00046747824,0.00083000155,0.0029852996,0.00052135397,0.0002490287,0.00028560514,0.00013346477,0.3964697,0.0038510796,0.5866347,0.007429705,0.00014252671],"about_ca_topic_score_codex":0.00088626624,"about_ca_topic_score_gemma":0.00042721073,"teacher_disagreement_score":0.09091135,"about_ca_system_score_codex":0.0017703638,"about_ca_system_score_gemma":0.0034285663,"threshold_uncertainty_score":0.4807909},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033454277,0.0317977,0.89843976,0.014225728,0.0056455834,0.0051428135,0.0018739534,0.0041521857,0.005267994],"genre_scores_gemma":[0.3044744,0.005001994,0.6763466,0.006032587,0.0016472691,0.0039707837,0.0009731409,0.00063663366,0.0009165479],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.61356175,0.31045464,0.034525864,0.017917886,0.02244763,0.0010921861],"domain_scores_gemma":[0.07792912,0.8501872,0.026940713,0.034177512,0.009544622,0.0012208945],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47678584,0.0044160336,0.011617116,0.011357864,0.0024375997,0.011844908,0.009027691,0.008368356,0.005988522],"category_scores_gemma":[0.87173843,0.004104248,0.017083637,0.0061404547,0.0054928265,0.01636851,0.0050851973,0.010717949,0.0012596144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011886075,0.0006508862,0.092611425,0.054830376,0.08326091,0.0058004777,0.0058391183,0.052352317,0.003906254,0.08987388,0.041699294,0.557289],"study_design_scores_gemma":[0.0064201043,0.003068778,0.024571516,0.023128368,0.070279956,0.004298776,0.0015193387,0.2118864,0.009999917,0.5803523,0.0633206,0.0011539282],"about_ca_topic_score_codex":0.0012728573,"about_ca_topic_score_gemma":0.0024075143,"teacher_disagreement_score":0.52321416,"about_ca_system_score_codex":0.0028773819,"about_ca_system_score_gemma":0.008058077,"threshold_uncertainty_score":0.6452162},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9221473,0.034865707,0.0185565,0.0034626601,0.0014077105,0.0011937898,0.008057578,0.0011790752,0.009129662],"genre_scores_gemma":[0.98101956,0.0027673177,0.008404847,0.00044700192,0.00044835208,0.0010508429,0.0042842245,0.00022015629,0.0013575885],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7223503,0.10330623,0.083168484,0.020537827,0.06826125,0.002375845],"domain_scores_gemma":[0.20787272,0.33368507,0.2013649,0.025930718,0.22758548,0.0035611282],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19025008,0.0008158945,0.0018488615,0.011221173,0.0011867745,0.004001346,0.0023638108,0.0015048506,0.0011593059],"category_scores_gemma":[0.5292588,0.00084245973,0.0024500228,0.007187987,0.00095314067,0.0028353727,0.0038055226,0.0013972179,0.0009478502],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039260583,0.00012275351,0.892804,0.0040386305,0.0028783102,0.00027308517,0.009462995,0.0011253344,0.0026697307,0.0002156163,0.0058044246,0.076679096],"study_design_scores_gemma":[0.00017623449,0.0017265967,0.97614485,0.0013158156,0.000879246,0.0012493869,0.0033823843,0.002671799,0.0032878343,0.000383568,0.008572135,0.00021011398],"about_ca_topic_score_codex":0.0026081882,"about_ca_topic_score_gemma":0.002914468,"teacher_disagreement_score":0.8097499,"about_ca_system_score_codex":0.0020190657,"about_ca_system_score_gemma":0.002944292,"threshold_uncertainty_score":0.9985658},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012314343,0.27125672,0.06084278,0.5928895,0.009397765,0.0010238945,0.0003071483,0.00010908097,0.05185889],"genre_scores_gemma":[0.3384074,0.29106066,0.13136964,0.21846217,0.010566641,0.0027715482,0.0002952583,0.000088466215,0.0069782543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9539866,0.028988902,0.0028310886,0.0027658571,0.010794151,0.00063348515],"domain_scores_gemma":[0.83423513,0.12966174,0.010257817,0.0104093375,0.01302035,0.0024156556],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07947079,0.0008667137,0.0016230558,0.0026392317,0.0023863532,0.011534634,0.002850983,0.0074463496,0.004324869],"category_scores_gemma":[0.059672967,0.00049536425,0.0008219574,0.0028180545,0.020969521,0.014466766,0.0044482932,0.006269959,0.0017520398],"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":[0.00029837925,0.00023565616,0.002973548,0.016555842,0.00023651894,0.00016713138,0.0035636525,0.0007998971,0.0014631129,0.646755,0.015151482,0.3117997],"study_design_scores_gemma":[0.00014092469,0.0005796365,0.0025843147,0.023107368,0.00027123463,0.0004644246,0.0054518534,0.0013167867,0.0018353098,0.7961564,0.16800423,0.00008753461],"about_ca_topic_score_codex":0.0012955071,"about_ca_topic_score_gemma":0.0020809537,"teacher_disagreement_score":0.9205292,"about_ca_system_score_codex":0.004516528,"about_ca_system_score_gemma":0.02296716,"threshold_uncertainty_score":0.42028672},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061847963,0.8283398,0.025654882,0.02996589,0.004029739,0.092828326,0.007478698,0.0006771381,0.0048407163],"genre_scores_gemma":[0.067011066,0.5020636,0.18753797,0.010373818,0.0018271318,0.22637188,0.0033946945,0.00034422948,0.001075652],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.5272084,0.24718083,0.1823426,0.009552903,0.03146275,0.002252469],"domain_scores_gemma":[0.37683964,0.4256951,0.10872799,0.018263679,0.06488911,0.005584431],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25025418,0.00441115,0.023758415,0.05460095,0.003729645,0.016836261,0.00668768,0.008450512,0.0128501],"category_scores_gemma":[0.59437615,0.006965659,0.015087883,0.04164148,0.006850584,0.027281463,0.006779248,0.0045976983,0.0036164601],"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":[0.0003892715,0.000039187755,0.0016283991,0.9137969,0.0033749724,0.00013723287,0.0011479141,0.00017735592,0.00036849547,0.0011098773,0.005982267,0.07184815],"study_design_scores_gemma":[0.0011986168,0.00016295855,0.003020632,0.95825464,0.013271415,0.00018556681,0.00143098,0.0004449602,0.00044893296,0.0036796408,0.017725559,0.00017619667],"about_ca_topic_score_codex":0.0077584656,"about_ca_topic_score_gemma":0.022966823,"teacher_disagreement_score":0.74974585,"about_ca_system_score_codex":0.017802421,"about_ca_system_score_gemma":0.06050435,"threshold_uncertainty_score":0.9245701},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062126115,0.016144292,0.88040215,0.0043024886,0.001342415,0.021043276,0.002741432,0.0015017727,0.010396014],"genre_scores_gemma":[0.291703,0.0016488379,0.6827385,0.0021134974,0.0003084559,0.019654045,0.0010847077,0.00019919255,0.00054976647],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.23303822,0.535623,0.15908548,0.01776426,0.052961756,0.0015273],"domain_scores_gemma":[0.05325297,0.78317547,0.05218262,0.069377765,0.04138539,0.000625829],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6951764,0.0035512233,0.006552143,0.029742297,0.0034771499,0.0076493225,0.0058974614,0.0069366773,0.0028368644],"category_scores_gemma":[0.888297,0.0027903891,0.009779756,0.020680359,0.006906791,0.010832756,0.0076430305,0.0034291542,0.0008914784],"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":[0.009938982,0.000629353,0.07799142,0.10185665,0.030758858,0.0007476297,0.028918615,0.012205879,0.010166124,0.07911921,0.01646777,0.6311996],"study_design_scores_gemma":[0.01605464,0.017363194,0.13572924,0.103665985,0.06513709,0.004298803,0.00908865,0.08798472,0.080464594,0.32359096,0.1520866,0.004535509],"about_ca_topic_score_codex":0.0044133742,"about_ca_topic_score_gemma":0.003779465,"teacher_disagreement_score":0.30482358,"about_ca_system_score_codex":0.0061698398,"about_ca_system_score_gemma":0.0113401385,"threshold_uncertainty_score":0.37590182},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076975427,0.0031099743,0.9334317,0.0043431227,0.0014572834,0.032081388,0.0078076744,0.0010382753,0.009033042],"genre_scores_gemma":[0.043106154,0.0017953272,0.823258,0.0019704446,0.0006075848,0.123002715,0.0039945594,0.000373743,0.0018914175],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76064265,0.17802279,0.027238812,0.0051383246,0.027616622,0.0013408493],"domain_scores_gemma":[0.37197882,0.5760485,0.009450626,0.017496353,0.02362545,0.0014001594],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2000522,0.0014679093,0.003193187,0.0036250835,0.0012106397,0.002173403,0.0044600302,0.004810702,0.024153227],"category_scores_gemma":[0.5731917,0.0017971608,0.0022227238,0.0029394133,0.0015255263,0.002916908,0.0027443732,0.0031511276,0.004705274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008994222,0.0007177526,0.013634826,0.013345811,0.0010598657,0.0014415807,0.00290797,0.019858748,0.0068108384,0.19566856,0.09837338,0.63718647],"study_design_scores_gemma":[0.017540796,0.009504863,0.02793662,0.007843969,0.0021717784,0.00475398,0.0010330166,0.06940199,0.016424777,0.4589634,0.38398802,0.00043683316],"about_ca_topic_score_codex":0.0011014427,"about_ca_topic_score_gemma":0.0010761009,"teacher_disagreement_score":0.7999478,"about_ca_system_score_codex":0.0013340445,"about_ca_system_score_gemma":0.004648626,"threshold_uncertainty_score":0.98647803},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986484,0.002267366,0.0038403736,0.001606984,0.00007370785,0.00005673285,0.00044228404,0.000009389832,0.0052191094],"genre_scores_gemma":[0.9982231,0.00028101407,0.0010136951,0.00007414103,0.000021808879,0.000026772734,0.00016072665,0.000003688147,0.00019501861],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975921,0.0012296861,0.00016219469,0.00028198882,0.00048406413,0.0002500351],"domain_scores_gemma":[0.9896191,0.006386198,0.001619958,0.0008827365,0.0010154196,0.00047657522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008986202,0.00031897362,0.0003421013,0.0014517771,0.0008767244,0.0011971548,0.00062915985,0.00043494697,0.001957395],"category_scores_gemma":[0.019740963,0.00022474612,0.0012783062,0.0014090852,0.0029972314,0.0018622652,0.0016693686,0.0010013684,0.0001082259],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028591426,0.00004837754,0.9298882,0.00009541929,0.00011657881,0.00017125276,0.016499195,0.00051198306,0.0007932025,0.0039159493,0.00040248298,0.04727145],"study_design_scores_gemma":[0.0000033551664,0.00010226846,0.9936241,0.00005785579,0.000023257,0.00011780405,0.0032567652,0.00045347374,0.00014289952,0.001421432,0.0007843783,0.000012476481],"about_ca_topic_score_codex":0.03817597,"about_ca_topic_score_gemma":0.041834343,"teacher_disagreement_score":0.9910138,"about_ca_system_score_codex":0.0019573933,"about_ca_system_score_gemma":0.0016029883,"threshold_uncertainty_score":0.07590753},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06892093,0.6215104,0.110818036,0.1357138,0.02160857,0.018967407,0.004627499,0.000515924,0.017317338],"genre_scores_gemma":[0.65242404,0.087723225,0.18844397,0.031924408,0.007291849,0.029061137,0.0021916004,0.00028443217,0.0006553448],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.18710603,0.4462918,0.28293094,0.01228737,0.06907505,0.0023087612],"domain_scores_gemma":[0.050451536,0.67789495,0.18639937,0.022611806,0.060070317,0.0025720394],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5841318,0.001100438,0.007346974,0.011578657,0.002962129,0.013493135,0.006800533,0.011530655,0.00456508],"category_scores_gemma":[0.89414155,0.0025552292,0.0100282915,0.014867295,0.012359402,0.01233028,0.0059367847,0.006902305,0.0013712817],"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":[0.009555258,0.00039204303,0.15395664,0.51591784,0.028746082,0.0006596232,0.009818032,0.0014443924,0.002138965,0.022893783,0.030141464,0.22433583],"study_design_scores_gemma":[0.011150853,0.0065940493,0.1832244,0.54108244,0.048027996,0.005909041,0.0066851946,0.010257139,0.0049252394,0.09350955,0.08717213,0.0014619844],"about_ca_topic_score_codex":0.0027265474,"about_ca_topic_score_gemma":0.0030075884,"teacher_disagreement_score":0.41586822,"about_ca_system_score_codex":0.010024515,"about_ca_system_score_gemma":0.016895726,"threshold_uncertainty_score":0.5128396},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781291,0.00040233793,0.020284459,0.00025453203,0.000019190169,0.00013454878,0.00027258697,0.00004114769,0.00046213914],"genre_scores_gemma":[0.98890066,0.00014763702,0.0102761835,0.00005371751,0.000010916206,0.00019316765,0.00025674695,0.000006538243,0.0001543914],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952348,0.003996449,0.0001519956,0.00026086776,0.00019598761,0.00015988355],"domain_scores_gemma":[0.91505617,0.077867225,0.0026457387,0.002317831,0.001518498,0.0005945324],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013432463,0.0009132687,0.0008985709,0.0006925067,0.00035260717,0.0007144157,0.0010796536,0.0014571255,0.0008015174],"category_scores_gemma":[0.030006608,0.0004963013,0.0018951206,0.00065035676,0.0008278792,0.00082974415,0.00080879964,0.0015192543,0.00009440615],"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":[0.0016021376,0.00059075427,0.052212432,0.00016277643,0.00061430124,0.00018640974,0.00018260961,0.93494624,0.0006115954,0.0016118386,0.00032182387,0.0069570425],"study_design_scores_gemma":[0.00021450759,0.00116876,0.007404317,0.000041277348,0.00014587899,0.00009352786,0.0000649696,0.98849213,0.0006333607,0.0015213971,0.0001894269,0.00003046252],"about_ca_topic_score_codex":0.005871278,"about_ca_topic_score_gemma":0.0033582714,"teacher_disagreement_score":0.98656756,"about_ca_system_score_codex":0.001217451,"about_ca_system_score_gemma":0.00092933537,"threshold_uncertainty_score":0.071038485},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34502935,0.030079907,0.6126254,0.0030025928,0.00063850224,0.0028358956,0.0010456423,0.00074030104,0.0040024016],"genre_scores_gemma":[0.5303615,0.010369813,0.45400095,0.0005907669,0.000234408,0.0028849277,0.000835051,0.00020752223,0.00051500194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8324543,0.14747176,0.0063871746,0.003322291,0.009771772,0.00059273455],"domain_scores_gemma":[0.61256766,0.35605204,0.012087291,0.00840681,0.009949323,0.00093694194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15151525,0.0009509329,0.0025193107,0.0030990397,0.00081503316,0.0019672941,0.0028936493,0.002002324,0.0019154687],"category_scores_gemma":[0.23076567,0.00096250867,0.0048945826,0.0036382107,0.00093256356,0.0030547439,0.0022897818,0.0023656513,0.00048680985],"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":[0.016226828,0.0015093739,0.17330685,0.006692924,0.016453845,0.00023349887,0.0052095326,0.026597658,0.0010794655,0.0070784464,0.0044988324,0.74111277],"study_design_scores_gemma":[0.008248038,0.026328223,0.33523977,0.01619468,0.01460413,0.003256275,0.00627282,0.5130343,0.008188265,0.04595362,0.021049643,0.0016302638],"about_ca_topic_score_codex":0.0012796883,"about_ca_topic_score_gemma":0.001805761,"teacher_disagreement_score":0.15151525,"about_ca_system_score_codex":0.0012737147,"about_ca_system_score_gemma":0.0017104285,"threshold_uncertainty_score":0.8012988},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029795736,0.048956253,0.75518686,0.15210648,0.0055311243,0.00093707594,0.00020566351,0.00052580464,0.033571217],"genre_scores_gemma":[0.12187203,0.034635175,0.8088445,0.01847368,0.0045292703,0.0058014067,0.00018957091,0.00049816776,0.00515621],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.633407,0.3168535,0.012442957,0.00811467,0.027549544,0.0016322556],"domain_scores_gemma":[0.40477532,0.49597532,0.013202535,0.063270174,0.018337606,0.004439108],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28929383,0.0022228316,0.0037414585,0.013899007,0.006567742,0.024021212,0.007972932,0.009473566,0.0071832584],"category_scores_gemma":[0.2728744,0.0017177999,0.002106888,0.0096093705,0.1302906,0.030837039,0.01797215,0.018554578,0.0035888096],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046328245,0.000062628096,0.00056296686,0.0023230792,0.00011098751,0.000095279756,0.008198365,0.0005392193,0.0002452361,0.9201198,0.006899068,0.060796976],"study_design_scores_gemma":[0.000037029626,0.000045147062,0.000249213,0.0025511198,0.000036167214,0.00010111079,0.0026460062,0.0008022311,0.00034126523,0.93140626,0.061741192,0.00004313916],"about_ca_topic_score_codex":0.0021833344,"about_ca_topic_score_gemma":0.0015666814,"teacher_disagreement_score":0.7107062,"about_ca_system_score_codex":0.0096392585,"about_ca_system_score_gemma":0.028193781,"threshold_uncertainty_score":0.87642723},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016691064,0.0005237297,0.9817462,0.0001406777,0.000073823925,0.00034300875,0.000076122466,0.00017043251,0.00023499125],"genre_scores_gemma":[0.14370118,0.00071659015,0.8531851,0.00011511733,0.000057577963,0.0015447858,0.0002938965,0.00009323738,0.00029243858],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9679602,0.026303396,0.0010018452,0.0016547387,0.0028384249,0.0002413922],"domain_scores_gemma":[0.82483166,0.15087236,0.006536686,0.009324895,0.00747036,0.00096402643],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.058339696,0.0008930567,0.0013494355,0.0018938729,0.00038799192,0.00095505285,0.0021913992,0.0008162375,0.0025499444],"category_scores_gemma":[0.1783362,0.00081986137,0.0020610373,0.0009835023,0.0010262785,0.0013147008,0.0015455091,0.0014204964,0.00037839814],"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":[0.0057166973,0.0012357255,0.06303276,0.0025185298,0.008496619,0.00090941327,0.00275425,0.257364,0.018384358,0.15334263,0.0036383397,0.48260665],"study_design_scores_gemma":[0.0014407947,0.0016641073,0.015021432,0.00029633386,0.0011998187,0.0010100635,0.00027045692,0.8504319,0.0068536336,0.11532601,0.006315462,0.00016998817],"about_ca_topic_score_codex":0.0025664675,"about_ca_topic_score_gemma":0.002421038,"teacher_disagreement_score":0.9416603,"about_ca_system_score_codex":0.0009750568,"about_ca_system_score_gemma":0.002486662,"threshold_uncertainty_score":0.3085335},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5312312,0.0018828715,0.44727412,0.009742678,0.00057946076,0.00094875705,0.0010187544,0.0007012548,0.006620837],"genre_scores_gemma":[0.9641463,0.00024623057,0.033700872,0.00032989978,0.00007166682,0.00054288824,0.00061937026,0.00010579353,0.00023692909],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8312271,0.13477427,0.0069276122,0.01116977,0.013990911,0.0019103311],"domain_scores_gemma":[0.20626566,0.7284787,0.027629185,0.024438042,0.01162982,0.0015585023],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17345904,0.0021106587,0.0020217502,0.0039701215,0.0020909002,0.0052975407,0.0034997282,0.0025268833,0.004110933],"category_scores_gemma":[0.48908865,0.000993191,0.0045721927,0.0066115055,0.009793268,0.006091791,0.004440807,0.0067536845,0.0005206649],"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":[0.0012915303,0.0005982473,0.77347267,0.0013314673,0.0074547003,0.00064361416,0.008290124,0.038615104,0.00081890577,0.07923208,0.0045184116,0.08373302],"study_design_scores_gemma":[0.0005064284,0.0019857525,0.25135717,0.0012178422,0.002367633,0.0008973247,0.005664991,0.3755231,0.0034343558,0.34861243,0.007971676,0.00046136914],"about_ca_topic_score_codex":0.006598562,"about_ca_topic_score_gemma":0.00380566,"teacher_disagreement_score":0.82654095,"about_ca_system_score_codex":0.003983303,"about_ca_system_score_gemma":0.0055060224,"threshold_uncertainty_score":0.91735005},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016708314,0.17220318,0.52580094,0.006557385,0.002050382,0.23793317,0.0193018,0.007866115,0.011578734],"genre_scores_gemma":[0.045441743,0.034914434,0.74042803,0.0013326934,0.00035551997,0.1719811,0.004263545,0.0005027381,0.00078031933],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.41447797,0.4546437,0.105785385,0.007377786,0.016370388,0.0013448087],"domain_scores_gemma":[0.21385095,0.72349656,0.027122522,0.012898923,0.021641377,0.0009897321],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3276958,0.00806871,0.016617814,0.059601225,0.0015330557,0.009747508,0.007282401,0.004756904,0.019407056],"category_scores_gemma":[0.70303726,0.0049332078,0.018535927,0.04299307,0.0022222372,0.008648192,0.008024085,0.0039162,0.0047784843],"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":[0.0045272796,0.00022876344,0.0030504658,0.5983232,0.028078929,0.0005033886,0.0026925644,0.013811779,0.0017043721,0.009264438,0.0140554095,0.32375947],"study_design_scores_gemma":[0.023178168,0.005114393,0.010585909,0.5207786,0.14746685,0.0016128289,0.0033849333,0.0720479,0.0063077006,0.095570974,0.11238613,0.0015656078],"about_ca_topic_score_codex":0.005289956,"about_ca_topic_score_gemma":0.008263786,"teacher_disagreement_score":0.6723042,"about_ca_system_score_codex":0.008907216,"about_ca_system_score_gemma":0.024990907,"threshold_uncertainty_score":0.8290708},"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":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057572443,0.72114104,0.15206662,0.027037958,0.0058636786,0.027265415,0.0029078724,0.00044974912,0.0056952843],"genre_scores_gemma":[0.75157183,0.053100288,0.1509607,0.0065678093,0.0019569504,0.034162126,0.0010926615,0.00021425195,0.0003734177],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.038477685,0.76531965,0.15755294,0.007541308,0.030328374,0.00078008225],"domain_scores_gemma":[0.010094119,0.87551916,0.06842076,0.023686267,0.02156045,0.00071930955],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86237854,0.003962799,0.014113885,0.022211203,0.0033072836,0.014687505,0.006815006,0.0077583003,0.0023265812],"category_scores_gemma":[0.9475702,0.0048032156,0.02434419,0.019799696,0.010663823,0.011590783,0.008349862,0.0064608594,0.00029568523],"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":[0.010591651,0.0003512705,0.15895943,0.3305745,0.3300422,0.00043455325,0.009169754,0.005642627,0.0008420974,0.0095556835,0.0045879004,0.13924831],"study_design_scores_gemma":[0.014307321,0.008898542,0.12785064,0.3315222,0.38995817,0.0015806645,0.0028520068,0.025562773,0.005736101,0.060513746,0.029724753,0.0014930876],"about_ca_topic_score_codex":0.0074688187,"about_ca_topic_score_gemma":0.010057319,"teacher_disagreement_score":0.13762146,"about_ca_system_score_codex":0.017138546,"about_ca_system_score_gemma":0.024803095,"threshold_uncertainty_score":0.16971183},"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":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98008186,0.016209055,0.0008814143,0.00044745542,0.0000990969,0.00028763487,0.0013804985,0.000016572003,0.0005964874],"genre_scores_gemma":[0.9960542,0.001907995,0.0005005031,0.00014812668,0.00023968973,0.0002687159,0.0006876427,0.0000124505605,0.00018076914],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96814436,0.009936793,0.010895696,0.0033806493,0.006483407,0.0011590789],"domain_scores_gemma":[0.7948585,0.05682969,0.1274256,0.010096469,0.007195487,0.003594218],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.023764713,0.000579356,0.001584317,0.008460155,0.0010084305,0.0024458554,0.0009577656,0.0015056567,0.002716388],"category_scores_gemma":[0.07590076,0.00059841067,0.002458559,0.010504767,0.0010413274,0.0024174477,0.0011270607,0.0008888964,0.0007087583],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041882313,0.000037369937,0.9958801,0.00024596837,0.00036936803,0.00018364732,0.00025447618,0.000023945011,0.00008592549,0.000035589535,0.00013993328,0.0023247367],"study_design_scores_gemma":[0.00008355613,0.0006078812,0.99320436,0.00026076616,0.00064685295,0.0028764883,0.0006471041,0.00028207136,0.00016500294,0.00021199006,0.0009855031,0.00002837851],"about_ca_topic_score_codex":0.0008843914,"about_ca_topic_score_gemma":0.0005968721,"teacher_disagreement_score":0.9984943,"about_ca_system_score_codex":0.0007169303,"about_ca_system_score_gemma":0.0014778416,"threshold_uncertainty_score":0.12568134},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7146387,0.06511561,0.15285838,0.0065159746,0.0019270553,0.033837266,0.011389883,0.0028978782,0.010819275],"genre_scores_gemma":[0.8150156,0.0064098327,0.14004533,0.0011651401,0.00037221203,0.03360745,0.0020123953,0.00055614056,0.00081578345],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.55354464,0.3369152,0.06508629,0.0057810326,0.03733902,0.001333807],"domain_scores_gemma":[0.09353413,0.8045541,0.06444196,0.013840081,0.022546379,0.0010833588],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43174648,0.0016016176,0.0031320625,0.011461539,0.0011502836,0.0053069345,0.0021593515,0.002196211,0.008947176],"category_scores_gemma":[0.6885608,0.0019843085,0.011371488,0.013139877,0.001981668,0.011723113,0.0055094543,0.0027696826,0.0007602383],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03926021,0.0022787587,0.43274564,0.091386534,0.036324736,0.0010966824,0.036655147,0.0053598126,0.002849704,0.0037525175,0.024559056,0.32373115],"study_design_scores_gemma":[0.02014009,0.044533312,0.6975783,0.05300535,0.0444268,0.004664117,0.027268896,0.041284043,0.004919017,0.007379687,0.053021703,0.0017787149],"about_ca_topic_score_codex":0.0012363284,"about_ca_topic_score_gemma":0.002596223,"teacher_disagreement_score":0.5682535,"about_ca_system_score_codex":0.0044730934,"about_ca_system_score_gemma":0.003209011,"threshold_uncertainty_score":0.70075774},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17971963,0.060173176,0.6429983,0.019605087,0.00088414823,0.038729705,0.007755399,0.006106782,0.044027727],"genre_scores_gemma":[0.26085684,0.007145334,0.71453315,0.0025994456,0.00026303568,0.011018965,0.0025613646,0.00038651904,0.0006353452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.49783415,0.4062376,0.050556485,0.0060957405,0.037828837,0.0014471529],"domain_scores_gemma":[0.18119662,0.7698593,0.016562821,0.016363943,0.014802575,0.0012147635],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24464051,0.0036361662,0.0048133787,0.021317225,0.0016190144,0.009958875,0.004280309,0.0040084883,0.0075269705],"category_scores_gemma":[0.7359182,0.0028187302,0.0046719713,0.012046031,0.002279632,0.00945096,0.008506303,0.0025736548,0.0023875693],"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":[0.0069037643,0.0011906484,0.019602254,0.028811943,0.0053946106,0.00064553955,0.0060442737,0.020845635,0.0026369065,0.016182449,0.017054878,0.87468714],"study_design_scores_gemma":[0.021448713,0.010394385,0.04090896,0.046735454,0.024197225,0.0067499,0.014021548,0.5069999,0.013064804,0.19114207,0.12266829,0.0016687126],"about_ca_topic_score_codex":0.0044949944,"about_ca_topic_score_gemma":0.006098588,"teacher_disagreement_score":0.7553595,"about_ca_system_score_codex":0.0038556126,"about_ca_system_score_gemma":0.014842368,"threshold_uncertainty_score":0.93149275},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02597814,0.022674339,0.9344269,0.005494762,0.0004959351,0.0024265884,0.0017461659,0.0003944279,0.0063627088],"genre_scores_gemma":[0.62059027,0.018498803,0.3393746,0.0034316953,0.0015236742,0.01213148,0.0026855685,0.0003986947,0.0013652567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4725459,0.47103474,0.018360583,0.012558365,0.023855483,0.0016449556],"domain_scores_gemma":[0.054118566,0.9112632,0.018067677,0.011698444,0.004343727,0.00050836254],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42791337,0.003989403,0.010204469,0.014324973,0.0010210887,0.011585671,0.0060394183,0.007863757,0.007040006],"category_scores_gemma":[0.7566097,0.0015290821,0.008100792,0.012505194,0.013724663,0.013951157,0.005960942,0.010741222,0.0008423473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006564928,0.00026811627,0.03448814,0.01064824,0.00728209,0.00064334366,0.0017412689,0.2162835,0.00033513573,0.49695623,0.006268816,0.21852018],"study_design_scores_gemma":[0.0013686863,0.001956701,0.010542306,0.0066948244,0.0034286326,0.0012561365,0.00038063072,0.25000712,0.0012979499,0.7068462,0.015774421,0.0004464419],"about_ca_topic_score_codex":0.001321242,"about_ca_topic_score_gemma":0.0005012237,"teacher_disagreement_score":0.57208663,"about_ca_system_score_codex":0.0047748145,"about_ca_system_score_gemma":0.0034263772,"threshold_uncertainty_score":0.7054847},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048281826,0.02400884,0.9087942,0.0050444333,0.0011794989,0.005415333,0.0004010927,0.00035555757,0.0065191654],"genre_scores_gemma":[0.6552216,0.006081315,0.32070887,0.0022588675,0.0007030224,0.013679807,0.0003822633,0.00036011176,0.00060407206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.30025277,0.6456198,0.018520566,0.0123642385,0.02201644,0.0012261329],"domain_scores_gemma":[0.052861884,0.90481627,0.019362649,0.017987538,0.004386585,0.0005850111],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58810383,0.0026509229,0.0075658937,0.006890597,0.0012180761,0.00571589,0.0059932014,0.008492724,0.0063763396],"category_scores_gemma":[0.86099774,0.0017233668,0.012333643,0.0060144495,0.012167225,0.012904913,0.0074398075,0.00773552,0.00053802074],"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":[0.022881093,0.0011851366,0.04273148,0.02347331,0.058304366,0.00074108667,0.0052008643,0.14765833,0.001409344,0.33651307,0.0057553328,0.35414666],"study_design_scores_gemma":[0.009974327,0.008961805,0.01877856,0.008599059,0.014826368,0.0010924462,0.00071477983,0.26440936,0.002629819,0.6578789,0.011730272,0.000404251],"about_ca_topic_score_codex":0.00091670494,"about_ca_topic_score_gemma":0.00039227807,"teacher_disagreement_score":0.41189617,"about_ca_system_score_codex":0.004613972,"about_ca_system_score_gemma":0.0053159404,"threshold_uncertainty_score":0.50794137},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4845612,0.34027174,0.052192476,0.024665538,0.0014721599,0.049398173,0.010577401,0.0019990646,0.034862243],"genre_scores_gemma":[0.8493978,0.04017788,0.08098276,0.003918982,0.00095080177,0.020100722,0.003107363,0.000451173,0.0009124938],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.24327382,0.615005,0.09490892,0.009309876,0.03425534,0.003247051],"domain_scores_gemma":[0.03296806,0.90255547,0.040667392,0.009732039,0.013356654,0.00072049623],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.51701605,0.0022932626,0.010820158,0.026173724,0.0015759951,0.02066694,0.0037861338,0.0061603915,0.00958744],"category_scores_gemma":[0.88651335,0.0024674535,0.012196391,0.060993202,0.00404433,0.03264945,0.0073992275,0.0023774665,0.0027596662],"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":[0.020488381,0.0022929774,0.17105019,0.34583983,0.03720635,0.0006109122,0.010706399,0.0077321343,0.00093010545,0.0065856655,0.014727589,0.38182947],"study_design_scores_gemma":[0.03847058,0.029306946,0.31975296,0.27954686,0.13443777,0.0042411415,0.019265082,0.05207072,0.0045346715,0.055700503,0.05961295,0.0030597202],"about_ca_topic_score_codex":0.0032342474,"about_ca_topic_score_gemma":0.0055112704,"teacher_disagreement_score":0.48298395,"about_ca_system_score_codex":0.007636621,"about_ca_system_score_gemma":0.015491935,"threshold_uncertainty_score":0.59560525},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05965274,0.6987487,0.124177784,0.083948635,0.010962341,0.011860128,0.0031945694,0.0010790775,0.0063760635],"genre_scores_gemma":[0.56412065,0.11640431,0.25921285,0.028164715,0.009339057,0.01893537,0.0026952922,0.00057698274,0.00055083126],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.08370867,0.5627457,0.26295525,0.018890746,0.069895655,0.0018040207],"domain_scores_gemma":[0.02063285,0.75635296,0.13377395,0.03774118,0.050431024,0.0010680963],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.79839724,0.002767471,0.010224866,0.024879038,0.003256643,0.015944242,0.008535909,0.008672079,0.0024858308],"category_scores_gemma":[0.9456127,0.0048117363,0.014236606,0.026435887,0.010708634,0.01901511,0.007866927,0.007115204,0.00069588836],"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":[0.004734588,0.0002631635,0.12917587,0.2569157,0.05116561,0.00029579832,0.013240162,0.0039965496,0.0016696579,0.013345046,0.017447807,0.5077501],"study_design_scores_gemma":[0.008450957,0.007772427,0.27463284,0.36046764,0.115902774,0.0036275226,0.0048780516,0.026232192,0.008246047,0.08504373,0.10224123,0.0025047075],"about_ca_topic_score_codex":0.0086300345,"about_ca_topic_score_gemma":0.008442813,"teacher_disagreement_score":0.20160276,"about_ca_system_score_codex":0.018390035,"about_ca_system_score_gemma":0.023532055,"threshold_uncertainty_score":0.24861217},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014925279,0.9974443,0.00010945549,0.00023053472,0.000074441115,0.0002974381,0.0002041768,0.000004726775,0.00014242437],"genre_scores_gemma":[0.02438783,0.9729778,0.00085752987,0.0004796541,0.00007214534,0.00097182073,0.00018415756,0.0000057386164,0.0000632217],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.97725075,0.007999505,0.008435492,0.0014293212,0.004391632,0.00049334177],"domain_scores_gemma":[0.9063676,0.069767654,0.01475396,0.0010402972,0.007344014,0.0007264949],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02057988,0.0015362069,0.008548876,0.017214866,0.0009999832,0.0034386104,0.0021831787,0.0026421817,0.0025677178],"category_scores_gemma":[0.09012348,0.0014063778,0.0071634566,0.017405879,0.0014891608,0.0039376807,0.0022067786,0.0013590708,0.0002351331],"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":[0.00012885181,0.000019511124,0.002302851,0.9598147,0.0056596394,0.00009377244,0.00034300584,0.000059081725,0.00008567924,0.000111666035,0.0008452581,0.030535944],"study_design_scores_gemma":[0.00014708709,0.00016053257,0.007191083,0.94885564,0.03525017,0.00033568538,0.0005456525,0.00007666593,0.00012097104,0.00012941011,0.0071481536,0.00003895826],"about_ca_topic_score_codex":0.010549712,"about_ca_topic_score_gemma":0.027797537,"teacher_disagreement_score":0.9794201,"about_ca_system_score_codex":0.00634271,"about_ca_system_score_gemma":0.018803975,"threshold_uncertainty_score":0.10883808},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97594553,0.0033458436,0.013023039,0.0039401255,0.00007392982,0.00048871245,0.0016104183,0.00011417141,0.0014582087],"genre_scores_gemma":[0.9952472,0.0003016622,0.003112693,0.00029384383,0.0001183051,0.0002161517,0.000499343,0.000029946468,0.00018084022],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93506944,0.04604637,0.008414168,0.0042977324,0.004142995,0.0020294134],"domain_scores_gemma":[0.43156782,0.34872064,0.18350138,0.020571634,0.0077480725,0.007890484],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12864715,0.00035585804,0.0009180667,0.0024803942,0.00063022756,0.0018783298,0.0011844345,0.000967178,0.0023182693],"category_scores_gemma":[0.2910601,0.00042735026,0.0016309393,0.003594752,0.0015527243,0.0023362404,0.0020770351,0.0012882787,0.00032790803],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005116288,0.00005355377,0.9879645,0.00011608858,0.00033756183,0.00004467179,0.0003643859,0.0007556453,0.0002399777,0.0004346017,0.00036539522,0.0088119935],"study_design_scores_gemma":[0.00008005366,0.00049710576,0.9872299,0.000120740544,0.0002928875,0.00022658422,0.00040889633,0.007927184,0.00038366034,0.0013680229,0.0014463312,0.000018617977],"about_ca_topic_score_codex":0.0022544714,"about_ca_topic_score_gemma":0.0028339496,"teacher_disagreement_score":0.87135285,"about_ca_system_score_codex":0.0010826369,"about_ca_system_score_gemma":0.001535812,"threshold_uncertainty_score":0.68035924},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02185591,0.00008890695,0.9714902,0.0010156083,0.00012144609,0.00082860084,0.00069208397,0.0031030204,0.000804248],"genre_scores_gemma":[0.048924513,0.000046655518,0.9485107,0.00020477045,0.00004226753,0.0006471985,0.001178808,0.00018264058,0.00026240267],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9618046,0.022438986,0.0054249787,0.0040869946,0.005601121,0.0006432501],"domain_scores_gemma":[0.911591,0.036660664,0.01200182,0.01594217,0.022768976,0.0010353337],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.061466012,0.0011748194,0.0011543147,0.004536377,0.0015046449,0.0028947226,0.0032541505,0.0013696444,0.0021886441],"category_scores_gemma":[0.11297477,0.0012205528,0.0028851703,0.006191957,0.0011372286,0.0030418409,0.0045792297,0.002709339,0.0012939773],"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":[0.00074388896,0.0007543708,0.08293048,0.0009833954,0.0013720143,0.00064225955,0.0060384613,0.048927005,0.007296487,0.022591066,0.020077547,0.807643],"study_design_scores_gemma":[0.001040429,0.0016020664,0.08199733,0.0008666877,0.0014497838,0.0026308072,0.0045184093,0.70349467,0.03714501,0.06288162,0.10172544,0.00064779696],"about_ca_topic_score_codex":0.004620191,"about_ca_topic_score_gemma":0.0035844846,"teacher_disagreement_score":0.93853396,"about_ca_system_score_codex":0.0014367022,"about_ca_system_score_gemma":0.0069353697,"threshold_uncertainty_score":0.32506722},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09089249,0.07062956,0.6823957,0.09446444,0.00868384,0.02521018,0.0050768508,0.006593609,0.01605329],"genre_scores_gemma":[0.26898634,0.007670977,0.66771114,0.018052358,0.0035211109,0.02951824,0.0021047299,0.0014621465,0.00097296905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.13262296,0.64614785,0.13562797,0.017795378,0.0657301,0.002075794],"domain_scores_gemma":[0.020240944,0.6833574,0.10170948,0.12142424,0.071188405,0.0020794962],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7837936,0.0017102846,0.0059918636,0.012324829,0.0038493415,0.012683698,0.011383835,0.0052775154,0.0021532788],"category_scores_gemma":[0.8985813,0.0032831233,0.006040129,0.013431521,0.007442442,0.014707302,0.009309045,0.007797632,0.0010024074],"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":[0.0034785352,0.0005209169,0.16184832,0.05876808,0.011829213,0.0005484591,0.025789151,0.0063741077,0.0040249056,0.036451496,0.057697333,0.63266945],"study_design_scores_gemma":[0.0032510604,0.0063187266,0.23693646,0.14254412,0.01395033,0.0029797154,0.011607124,0.04416548,0.023514532,0.15283908,0.35981518,0.002078163],"about_ca_topic_score_codex":0.0024050018,"about_ca_topic_score_gemma":0.0023067982,"teacher_disagreement_score":0.21620637,"about_ca_system_score_codex":0.010362356,"about_ca_system_score_gemma":0.024401518,"threshold_uncertainty_score":0.266621},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9503197,0.0011196512,0.014850785,0.007218885,0.00021135337,0.001863513,0.005459483,0.00017955794,0.018776918],"genre_scores_gemma":[0.9879241,0.00057968294,0.004388416,0.0020421173,0.000116109186,0.0018239237,0.0016649116,0.000045309283,0.0014153995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.790866,0.14870033,0.015314062,0.0054792864,0.034802467,0.0048379395],"domain_scores_gemma":[0.6592727,0.22669895,0.047943432,0.01183539,0.05150253,0.0027470228],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11318432,0.00036450682,0.00047975342,0.004795447,0.0009809289,0.0028007072,0.0014950664,0.0012844182,0.004247212],"category_scores_gemma":[0.32860938,0.00036505386,0.00070150685,0.005062085,0.0009126572,0.0017374123,0.0023583039,0.0011649106,0.0012034774],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032008946,0.00020833724,0.89536667,0.0010344732,0.00020053833,0.00018182938,0.030574845,0.00044294042,0.0007714954,0.0015384747,0.012614018,0.056746222],"study_design_scores_gemma":[0.00009217462,0.0007859868,0.92038834,0.0015353151,0.000087657034,0.000666884,0.033515982,0.00498736,0.0015960382,0.0013122824,0.034953468,0.000078424404],"about_ca_topic_score_codex":0.011733128,"about_ca_topic_score_gemma":0.008231857,"teacher_disagreement_score":0.88681567,"about_ca_system_score_codex":0.0023352148,"about_ca_system_score_gemma":0.0026533485,"threshold_uncertainty_score":0.59858304},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863927,0.0008643148,0.003166449,0.0036258071,0.000062725354,0.0005863414,0.0011585411,0.000077700366,0.0040654484],"genre_scores_gemma":[0.99265563,0.0004995221,0.00428476,0.00037917143,0.000084287836,0.00074941607,0.0007022718,0.000015987509,0.0006289513],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99178714,0.005492033,0.00072414026,0.0005454912,0.0007808452,0.0006704203],"domain_scores_gemma":[0.93410367,0.03606079,0.021860944,0.0020361554,0.0029317255,0.00300669],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012478453,0.0003093203,0.0003584158,0.0017443491,0.0009201952,0.0010156947,0.0009056627,0.0010760286,0.008247046],"category_scores_gemma":[0.05953287,0.00025479743,0.00040599215,0.0024527959,0.0005540491,0.0016186676,0.0010886302,0.000891311,0.001214963],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009583334,0.00012050874,0.98740876,0.00010234859,0.000014461634,0.000092346956,0.00043847467,0.00013737734,0.00007965909,0.000060360915,0.0007094901,0.01074031],"study_design_scores_gemma":[0.00003620686,0.00036823942,0.99322647,0.00027004123,0.00004702706,0.00020934641,0.002451632,0.0011314051,0.00031994295,0.0002047416,0.0017128178,0.000022118293],"about_ca_topic_score_codex":0.010632428,"about_ca_topic_score_gemma":0.014010192,"teacher_disagreement_score":0.9875215,"about_ca_system_score_codex":0.000637313,"about_ca_system_score_gemma":0.0017254264,"threshold_uncertainty_score":0.06599319},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001235862,0.1007879,0.026396442,0.8514837,0.0095298365,0.00016009105,0.00012024641,0.000088506255,0.010197374],"genre_scores_gemma":[0.19900806,0.15598653,0.15247385,0.44590798,0.039006457,0.002061304,0.00016632616,0.00069224427,0.004697332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5287163,0.36420125,0.031313393,0.015210467,0.05776939,0.0027891563],"domain_scores_gemma":[0.23593076,0.69866157,0.014096898,0.020746946,0.025718417,0.004845402],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.40234518,0.0029898738,0.008837229,0.015761642,0.010111422,0.03686165,0.008076373,0.024712916,0.0055724136],"category_scores_gemma":[0.6117175,0.0026021295,0.0030947293,0.010090382,0.099960566,0.058707844,0.019331403,0.048519343,0.0020655626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032334292,0.00009206778,0.0011080289,0.0041645723,0.00066586846,0.00021069901,0.004679897,0.0014516488,0.00012625766,0.7835706,0.08970277,0.113904186],"study_design_scores_gemma":[0.00018420305,0.000145076,0.0004132566,0.009569521,0.00011351884,0.0001509454,0.0015038395,0.0014737607,0.00011265188,0.9218832,0.06433883,0.000111125046],"about_ca_topic_score_codex":0.0072060106,"about_ca_topic_score_gemma":0.004632734,"teacher_disagreement_score":0.5976548,"about_ca_system_score_codex":0.02715783,"about_ca_system_score_gemma":0.02759241,"threshold_uncertainty_score":0.7370148},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9845546,0.0001485968,0.014163097,0.00006368623,0.00000419499,0.000049356167,0.00062073284,0.000044718403,0.00035109752],"genre_scores_gemma":[0.9929461,0.00013218958,0.0053338064,0.000008894749,0.000003206054,0.00009891803,0.0010331598,0.000021919894,0.00042189835],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979013,0.0000636716,0.000012888089,0.000064094405,0.00002334466,0.000045932804],"domain_scores_gemma":[0.99830985,0.0011684468,0.00026313623,0.000050595634,0.00012577379,0.00008224129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012977745,0.00067201396,0.00043001916,0.00076633727,0.00023386319,0.0006633729,0.0007133322,0.00072544947,0.0010896568],"category_scores_gemma":[0.004187168,0.00045139474,0.0010483589,0.0004991512,0.0002712919,0.00035289148,0.0004437833,0.00061685196,0.00020108353],"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":[0.00028896448,0.00007985272,0.2128363,0.00007378122,0.00017374102,0.00019124185,0.00032927474,0.77594805,0.0007153311,0.0006423813,0.00038022755,0.008341004],"study_design_scores_gemma":[0.000019433617,0.000121826,0.06154303,0.0000285838,0.000045204553,0.000073134965,0.00015418442,0.9369293,0.00024071797,0.00050326105,0.0003261427,0.000015219836],"about_ca_topic_score_codex":0.055055503,"about_ca_topic_score_gemma":0.02779445,"teacher_disagreement_score":0.055055503,"about_ca_system_score_codex":0.0014940866,"about_ca_system_score_gemma":0.0010006898,"threshold_uncertainty_score":0.10947007},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9668276,0.0007554931,0.009841759,0.0003525496,0.00007945809,0.0010975088,0.016268888,0.00011477768,0.004662024],"genre_scores_gemma":[0.96548784,0.00018366205,0.0075791935,0.00012071646,0.000046462734,0.00038267073,0.025930168,0.000025796264,0.00024346032],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91078484,0.044718925,0.007762992,0.004855744,0.029818963,0.0020585128],"domain_scores_gemma":[0.6737297,0.14906369,0.065979555,0.03130113,0.07749616,0.002429729],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06087078,0.0008546623,0.00073052285,0.0054945196,0.0008483956,0.002817521,0.0022144893,0.00078983436,0.000617243],"category_scores_gemma":[0.21560071,0.0005253817,0.0010392194,0.008972178,0.0011136126,0.00097596075,0.002253457,0.0008113914,0.0003013765],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000370723,0.00009235926,0.9867966,0.0001785379,0.0005444431,0.000051915784,0.0007142016,0.0017572778,0.00041288268,0.00020883109,0.00064651814,0.00822568],"study_design_scores_gemma":[0.00006323411,0.00012583438,0.98732775,0.00022254056,0.00021444545,0.00010424041,0.0005185387,0.006489407,0.0015630294,0.00014917772,0.0031937428,0.000028033408],"about_ca_topic_score_codex":0.108282916,"about_ca_topic_score_gemma":0.089398906,"teacher_disagreement_score":0.93912923,"about_ca_system_score_codex":0.0037445521,"about_ca_system_score_gemma":0.0071322797,"threshold_uncertainty_score":0.32191932},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015522092,0.122688204,0.7890942,0.0062246635,0.0018908579,0.004601738,0.04954028,0.0028933822,0.0075445063],"genre_scores_gemma":[0.37010968,0.030453458,0.5565512,0.0025442813,0.0018048832,0.01861515,0.01733302,0.0010044702,0.001583799],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8174618,0.14728364,0.01723237,0.006773793,0.010733164,0.00051522447],"domain_scores_gemma":[0.39517158,0.55132705,0.029738951,0.015717853,0.007626088,0.00041840988],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15787287,0.003780708,0.006270886,0.020959074,0.00062587555,0.005800538,0.002561312,0.0024190443,0.017480861],"category_scores_gemma":[0.43893132,0.0011243444,0.017760798,0.011789586,0.0014143593,0.0047793644,0.0026282256,0.0045552314,0.0011342186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005503626,0.00018849543,0.022126291,0.165983,0.17893855,0.00035996587,0.0017941586,0.080826096,0.0016665173,0.057607237,0.04044051,0.44456556],"study_design_scores_gemma":[0.0036051834,0.003253172,0.03763266,0.06423004,0.20199546,0.001446537,0.0012300318,0.13306618,0.0065729516,0.39296964,0.1528263,0.0011718882],"about_ca_topic_score_codex":0.0012115211,"about_ca_topic_score_gemma":0.0013414552,"teacher_disagreement_score":0.84212714,"about_ca_system_score_codex":0.0029690755,"about_ca_system_score_gemma":0.002370095,"threshold_uncertainty_score":0.83492154},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030780565,0.055373795,0.4178292,0.28012645,0.04096311,0.1797889,0.0062192176,0.004020738,0.012600549],"genre_scores_gemma":[0.011735792,0.008919826,0.83340514,0.013557746,0.00163437,0.12789649,0.0016260841,0.00033764524,0.00088693755],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.101724416,0.6280935,0.20884942,0.011298998,0.045596756,0.004436889],"domain_scores_gemma":[0.053782,0.6457726,0.059851017,0.033725414,0.19875559,0.008113482],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7103681,0.010700151,0.019529164,0.048078306,0.010675894,0.02334232,0.038540907,0.04891593,0.014616797],"category_scores_gemma":[0.87782407,0.016069524,0.047351737,0.03791124,0.026421145,0.029171936,0.040963795,0.05155333,0.010333466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001270385,0.0004493684,0.0026345793,0.43771127,0.009256703,0.0013532093,0.033131704,0.00844462,0.0014495204,0.060946792,0.21448098,0.22887087],"study_design_scores_gemma":[0.004553518,0.0006317597,0.0027494177,0.63160163,0.008861464,0.00082671415,0.00903712,0.016594902,0.0024604464,0.12767226,0.19369252,0.0013182405],"about_ca_topic_score_codex":0.010362375,"about_ca_topic_score_gemma":0.008890549,"teacher_disagreement_score":0.2896319,"about_ca_system_score_codex":0.037234128,"about_ca_system_score_gemma":0.1005061,"threshold_uncertainty_score":0.35716778},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002886072,0.001519923,0.9924992,0.00047215147,0.0001766869,0.00087797176,0.0006987056,0.00028098564,0.00058837753],"genre_scores_gemma":[0.10700465,0.002488973,0.87404275,0.00042055832,0.0005015455,0.010023681,0.0028603447,0.0004264086,0.0022310703],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93982667,0.051820926,0.0020154035,0.0024211921,0.0034206402,0.00049512176],"domain_scores_gemma":[0.8230696,0.15878047,0.005799329,0.00663214,0.0048891073,0.0008293852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08011884,0.0025085039,0.002497216,0.0051112915,0.0008934643,0.0028828196,0.005450797,0.0023176991,0.0075383387],"category_scores_gemma":[0.13246676,0.001204677,0.00765875,0.0031190978,0.0015943842,0.0015653245,0.00332004,0.0039035045,0.0008035211],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014793844,0.0005741538,0.058664035,0.00502546,0.011107683,0.0014523992,0.0023527846,0.17055592,0.0015110032,0.33278307,0.025209073,0.38928506],"study_design_scores_gemma":[0.00059962174,0.00056389964,0.009600552,0.0010894937,0.0019228453,0.0016885261,0.00045286198,0.56658286,0.0011221769,0.38518938,0.030855974,0.0003317609],"about_ca_topic_score_codex":0.0034454032,"about_ca_topic_score_gemma":0.0029986484,"teacher_disagreement_score":0.08011884,"about_ca_system_score_codex":0.0019133077,"about_ca_system_score_gemma":0.0046690037,"threshold_uncertainty_score":0.42371398},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99862075,0.00027335458,0.00033172473,0.00020552441,0.000008812202,0.000025638725,0.00034174044,0.0000047885987,0.00018773807],"genre_scores_gemma":[0.99887925,0.00010658444,0.00031708242,0.000048035414,0.000007078747,0.000033632157,0.00048426617,0.0000031999873,0.00012086748],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99780864,0.0012340499,0.00015450853,0.00028779375,0.00022553267,0.00028952587],"domain_scores_gemma":[0.99080676,0.0025767952,0.0033835887,0.0010953547,0.0010522803,0.0010852495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068113143,0.00020858318,0.0004301692,0.00097184506,0.0013085434,0.0012905735,0.00071162224,0.00076478923,0.0012134903],"category_scores_gemma":[0.016949566,0.00040411958,0.0009184775,0.0014941308,0.0004954554,0.0013923249,0.0011937022,0.0015947327,0.00021360733],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009529796,0.00009931985,0.9963379,0.0000111240215,0.00006164199,0.00004690128,0.0014358425,0.00004435149,0.00006851733,0.00005861296,0.00013777193,0.001602776],"study_design_scores_gemma":[0.0000074495547,0.00016618131,0.9971456,0.000022246053,0.000037590675,0.000090702844,0.0017461961,0.0003664473,0.00003727098,0.0000966096,0.00027297394,0.000010805053],"about_ca_topic_score_codex":0.026491107,"about_ca_topic_score_gemma":0.034240298,"teacher_disagreement_score":0.026491107,"about_ca_system_score_codex":0.0011016106,"about_ca_system_score_gemma":0.0015270581,"threshold_uncertainty_score":0.052673817},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60978955,0.0010593935,0.0979723,0.00040002755,0.00016009816,0.0020916204,0.23148465,0.011740984,0.04530145],"genre_scores_gemma":[0.67832917,0.0009713362,0.21739,0.00010239191,0.000030425292,0.0012740754,0.09422039,0.0005295299,0.007152677],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891496,0.00008608736,0.00009211988,0.00016795975,0.0006360367,0.00010289159],"domain_scores_gemma":[0.9979298,0.00027677976,0.0003156809,0.00021259846,0.0011445232,0.000120578836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048454828,0.00096091937,0.0005507985,0.0068782256,0.00056982454,0.0012692937,0.0013821956,0.00044559228,0.007660936],"category_scores_gemma":[0.0028884301,0.00036274322,0.0008653842,0.007027876,0.0003436073,0.00091531454,0.0014658684,0.000460105,0.0033310917],"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":[0.00066655804,0.00032038218,0.49536735,0.0032316593,0.0005546107,0.0007998636,0.004364114,0.012786831,0.013597959,0.0036511987,0.05899496,0.4056645],"study_design_scores_gemma":[0.00006844202,0.00020433345,0.8584522,0.0005315937,0.00022627726,0.0012038315,0.004197011,0.039458275,0.013035777,0.0022579322,0.08007449,0.00028984225],"about_ca_topic_score_codex":0.16243184,"about_ca_topic_score_gemma":0.27557573,"teacher_disagreement_score":0.16243184,"about_ca_system_score_codex":0.00075934996,"about_ca_system_score_gemma":0.0019689444,"threshold_uncertainty_score":0.32297277},"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":"methods","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002454386,0.07625529,0.7970708,0.04520434,0.024364656,0.03720035,0.004320286,0.002478283,0.010651601],"genre_scores_gemma":[0.033689175,0.03025048,0.7760521,0.033798743,0.0073993863,0.114877075,0.0017442055,0.00087217474,0.0013165929],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.039395757,0.7502058,0.16384567,0.009325844,0.036140736,0.0010861866],"domain_scores_gemma":[0.025391344,0.7418283,0.11380768,0.062366605,0.05523557,0.001370476],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8157248,0.010376404,0.02192412,0.026111146,0.0058346284,0.026560338,0.01919788,0.036368225,0.0061770515],"category_scores_gemma":[0.9343851,0.00991934,0.03125704,0.030110065,0.02873822,0.01683353,0.016850015,0.037049778,0.006168825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005080596,0.00036468406,0.0051792874,0.24593599,0.026821626,0.0014798326,0.014599951,0.020811824,0.001431639,0.22693318,0.093297444,0.3580639],"study_design_scores_gemma":[0.005853017,0.0024699683,0.0047919387,0.36109468,0.013528135,0.0020429455,0.0016099788,0.027950412,0.0062546358,0.35864356,0.21420375,0.0015570133],"about_ca_topic_score_codex":0.0055387276,"about_ca_topic_score_gemma":0.0029880733,"teacher_disagreement_score":0.18427521,"about_ca_system_score_codex":0.018386714,"about_ca_system_score_gemma":0.033582628,"threshold_uncertainty_score":0.2272442},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015775377,0.005429813,0.96752745,0.0018879195,0.0006873091,0.0057092686,0.00055088865,0.00040796117,0.0020240447],"genre_scores_gemma":[0.28570712,0.0019487195,0.6930794,0.0012045285,0.0004192182,0.016192142,0.0004137413,0.00016895823,0.00086604804],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.37580782,0.5878139,0.014588722,0.0102128405,0.010765118,0.00081159006],"domain_scores_gemma":[0.17653279,0.7963843,0.012359626,0.0109159425,0.0030440942,0.00076320797],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43742293,0.0049022716,0.012847301,0.0075043207,0.00095127866,0.007150561,0.004415891,0.0058317054,0.006759278],"category_scores_gemma":[0.5900668,0.0026200886,0.014118763,0.004144793,0.0044636796,0.0051350975,0.0052245203,0.0064626783,0.0005300147],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016791428,0.0011572755,0.019183014,0.018072657,0.058341965,0.001540298,0.0010579904,0.55907977,0.0013043218,0.16548502,0.003331441,0.15465485],"study_design_scores_gemma":[0.0039663115,0.0031597516,0.0020179236,0.0018886625,0.010605996,0.00038196042,0.000111318805,0.7755641,0.001068385,0.19620353,0.0047807205,0.00025137904],"about_ca_topic_score_codex":0.0016478968,"about_ca_topic_score_gemma":0.00095079344,"teacher_disagreement_score":0.56257707,"about_ca_system_score_codex":0.0047147293,"about_ca_system_score_gemma":0.00605332,"threshold_uncertainty_score":0.6937577},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12343599,0.026155496,0.826004,0.0031248217,0.00093748624,0.01404406,0.0009575925,0.00059273135,0.0047477786],"genre_scores_gemma":[0.5737268,0.0048158807,0.396107,0.0015063446,0.00019200006,0.02244628,0.00054069486,0.00013651415,0.000528538],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.6081162,0.3712999,0.009261519,0.0044129533,0.0056936042,0.0012158002],"domain_scores_gemma":[0.15077539,0.8148647,0.015319808,0.010932028,0.007109565,0.0009985319],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28687578,0.0025965811,0.0059685498,0.0036812013,0.00096612866,0.0032709762,0.003578423,0.0054391176,0.005206075],"category_scores_gemma":[0.57494235,0.0015879574,0.012135228,0.0032780329,0.0022950112,0.004146039,0.0037547427,0.0059409286,0.00048961974],"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":[0.02800309,0.0018784112,0.024640433,0.017188247,0.026795045,0.00065871055,0.002187174,0.7089602,0.0005589207,0.06957082,0.0036707965,0.115888156],"study_design_scores_gemma":[0.01246688,0.0069275107,0.0038422728,0.0066674165,0.0072139315,0.00054503465,0.00037149116,0.87799287,0.00071509246,0.078347385,0.004616467,0.00029377214],"about_ca_topic_score_codex":0.003619016,"about_ca_topic_score_gemma":0.0022282805,"teacher_disagreement_score":0.7131242,"about_ca_system_score_codex":0.004929593,"about_ca_system_score_gemma":0.0055132494,"threshold_uncertainty_score":0.87940913},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069707766,0.08963256,0.4699016,0.0076748217,0.0029979972,0.2887114,0.052332345,0.008141462,0.010900133],"genre_scores_gemma":[0.0797934,0.009393683,0.73647016,0.0011647971,0.00036876494,0.16194427,0.009649423,0.00035685964,0.0008585834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.64607036,0.17215784,0.14619474,0.011522106,0.021806197,0.0022487605],"domain_scores_gemma":[0.3797089,0.5185743,0.029255483,0.022190284,0.048435446,0.0018356346],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28672332,0.0056087864,0.014634643,0.05762287,0.003692439,0.0065431073,0.0053518694,0.006952468,0.01680215],"category_scores_gemma":[0.6898858,0.003767881,0.018447366,0.03138955,0.0017872306,0.009128915,0.005727463,0.0022647295,0.002967107],"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":[0.021035554,0.0006892601,0.022863261,0.2919187,0.027232883,0.0011514364,0.0030386096,0.007435718,0.005456345,0.008151121,0.036542106,0.5744851],"study_design_scores_gemma":[0.05952494,0.013213742,0.0868165,0.29581943,0.23174489,0.0042872312,0.003490075,0.06407962,0.02231134,0.06757594,0.14818642,0.0029500169],"about_ca_topic_score_codex":0.0072253477,"about_ca_topic_score_gemma":0.010364507,"teacher_disagreement_score":0.7132767,"about_ca_system_score_codex":0.006925026,"about_ca_system_score_gemma":0.030585216,"threshold_uncertainty_score":0.8795971},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8066431,0.002740497,0.17648962,0.00033546274,0.00029629224,0.0009678778,0.0027997463,0.0005193895,0.009207902],"genre_scores_gemma":[0.96250516,0.00026388903,0.03545959,0.000056134384,0.000052594005,0.00048957876,0.00082364125,0.00005459042,0.000294936],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.888696,0.059595425,0.018069344,0.01033305,0.021707844,0.0015982793],"domain_scores_gemma":[0.68822825,0.19704968,0.05584993,0.017273948,0.0400996,0.0014985314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09648629,0.0006123471,0.0012071416,0.01005391,0.0009573254,0.0023580235,0.001874339,0.0007150345,0.0011621037],"category_scores_gemma":[0.22629862,0.0007431574,0.0019151779,0.006129305,0.001578982,0.00244429,0.0031760216,0.0010925984,0.00025802216],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049877877,0.00004925606,0.9485668,0.0008216667,0.0017748154,0.000076476055,0.0037318796,0.002294669,0.0012188145,0.0015223895,0.0011121996,0.03833212],"study_design_scores_gemma":[0.0000670308,0.0005188764,0.96400183,0.0004484807,0.00068198325,0.00076816574,0.0030723421,0.01589035,0.0034692844,0.0066927485,0.0042255204,0.00016341987],"about_ca_topic_score_codex":0.005808953,"about_ca_topic_score_gemma":0.005312883,"teacher_disagreement_score":0.09648629,"about_ca_system_score_codex":0.0018566365,"about_ca_system_score_gemma":0.0015644319,"threshold_uncertainty_score":0.5102744},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002560359,0.8300479,0.10293487,0.013327398,0.0033250612,0.042372826,0.0026777652,0.0004603847,0.0022933471],"genre_scores_gemma":[0.07064302,0.3791067,0.38622436,0.0072663543,0.0015155978,0.15289243,0.0015155581,0.00029331874,0.0005426612],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.18843387,0.5588197,0.18773481,0.01283741,0.05072735,0.0014468961],"domain_scores_gemma":[0.13045672,0.7416944,0.06901836,0.020664299,0.037094317,0.0010719652],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58159316,0.005059206,0.018484304,0.06862366,0.0035804047,0.017353673,0.008351729,0.007347325,0.009013036],"category_scores_gemma":[0.81670386,0.0063145943,0.019743035,0.057905808,0.009559494,0.018396283,0.012221347,0.005844813,0.0016413477],"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":[0.00035940693,0.000051399238,0.002044974,0.86363363,0.014284052,0.00012815953,0.002548737,0.00054977485,0.0001809443,0.00581517,0.005497012,0.10490684],"study_design_scores_gemma":[0.0009905979,0.00022328629,0.0018523067,0.9155721,0.036500473,0.00037790454,0.0011334397,0.0012532611,0.00046107688,0.019267643,0.022136614,0.0002313301],"about_ca_topic_score_codex":0.0050617536,"about_ca_topic_score_gemma":0.010028222,"teacher_disagreement_score":0.41840684,"about_ca_system_score_codex":0.021713346,"about_ca_system_score_gemma":0.052516375,"threshold_uncertainty_score":0.5159702},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94663715,0.0013428371,0.04224944,0.00079761975,0.00013409769,0.00024975408,0.0031521705,0.0005755574,0.0048613534],"genre_scores_gemma":[0.986667,0.0004225195,0.0100667365,0.000108569475,0.000041901236,0.00009029881,0.0018134648,0.000030604944,0.00075903477],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99931777,0.00028013138,0.00005619859,0.00014698601,0.00014968608,0.000049142345],"domain_scores_gemma":[0.99706703,0.0016987461,0.00045547442,0.0001783024,0.00048822234,0.00011213948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018322992,0.000921348,0.0003790274,0.0010107153,0.00016718358,0.00066871097,0.00039340527,0.0003755365,0.0017105337],"category_scores_gemma":[0.009654429,0.00028828744,0.00056250155,0.0007610643,0.00022014871,0.0003058075,0.0003566689,0.0008026261,0.0011689423],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016459073,0.00012092351,0.96635824,0.00006826076,0.00020803876,0.000092457616,0.000055574303,0.011830236,0.00052555965,0.00010112617,0.0017038196,0.018771192],"study_design_scores_gemma":[0.00009563498,0.000512274,0.79053015,0.00020611008,0.00041297273,0.0006151844,0.000117172196,0.20221823,0.001355199,0.0011063213,0.002780509,0.000050187078],"about_ca_topic_score_codex":0.014276953,"about_ca_topic_score_gemma":0.009920974,"teacher_disagreement_score":0.014276953,"about_ca_system_score_codex":0.00036385673,"about_ca_system_score_gemma":0.00090111484,"threshold_uncertainty_score":0.028387725},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019177195,0.06806305,0.8919429,0.002623121,0.0024886576,0.0123755485,0.0008612982,0.0008152465,0.0016530089],"genre_scores_gemma":[0.24378985,0.009683211,0.7048951,0.0028183148,0.000729472,0.036343742,0.00072704145,0.0004056185,0.000607727],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.24905019,0.707368,0.018187122,0.01105528,0.013671096,0.0006683191],"domain_scores_gemma":[0.21981037,0.71758246,0.02907127,0.019010594,0.013098172,0.0014270643],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47794038,0.0038624553,0.011637238,0.00678077,0.0015303224,0.0044881226,0.006415841,0.0057153427,0.0043179505],"category_scores_gemma":[0.6504575,0.0021877913,0.01562427,0.005107874,0.004479069,0.0060944017,0.004779278,0.00740614,0.00047413312],"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":[0.08884891,0.0011564856,0.017496675,0.081181005,0.2903891,0.00040554535,0.0024528771,0.063340664,0.0013124641,0.092944205,0.010154282,0.35031775],"study_design_scores_gemma":[0.07442019,0.018962333,0.018754145,0.029705336,0.13694029,0.0008449008,0.00071144185,0.40618184,0.0027928608,0.2852926,0.02417507,0.0012190411],"about_ca_topic_score_codex":0.0023839728,"about_ca_topic_score_gemma":0.0018665431,"teacher_disagreement_score":0.5220596,"about_ca_system_score_codex":0.0036008495,"about_ca_system_score_gemma":0.005549446,"threshold_uncertainty_score":0.6437925},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028481705,0.0164154,0.9704249,0.008488933,0.000255628,0.000250585,0.00026432364,0.00019405744,0.000857988],"genre_scores_gemma":[0.18476397,0.014804441,0.7917403,0.0045176726,0.0009344031,0.0020489218,0.00044860845,0.00029672863,0.00044496264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.7919744,0.18831773,0.005664284,0.005887856,0.0074776416,0.0006780918],"domain_scores_gemma":[0.5221194,0.44704714,0.013121041,0.0129714655,0.004267213,0.00047379124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17048483,0.0024463488,0.0040951893,0.0029583585,0.0008684443,0.004927846,0.005265618,0.005693741,0.0020714279],"category_scores_gemma":[0.41596222,0.0018964163,0.008004857,0.004165443,0.0036655418,0.005712642,0.002846532,0.0111146625,0.00048111472],"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":[0.0012486764,0.00020418198,0.009324849,0.016984813,0.025129098,0.0008436241,0.0017115084,0.22367056,0.0014496916,0.37130517,0.016055264,0.33207256],"study_design_scores_gemma":[0.00050632283,0.00022608164,0.0014876534,0.004663106,0.0048235077,0.0003622193,0.00011675739,0.09187907,0.0012562644,0.88213676,0.012346312,0.00019600922],"about_ca_topic_score_codex":0.0026589632,"about_ca_topic_score_gemma":0.0028771865,"teacher_disagreement_score":0.82951516,"about_ca_system_score_codex":0.0039677387,"about_ca_system_score_gemma":0.0054367785,"threshold_uncertainty_score":0.90162075},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99202394,0.0011902883,0.004671948,0.000111031055,0.00003131718,0.0000936311,0.0004033154,0.000012991997,0.0014613984],"genre_scores_gemma":[0.99660885,0.00023804314,0.0026848915,0.000013766459,0.000021090027,0.0000741527,0.0003168708,0.00000435832,0.00003805655],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9624707,0.027623557,0.0035690512,0.0017038255,0.004082296,0.00055049226],"domain_scores_gemma":[0.91170114,0.049488652,0.026149454,0.004031806,0.006944559,0.0016844053],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029122652,0.0004044173,0.00055045815,0.0074561923,0.0006766636,0.0019541718,0.0007120319,0.00057188934,0.00069828227],"category_scores_gemma":[0.115138665,0.0002637287,0.0006698827,0.004695615,0.0012435474,0.001244189,0.0028001666,0.00046679712,0.0000760087],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000215923,0.000020693262,0.9936586,0.00013083484,0.00032941598,0.0000733728,0.00080199045,0.00025695248,0.00016204568,0.00019139754,0.0000605132,0.0040981453],"study_design_scores_gemma":[0.0000066432635,0.00017961179,0.9955793,0.00012159622,0.00015609944,0.0003099379,0.0014056193,0.001084935,0.00024042645,0.00043991674,0.00045797008,0.000017833823],"about_ca_topic_score_codex":0.0013894585,"about_ca_topic_score_gemma":0.0024552261,"teacher_disagreement_score":0.97087735,"about_ca_system_score_codex":0.00065081776,"about_ca_system_score_gemma":0.00061362656,"threshold_uncertainty_score":0.15401715},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004928428,0.005549259,0.98209023,0.0015985143,0.00031257136,0.0033384757,0.00045665615,0.00056999986,0.0011558805],"genre_scores_gemma":[0.16799119,0.0035038802,0.8024204,0.0021119728,0.00041117758,0.021713335,0.00076519547,0.00027055945,0.0008123486],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.60672903,0.36740318,0.010918138,0.0061069676,0.007863196,0.0009794472],"domain_scores_gemma":[0.4687729,0.4734731,0.026659422,0.020308606,0.009244702,0.0015413805],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2615066,0.0023461864,0.00649474,0.0048017823,0.0012893111,0.003023366,0.006940058,0.003964817,0.005994429],"category_scores_gemma":[0.3933521,0.0018931095,0.007384889,0.005441517,0.002242103,0.0031842585,0.0038117426,0.005440093,0.00091602164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005907368,0.00054489437,0.019940045,0.015061434,0.026704239,0.00091472117,0.002711134,0.31307465,0.0006104902,0.1951934,0.024763372,0.3945742],"study_design_scores_gemma":[0.005865855,0.0020472754,0.0033227785,0.004478756,0.0068592895,0.00075048726,0.00025256607,0.5851321,0.0012985994,0.37449577,0.015196946,0.00029950243],"about_ca_topic_score_codex":0.0017524827,"about_ca_topic_score_gemma":0.0014031617,"teacher_disagreement_score":0.73849344,"about_ca_system_score_codex":0.0026066564,"about_ca_system_score_gemma":0.006718695,"threshold_uncertainty_score":0.9106939},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016713824,0.0007411709,0.9814694,0.00021038747,0.00010482765,0.00016821323,0.000069095695,0.00019534581,0.00032775002],"genre_scores_gemma":[0.35226873,0.0006623935,0.64459956,0.00044634752,0.00018623272,0.000726588,0.0003376712,0.00008217878,0.0006902871],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94433385,0.040305655,0.0027204254,0.00608614,0.006031649,0.0005222268],"domain_scores_gemma":[0.8901667,0.085288756,0.0089993235,0.00972429,0.0053836415,0.00043733875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.067078516,0.00093026995,0.0020047897,0.0021950807,0.000780998,0.001259903,0.003128722,0.001994873,0.0011897308],"category_scores_gemma":[0.20460247,0.0007995051,0.0020807865,0.0016815893,0.0014623926,0.0011578894,0.001593579,0.0019203649,0.00024662193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002306881,0.00046479664,0.1818758,0.0019228262,0.0074599735,0.0012399518,0.001586837,0.20455274,0.009949611,0.06427585,0.0044483813,0.5199163],"study_design_scores_gemma":[0.00051450735,0.000958047,0.07822641,0.0006580627,0.0030234475,0.001311793,0.00022500636,0.79470205,0.008208799,0.10156815,0.01031845,0.0002852148],"about_ca_topic_score_codex":0.0046722135,"about_ca_topic_score_gemma":0.0030947968,"teacher_disagreement_score":0.067078516,"about_ca_system_score_codex":0.0009944594,"about_ca_system_score_gemma":0.0018428996,"threshold_uncertainty_score":0.35474932},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6815314,0.0035977475,0.27390066,0.0021667255,0.00025420147,0.020316655,0.00035070835,0.0007316001,0.01715014],"genre_scores_gemma":[0.6406337,0.0028113942,0.33879444,0.00053985947,0.000097717195,0.015567342,0.00025209106,0.00028867618,0.0010147166],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.36225092,0.5525965,0.032037403,0.0074981153,0.042480495,0.0031366504],"domain_scores_gemma":[0.11946427,0.7929573,0.029897537,0.022228982,0.033884663,0.0015672517],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37038144,0.0016447196,0.0014247795,0.010716725,0.0038451767,0.0069622397,0.0039340076,0.0023255078,0.001825977],"category_scores_gemma":[0.64195347,0.0015005977,0.0018620153,0.0064656516,0.006600197,0.0074992864,0.008220731,0.0020310935,0.00064429967],"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":[0.0021227105,0.001132509,0.04122712,0.01235796,0.0005489664,0.0007137858,0.40625596,0.0035955484,0.009591744,0.0042077773,0.0016025405,0.51664335],"study_design_scores_gemma":[0.0023824538,0.018411495,0.16267805,0.03407549,0.0030695393,0.008477319,0.48308742,0.04818993,0.072625436,0.033471588,0.13150361,0.0020277197],"about_ca_topic_score_codex":0.0016029495,"about_ca_topic_score_gemma":0.0023352413,"teacher_disagreement_score":0.6296185,"about_ca_system_score_codex":0.005373682,"about_ca_system_score_gemma":0.008101286,"threshold_uncertainty_score":0.7764318},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011885302,0.011333477,0.007133317,0.9646833,0.011727039,0.00005336491,0.000053203577,0.00013007155,0.0036976682],"genre_scores_gemma":[0.068187274,0.011825835,0.026954206,0.87105334,0.017574938,0.0006217379,0.00008853172,0.00030206217,0.003392127],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5997297,0.2554029,0.039359488,0.021574583,0.07980838,0.0041249683],"domain_scores_gemma":[0.113964535,0.7149882,0.035419352,0.051005427,0.07517692,0.0094456],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4385074,0.0013475388,0.0036148247,0.007178853,0.0097704595,0.019757649,0.0074901497,0.038445923,0.0059797494],"category_scores_gemma":[0.77206534,0.0020871002,0.0026910014,0.0051599387,0.07611479,0.02284128,0.014142663,0.07581473,0.004968271],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027268572,0.00012100154,0.0034483974,0.0032651995,0.00054081675,0.0013065438,0.028590638,0.00038870276,0.00093028444,0.17138878,0.66512126,0.1246257],"study_design_scores_gemma":[0.00025588655,0.00020686723,0.0019609972,0.01666573,0.00033376127,0.0030738865,0.013875743,0.0018600953,0.0012659135,0.53581685,0.4242853,0.00039891552],"about_ca_topic_score_codex":0.0017974772,"about_ca_topic_score_gemma":0.0015978416,"teacher_disagreement_score":0.56149256,"about_ca_system_score_codex":0.0060691056,"about_ca_system_score_gemma":0.023341144,"threshold_uncertainty_score":0.69242036},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82803035,0.015395314,0.026093086,0.08953193,0.0009646789,0.016110227,0.00041551425,0.00032156624,0.0231374],"genre_scores_gemma":[0.9377042,0.005255848,0.027341554,0.012853451,0.00025704692,0.0134193655,0.00019385424,0.000083867635,0.0028907913],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.6691256,0.24839035,0.026725842,0.0082391715,0.030796068,0.016722955],"domain_scores_gemma":[0.49763402,0.37430736,0.042575687,0.020658473,0.03886025,0.0259642],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2671897,0.0007294175,0.0012194675,0.002383194,0.015447758,0.008170453,0.0050818496,0.003443642,0.0046275165],"category_scores_gemma":[0.32532462,0.0014813105,0.0008383908,0.0030672099,0.0086425105,0.004009221,0.011752091,0.0029693437,0.0010616285],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006750525,0.00039107943,0.11604735,0.008032051,0.00013253465,0.0022628016,0.7167815,0.00025493946,0.002162224,0.0045818132,0.008758836,0.13991983],"study_design_scores_gemma":[0.0003528509,0.0017322466,0.15936273,0.019071562,0.00019168691,0.0018412557,0.67851585,0.00094979594,0.0021985534,0.00581638,0.12977023,0.00019692777],"about_ca_topic_score_codex":0.061031915,"about_ca_topic_score_gemma":0.10449372,"teacher_disagreement_score":0.73281026,"about_ca_system_score_codex":0.018457642,"about_ca_system_score_gemma":0.078539,"threshold_uncertainty_score":0.90368557},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4175545,0.0014098126,0.5733109,0.0019098219,0.00011923939,0.0008906131,0.0029701334,0.0008764347,0.00095856277],"genre_scores_gemma":[0.69314015,0.00041536355,0.2998764,0.00036846934,0.00009535375,0.0010979678,0.0035038635,0.00014129892,0.0013611534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9873209,0.009992372,0.0005694082,0.0014452111,0.0003690377,0.00030317332],"domain_scores_gemma":[0.9461237,0.046400268,0.002322158,0.0028776792,0.001584288,0.00069190015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051300332,0.001134014,0.0022414587,0.0016729842,0.0011813905,0.0015825892,0.0035435895,0.0016637525,0.0024648963],"category_scores_gemma":[0.08035374,0.0013782437,0.0033580032,0.0014359403,0.0009977296,0.0009067575,0.0024322267,0.0025125723,0.00036094929],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038374981,0.00053237955,0.51920193,0.000536441,0.0061668567,0.0009381929,0.000925704,0.3736961,0.001280709,0.008803296,0.0044604917,0.07962043],"study_design_scores_gemma":[0.00032551558,0.00031979117,0.04561087,0.00012596627,0.00068338116,0.00039639146,0.00016435742,0.94273704,0.00044890185,0.007538857,0.001586779,0.00006210002],"about_ca_topic_score_codex":0.02904531,"about_ca_topic_score_gemma":0.02020604,"teacher_disagreement_score":0.051300332,"about_ca_system_score_codex":0.0012462735,"about_ca_system_score_gemma":0.0032843533,"threshold_uncertainty_score":0.27130532},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7753466,0.0020932567,0.21364953,0.00080321706,0.00014198555,0.001757399,0.00045634023,0.0002901873,0.0054615503],"genre_scores_gemma":[0.9076438,0.00039952813,0.08829434,0.0002653962,0.000056376764,0.0014672765,0.00049889134,0.000058725458,0.001315674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9730268,0.023694191,0.00054056034,0.001164662,0.0010618456,0.00051200646],"domain_scores_gemma":[0.39796197,0.58076185,0.0067007225,0.006688745,0.0068348898,0.0010518002],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.051144816,0.0011066847,0.001397802,0.0018158443,0.0008005557,0.0012206039,0.0019492519,0.002063911,0.00286618],"category_scores_gemma":[0.16278341,0.0005476648,0.0016651431,0.0018674504,0.0014359477,0.001774186,0.0009778556,0.0016816573,0.00023238751],"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":[0.0068377475,0.002859037,0.042787462,0.0010092754,0.0012808501,0.0005409253,0.0008685241,0.84752584,0.0013277472,0.05098005,0.0025153288,0.041467264],"study_design_scores_gemma":[0.0006133203,0.002090541,0.005234603,0.00012820246,0.00025720344,0.000139905,0.00023595407,0.98195165,0.0009018476,0.0076270415,0.0007608625,0.000058837606],"about_ca_topic_score_codex":0.008429251,"about_ca_topic_score_gemma":0.005713224,"teacher_disagreement_score":0.94885516,"about_ca_system_score_codex":0.0028392773,"about_ca_system_score_gemma":0.0017196366,"threshold_uncertainty_score":0.2704829},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5004105,0.0013490834,0.48516005,0.002603449,0.00018723498,0.0013685523,0.0010155059,0.00045920393,0.0074464153],"genre_scores_gemma":[0.8857378,0.00033559834,0.11066317,0.0002445157,0.00004077831,0.0013741291,0.00061828113,0.00007007657,0.00091570395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9714386,0.025301281,0.0005071524,0.0011062105,0.0010838662,0.0005629908],"domain_scores_gemma":[0.48513922,0.49127758,0.0074301404,0.00661793,0.008253897,0.0012811762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054618455,0.000915547,0.001807696,0.0016835916,0.0011238588,0.001774447,0.002634742,0.0024612446,0.0033907872],"category_scores_gemma":[0.23558392,0.00071967463,0.002125658,0.0021259533,0.0016425943,0.0024583312,0.0020562646,0.0031977633,0.00022987508],"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":[0.0009392232,0.00034176657,0.039247554,0.00039332215,0.00047233235,0.00055448245,0.00078024756,0.9027356,0.0003450244,0.03671673,0.0019918897,0.015481882],"study_design_scores_gemma":[0.000111558635,0.00016665725,0.0016707117,0.00006925201,0.00007640014,0.0000813584,0.00013848467,0.98935074,0.00014449349,0.007817791,0.0003536364,0.000019011964],"about_ca_topic_score_codex":0.013063104,"about_ca_topic_score_gemma":0.006774671,"teacher_disagreement_score":0.054618455,"about_ca_system_score_codex":0.002700877,"about_ca_system_score_gemma":0.002232731,"threshold_uncertainty_score":0.28885347},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00353035,0.0005140539,0.9945293,0.00039930007,0.00009039517,0.00014240947,0.00031101197,0.00017407253,0.00030914662],"genre_scores_gemma":[0.24596938,0.002512213,0.7411592,0.0007015025,0.0008495656,0.0033341253,0.001771281,0.00026000137,0.0034426525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96649265,0.025786115,0.0012210475,0.0027806873,0.0030528416,0.0006666518],"domain_scores_gemma":[0.86401486,0.1187605,0.0069013946,0.0065831114,0.0030535106,0.00068661507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053418573,0.0023874422,0.0028058551,0.0037498837,0.00084638014,0.002383262,0.006840171,0.00247677,0.005612857],"category_scores_gemma":[0.106867366,0.0010870027,0.0056257765,0.003430075,0.0023858696,0.0029301918,0.0029055371,0.0048668836,0.001164828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006318467,0.00032418605,0.021695647,0.0015271369,0.002384792,0.0009560621,0.0015441019,0.2995126,0.0013492682,0.53678,0.008610527,0.12468385],"study_design_scores_gemma":[0.00007587121,0.0003022361,0.0021476443,0.00013653185,0.0002985607,0.00035125745,0.0001231819,0.67320055,0.00066606945,0.31715646,0.0054626726,0.00007895725],"about_ca_topic_score_codex":0.0038933186,"about_ca_topic_score_gemma":0.002569537,"teacher_disagreement_score":0.053418573,"about_ca_system_score_codex":0.0016742846,"about_ca_system_score_gemma":0.0028294998,"threshold_uncertainty_score":0.28250784},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64941317,0.0014695544,0.34099376,0.0020787034,0.00006515955,0.00044174236,0.0011200522,0.00021907398,0.004198706],"genre_scores_gemma":[0.9493638,0.000633677,0.046884336,0.0001368221,0.00003800329,0.0002563756,0.0005267569,0.00003134433,0.0021289005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99404,0.0044351215,0.00017467017,0.00039308963,0.0006223494,0.0003348399],"domain_scores_gemma":[0.96842086,0.027004775,0.0016484462,0.0005260301,0.001954933,0.0004449135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013176785,0.00062878703,0.0008153792,0.0017361086,0.00095532223,0.0015702576,0.00261227,0.0010414138,0.0013985856],"category_scores_gemma":[0.04262846,0.00073872274,0.0010094071,0.0011666918,0.0009657863,0.0007622376,0.001134866,0.00081723946,0.00014629897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003285864,0.00007357523,0.036815435,0.000107623135,0.00033211778,0.00015665169,0.000498905,0.9287806,0.00011241652,0.009517638,0.0005695672,0.022706987],"study_design_scores_gemma":[0.000058957005,0.00006229382,0.011351902,0.000051164345,0.000077340104,0.00005192592,0.00018201995,0.9794813,0.000045428806,0.008026469,0.0005814016,0.000029705383],"about_ca_topic_score_codex":0.7244066,"about_ca_topic_score_gemma":0.6167349,"teacher_disagreement_score":0.2755934,"about_ca_system_score_codex":0.0064111156,"about_ca_system_score_gemma":0.0073977564,"threshold_uncertainty_score":0.55443287},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042490218,0.012237689,0.93406135,0.0021367837,0.0006580091,0.0029364768,0.0015118903,0.0009838401,0.0029836555],"genre_scores_gemma":[0.28562343,0.004294707,0.6990051,0.001117612,0.00020435762,0.008120258,0.0007010388,0.00027169148,0.00066176266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.84898025,0.14321977,0.002279799,0.0020899044,0.0030572992,0.00037300054],"domain_scores_gemma":[0.6001935,0.3841426,0.0057535106,0.0053932886,0.0040495517,0.0004675528],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12413755,0.0021625163,0.005608776,0.0048604514,0.00057764066,0.0021654612,0.0023205779,0.0039744815,0.0050667175],"category_scores_gemma":[0.2625961,0.0013230048,0.0145534165,0.0036050363,0.0009948883,0.0026076164,0.0020266108,0.0043027126,0.00044136314],"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":[0.011117631,0.0005968978,0.019938778,0.010246393,0.03533907,0.0010582502,0.0009069191,0.7146376,0.0014929876,0.057337657,0.009491437,0.13783647],"study_design_scores_gemma":[0.0040860847,0.0020183846,0.0022743323,0.0019677232,0.007166636,0.00077181857,0.0001357612,0.92883563,0.00088015595,0.044358213,0.0072590923,0.0002462398],"about_ca_topic_score_codex":0.004267908,"about_ca_topic_score_gemma":0.0031257577,"teacher_disagreement_score":0.8758625,"about_ca_system_score_codex":0.0018360978,"about_ca_system_score_gemma":0.0032443085,"threshold_uncertainty_score":0.65651},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07010712,0.00066605094,0.9229956,0.0022058638,0.0000882393,0.00071215455,0.0004591487,0.00028821846,0.0024775767],"genre_scores_gemma":[0.46348447,0.00043960143,0.53164726,0.00071655074,0.00017868188,0.0013409771,0.00074441376,0.000058498812,0.0013895455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9621407,0.028964836,0.0019173623,0.0027788216,0.0033469093,0.0008513454],"domain_scores_gemma":[0.8170579,0.16733338,0.0072537297,0.0022958512,0.0052539934,0.00080503855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.061752427,0.0012592509,0.002735045,0.0029929995,0.001109918,0.0038170568,0.0029318721,0.0022928766,0.0026531655],"category_scores_gemma":[0.17514125,0.0011792544,0.0015080658,0.0018275767,0.0016890559,0.003332007,0.0014892543,0.0032637985,0.00072193146],"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":[0.0010904683,0.00045314452,0.044403024,0.00057157624,0.00068242365,0.0003967253,0.001568933,0.6028141,0.00090425846,0.100850664,0.010813958,0.23545066],"study_design_scores_gemma":[0.00015675473,0.00006451006,0.0023930068,0.00021966816,0.00008589868,0.00008533969,0.0001104583,0.9050916,0.0005907473,0.09032888,0.0008239847,0.000049085884],"about_ca_topic_score_codex":0.008076854,"about_ca_topic_score_gemma":0.007695614,"teacher_disagreement_score":0.061752427,"about_ca_system_score_codex":0.0026359956,"about_ca_system_score_gemma":0.0029545382,"threshold_uncertainty_score":0.32658195},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7804084,0.006634055,0.114712894,0.02633024,0.0006949414,0.0144932,0.00031742043,0.00017866754,0.056230202],"genre_scores_gemma":[0.8458205,0.008277384,0.12243219,0.0048461026,0.0003806146,0.010098706,0.00013897927,0.00011898098,0.007886604],"study_design_codex":"qualitative","study_design_gemma":"case_report","domain_scores_codex":[0.8963365,0.08860594,0.0033846628,0.0022684706,0.0069119325,0.0024925137],"domain_scores_gemma":[0.9261865,0.053208012,0.0075374395,0.0065919724,0.0043727793,0.002103252],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0643605,0.0012105105,0.0006606121,0.004431497,0.012800204,0.0074385013,0.0043565226,0.0053859567,0.0021784648],"category_scores_gemma":[0.06549037,0.00097413897,0.00091523473,0.0032032384,0.01109896,0.0056332555,0.0119316885,0.003074703,0.0009100114],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021392899,0.0013606885,0.04584458,0.0025737518,0.00010620656,0.056248546,0.716123,0.000599554,0.0029844502,0.033600163,0.0066383635,0.1337068],"study_design_scores_gemma":[0.0001324025,0.0013887208,0.010657247,0.0042999564,0.00019061781,0.06977698,0.7645907,0.0022873613,0.005355763,0.017922416,0.123229526,0.00016827449],"about_ca_topic_score_codex":0.003241622,"about_ca_topic_score_gemma":0.009069777,"teacher_disagreement_score":0.9356395,"about_ca_system_score_codex":0.003840876,"about_ca_system_score_gemma":0.0063951313,"threshold_uncertainty_score":0.34037495},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005730077,0.0006657079,0.99233025,0.00025332352,0.000118477205,0.0001906265,0.00016871185,0.00016875645,0.00037407206],"genre_scores_gemma":[0.1941754,0.00086531765,0.79908437,0.0005965339,0.0002121867,0.0028162834,0.00076636585,0.00020669895,0.0012767728],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93969244,0.046319127,0.0025497144,0.0048672827,0.005893132,0.000678359],"domain_scores_gemma":[0.81775296,0.14163229,0.012184743,0.014764612,0.01312617,0.0005391201],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.074594274,0.0012744374,0.00235788,0.0028516785,0.0006696271,0.0015442219,0.0031910148,0.002713635,0.0028978153],"category_scores_gemma":[0.24135561,0.00064665644,0.0026714492,0.0027856645,0.0024005726,0.0023413072,0.0018678905,0.0027026706,0.0008308736],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001158238,0.00045350287,0.07158857,0.003960165,0.006046546,0.0007771794,0.002251953,0.15214036,0.008299785,0.26456058,0.016955128,0.471808],"study_design_scores_gemma":[0.0007791123,0.0019526341,0.05141578,0.0022683444,0.0033055432,0.0022232935,0.0005745488,0.5208187,0.013244085,0.37166223,0.031235456,0.00052023807],"about_ca_topic_score_codex":0.0019820915,"about_ca_topic_score_gemma":0.0016309563,"teacher_disagreement_score":0.92540574,"about_ca_system_score_codex":0.0012904832,"about_ca_system_score_gemma":0.003181632,"threshold_uncertainty_score":0.39449692},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7981859,0.0014834916,0.09676128,0.005601945,0.0007567214,0.07238592,0.0009354533,0.003189584,0.020699704],"genre_scores_gemma":[0.58633643,0.00088716915,0.35239425,0.0015668377,0.0003098854,0.05499961,0.00048743494,0.000103209815,0.0029152615],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930593,0.004673547,0.0007157393,0.00037684472,0.00077825587,0.0003963565],"domain_scores_gemma":[0.9844247,0.009813744,0.0028679224,0.00084510894,0.00076389284,0.0012845667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012065682,0.0007940778,0.0004840414,0.0013842441,0.0004969583,0.0010997369,0.0009152683,0.0014315023,0.009257503],"category_scores_gemma":[0.030687287,0.0003753919,0.00091428694,0.00069067476,0.00029575796,0.001050573,0.0010610395,0.00081245677,0.00076790137],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068825143,0.057410784,0.029702459,0.007553527,0.00049349875,0.0001650343,0.0019865034,0.005010265,0.010791171,0.0017404511,0.007784985,0.87047887],"study_design_scores_gemma":[0.037643973,0.20933537,0.60207266,0.009434319,0.005199754,0.0009333067,0.0032869005,0.021128427,0.026014185,0.006613416,0.07786145,0.00047626562],"about_ca_topic_score_codex":0.0004618565,"about_ca_topic_score_gemma":0.0013984386,"teacher_disagreement_score":0.9879343,"about_ca_system_score_codex":0.00066953833,"about_ca_system_score_gemma":0.00203391,"threshold_uncertainty_score":0.06381017},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99918276,0.00015334034,0.00006349169,0.0001405439,0.000009139013,0.000010418097,0.00019323663,0.000002888075,0.0002441736],"genre_scores_gemma":[0.99964285,0.00004778714,0.000056486224,0.00003225291,0.000010511147,0.000008837844,0.00013891283,0.0000019874255,0.00006028757],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9967109,0.0017845787,0.0002073994,0.00040473678,0.0003941402,0.00049818616],"domain_scores_gemma":[0.9911678,0.0026580896,0.0031030609,0.0010531296,0.00043139848,0.0015865352],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0054299165,0.00028057722,0.00027964253,0.0007942879,0.00065886095,0.0009028603,0.000623394,0.0005830503,0.0018805875],"category_scores_gemma":[0.015257911,0.00025979232,0.0007334068,0.0009504293,0.00035509994,0.00062904233,0.00091266236,0.0008574516,0.0001785973],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015001596,0.000045908884,0.99881977,0.0000038225508,0.0000778493,0.000035796587,0.00008873076,0.000013739278,0.000084209365,0.000014391803,0.00007349425,0.0005923279],"study_design_scores_gemma":[0.0000056123436,0.00006820627,0.99955064,0.0000047617577,0.000029910256,0.00004720736,0.00012022457,0.00009652045,0.0000146798975,0.000008195238,0.000051703555,0.0000023949995],"about_ca_topic_score_codex":0.010965554,"about_ca_topic_score_gemma":0.015655475,"teacher_disagreement_score":0.9945701,"about_ca_system_score_codex":0.00038100922,"about_ca_system_score_gemma":0.0006502985,"threshold_uncertainty_score":0.028716505},"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":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08371622,0.013706742,0.08165073,0.013848851,0.0023206167,0.63618845,0.106954955,0.00045495172,0.061158497],"genre_scores_gemma":[0.12248587,0.011436291,0.22814663,0.008964385,0.0014665903,0.5687253,0.048085313,0.00011931358,0.010570405],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9771214,0.013253341,0.002582687,0.0015705775,0.004959806,0.000512201],"domain_scores_gemma":[0.9847231,0.0035979156,0.0016260446,0.0016538908,0.007277734,0.0011213102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033428237,0.001350358,0.0009283172,0.004123283,0.0026505182,0.0021005494,0.0035370693,0.0019262094,0.005640403],"category_scores_gemma":[0.023703888,0.0012329473,0.0006223589,0.007873424,0.0027323372,0.001256144,0.0021309066,0.0027137282,0.002652763],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025553403,0.0041630734,0.46168298,0.011476433,0.0004013074,0.0014080829,0.0071160444,0.0042614723,0.0035295424,0.025981879,0.16692385,0.31050003],"study_design_scores_gemma":[0.0016465454,0.0022968275,0.6055273,0.007986238,0.00036478767,0.0011326091,0.0052892487,0.003562482,0.0012827484,0.0067311414,0.36393216,0.00024792965],"about_ca_topic_score_codex":0.039755397,"about_ca_topic_score_gemma":0.066357754,"teacher_disagreement_score":0.039755397,"about_ca_system_score_codex":0.003408476,"about_ca_system_score_gemma":0.014888134,"threshold_uncertainty_score":0.17678756},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03375107,0.03662799,0.74539274,0.12988779,0.004648561,0.034612678,0.000706009,0.00024144548,0.014131786],"genre_scores_gemma":[0.21734436,0.008372166,0.69349843,0.020184306,0.001328655,0.058082078,0.00021707597,0.000106514366,0.00086631626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.09310271,0.8134896,0.062041633,0.008601106,0.021289552,0.0014753545],"domain_scores_gemma":[0.09317434,0.75863314,0.03468526,0.07451852,0.036721483,0.002267276],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7676581,0.0022940212,0.0050289626,0.026782144,0.011197845,0.02040957,0.0066530965,0.011903587,0.0017120196],"category_scores_gemma":[0.7283162,0.0024771376,0.0045507923,0.01846249,0.07117925,0.02338648,0.021183848,0.013789255,0.00062712736],"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":[0.0007654387,0.00030044626,0.012751235,0.026544746,0.0011711288,0.0006879268,0.1957578,0.0023754002,0.0023993663,0.5520333,0.00846786,0.1967453],"study_design_scores_gemma":[0.0005420906,0.0010490821,0.0043202443,0.078394495,0.0009888115,0.002108497,0.079792775,0.0070215096,0.0037387153,0.69095874,0.13068467,0.00040046766],"about_ca_topic_score_codex":0.0016853422,"about_ca_topic_score_gemma":0.0020565866,"teacher_disagreement_score":0.23234189,"about_ca_system_score_codex":0.016151251,"about_ca_system_score_gemma":0.044984818,"threshold_uncertainty_score":0.286519},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006453763,0.002257095,0.98560405,0.0021582465,0.00012251378,0.0002126005,0.00037703803,0.00019083283,0.0026239203],"genre_scores_gemma":[0.27918768,0.004882546,0.70541525,0.001359746,0.0011468327,0.0018455863,0.0010748919,0.00017463039,0.004912853],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9777264,0.01636747,0.00068744185,0.002247904,0.0023109245,0.0006598988],"domain_scores_gemma":[0.8727313,0.11602618,0.0038498535,0.0022215743,0.004187276,0.0009838294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04673271,0.0025583033,0.0041324864,0.0049806936,0.0010596466,0.0054178294,0.005983483,0.0047882954,0.005441922],"category_scores_gemma":[0.13134472,0.0022006144,0.0026606242,0.0030913684,0.0045704334,0.005098033,0.0029400256,0.005318664,0.0011345623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032783693,0.00015942047,0.005088989,0.00064843195,0.0006137231,0.0005821385,0.00047130696,0.56324345,0.0005255398,0.3444249,0.004359066,0.0795552],"study_design_scores_gemma":[0.00009422803,0.00010697676,0.0009995276,0.0001995795,0.00017021503,0.00019924366,0.00003905351,0.73756176,0.00017439554,0.2574401,0.0029358356,0.00007907487],"about_ca_topic_score_codex":0.016684242,"about_ca_topic_score_gemma":0.010151286,"teacher_disagreement_score":0.04673271,"about_ca_system_score_codex":0.004942873,"about_ca_system_score_gemma":0.004548242,"threshold_uncertainty_score":0.24714917},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.992073,0.0014267768,0.0030358946,0.00026478496,0.000053877193,0.00015572824,0.0013460149,0.000024009032,0.0016198503],"genre_scores_gemma":[0.9968856,0.00021028022,0.0015354169,0.00009592303,0.000037654634,0.00008965823,0.0010692205,0.000011516061,0.00006465906],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.88819546,0.07561165,0.016338453,0.005062314,0.013432847,0.0013593406],"domain_scores_gemma":[0.7292881,0.1512808,0.07440339,0.024101207,0.019563526,0.001362989],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09160251,0.00034852882,0.0008128115,0.0050205495,0.0005913126,0.0023029724,0.0013702614,0.0006573861,0.0005250906],"category_scores_gemma":[0.21933109,0.0004581179,0.00093986647,0.0048947358,0.0009184693,0.0018596327,0.002730998,0.0008929788,0.00024804342],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089697125,0.0000064885844,0.99761766,0.00003107095,0.00008942235,0.000022063932,0.00024078296,0.00008584144,0.000039712842,0.000040725306,0.00007574513,0.001660677],"study_design_scores_gemma":[0.000015338743,0.00012913322,0.995641,0.00012511032,0.0001485304,0.00048127933,0.0006033346,0.0013329234,0.00042477757,0.0001368531,0.00094293564,0.000018715173],"about_ca_topic_score_codex":0.0021239675,"about_ca_topic_score_gemma":0.0024111748,"teacher_disagreement_score":0.9083975,"about_ca_system_score_codex":0.0009816908,"about_ca_system_score_gemma":0.00075022277,"threshold_uncertainty_score":0.48444617},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33891392,0.016251827,0.6299645,0.0024681196,0.0010604768,0.005029603,0.0006447403,0.000999425,0.004667482],"genre_scores_gemma":[0.65788823,0.00204231,0.33165953,0.0018259035,0.00025188088,0.004208296,0.00073449616,0.00016612561,0.0012232366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8317263,0.14233357,0.011607061,0.0048041753,0.008819305,0.0007095166],"domain_scores_gemma":[0.53281784,0.42669562,0.01823223,0.010792885,0.009211183,0.0022502015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16946247,0.0013804047,0.0046730824,0.002252981,0.00046839035,0.0021582248,0.002852054,0.0039980235,0.0016970129],"category_scores_gemma":[0.30984628,0.0006528707,0.0038292243,0.0012550075,0.0012175292,0.002671621,0.0015968347,0.0038727378,0.00027518385],"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":[0.08382929,0.0014603391,0.025662282,0.005867572,0.010059632,0.00035969928,0.0013032584,0.18664154,0.003313685,0.02645304,0.0034948622,0.65155476],"study_design_scores_gemma":[0.025543628,0.035667706,0.019780204,0.001967312,0.0066065053,0.0009715658,0.00019538302,0.8661261,0.0059326096,0.026148275,0.010478525,0.0005822311],"about_ca_topic_score_codex":0.00077427976,"about_ca_topic_score_gemma":0.00071844866,"teacher_disagreement_score":0.83053756,"about_ca_system_score_codex":0.001659372,"about_ca_system_score_gemma":0.0029098447,"threshold_uncertainty_score":0.89621395},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043935534,0.00015926256,0.93309927,0.00053983065,0.000041350377,0.0008094313,0.000958031,0.018613074,0.0018442699],"genre_scores_gemma":[0.117294535,0.00007806442,0.8796546,0.00010883954,0.000025198337,0.00065490115,0.0011819418,0.00044210587,0.0005598657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947299,0.001986428,0.000946082,0.00096246,0.0011307758,0.00024437057],"domain_scores_gemma":[0.96929044,0.019541316,0.0031210203,0.0022654275,0.0053837495,0.00039807847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013627059,0.0012780525,0.00097604346,0.0045093345,0.00067041314,0.0024144459,0.0019313305,0.0010973467,0.003701013],"category_scores_gemma":[0.05760754,0.0010156424,0.0012302978,0.0023293232,0.00044317605,0.0024544473,0.0018003646,0.0016015985,0.0015950251],"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":[0.00062716106,0.00071453414,0.1856923,0.00022204583,0.00038022557,0.0001916001,0.00067391095,0.1261769,0.0032661185,0.009573412,0.018501058,0.6539808],"study_design_scores_gemma":[0.00014128837,0.00012253043,0.010456746,0.000057764246,0.000073074276,0.00014455648,0.00013164313,0.97297895,0.0038832095,0.007683043,0.0042918087,0.00003536595],"about_ca_topic_score_codex":0.007690944,"about_ca_topic_score_gemma":0.0042964416,"teacher_disagreement_score":0.013627059,"about_ca_system_score_codex":0.0014416497,"about_ca_system_score_gemma":0.0030086753,"threshold_uncertainty_score":0.07206762},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6068796,0.0029531228,0.38442895,0.0017543391,0.00010793342,0.0005072731,0.001987144,0.00022887473,0.0011527481],"genre_scores_gemma":[0.9707228,0.00043643147,0.026502453,0.00012212733,0.00007390448,0.0003638969,0.0012730135,0.000024040293,0.00048130617],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915046,0.0063351644,0.00045980228,0.00096603774,0.00047286964,0.00026144244],"domain_scores_gemma":[0.905889,0.08556971,0.0047020162,0.0025206655,0.0006990656,0.0006196462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023845954,0.00052724243,0.0010239942,0.0018701988,0.00042538086,0.0009674444,0.0016199427,0.0008682494,0.0025859773],"category_scores_gemma":[0.069216214,0.0003351884,0.0025816541,0.0015432031,0.0009339819,0.00097264035,0.0016187584,0.0012701796,0.0001746274],"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":[0.0015917978,0.00036138706,0.5577124,0.00092169386,0.0037237203,0.0012802187,0.0011089016,0.254619,0.0011404809,0.029789174,0.0027362471,0.14501497],"study_design_scores_gemma":[0.00018593557,0.00067762536,0.298458,0.00029169343,0.00059524755,0.000671738,0.00049300335,0.6174518,0.00070166204,0.07797464,0.0023837984,0.00011481999],"about_ca_topic_score_codex":0.012578367,"about_ca_topic_score_gemma":0.007043737,"teacher_disagreement_score":0.023845954,"about_ca_system_score_codex":0.0011256749,"about_ca_system_score_gemma":0.0016513012,"threshold_uncertainty_score":0.12611097},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.593768,0.045159806,0.24682477,0.0033928805,0.0031500857,0.071436144,0.012320443,0.0012210748,0.022726713],"genre_scores_gemma":[0.68431085,0.0052682725,0.2060467,0.0005434036,0.0004476904,0.09748134,0.004410341,0.0004011316,0.0010902302],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.46156764,0.30503738,0.15896235,0.014724022,0.05723077,0.002477792],"domain_scores_gemma":[0.2919052,0.3872869,0.0759158,0.034280926,0.20799394,0.002617242],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4358364,0.0014457309,0.0049073845,0.019609878,0.0025090396,0.0037997316,0.002722132,0.001870401,0.0022733049],"category_scores_gemma":[0.5637624,0.0013027056,0.0067657377,0.010496032,0.0029579941,0.0033464835,0.0063720364,0.0016664863,0.0006816107],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00883135,0.00074159255,0.41607475,0.081384026,0.019585747,0.0009746623,0.076981224,0.004196166,0.014369226,0.00642896,0.024009114,0.34642318],"study_design_scores_gemma":[0.0056217923,0.005573693,0.730319,0.06042423,0.02111987,0.002687831,0.029449403,0.028869884,0.023522645,0.014359289,0.07632324,0.0017291297],"about_ca_topic_score_codex":0.0019776612,"about_ca_topic_score_gemma":0.0034994557,"teacher_disagreement_score":0.56416357,"about_ca_system_score_codex":0.003326969,"about_ca_system_score_gemma":0.007912249,"threshold_uncertainty_score":0.6957142},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85272413,0.0020418512,0.12993424,0.0054396107,0.0002464097,0.0011777285,0.003645586,0.00035739114,0.0044331206],"genre_scores_gemma":[0.9307676,0.0011541878,0.06434783,0.00022426927,0.00007634475,0.00087382697,0.0015726254,0.000031309126,0.00095202244],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996119,0.002983177,0.00012283241,0.00028651816,0.0002973215,0.00019112909],"domain_scores_gemma":[0.9942173,0.004700274,0.00040052546,0.00012677917,0.00037212152,0.0001830079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005411628,0.0013172884,0.0014775265,0.002923062,0.0010856831,0.001539726,0.0019914897,0.0013068564,0.0028492077],"category_scores_gemma":[0.010565189,0.0009427498,0.0021736512,0.0037669113,0.0006821293,0.0012379203,0.0016781674,0.0026325479,0.0003626483],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064232346,0.0016643849,0.74574286,0.00089733326,0.0051696007,0.0010998353,0.0068042744,0.12080854,0.0009178922,0.028533773,0.008990088,0.07872919],"study_design_scores_gemma":[0.00026173276,0.0008842838,0.09462817,0.0005918826,0.00156187,0.0003041711,0.0024395168,0.87407553,0.00028781686,0.021444503,0.0034022105,0.00011835084],"about_ca_topic_score_codex":0.040191993,"about_ca_topic_score_gemma":0.041289963,"teacher_disagreement_score":0.040191993,"about_ca_system_score_codex":0.0025655353,"about_ca_system_score_gemma":0.0040580034,"threshold_uncertainty_score":0.07991612},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31518832,0.0022725526,0.67221266,0.0009074117,0.00023263045,0.0047354554,0.000964043,0.00032700156,0.0031598827],"genre_scores_gemma":[0.54289913,0.00095489563,0.44321787,0.00041060383,0.000085028194,0.010737148,0.0008525733,0.0001201159,0.00072266656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.57184654,0.39679778,0.0075614434,0.0081669,0.014954085,0.00067327917],"domain_scores_gemma":[0.16308711,0.7816473,0.02166548,0.021247102,0.01185518,0.0004977662],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26445973,0.001646081,0.0013352844,0.0036362854,0.0007969277,0.0023914021,0.002505207,0.0018287173,0.0024930846],"category_scores_gemma":[0.54714954,0.0010220741,0.0037082445,0.0050532664,0.0021553996,0.0032425434,0.0031962711,0.002279493,0.00044156198],"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":[0.008232064,0.004030882,0.2907883,0.003996192,0.008998518,0.0002959349,0.008583293,0.055162653,0.0031861484,0.036637574,0.0041283076,0.57596016],"study_design_scores_gemma":[0.0036390692,0.012080782,0.27811283,0.0024750438,0.0028703357,0.001004796,0.005378649,0.63694644,0.006251729,0.03855891,0.01193745,0.00074402435],"about_ca_topic_score_codex":0.0025577205,"about_ca_topic_score_gemma":0.0027151003,"teacher_disagreement_score":0.7355403,"about_ca_system_score_codex":0.0025605445,"about_ca_system_score_gemma":0.0024335727,"threshold_uncertainty_score":0.9070521},"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":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34052286,0.26155904,0.29179898,0.05390155,0.0058098654,0.02310739,0.011210776,0.00083588646,0.011253699],"genre_scores_gemma":[0.83816665,0.01643027,0.113320954,0.006989485,0.0012732089,0.020205183,0.0030990995,0.0002210394,0.00029408705],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.09713309,0.6633084,0.19177788,0.012464519,0.033810046,0.0015060114],"domain_scores_gemma":[0.012706755,0.80186385,0.1471807,0.018977307,0.018482951,0.0007884328],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.72230434,0.0015698508,0.004624612,0.011091108,0.001638988,0.009567548,0.0038767348,0.00413375,0.0038438584],"category_scores_gemma":[0.9124311,0.00200283,0.009607446,0.015185811,0.008017351,0.008383941,0.006316489,0.0050812564,0.00038839644],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010829539,0.00037938115,0.6983098,0.09292261,0.043934617,0.00035138588,0.009357896,0.004747964,0.00078724616,0.015646229,0.0118937455,0.110839665],"study_design_scores_gemma":[0.009202378,0.0071537625,0.66706395,0.12557194,0.045246214,0.0035376344,0.0056486777,0.034832858,0.004885489,0.06616634,0.029211076,0.0014796798],"about_ca_topic_score_codex":0.0028164203,"about_ca_topic_score_gemma":0.0023376278,"teacher_disagreement_score":0.27769566,"about_ca_system_score_codex":0.008103195,"about_ca_system_score_gemma":0.0113087045,"threshold_uncertainty_score":0.34244823},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003139818,0.73834175,0.032472044,0.009782692,0.0019513237,0.20321797,0.0067361346,0.0003116323,0.0040465863],"genre_scores_gemma":[0.023147112,0.38553163,0.23167524,0.0042066937,0.00035606415,0.35109445,0.0028985396,0.000103283455,0.0009869726],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.6784938,0.16139632,0.09778316,0.01053367,0.047592655,0.0042005028],"domain_scores_gemma":[0.7313128,0.11784137,0.034153953,0.011083999,0.10162917,0.003978667],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2681282,0.0046564513,0.011055455,0.07814562,0.0074413326,0.012522837,0.0069734934,0.0046682055,0.004476397],"category_scores_gemma":[0.3305075,0.003647754,0.010498673,0.07670481,0.0060176235,0.006596774,0.011307579,0.0044971625,0.0008943702],"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":[0.0003035322,0.000074115815,0.003432389,0.820224,0.0047777165,0.0003635638,0.0066755502,0.0009774764,0.000950417,0.0067359796,0.014034263,0.14145088],"study_design_scores_gemma":[0.00066732086,0.00026822378,0.009109859,0.8779406,0.013605993,0.0004103113,0.0028773067,0.00076051004,0.0006718656,0.0036422776,0.089767076,0.00027859092],"about_ca_topic_score_codex":0.24594155,"about_ca_topic_score_gemma":0.49403548,"teacher_disagreement_score":0.913427,"about_ca_system_score_codex":0.086573005,"about_ca_system_score_gemma":0.31623116,"threshold_uncertainty_score":0.9025282},"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":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04206621,0.0067139356,0.20630321,0.73104775,0.0040637506,0.0014884484,0.0013155012,0.00035042263,0.0066507026],"genre_scores_gemma":[0.415847,0.010773432,0.44609758,0.10564759,0.012498786,0.0056083463,0.00073043624,0.00038918445,0.0024077138],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7028067,0.22052893,0.034998424,0.006363405,0.03373586,0.001566619],"domain_scores_gemma":[0.27527502,0.6359009,0.036717243,0.017594794,0.03250378,0.0020083024],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14684962,0.00050524075,0.0010931627,0.0052463096,0.00196382,0.0046818736,0.0030330948,0.0032110964,0.0015989153],"category_scores_gemma":[0.48174515,0.00085965556,0.0019795953,0.004981145,0.005526507,0.005591282,0.0032479912,0.0068993606,0.0009069934],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009883469,0.00023543903,0.08262478,0.0048898454,0.00041974767,0.0048840335,0.023649897,0.0077668517,0.0017727335,0.07856018,0.14377886,0.65042937],"study_design_scores_gemma":[0.00040737502,0.0011288988,0.13784693,0.01648657,0.0006050999,0.032019913,0.034265965,0.076984875,0.004888465,0.41936505,0.2750676,0.0009332754],"about_ca_topic_score_codex":0.006447849,"about_ca_topic_score_gemma":0.0073533966,"teacher_disagreement_score":0.85315037,"about_ca_system_score_codex":0.009022173,"about_ca_system_score_gemma":0.0088997,"threshold_uncertainty_score":0.7766243},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877752,0.00054334156,0.008350136,0.00013773562,0.000045016317,0.0014665523,0.00037591724,0.00006474442,0.0012415153],"genre_scores_gemma":[0.99355906,0.000113750124,0.004767812,0.00004537094,0.00003609258,0.0009653226,0.00035117255,0.000020945594,0.00014036355],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8114168,0.120930694,0.017152023,0.008227151,0.03993108,0.002342322],"domain_scores_gemma":[0.632155,0.2107232,0.07204044,0.01659169,0.06583867,0.0026510183],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13589998,0.0005526999,0.0011616272,0.00464711,0.0014832753,0.0016361994,0.0015578689,0.00068133505,0.0006652609],"category_scores_gemma":[0.26680097,0.0005544881,0.0010461994,0.004327551,0.0022908375,0.0016788673,0.0024425406,0.00089108985,0.0002210542],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011614857,0.0003297608,0.93590987,0.00063689693,0.0008034109,0.00014769603,0.02555962,0.00060487556,0.0010710103,0.00015438563,0.0007047673,0.03291625],"study_design_scores_gemma":[0.00010093596,0.0011183828,0.9873584,0.00016165093,0.00018692113,0.00021127798,0.0047755227,0.003613925,0.0010851359,0.00019868012,0.0011260334,0.000063115265],"about_ca_topic_score_codex":0.010908042,"about_ca_topic_score_gemma":0.011858305,"teacher_disagreement_score":0.86410004,"about_ca_system_score_codex":0.0036872905,"about_ca_system_score_gemma":0.003479684,"threshold_uncertainty_score":0.7187164},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03281245,0.02302524,0.83013576,0.06574637,0.0038216165,0.033846702,0.0007968739,0.00096164894,0.008853476],"genre_scores_gemma":[0.20931701,0.0047365967,0.72231853,0.008899322,0.00047622874,0.0524195,0.00031765585,0.00053701113,0.000978114],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.14372236,0.79189503,0.034532994,0.010713903,0.017545631,0.0015901295],"domain_scores_gemma":[0.11710014,0.7764341,0.02606776,0.053608164,0.025523392,0.0012665186],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7170306,0.0032511482,0.005484029,0.018620795,0.0094792815,0.025493149,0.009886957,0.008022726,0.0071922825],"category_scores_gemma":[0.80042875,0.00451455,0.0077950424,0.012256085,0.049213476,0.03982024,0.021212455,0.012837326,0.0013909765],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041288062,0.000103881604,0.0036685416,0.03241958,0.0012560933,0.000497875,0.66976035,0.0014374959,0.002192257,0.1485983,0.009633769,0.13001896],"study_design_scores_gemma":[0.0008116791,0.00065925455,0.003869942,0.1008053,0.0015782256,0.0011604812,0.25641948,0.010050312,0.003781241,0.46463344,0.15547332,0.00075741607],"about_ca_topic_score_codex":0.0041166255,"about_ca_topic_score_gemma":0.004248291,"teacher_disagreement_score":0.28296942,"about_ca_system_score_codex":0.017363196,"about_ca_system_score_gemma":0.0347165,"threshold_uncertainty_score":0.3489517},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96185637,0.009315285,0.003563997,0.0038081373,0.00020692233,0.00023123008,0.015570299,0.00004014748,0.0054075373],"genre_scores_gemma":[0.9952872,0.0007921151,0.0016176647,0.00012198604,0.00004286947,0.000051702806,0.0019843325,0.0000068276054,0.0000953242],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9850941,0.0072531817,0.0013079811,0.0008354218,0.0046139634,0.0008953968],"domain_scores_gemma":[0.9584017,0.02431142,0.009102652,0.0013015609,0.006095952,0.0007867684],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0120188445,0.0004438865,0.0004673127,0.0048458786,0.0003835813,0.0016550936,0.001423822,0.00053389586,0.0011336483],"category_scores_gemma":[0.07648297,0.00027663118,0.0010249302,0.0053236843,0.0006205763,0.00061967445,0.0011840092,0.0009435302,0.00009655794],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018172553,0.000012217514,0.9917442,0.00014072341,0.00031333245,0.00005077196,0.00012409127,0.0008046503,0.000024624573,0.0003977625,0.00087206706,0.005333738],"study_design_scores_gemma":[0.000015307725,0.00003716854,0.99568415,0.00018470833,0.00015344743,0.00014240101,0.00032344382,0.0024804468,0.000060480965,0.00021556362,0.0006916721,0.000011246433],"about_ca_topic_score_codex":0.4496326,"about_ca_topic_score_gemma":0.3176887,"teacher_disagreement_score":0.98798114,"about_ca_system_score_codex":0.01015871,"about_ca_system_score_gemma":0.0049763797,"threshold_uncertainty_score":0.8940309},"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":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17728952,0.0038830996,0.2496535,0.003224932,0.00039846258,0.4847591,0.018461326,0.0009117173,0.061418384],"genre_scores_gemma":[0.30547982,0.002267169,0.48792458,0.0009541102,0.000102760976,0.19425659,0.0041306647,0.00015616487,0.0047281724],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8673143,0.06446732,0.016644869,0.008311828,0.03872013,0.0045415657],"domain_scores_gemma":[0.83530575,0.018224848,0.010587628,0.01158537,0.11997572,0.0043207016],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12852952,0.0021057252,0.0012807095,0.0074747247,0.011828471,0.00546253,0.0053008567,0.0011268611,0.005954641],"category_scores_gemma":[0.112864524,0.0020661356,0.0013781125,0.017184123,0.0040575373,0.0019498485,0.0056058057,0.0015554759,0.00087670906],"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":[0.0023220612,0.0023903532,0.33454284,0.019061502,0.0008153992,0.0006483037,0.057469223,0.004637393,0.006381547,0.022470279,0.022075852,0.52718514],"study_design_scores_gemma":[0.0015821584,0.0033917436,0.73202413,0.0067573045,0.0008914442,0.0004860399,0.04635872,0.011922151,0.009810943,0.003471243,0.18269894,0.0006052309],"about_ca_topic_score_codex":0.92854303,"about_ca_topic_score_gemma":0.9575715,"teacher_disagreement_score":0.9083038,"about_ca_system_score_codex":0.091696195,"about_ca_system_score_gemma":0.3129278,"threshold_uncertainty_score":0.6797372},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024098894,0.094207615,0.4853539,0.0426154,0.011188855,0.2788536,0.032974005,0.010703426,0.020004472],"genre_scores_gemma":[0.074528694,0.016235499,0.52819407,0.012013381,0.0016404521,0.3541766,0.008821937,0.0014380404,0.0029512555],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.1128926,0.45618525,0.36583483,0.015157489,0.048071217,0.00185872],"domain_scores_gemma":[0.034355752,0.7381873,0.101742394,0.06442363,0.06011741,0.0011735045],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.73879755,0.0073927543,0.020972228,0.07514707,0.004660935,0.017066382,0.0106099,0.012296957,0.020301403],"category_scores_gemma":[0.90330005,0.007597991,0.017694313,0.05591958,0.012426857,0.02038351,0.012358936,0.0072169313,0.0081309015],"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":[0.0031030634,0.00030232404,0.014302323,0.6263784,0.018648783,0.0008429911,0.009437731,0.0032328884,0.0037471203,0.019771619,0.082376786,0.21785589],"study_design_scores_gemma":[0.009369598,0.0012647673,0.026931103,0.5931417,0.032615636,0.0016786776,0.0029239992,0.018602056,0.011882083,0.098284535,0.20145977,0.0018460997],"about_ca_topic_score_codex":0.004461127,"about_ca_topic_score_gemma":0.0067462707,"teacher_disagreement_score":0.26120245,"about_ca_system_score_codex":0.015196726,"about_ca_system_score_gemma":0.043055087,"threshold_uncertainty_score":0.32210916},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5378821,0.003656776,0.42399177,0.0075133815,0.00028628058,0.005094172,0.005749154,0.00074480753,0.015081588],"genre_scores_gemma":[0.79435813,0.0009264902,0.19944257,0.00055106776,0.00014706377,0.0014938219,0.0024008625,0.000036425423,0.00064354815],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9795267,0.014571426,0.0017378177,0.0013494564,0.0022318894,0.0005826528],"domain_scores_gemma":[0.95530266,0.029992783,0.004157557,0.0029883967,0.006715882,0.0008427657],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020565836,0.00069482444,0.0015955489,0.0077220257,0.0005150143,0.0020099594,0.0012810181,0.0008653842,0.0018647042],"category_scores_gemma":[0.0888173,0.00043915585,0.0013861894,0.003080545,0.00030831163,0.0011839935,0.0016388342,0.00074791425,0.0006908328],"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":[0.0005724399,0.00036693324,0.7264944,0.00046500837,0.00049676327,0.00024550347,0.00042021106,0.008818323,0.0010758593,0.0043591238,0.0046019065,0.25208357],"study_design_scores_gemma":[0.0005029235,0.001390963,0.72898775,0.0012411057,0.0011101506,0.0015015566,0.0027263486,0.22329725,0.004288572,0.02252454,0.012270367,0.00015836807],"about_ca_topic_score_codex":0.0085396785,"about_ca_topic_score_gemma":0.005605819,"teacher_disagreement_score":0.9794342,"about_ca_system_score_codex":0.0012137642,"about_ca_system_score_gemma":0.0038727834,"threshold_uncertainty_score":0.10876387},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"reproducibility","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reproducibility","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15540345,0.00206717,0.8357941,0.00022255788,0.00038366343,0.0009839206,0.0009939962,0.00058514514,0.0035660102],"genre_scores_gemma":[0.7390404,0.00046687803,0.25581688,0.00020299519,0.00014783011,0.0018030438,0.0012031266,0.00036938483,0.00094949635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.94374514,0.035969354,0.0031047442,0.0059713167,0.010603749,0.00060562504],"domain_scores_gemma":[0.7017459,0.25734892,0.011751897,0.017482735,0.010822782,0.0008476485],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07002945,0.001225722,0.0011067573,0.0038265805,0.0006431748,0.0015445292,0.0018330887,0.0020156328,0.0026685225],"category_scores_gemma":[0.18056132,0.0003479565,0.002117359,0.002859305,0.0021732831,0.0013074696,0.0015096723,0.0017963124,0.00063203264],"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":[0.003762578,0.001779776,0.35639155,0.0026840302,0.007937679,0.00091150607,0.0025830646,0.097547755,0.039673794,0.0364994,0.0077624894,0.44246635],"study_design_scores_gemma":[0.00051128713,0.009845482,0.4389716,0.00060871016,0.0019814083,0.0033221692,0.0009462548,0.3997692,0.07446418,0.050215013,0.018621832,0.0007429262],"about_ca_topic_score_codex":0.0007834264,"about_ca_topic_score_gemma":0.0006386504,"teacher_disagreement_score":0.92997056,"about_ca_system_score_codex":0.00085016666,"about_ca_system_score_gemma":0.0011856451,"threshold_uncertainty_score":0.37035555},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031321014,0.15314448,0.51209533,0.2817934,0.028521346,0.00051636295,0.0009155236,0.0010730389,0.018808404],"genre_scores_gemma":[0.2748763,0.06901134,0.49746183,0.10991125,0.039763574,0.0038786132,0.0007416835,0.0015684156,0.0027870368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3792777,0.5197973,0.03259264,0.017642057,0.048396774,0.0022935197],"domain_scores_gemma":[0.09519735,0.8461824,0.014760552,0.021639528,0.020971272,0.0012489227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41675228,0.0031205972,0.0071196994,0.014912372,0.0035305326,0.01955856,0.012226392,0.014992431,0.0069591184],"category_scores_gemma":[0.8143043,0.003200111,0.006409728,0.009494503,0.030759411,0.028109184,0.011761714,0.02962153,0.002159292],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045522916,0.000050856135,0.0014832492,0.006294528,0.0023732476,0.00038203827,0.0056672203,0.0053265197,0.00016843351,0.7620097,0.054380015,0.16140896],"study_design_scores_gemma":[0.00014944669,0.00007196878,0.00034352107,0.005810041,0.0004486867,0.00024038603,0.0006207033,0.0031450416,0.0002905173,0.93385893,0.05486825,0.00015256525],"about_ca_topic_score_codex":0.004523175,"about_ca_topic_score_gemma":0.0019050817,"teacher_disagreement_score":0.5832477,"about_ca_system_score_codex":0.008956512,"about_ca_system_score_gemma":0.009302767,"threshold_uncertainty_score":0.7192483},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7873304,0.025906814,0.022085566,0.00638567,0.008699275,0.13318442,0.0025931525,0.00062448264,0.013190307],"genre_scores_gemma":[0.8779498,0.0033779787,0.017404085,0.0017868979,0.0011396004,0.09567686,0.00046314468,0.000044224707,0.002157482],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.84132385,0.14116535,0.00659257,0.004101532,0.0041337004,0.0026829508],"domain_scores_gemma":[0.9014227,0.074888065,0.012258434,0.0047799507,0.0028020337,0.0038487406],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.053757284,0.0038065044,0.0073008216,0.0026823757,0.0013802332,0.003087177,0.002676812,0.008143124,0.015888056],"category_scores_gemma":[0.11943549,0.0019052612,0.008831024,0.0022157023,0.0052759857,0.005111008,0.0031108547,0.006051814,0.0012907259],"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":[0.96750236,0.003554996,0.00074319326,0.003973148,0.0027253644,0.000048682756,0.00013051387,0.0012995874,0.00018118812,0.0013140704,0.0005209735,0.01800602],"study_design_scores_gemma":[0.92593884,0.0643712,0.0009370999,0.0008619247,0.0019914096,0.000052581032,0.000067731366,0.0024895007,0.0002420853,0.002142836,0.0008488326,0.00005608523],"about_ca_topic_score_codex":0.002427064,"about_ca_topic_score_gemma":0.0013493482,"teacher_disagreement_score":0.9462427,"about_ca_system_score_codex":0.00594993,"about_ca_system_score_gemma":0.0062447824,"threshold_uncertainty_score":0.28429908},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99660707,0.00038510715,0.0016604436,0.00018053569,0.000020888581,0.00033483873,0.0005501763,0.000006802931,0.000254126],"genre_scores_gemma":[0.9954827,0.00014957407,0.0028570518,0.00015553762,0.000029780034,0.00048955367,0.0007943618,0.000004324925,0.000037109527],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.947524,0.035062373,0.005187209,0.0022903765,0.008959146,0.0009768909],"domain_scores_gemma":[0.88877785,0.047604807,0.03943557,0.012220665,0.009421665,0.0025394345],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032599144,0.00034863933,0.00074346724,0.0016846362,0.0010900727,0.0014032064,0.0011161068,0.0008226814,0.0005795844],"category_scores_gemma":[0.09197728,0.0005475382,0.0014575071,0.0039258786,0.00079309626,0.0010807182,0.0017773244,0.0014927755,0.00017292505],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016606554,0.00014804881,0.9970584,0.0000557784,0.00016874362,0.000034115845,0.00031603963,0.000031648222,0.00009811576,0.000023281942,0.00010562656,0.0017942076],"study_design_scores_gemma":[0.00008895631,0.00076022436,0.99638903,0.00007861814,0.00022101868,0.00024774196,0.00071219495,0.00076895126,0.00015593896,0.00004245056,0.00051746593,0.000017328186],"about_ca_topic_score_codex":0.012555226,"about_ca_topic_score_gemma":0.013471109,"teacher_disagreement_score":0.96740085,"about_ca_system_score_codex":0.001468642,"about_ca_system_score_gemma":0.0032025261,"threshold_uncertainty_score":0.1724028},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9732805,0.0009280138,0.014475844,0.0002535354,0.00015253054,0.0082027,0.0006781166,0.0000363221,0.0019924873],"genre_scores_gemma":[0.9695255,0.00031663402,0.015699781,0.00044129725,0.000056581583,0.012098564,0.001132403,0.00002322356,0.000705918],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9490793,0.03711053,0.0040510264,0.0030050657,0.005966577,0.00078749924],"domain_scores_gemma":[0.97413456,0.011460499,0.004927562,0.0041181534,0.00457144,0.00078781275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.051315695,0.00049130723,0.00050504744,0.0016628394,0.0011201425,0.0011465319,0.0016195402,0.0011595748,0.0016116289],"category_scores_gemma":[0.09354335,0.00052150607,0.0009878549,0.0013055564,0.0010970634,0.00091138284,0.0019092899,0.00059768243,0.00036477347],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005516309,0.001819802,0.9292616,0.00065312814,0.0014674545,0.00029574873,0.014054041,0.00023675428,0.0027118786,0.0011598599,0.0012166008,0.041606974],"study_design_scores_gemma":[0.0015320958,0.008520046,0.9708574,0.0004256524,0.00097640936,0.00057954487,0.0075132153,0.0017249045,0.0026613527,0.0007920362,0.00434634,0.00007097519],"about_ca_topic_score_codex":0.0058109174,"about_ca_topic_score_gemma":0.01060463,"teacher_disagreement_score":0.94868433,"about_ca_system_score_codex":0.001075735,"about_ca_system_score_gemma":0.0020059824,"threshold_uncertainty_score":0.27138656},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9890848,0.0009880805,0.0006645268,0.0004530113,0.00003228861,0.00035340412,0.005650189,0.0000100437055,0.0027636122],"genre_scores_gemma":[0.99610376,0.00026666315,0.00035526618,0.00016150725,0.000012195644,0.0001659982,0.0023293772,0.0000069018047,0.00059828203],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968514,0.00066506484,0.00018126545,0.0004744101,0.001381519,0.0004464127],"domain_scores_gemma":[0.9941689,0.00074910687,0.0014851347,0.0009822692,0.0018773387,0.0007372371],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004598362,0.00019653764,0.0003594509,0.0006904639,0.0014489775,0.0010800754,0.00093406154,0.00034015148,0.0010794849],"category_scores_gemma":[0.012831169,0.00020332205,0.0005692711,0.0013718532,0.00050278247,0.00032385797,0.0007297784,0.0003587491,0.00013752698],"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":[0.00015422664,0.000010879193,0.995242,0.000023607186,0.00007654245,0.000034476736,0.00068290933,0.00003670796,0.00011180492,0.000058202553,0.0010789492,0.0024898122],"study_design_scores_gemma":[0.0000116407955,0.00001691987,0.99856156,0.00001678221,0.000039600545,0.000033235592,0.00035636887,0.00007180046,0.000021333553,0.00001674755,0.00085047586,0.0000034282739],"about_ca_topic_score_codex":0.77504754,"about_ca_topic_score_gemma":0.811602,"teacher_disagreement_score":0.9954493,"about_ca_system_score_codex":0.0045507103,"about_ca_system_score_gemma":0.0067088054,"threshold_uncertainty_score":0.45255446},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060824575,0.0011668749,0.9887683,0.0006269945,0.00027661351,0.00074667984,0.0009488169,0.00046613408,0.0009171873],"genre_scores_gemma":[0.43758726,0.0065940926,0.5075529,0.0012021512,0.001443147,0.01660363,0.005840463,0.00046563652,0.022710731],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9717581,0.022266144,0.00075004855,0.0029428652,0.0015544465,0.0007282883],"domain_scores_gemma":[0.9478498,0.046676513,0.0019855015,0.0014760596,0.0017213115,0.00029080722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040821325,0.0034420714,0.00473844,0.003994034,0.0009841284,0.0024851237,0.008280392,0.0042322986,0.012162216],"category_scores_gemma":[0.063849136,0.0016746727,0.0038526268,0.0041520856,0.0022511617,0.0025457551,0.0029585483,0.0059242244,0.001972866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079795485,0.0001843634,0.0076987534,0.0008732396,0.001363951,0.0011410011,0.00043652425,0.78443205,0.0004261349,0.14591894,0.0065849237,0.050142206],"study_design_scores_gemma":[0.00018136464,0.0001290844,0.0006849217,0.00007206684,0.00018224698,0.00018392422,0.000045766334,0.9324339,0.00008944153,0.06316021,0.0027907172,0.000046477653],"about_ca_topic_score_codex":0.014116513,"about_ca_topic_score_gemma":0.005838272,"teacher_disagreement_score":0.040821325,"about_ca_system_score_codex":0.0024913824,"about_ca_system_score_gemma":0.0032020905,"threshold_uncertainty_score":0.21588641},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076959566,0.00063291116,0.98685455,0.00096874335,0.00010523249,0.0021466024,0.00023472517,0.00041774666,0.0009436741],"genre_scores_gemma":[0.11937756,0.00026660613,0.8726133,0.00050564297,0.0001119288,0.0065532364,0.00022989261,0.000046468314,0.00029535047],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.88853353,0.09222934,0.0040677637,0.0068938704,0.007525044,0.0007503492],"domain_scores_gemma":[0.5936463,0.37901416,0.011311179,0.008548811,0.0058034137,0.0016761728],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13752928,0.0020887365,0.0051294854,0.008661095,0.0016172649,0.004117699,0.004638996,0.003983365,0.006782257],"category_scores_gemma":[0.27786705,0.0018946797,0.006246398,0.0030214118,0.004511268,0.0040075136,0.0045426455,0.0045859423,0.00066501333],"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":[0.0043632733,0.0007513482,0.008249346,0.0063851383,0.0050290534,0.00048222955,0.003523069,0.50199187,0.0014052046,0.11451761,0.0036345252,0.34966728],"study_design_scores_gemma":[0.0011298076,0.00072711415,0.0013015612,0.0007817698,0.0008471763,0.00011494384,0.00021411554,0.7573338,0.0008653295,0.23260802,0.0039702193,0.00010612861],"about_ca_topic_score_codex":0.0041039945,"about_ca_topic_score_gemma":0.004115288,"teacher_disagreement_score":0.86247075,"about_ca_system_score_codex":0.0055799573,"about_ca_system_score_gemma":0.007207563,"threshold_uncertainty_score":0.72733307},"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":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.333668,0.28931245,0.20436569,0.0084700985,0.002000001,0.097984135,0.047441963,0.0011748131,0.015582911],"genre_scores_gemma":[0.6225111,0.029173564,0.20240031,0.002052748,0.0003295854,0.13271277,0.009975876,0.0002867781,0.00055740174],"study_design_codex":"observational","study_design_gemma":"systematic_review","domain_scores_codex":[0.39302954,0.20562826,0.31958258,0.011951996,0.06717614,0.0026314503],"domain_scores_gemma":[0.16408582,0.6599303,0.11008406,0.021849344,0.04282441,0.0012260649],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35114327,0.0020878422,0.0083042765,0.054884233,0.0016931115,0.0057436666,0.0035224492,0.0025872642,0.0032623673],"category_scores_gemma":[0.66910803,0.0017242851,0.019825611,0.047354136,0.004225867,0.0070630894,0.0070956387,0.0030339775,0.0004274621],"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":[0.0039468533,0.00050152227,0.34784725,0.2642313,0.051350925,0.0006503939,0.028411195,0.0039471923,0.0014817975,0.0127791455,0.010218758,0.27463362],"study_design_scores_gemma":[0.0048024077,0.0044461587,0.48622254,0.27813637,0.064278066,0.0050996807,0.022485383,0.01222355,0.0053687864,0.045174237,0.069906406,0.0018563516],"about_ca_topic_score_codex":0.0014941535,"about_ca_topic_score_gemma":0.0020083599,"teacher_disagreement_score":0.64885676,"about_ca_system_score_codex":0.009013641,"about_ca_system_score_gemma":0.010873954,"threshold_uncertainty_score":0.8001559},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022083323,0.04916718,0.4878354,0.30170575,0.022146193,0.09152952,0.0018870593,0.0015240479,0.022121549],"genre_scores_gemma":[0.14389071,0.0051272977,0.6998161,0.025350466,0.0024638362,0.12228258,0.00028758982,0.00023238671,0.0005490905],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.03405297,0.9049517,0.0395833,0.003780474,0.01690425,0.0007273553],"domain_scores_gemma":[0.043565106,0.8755485,0.029780852,0.02768807,0.020822322,0.0025951401],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.83795446,0.002612178,0.00656461,0.010878192,0.0046441425,0.018588355,0.004782307,0.011386411,0.005557259],"category_scores_gemma":[0.92435485,0.0028212243,0.007077467,0.009429985,0.022020098,0.01727802,0.009949989,0.010449839,0.0009713877],"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":[0.007613188,0.0005275378,0.010784573,0.11635418,0.010153793,0.0005144043,0.026204525,0.0049749864,0.0008805525,0.20625083,0.05824557,0.55749583],"study_design_scores_gemma":[0.017509563,0.0053988476,0.01693869,0.16338235,0.011203127,0.0013616469,0.009187486,0.032303724,0.0040061856,0.55614233,0.18116395,0.0014021038],"about_ca_topic_score_codex":0.0017443334,"about_ca_topic_score_gemma":0.0023344706,"teacher_disagreement_score":0.16204554,"about_ca_system_score_codex":0.018060949,"about_ca_system_score_gemma":0.04677042,"threshold_uncertainty_score":0.19983107},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22641647,0.0059383516,0.7312798,0.004625569,0.00044220383,0.0027572305,0.017035516,0.0030168816,0.008487892],"genre_scores_gemma":[0.5044753,0.0029961185,0.46213534,0.0008206265,0.000111913745,0.0045608883,0.022018798,0.0009276786,0.0019534184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8843195,0.10476797,0.0028718547,0.0035952504,0.003630172,0.0008152506],"domain_scores_gemma":[0.6045981,0.3591187,0.007929919,0.012176181,0.015469411,0.0007077097],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11634215,0.0012908059,0.0022374974,0.0038122113,0.0008011398,0.0024798797,0.003058407,0.0015174038,0.0049363547],"category_scores_gemma":[0.3678858,0.0008206704,0.004931354,0.008249655,0.0009583498,0.003262383,0.0021115418,0.0028582609,0.0007890144],"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":[0.0039825193,0.0010804805,0.20744431,0.0046541938,0.011497861,0.0006539835,0.0037426099,0.23521069,0.0003581146,0.0966713,0.056831475,0.37787256],"study_design_scores_gemma":[0.0017762296,0.0016148888,0.1103097,0.0015907,0.002910843,0.0005424776,0.0034955726,0.79715896,0.0006269108,0.047806855,0.031762067,0.000404821],"about_ca_topic_score_codex":0.06459802,"about_ca_topic_score_gemma":0.04688057,"teacher_disagreement_score":0.8836579,"about_ca_system_score_codex":0.0034256787,"about_ca_system_score_gemma":0.0054751863,"threshold_uncertainty_score":0.6152835},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8529192,0.010730045,0.00842157,0.003046018,0.0031293435,0.11655014,0.0013707605,0.00029937064,0.0035335673],"genre_scores_gemma":[0.793227,0.0030015928,0.025915949,0.002965346,0.0017897247,0.17005524,0.0006141633,0.000050213937,0.0023806929],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.96930224,0.024116162,0.00190253,0.0022670003,0.0012726978,0.0011394329],"domain_scores_gemma":[0.97559583,0.014064993,0.0046563023,0.002300039,0.001607008,0.001775855],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02906554,0.0026800232,0.0045923223,0.0011443387,0.0015832266,0.0018707393,0.0025338756,0.005041858,0.00894168],"category_scores_gemma":[0.043025862,0.0011938342,0.005144214,0.0010067228,0.0026786495,0.0033462546,0.0017136821,0.0042275586,0.00081636186],"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":[0.95008796,0.016864577,0.0036350181,0.003221925,0.0046368833,0.000054619548,0.00042346923,0.0003759161,0.0003404625,0.0006494569,0.0010816812,0.018628027],"study_design_scores_gemma":[0.8866844,0.104014516,0.002910559,0.00046547432,0.0033367337,0.000028406965,0.000114587776,0.0010416454,0.00014958465,0.00043346218,0.0007870239,0.000033541855],"about_ca_topic_score_codex":0.0025260877,"about_ca_topic_score_gemma":0.0029435612,"teacher_disagreement_score":0.97093445,"about_ca_system_score_codex":0.0020141676,"about_ca_system_score_gemma":0.00494966,"threshold_uncertainty_score":0.15371507},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08010866,0.0033868246,0.4275031,0.005090176,0.00026270398,0.012809769,0.44402033,0.01739139,0.009426947],"genre_scores_gemma":[0.15471117,0.0017108832,0.58180714,0.0006054635,0.0003040269,0.01051675,0.24873503,0.0010835949,0.0005259445],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95185614,0.02448879,0.009481658,0.005965718,0.0073521677,0.0008555245],"domain_scores_gemma":[0.6853982,0.12859832,0.0478081,0.07816866,0.048942152,0.0110845445],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07039164,0.001497418,0.0030968632,0.025156414,0.0013946035,0.0053184475,0.0059830607,0.001628566,0.0048323716],"category_scores_gemma":[0.20742936,0.0018201008,0.002113738,0.036672715,0.0014810094,0.0053260257,0.0083151655,0.0027447543,0.0031071985],"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":[0.0011423276,0.0008899112,0.5777654,0.0036235715,0.0019466322,0.0002723545,0.0037324505,0.0221721,0.0022847725,0.0111200875,0.057120897,0.31792942],"study_design_scores_gemma":[0.0007950634,0.0006562536,0.7581945,0.0031518892,0.0012386376,0.00042952382,0.0040898225,0.084059246,0.004330597,0.026916854,0.11553019,0.0006074542],"about_ca_topic_score_codex":0.09117515,"about_ca_topic_score_gemma":0.05806093,"teacher_disagreement_score":0.92960835,"about_ca_system_score_codex":0.008302863,"about_ca_system_score_gemma":0.025085647,"threshold_uncertainty_score":0.372271},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10260665,0.0073851934,0.75308466,0.01948206,0.001207702,0.08879303,0.006987388,0.0021780636,0.018275313],"genre_scores_gemma":[0.10575682,0.0014325308,0.81896687,0.00087516254,0.0001049374,0.070894495,0.0011295065,0.00031562947,0.0005240297],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.48657036,0.37153432,0.07162807,0.02172307,0.04502439,0.0035198429],"domain_scores_gemma":[0.19890654,0.62969744,0.041680396,0.05211545,0.07586686,0.0017332289],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47274715,0.0031519276,0.0059847967,0.0964572,0.007698189,0.020408845,0.0059799417,0.0028254096,0.0057591],"category_scores_gemma":[0.71159476,0.003333919,0.007206529,0.060967676,0.01278504,0.022697479,0.024512293,0.0048890947,0.0012998106],"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":[0.00055645383,0.00020924234,0.016492233,0.045354705,0.0019561658,0.0011465091,0.4243453,0.0022050214,0.0042270394,0.059020273,0.013787012,0.4307],"study_design_scores_gemma":[0.0013782145,0.0011075742,0.03366052,0.06705306,0.0045450553,0.0016355616,0.4035225,0.02165033,0.011803995,0.29654917,0.15596268,0.0011313726],"about_ca_topic_score_codex":0.0047007054,"about_ca_topic_score_gemma":0.0069416817,"teacher_disagreement_score":0.52725285,"about_ca_system_score_codex":0.01714535,"about_ca_system_score_gemma":0.046534665,"threshold_uncertainty_score":0.6501967},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92087513,0.0018309952,0.07047165,0.00095660915,0.000054318618,0.00014948657,0.0009055184,0.0012100859,0.0035462743],"genre_scores_gemma":[0.96461016,0.0005968613,0.031580254,0.00011924653,0.000026024692,0.00006864248,0.0011303469,0.00010394471,0.0017645727],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979944,0.0009371945,0.0001247256,0.0004484148,0.00035060183,0.00014474218],"domain_scores_gemma":[0.994588,0.0032905284,0.0004457444,0.0002132122,0.001255606,0.00020685111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063505224,0.0016047728,0.0006402514,0.001878935,0.00083346455,0.0016817662,0.0016757366,0.0007688034,0.0008449595],"category_scores_gemma":[0.008813733,0.00043456757,0.0016799769,0.0008406018,0.00039435376,0.00065467414,0.0010230367,0.00074579904,0.00020253805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011427632,0.00025710627,0.19194633,0.00024607236,0.0017897701,0.00007972977,0.00041403773,0.7069072,0.0022883846,0.0013822352,0.0009659201,0.09258046],"study_design_scores_gemma":[0.000051113635,0.00019625708,0.052499585,0.000060430077,0.00026114992,0.00005652322,0.0002769622,0.9428812,0.0016858326,0.00088718307,0.0010702185,0.00007354476],"about_ca_topic_score_codex":0.6021088,"about_ca_topic_score_gemma":0.5153096,"teacher_disagreement_score":0.39789122,"about_ca_system_score_codex":0.0064758016,"about_ca_system_score_gemma":0.0060731485,"threshold_uncertainty_score":0.800469},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8282271,0.00083704625,0.15437733,0.0007749755,0.00042133217,0.0059353965,0.0021623794,0.00023684096,0.0070277],"genre_scores_gemma":[0.9100976,0.00013700042,0.08391606,0.00025867778,0.000082835446,0.0027684723,0.0024617587,0.00006504111,0.00021257465],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.87806225,0.081428766,0.016837547,0.0067938664,0.0148703065,0.0020072733],"domain_scores_gemma":[0.6546025,0.21873271,0.03922653,0.03432563,0.05061534,0.0024973294],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15658206,0.0008806461,0.0010395715,0.007178897,0.0013456566,0.0033075993,0.0032384465,0.0012464599,0.00093380484],"category_scores_gemma":[0.27459443,0.0004753212,0.0016587141,0.002933522,0.0021505686,0.0024934465,0.0044245617,0.001438088,0.0003660633],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061429845,0.00036225485,0.96216065,0.00024466467,0.00030816923,0.0001397786,0.0023327847,0.0020942998,0.00073044066,0.002452363,0.0014377258,0.027122645],"study_design_scores_gemma":[0.00066357653,0.0023815695,0.87192035,0.0014221603,0.0006176304,0.0026977179,0.0062864046,0.08442922,0.0064535853,0.007068975,0.01587744,0.00018132164],"about_ca_topic_score_codex":0.0031139704,"about_ca_topic_score_gemma":0.0026154846,"teacher_disagreement_score":0.84341794,"about_ca_system_score_codex":0.0020526045,"about_ca_system_score_gemma":0.003822582,"threshold_uncertainty_score":0.82809496},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1986789,0.010796047,0.5520072,0.028523631,0.004358662,0.115662634,0.0070337527,0.0021675143,0.08077165],"genre_scores_gemma":[0.3324573,0.0065730796,0.46434736,0.0068073296,0.0007077659,0.17982978,0.0025112901,0.0015965974,0.005169435],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.17182101,0.665788,0.056310527,0.0095238825,0.09247974,0.004076818],"domain_scores_gemma":[0.06934466,0.69275826,0.055994887,0.026260791,0.15328537,0.0023559863],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.59911543,0.0024552576,0.003838503,0.018297147,0.01023046,0.012843944,0.006802807,0.003733011,0.010961728],"category_scores_gemma":[0.83512443,0.00274477,0.0034925085,0.024540866,0.015699029,0.014181916,0.018922567,0.006494592,0.0031445036],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082716986,0.0002612492,0.02270518,0.0339276,0.00050262775,0.0013416285,0.6265642,0.002136619,0.0029460522,0.0263982,0.026012624,0.2563769],"study_design_scores_gemma":[0.00067402294,0.0017063941,0.033561897,0.06726884,0.0010378012,0.002538452,0.4626528,0.014436639,0.007340502,0.044756897,0.36327878,0.0007469479],"about_ca_topic_score_codex":0.0069581163,"about_ca_topic_score_gemma":0.009679623,"teacher_disagreement_score":0.40088457,"about_ca_system_score_codex":0.023973793,"about_ca_system_score_gemma":0.05207394,"threshold_uncertainty_score":0.49436212},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4424878,0.0026905083,0.5218157,0.008198875,0.00021584127,0.000921968,0.007880913,0.00088421436,0.014904124],"genre_scores_gemma":[0.9188909,0.0015001724,0.05298092,0.00073706266,0.00023163186,0.001083535,0.0036809281,0.00017254638,0.0207223],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653924,0.001936389,0.00011329654,0.0008046944,0.00022536694,0.00038096972],"domain_scores_gemma":[0.98871464,0.008089628,0.0011801069,0.00047316702,0.0009784097,0.0005641017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010627218,0.0012231756,0.0027271956,0.0026607572,0.0016408907,0.0030692986,0.005686047,0.0028962095,0.009429615],"category_scores_gemma":[0.025791802,0.0018590904,0.0028314996,0.0020083457,0.0023477382,0.0022486334,0.002477139,0.0032110813,0.001250247],"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":[0.0009413268,0.00037119456,0.07147392,0.00030839184,0.0014129897,0.001645319,0.0029613946,0.7466438,0.00095268537,0.12193611,0.007972987,0.043379802],"study_design_scores_gemma":[0.00021498914,0.000104318,0.009944586,0.00013330621,0.00032722615,0.00028043962,0.00031422862,0.9233308,0.0000802277,0.0629173,0.0022657455,0.00008687448],"about_ca_topic_score_codex":0.11860383,"about_ca_topic_score_gemma":0.06731501,"teacher_disagreement_score":0.11860383,"about_ca_system_score_codex":0.0033198365,"about_ca_system_score_gemma":0.0029531014,"threshold_uncertainty_score":0.23582697},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10219172,0.013686051,0.6551437,0.065698996,0.0143646365,0.0039101387,0.021814765,0.0052020676,0.11798795],"genre_scores_gemma":[0.43837023,0.0034474623,0.5154626,0.015048316,0.0025300346,0.009030443,0.00565713,0.0011029037,0.009350837],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9518967,0.037361033,0.0024615237,0.0029933264,0.004559003,0.00072846445],"domain_scores_gemma":[0.87459147,0.10818832,0.004404891,0.007678219,0.0044328156,0.0007043357],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03844318,0.001283784,0.0014949534,0.002215815,0.0013675088,0.0043783667,0.002236432,0.0019646978,0.04265577],"category_scores_gemma":[0.13509318,0.0006696207,0.002475889,0.0032551636,0.0044160043,0.004993833,0.002834226,0.004497705,0.0059538824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034059803,0.00027321454,0.029524278,0.0066609993,0.0009624877,0.0005667927,0.005309199,0.0033970384,0.0010457359,0.33978787,0.2022342,0.4068322],"study_design_scores_gemma":[0.0005140553,0.00057100673,0.010547127,0.0054447586,0.00048261145,0.0011225527,0.0030070893,0.01494508,0.0012529192,0.7790092,0.18287157,0.0002319662],"about_ca_topic_score_codex":0.0011385005,"about_ca_topic_score_gemma":0.0012834343,"teacher_disagreement_score":0.9615568,"about_ca_system_score_codex":0.0018120488,"about_ca_system_score_gemma":0.0017822194,"threshold_uncertainty_score":0.20330942},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026451752,0.0005367111,0.9929096,0.0011048816,0.00009985557,0.00018605763,0.0003406481,0.00037308838,0.0018039499],"genre_scores_gemma":[0.12157194,0.0017680619,0.87039685,0.0011941466,0.00037674484,0.0014110206,0.0009015774,0.00020984955,0.002169794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9499737,0.040942054,0.0014608497,0.003475646,0.0035818543,0.00056585384],"domain_scores_gemma":[0.62789226,0.34569675,0.007997833,0.0120770885,0.005485676,0.0008503661],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037039954,0.0016621572,0.0019060584,0.006052916,0.001784208,0.0027746838,0.0036224942,0.0026303052,0.007855822],"category_scores_gemma":[0.17192924,0.0014833297,0.0024843249,0.005784775,0.003535888,0.0053353193,0.0041623665,0.0037860293,0.0012968397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029268535,0.00012333083,0.005089389,0.0014338035,0.00062656694,0.00041626178,0.0010111637,0.12500557,0.00066537544,0.6188703,0.01036382,0.23610182],"study_design_scores_gemma":[0.000077679906,0.000037562368,0.00032254038,0.0001731952,0.00012085959,0.00011962562,0.00005991811,0.11846537,0.00037784025,0.87235415,0.007864072,0.000027242897],"about_ca_topic_score_codex":0.003274582,"about_ca_topic_score_gemma":0.0034619954,"teacher_disagreement_score":0.96296006,"about_ca_system_score_codex":0.0022704753,"about_ca_system_score_gemma":0.0037870097,"threshold_uncertainty_score":0.19588834},"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":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06270946,0.60333115,0.12911825,0.032834295,0.016322922,0.09934125,0.02524915,0.0014586917,0.029634852],"genre_scores_gemma":[0.42452207,0.11648558,0.14073612,0.032210343,0.0040294393,0.2643712,0.008713218,0.0009768634,0.007955216],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.3058331,0.36328346,0.2578328,0.020747695,0.049400993,0.0029019893],"domain_scores_gemma":[0.111705534,0.6673232,0.13429466,0.054568112,0.030473616,0.0016349307],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5384464,0.002932395,0.012288661,0.025580073,0.0026975898,0.008743958,0.0061819796,0.0071700625,0.0144789675],"category_scores_gemma":[0.77663285,0.0036759076,0.009196018,0.029866142,0.006019138,0.011032113,0.007340411,0.002946087,0.0032623534],"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":[0.009867908,0.00039095813,0.044463668,0.6571931,0.021595836,0.0033243946,0.012883312,0.0011318943,0.0016971026,0.016385509,0.02963737,0.20142893],"study_design_scores_gemma":[0.0107245715,0.0027302236,0.06810742,0.5748698,0.0669741,0.0054545007,0.004897591,0.0050168387,0.005683636,0.083254494,0.17127198,0.001014776],"about_ca_topic_score_codex":0.002099844,"about_ca_topic_score_gemma":0.002801786,"teacher_disagreement_score":0.46155357,"about_ca_system_score_codex":0.0056985156,"about_ca_system_score_gemma":0.015366604,"threshold_uncertainty_score":0.56917775},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6517878,0.0016853937,0.1337893,0.0013003161,0.0010439479,0.13958067,0.037532713,0.0014092182,0.03187055],"genre_scores_gemma":[0.47900984,0.0019663977,0.24354823,0.00059762096,0.0002337518,0.23664024,0.025756365,0.00051925774,0.011728188],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99429375,0.0017971488,0.0012790143,0.0004066585,0.0019050698,0.00031824192],"domain_scores_gemma":[0.9905895,0.0013955613,0.0013554472,0.0011230399,0.005227504,0.00030901542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007474929,0.0011760449,0.0010648461,0.0021659383,0.0007672412,0.00057375716,0.00086905516,0.00032412578,0.0045756907],"category_scores_gemma":[0.013098648,0.00039977673,0.0016241211,0.0021382896,0.0008645584,0.00034052395,0.0013290029,0.0012094226,0.002012926],"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":[0.004619865,0.004603919,0.2435535,0.0048616836,0.0010355461,0.0007564831,0.0069716913,0.0036179284,0.027050225,0.0050164927,0.05501315,0.64289945],"study_design_scores_gemma":[0.001034405,0.0043159085,0.9334388,0.00041046413,0.00020658525,0.00036959728,0.0010533914,0.0024748622,0.0059375763,0.0016767265,0.04890926,0.00017241809],"about_ca_topic_score_codex":0.004989068,"about_ca_topic_score_gemma":0.01255149,"teacher_disagreement_score":0.007474929,"about_ca_system_score_codex":0.0011862636,"about_ca_system_score_gemma":0.003543138,"threshold_uncertainty_score":0.03953165},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077788316,0.9604509,0.026859583,0.0013888441,0.0011686276,0.004621459,0.00319733,0.00027640848,0.0012590474],"genre_scores_gemma":[0.04359332,0.80934507,0.11015051,0.0029742848,0.0011347934,0.028156739,0.0035693003,0.00032138376,0.0007545475],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8586923,0.09947282,0.026365869,0.004756586,0.0101903975,0.0005221632],"domain_scores_gemma":[0.7028116,0.25869116,0.020232223,0.007998499,0.00967932,0.0005872688],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09278422,0.004789954,0.019915516,0.022612331,0.0009644856,0.004995665,0.0048125493,0.0034710155,0.010976657],"category_scores_gemma":[0.3362364,0.002595217,0.033586703,0.01666343,0.0016480616,0.0038760684,0.0031733343,0.0036032707,0.0014544568],"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":[0.0005492236,0.000034121313,0.0012783076,0.7067843,0.19472222,0.00013630677,0.00017472835,0.0017767078,0.00015861054,0.0027000187,0.0067467,0.08493882],"study_design_scores_gemma":[0.0020288774,0.00036100077,0.002907174,0.4308106,0.49912155,0.0003985608,0.00018192014,0.002658532,0.00059025607,0.015836896,0.044845995,0.0002586736],"about_ca_topic_score_codex":0.0054646446,"about_ca_topic_score_gemma":0.010081669,"teacher_disagreement_score":0.9072158,"about_ca_system_score_codex":0.00575738,"about_ca_system_score_gemma":0.012521721,"threshold_uncertainty_score":0.49069571},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15899171,0.0017970329,0.8338682,0.0011362141,0.00023314834,0.0015699739,0.0009946357,0.00053520635,0.0008738645],"genre_scores_gemma":[0.756926,0.0009296152,0.23659435,0.00035245568,0.00019920878,0.0029642393,0.0010162361,0.00009319391,0.0009246923],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9061195,0.08037709,0.002506981,0.0060293367,0.0038709017,0.0010962021],"domain_scores_gemma":[0.63645285,0.3199779,0.023772618,0.013553311,0.0048267576,0.0014165402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1324485,0.0015755766,0.0025764583,0.0029256814,0.0008358585,0.0017711661,0.003943507,0.002049574,0.002770411],"category_scores_gemma":[0.20686203,0.0010045824,0.0065155076,0.0022962606,0.0018855454,0.0031511574,0.0031686875,0.0026602536,0.0002771087],"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":[0.004416608,0.0009222813,0.40477645,0.0027415704,0.017606935,0.0006354307,0.0012481303,0.3413566,0.0015832605,0.044868663,0.0033282472,0.17651586],"study_design_scores_gemma":[0.00055396464,0.0022048615,0.083069585,0.00042015634,0.003453458,0.0002827519,0.0004594235,0.8554201,0.0013586504,0.04966504,0.002873417,0.00023859875],"about_ca_topic_score_codex":0.007324865,"about_ca_topic_score_gemma":0.0051558604,"teacher_disagreement_score":0.1324485,"about_ca_system_score_codex":0.001555413,"about_ca_system_score_gemma":0.002878749,"threshold_uncertainty_score":0.70046294},"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":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007967143,0.10140649,0.78514314,0.06898426,0.016966615,0.0015983378,0.0013016266,0.0019643726,0.021838432],"genre_scores_gemma":[0.01756202,0.12797157,0.75115424,0.05076736,0.027315555,0.005346777,0.0010459654,0.0025241289,0.01631245],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.944242,0.046644848,0.003485997,0.0011454342,0.004088386,0.00039345777],"domain_scores_gemma":[0.63384885,0.3488909,0.004457357,0.003158207,0.008537513,0.0011072165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.065755524,0.0036742156,0.002751559,0.005061835,0.00097066985,0.004134932,0.0026726285,0.0063540465,0.02852116],"category_scores_gemma":[0.24159935,0.001525737,0.0048275795,0.004329265,0.0039207186,0.007636169,0.003425744,0.011442958,0.010473419],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026386994,0.00018109813,0.0005376074,0.015779115,0.0006128733,0.00094750786,0.0022497482,0.009159451,0.0011527579,0.21229653,0.44325262,0.31356686],"study_design_scores_gemma":[0.00015002901,0.0001999722,0.0005416336,0.011050028,0.00019164896,0.0012584222,0.00030530166,0.0053236363,0.00085989624,0.4522056,0.5277445,0.00016941472],"about_ca_topic_score_codex":0.0011818329,"about_ca_topic_score_gemma":0.0012446258,"teacher_disagreement_score":0.065755524,"about_ca_system_score_codex":0.0027857213,"about_ca_system_score_gemma":0.004064386,"threshold_uncertainty_score":0.34775263},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44982925,0.0012720937,0.53646153,0.002608266,0.00028047865,0.0014439381,0.0050981524,0.0009739464,0.0020324162],"genre_scores_gemma":[0.8761223,0.0008074426,0.10911019,0.0003952153,0.00017956056,0.0036426876,0.004106625,0.00016640121,0.0054696547],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9833641,0.013464329,0.00042106313,0.0016198162,0.00045187742,0.0006788395],"domain_scores_gemma":[0.93434155,0.055437304,0.0052347463,0.0022755829,0.0017992486,0.00091160875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030378046,0.0017991515,0.002411324,0.0021013122,0.0011793975,0.002141454,0.0037905627,0.002470426,0.0056442413],"category_scores_gemma":[0.055051334,0.0013744661,0.003991706,0.0024329892,0.0017778339,0.001383564,0.0030078955,0.003250337,0.0005614919],"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":[0.0009746585,0.0005720963,0.1771393,0.00055470766,0.0026870805,0.00087713334,0.0015520232,0.7414324,0.0005783355,0.042428635,0.0034386627,0.027764894],"study_design_scores_gemma":[0.00007883464,0.0002329491,0.009314393,0.00005963118,0.00018872674,0.000078322664,0.00016308049,0.9778074,0.000091609174,0.01083064,0.0011148239,0.00003951772],"about_ca_topic_score_codex":0.035418127,"about_ca_topic_score_gemma":0.025558895,"teacher_disagreement_score":0.035418127,"about_ca_system_score_codex":0.0023562866,"about_ca_system_score_gemma":0.002962119,"threshold_uncertainty_score":0.1606564},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20297079,0.0013472917,0.78984654,0.0005690168,0.00013619575,0.0010824999,0.0006665404,0.0009534542,0.0024276497],"genre_scores_gemma":[0.5975777,0.00035752353,0.39959586,0.00016808858,0.000095077616,0.0007704229,0.0010428156,0.0001611285,0.00023136383],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9477492,0.03928997,0.003607374,0.0029459114,0.005625266,0.00078222266],"domain_scores_gemma":[0.7145182,0.26085007,0.0067649693,0.007861379,0.009131012,0.0008744216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.069993146,0.002201317,0.0019671416,0.006034297,0.0012330507,0.0031362935,0.002028805,0.0017358996,0.0012255342],"category_scores_gemma":[0.18132684,0.0007751878,0.0022645819,0.0035496373,0.0015598513,0.0028246804,0.00238795,0.0032194732,0.00046948975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012991757,0.00065430993,0.3081467,0.0015187148,0.0019539602,0.0007931278,0.0011256844,0.349238,0.00906673,0.008053378,0.002224186,0.31592605],"study_design_scores_gemma":[0.00014607262,0.00090126245,0.034950342,0.00047667118,0.00079865096,0.00038650818,0.0005213538,0.9293695,0.012748987,0.016107574,0.0034739042,0.00011910372],"about_ca_topic_score_codex":0.0030307958,"about_ca_topic_score_gemma":0.002915366,"teacher_disagreement_score":0.069993146,"about_ca_system_score_codex":0.0010562722,"about_ca_system_score_gemma":0.0030860605,"threshold_uncertainty_score":0.37016356},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9784493,0.00040353407,0.0019580862,0.00041102947,0.000035985657,0.0017842349,0.0126851825,0.0000800442,0.0041925223],"genre_scores_gemma":[0.9723884,0.0004992232,0.00452566,0.00044815466,0.00002984165,0.0012485324,0.018502526,0.00006879468,0.0022889161],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99277943,0.0015018301,0.0005624553,0.0008234437,0.003148915,0.0011838877],"domain_scores_gemma":[0.95505935,0.005848082,0.0056713964,0.003865267,0.027303446,0.00225253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011548952,0.0009046428,0.000756039,0.0026136627,0.0033211317,0.0017735569,0.002288253,0.000744447,0.001710216],"category_scores_gemma":[0.034835815,0.00063864095,0.0010848457,0.004861144,0.0016924725,0.0009025593,0.0019308287,0.0009867667,0.00075477455],"study_design_candidate":"bench_or_experimental","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":[0.0002265561,0.00013498102,0.9804088,0.00017474307,0.00012206991,0.00014224187,0.0029932144,0.0003187418,0.00040755817,0.00014864418,0.0039057662,0.011016577],"study_design_scores_gemma":[0.00005906902,0.000072404844,0.991122,0.000109303546,0.00008240104,0.000092002454,0.0015068442,0.0018845748,0.00034091494,0.00005717031,0.0046442114,0.00002906962],"about_ca_topic_score_codex":0.97706133,"about_ca_topic_score_gemma":0.98583686,"teacher_disagreement_score":0.025040865,"about_ca_system_score_codex":0.025040865,"about_ca_system_score_gemma":0.05434621,"threshold_uncertainty_score":0.18168503},"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":"protocol","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0220781,0.02945122,0.43708467,0.04578808,0.026550993,0.4230921,0.0036863014,0.0015952113,0.010673218],"genre_scores_gemma":[0.08528386,0.0022027562,0.27771616,0.016812796,0.0017267518,0.61443746,0.00050015684,0.00017880183,0.0011412218],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.11584425,0.79512286,0.051787533,0.013418734,0.022223648,0.0016029014],"domain_scores_gemma":[0.14811839,0.69938046,0.058140162,0.06636619,0.024491677,0.003503055],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7173295,0.0030202472,0.009113482,0.008514314,0.0037424627,0.008456979,0.006745411,0.018348636,0.007937907],"category_scores_gemma":[0.778221,0.0027146898,0.014096016,0.005634266,0.012611528,0.0071732677,0.00566577,0.010703615,0.0022061467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.063718304,0.0021353497,0.045056753,0.17099981,0.03556576,0.0019902482,0.0137984045,0.007812778,0.0018049321,0.26606205,0.09161509,0.2994406],"study_design_scores_gemma":[0.09458508,0.020236468,0.02267618,0.14941226,0.021126045,0.0022828686,0.002437856,0.06175803,0.0071962364,0.3598509,0.2571703,0.0012677409],"about_ca_topic_score_codex":0.0007352711,"about_ca_topic_score_gemma":0.000731994,"teacher_disagreement_score":0.2826705,"about_ca_system_score_codex":0.008555414,"about_ca_system_score_gemma":0.018072749,"threshold_uncertainty_score":0.3485831},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064210887,0.0002423891,0.99256355,0.000093576404,0.000027035052,0.00031124707,0.00010961567,0.000076242526,0.00015538766],"genre_scores_gemma":[0.1679963,0.0005518362,0.8267884,0.00023503842,0.0000728463,0.0027481294,0.00066879374,0.000054823173,0.00088382134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92542475,0.06561477,0.0022953865,0.0036573913,0.0025074296,0.0005001875],"domain_scores_gemma":[0.83889896,0.13677703,0.008092149,0.010577652,0.005038779,0.00061534945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05993408,0.0017303375,0.00268626,0.0017905019,0.00075770076,0.0014743045,0.0038366583,0.0018172943,0.0043031517],"category_scores_gemma":[0.13136423,0.001163003,0.0030197203,0.0020518086,0.0026092874,0.0021841615,0.0029619276,0.0018178758,0.00047387937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014563367,0.00047482408,0.035310883,0.0030697451,0.0027946536,0.0007828115,0.0017689143,0.45147648,0.0016185432,0.23809409,0.003108037,0.26004466],"study_design_scores_gemma":[0.00039626338,0.0006269937,0.0067252405,0.00034104454,0.00034084427,0.00028601984,0.00020453776,0.7872726,0.00079681654,0.19878173,0.0041141417,0.000113867594],"about_ca_topic_score_codex":0.0052331216,"about_ca_topic_score_gemma":0.0031131078,"teacher_disagreement_score":0.9400659,"about_ca_system_score_codex":0.0012188932,"about_ca_system_score_gemma":0.0027918983,"threshold_uncertainty_score":0.31696552},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006240266,0.00020791593,0.9984731,0.000058561436,0.00003232642,0.00007754083,0.000059652706,0.00016363863,0.00030319608],"genre_scores_gemma":[0.076353416,0.0008736144,0.91876113,0.00015109516,0.00025351648,0.0016191836,0.0006397793,0.0004059518,0.0009424073],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9417606,0.04106497,0.0032234539,0.004804831,0.008379127,0.0007671076],"domain_scores_gemma":[0.6026925,0.35458308,0.012568404,0.015035074,0.014097911,0.0010229626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07566302,0.0028929035,0.0033589161,0.010199586,0.001023509,0.004454396,0.006774767,0.0033664107,0.008237605],"category_scores_gemma":[0.35722363,0.0012819933,0.0046018837,0.007053699,0.00417934,0.0047897,0.006180152,0.0073209587,0.0018845818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035562465,0.00019117795,0.010340392,0.0012949035,0.0008974437,0.0006696631,0.0012468662,0.30372158,0.0016525827,0.33499774,0.0050618723,0.33957016],"study_design_scores_gemma":[0.000083543324,0.00019215688,0.001736613,0.00046521265,0.00014503351,0.00043867872,0.00019276993,0.7893004,0.0016491349,0.19792347,0.0077240225,0.00014889246],"about_ca_topic_score_codex":0.00419624,"about_ca_topic_score_gemma":0.0017142418,"teacher_disagreement_score":0.07566302,"about_ca_system_score_codex":0.0021581016,"about_ca_system_score_gemma":0.0027892776,"threshold_uncertainty_score":0.4001491},"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":"protocol","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016218364,0.0003908238,0.020712145,0.0017143344,0.0006286999,0.97104496,0.0016781526,0.0001900606,0.0020189462],"genre_scores_gemma":[0.0010522228,0.00014486378,0.021712178,0.00025403878,0.000052226762,0.97600377,0.0004961446,0.000022090171,0.0002625419],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5980771,0.29308063,0.07331012,0.008390034,0.021048486,0.00609371],"domain_scores_gemma":[0.58810425,0.17705666,0.031534903,0.053299375,0.14063483,0.009369942],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4327235,0.004130805,0.006288987,0.01437641,0.0077960496,0.008704523,0.0068888455,0.010123437,0.029678337],"category_scores_gemma":[0.3865358,0.0046853297,0.0066892416,0.011885535,0.008738736,0.007952035,0.010625182,0.014268923,0.013965845],"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":[0.023350293,0.004611428,0.00778571,0.12759463,0.0012190505,0.0022021944,0.074771166,0.0067710867,0.009082241,0.07461793,0.30871916,0.3592751],"study_design_scores_gemma":[0.028232027,0.005020195,0.020812087,0.08267244,0.0008990574,0.0009767119,0.02330438,0.0080328565,0.0083115725,0.05453847,0.7658719,0.0013283432],"about_ca_topic_score_codex":0.0026411354,"about_ca_topic_score_gemma":0.003498508,"teacher_disagreement_score":0.5672765,"about_ca_system_score_codex":0.014740091,"about_ca_system_score_gemma":0.08464621,"threshold_uncertainty_score":0.69955295},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97724324,0.00014766038,0.004063229,0.00007321516,0.000047816437,0.016736165,0.0004758446,0.00004309938,0.0011698694],"genre_scores_gemma":[0.93543804,0.00037700625,0.02525663,0.00027592864,0.000108789136,0.035880003,0.0012548056,0.000037058144,0.0013717348],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99472755,0.0029716464,0.00046942828,0.00058115495,0.0007675366,0.00048263182],"domain_scores_gemma":[0.99233866,0.0017724822,0.0010339872,0.0015896581,0.0015482482,0.0017168955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013791531,0.0013166299,0.0007310413,0.002575683,0.0024954122,0.00068215985,0.0009550929,0.0010096678,0.0029947858],"category_scores_gemma":[0.009931672,0.0011109986,0.0012704586,0.001109186,0.0010507467,0.0007809261,0.0012826791,0.0013216371,0.0013137495],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027084851,0.03317916,0.9077578,0.0002476979,0.00007091962,0.0010345412,0.007017154,0.00026591093,0.004224949,0.00014665752,0.00085630966,0.04249039],"study_design_scores_gemma":[0.0012795861,0.04732451,0.9418307,0.000067187866,0.000075619624,0.0008418495,0.004897748,0.00080611947,0.0009796257,0.00012246729,0.0016998773,0.00007472294],"about_ca_topic_score_codex":0.0042911693,"about_ca_topic_score_gemma":0.008114727,"teacher_disagreement_score":0.013791531,"about_ca_system_score_codex":0.0007003042,"about_ca_system_score_gemma":0.0030395759,"threshold_uncertainty_score":0.07293749},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2593162,0.029823724,0.6866794,0.0035273575,0.001370805,0.013987062,0.00084478344,0.00048533257,0.0039653056],"genre_scores_gemma":[0.7622264,0.0033041039,0.21771027,0.0014468686,0.00049281336,0.013166605,0.00056911685,0.00014259858,0.00094114343],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.4682651,0.5094813,0.008098192,0.005590676,0.007838337,0.0007263743],"domain_scores_gemma":[0.114303924,0.83932865,0.020318914,0.020984914,0.0040526125,0.0010109323],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.49359316,0.0024888583,0.0048838784,0.0027773173,0.0006234192,0.00282926,0.0044215424,0.004908514,0.0040602763],"category_scores_gemma":[0.5779218,0.00097145577,0.0104667,0.0020492657,0.003986475,0.0037303306,0.00312426,0.005496597,0.00034307767],"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":[0.19183253,0.005321181,0.07293262,0.015083711,0.108492315,0.0008287356,0.0023289016,0.26537025,0.0014707269,0.08318289,0.0059951926,0.24716093],"study_design_scores_gemma":[0.057353117,0.03813259,0.022239197,0.0029815317,0.022907695,0.0007843798,0.0004671826,0.765723,0.0013925413,0.0813197,0.0063131456,0.00038589755],"about_ca_topic_score_codex":0.00090483465,"about_ca_topic_score_gemma":0.0005161621,"teacher_disagreement_score":0.50640684,"about_ca_system_score_codex":0.0026746513,"about_ca_system_score_gemma":0.002738701,"threshold_uncertainty_score":0.62448984},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.902643,0.014196355,0.039592937,0.019661443,0.0005076771,0.008726291,0.0023653698,0.00027271936,0.012034159],"genre_scores_gemma":[0.97658086,0.0006986763,0.018382195,0.0015095056,0.000104881874,0.0023724732,0.00018605415,0.000015647629,0.00014974129],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.5834768,0.36626852,0.024697278,0.0039231693,0.020138022,0.0014963265],"domain_scores_gemma":[0.10201335,0.83633876,0.03753706,0.0077458373,0.014798204,0.0015669054],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30494505,0.00046202407,0.0013969411,0.0022470376,0.00049573864,0.0016466986,0.0012458984,0.0022877227,0.0037954866],"category_scores_gemma":[0.7038611,0.0005157529,0.0028466673,0.0023175385,0.0019668308,0.0025065085,0.0011082692,0.0017759469,0.00038744195],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019056119,0.0018679128,0.66097933,0.010785302,0.0035609528,0.00023420274,0.009380711,0.00537725,0.0011358133,0.0015928915,0.0043342886,0.28169525],"study_design_scores_gemma":[0.004817735,0.028522516,0.92645264,0.0031206508,0.003696227,0.00031665913,0.004680606,0.01653008,0.0019264333,0.002140803,0.007588126,0.0002075259],"about_ca_topic_score_codex":0.0047091614,"about_ca_topic_score_gemma":0.002987481,"teacher_disagreement_score":0.69505495,"about_ca_system_score_codex":0.0039287605,"about_ca_system_score_gemma":0.004661062,"threshold_uncertainty_score":0.8571265},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23877895,0.6887083,0.042642485,0.0019123614,0.004557591,0.016320683,0.002438383,0.0012198334,0.0034213993],"genre_scores_gemma":[0.92346925,0.036320012,0.021155877,0.0018790304,0.00044673766,0.014630479,0.0008113329,0.00016273583,0.0011244942],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9309515,0.052059487,0.0087598525,0.005008145,0.0025049953,0.00071607635],"domain_scores_gemma":[0.85707045,0.12162036,0.009738191,0.007901622,0.0028927021,0.0007766795],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.082787365,0.0039457856,0.014099051,0.0023143555,0.0011093629,0.0034974858,0.0023830882,0.004760619,0.0050612926],"category_scores_gemma":[0.12317408,0.0021704847,0.04822982,0.0023292424,0.002548688,0.0034363954,0.0018560843,0.003332405,0.0004092968],"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":[0.060571726,0.00039481153,0.003584976,0.04881335,0.8745777,0.00012134157,0.00021775677,0.0006000079,0.0005566317,0.00027497936,0.00043951368,0.009847301],"study_design_scores_gemma":[0.016532855,0.0031872245,0.0023588287,0.002094623,0.97312886,0.000065307475,0.0000549049,0.00061611616,0.00036710416,0.0007902311,0.0007515236,0.000052430358],"about_ca_topic_score_codex":0.0025318651,"about_ca_topic_score_gemma":0.0034843595,"teacher_disagreement_score":0.9172126,"about_ca_system_score_codex":0.0028740515,"about_ca_system_score_gemma":0.0021147511,"threshold_uncertainty_score":0.4378267},"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":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986349,0.0076562045,0.00096387276,0.0016991451,0.00012574047,0.00038483567,0.0010519639,0.00003512055,0.001734215],"genre_scores_gemma":[0.99726665,0.0009953562,0.0005901093,0.00019181117,0.00015566322,0.0001346517,0.0004348883,0.000013836611,0.00021703776],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9553264,0.017983444,0.013960953,0.0018562741,0.0098128505,0.0010602059],"domain_scores_gemma":[0.564538,0.1782784,0.21669312,0.009610649,0.019193908,0.011685868],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.051749986,0.0004960222,0.0011977308,0.005005803,0.00055066514,0.0028498352,0.00085354084,0.0011640154,0.0048423368],"category_scores_gemma":[0.16455258,0.00044218602,0.0021802264,0.0044538416,0.0006988265,0.0019420765,0.0015663868,0.0015633479,0.0007485953],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005577216,0.00010376885,0.9905482,0.0005399677,0.0009391862,0.0001029349,0.00043456527,0.000071067385,0.00028169606,0.000047077127,0.0006128946,0.0057610176],"study_design_scores_gemma":[0.000045530076,0.00041876946,0.9973853,0.00016927693,0.00024939445,0.00042455964,0.00031346592,0.00019505946,0.00008229475,0.000070666065,0.00062621717,0.000019388519],"about_ca_topic_score_codex":0.0005932729,"about_ca_topic_score_gemma":0.0006453124,"teacher_disagreement_score":0.94825,"about_ca_system_score_codex":0.0007202568,"about_ca_system_score_gemma":0.0011032657,"threshold_uncertainty_score":0.27368337},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5200224,0.007986601,0.45664302,0.0034354106,0.00077489455,0.0025376973,0.0034760586,0.0010103326,0.0041135424],"genre_scores_gemma":[0.8706078,0.00069580827,0.123041354,0.0009345977,0.0002303898,0.0013110583,0.0023835457,0.00018099515,0.00061450584],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.6504805,0.29612404,0.019644944,0.013322733,0.018668426,0.0017592995],"domain_scores_gemma":[0.13233571,0.80557716,0.027187916,0.02108588,0.013268394,0.00054485956],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29205847,0.0012514222,0.0013553784,0.0035638704,0.0014615441,0.003109443,0.0026228526,0.0033539427,0.001347696],"category_scores_gemma":[0.62197036,0.0008683711,0.0036039576,0.00530771,0.003180064,0.0032863175,0.003829881,0.002096628,0.00027779886],"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":[0.0034900869,0.00036153893,0.63713574,0.0026008633,0.008001065,0.00058356026,0.0036576164,0.17876813,0.0011278931,0.016521739,0.003997956,0.14375383],"study_design_scores_gemma":[0.0015011843,0.0035430386,0.26304495,0.0042575416,0.0066051204,0.002989262,0.0021828318,0.5890253,0.016703418,0.090931125,0.018554255,0.0006618709],"about_ca_topic_score_codex":0.0057977396,"about_ca_topic_score_gemma":0.0038324255,"teacher_disagreement_score":0.70794153,"about_ca_system_score_codex":0.0032730338,"about_ca_system_score_gemma":0.0026248728,"threshold_uncertainty_score":0.87301797},"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":"protocol","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036459526,0.068838574,0.27810758,0.022895223,0.009012583,0.60106677,0.007619565,0.0011073853,0.0077063567],"genre_scores_gemma":[0.010446629,0.006849863,0.3860991,0.0029034477,0.00048826457,0.5913197,0.0012972732,0.00015545609,0.00044030749],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.13530968,0.46555042,0.33440667,0.013025553,0.048867166,0.002840489],"domain_scores_gemma":[0.13147998,0.55499226,0.09784146,0.052708846,0.15750578,0.0054717315],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.71292996,0.0066220956,0.021295054,0.043886516,0.008797211,0.017181708,0.01602911,0.019749874,0.014288198],"category_scores_gemma":[0.81118345,0.007635548,0.03722274,0.0340169,0.011900413,0.014844857,0.016473187,0.016458547,0.0052004154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002343797,0.00022298867,0.0038403843,0.73203135,0.016182944,0.00060820923,0.01641672,0.002352082,0.0010773937,0.03695556,0.039285388,0.14868318],"study_design_scores_gemma":[0.008120643,0.00093827,0.0059087467,0.7149064,0.0238961,0.0009505517,0.0048620463,0.0067633055,0.0024732833,0.113572486,0.11676212,0.0008460556],"about_ca_topic_score_codex":0.004558796,"about_ca_topic_score_gemma":0.0059397006,"teacher_disagreement_score":0.28707004,"about_ca_system_score_codex":0.021030243,"about_ca_system_score_gemma":0.07340462,"threshold_uncertainty_score":0.3540085},"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":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01976767,0.11397225,0.682302,0.030537639,0.0034027123,0.13955848,0.0029786888,0.000708926,0.0067716455],"genre_scores_gemma":[0.07547943,0.014780953,0.8239592,0.0018211831,0.00058529474,0.08227416,0.0008601634,0.00009378962,0.00014589535],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.056277335,0.76364183,0.14426894,0.0067962045,0.02777375,0.0012420077],"domain_scores_gemma":[0.04201856,0.82564294,0.058412213,0.028257497,0.043909337,0.0017593895],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.81406754,0.00432871,0.016740402,0.06363496,0.005077478,0.02623626,0.009325441,0.007885204,0.0050568376],"category_scores_gemma":[0.9086129,0.0041335816,0.018720366,0.045033917,0.010565238,0.018136939,0.018738844,0.0080964025,0.0010095374],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024314937,0.0004932051,0.011171272,0.3744179,0.014981495,0.00025988743,0.021814516,0.008689097,0.0011577214,0.047496673,0.011231019,0.50585574],"study_design_scores_gemma":[0.0072165783,0.0025482364,0.019361185,0.54504466,0.02617901,0.00067602535,0.014645821,0.035966948,0.004163116,0.2785553,0.06416344,0.001479706],"about_ca_topic_score_codex":0.004045802,"about_ca_topic_score_gemma":0.0041461275,"teacher_disagreement_score":0.18593246,"about_ca_system_score_codex":0.028507408,"about_ca_system_score_gemma":0.05292981,"threshold_uncertainty_score":0.22928786},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4865938,0.001796046,0.4994492,0.0016890483,0.00026959076,0.00033084137,0.00069313706,0.000685051,0.008493198],"genre_scores_gemma":[0.9730249,0.00013441859,0.02581284,0.00013994929,0.000078572375,0.0001300775,0.00023731486,0.00009507892,0.00034697822],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94376576,0.039323457,0.0023462127,0.006124461,0.007392852,0.0010472593],"domain_scores_gemma":[0.42653665,0.52315915,0.024588179,0.0156142665,0.008780859,0.0013208726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.063414074,0.0010493002,0.002015884,0.004334131,0.0010211233,0.0038239986,0.0029705437,0.0022748811,0.0018643314],"category_scores_gemma":[0.41640103,0.0007895849,0.0018365363,0.0037095486,0.0045585237,0.0025451535,0.0027849704,0.0028440806,0.0004232976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011873535,0.00017966364,0.6331563,0.00066919986,0.0016315879,0.0026024107,0.0016958389,0.25305614,0.0014413433,0.04699138,0.0033198227,0.054068964],"study_design_scores_gemma":[0.00011199988,0.00036614446,0.08314411,0.0002630237,0.00042647586,0.0033686978,0.00059811445,0.80020887,0.0026688916,0.10611293,0.0024935473,0.00023711413],"about_ca_topic_score_codex":0.007884999,"about_ca_topic_score_gemma":0.0033878363,"teacher_disagreement_score":0.063414074,"about_ca_system_score_codex":0.0029474532,"about_ca_system_score_gemma":0.0032995215,"threshold_uncertainty_score":0.3353697},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99300694,0.00035848355,0.0032999194,0.00006270883,0.000039606963,0.0006786057,0.00059599645,0.00006602195,0.001891817],"genre_scores_gemma":[0.99088097,0.00017237238,0.005845857,0.0000674581,0.000019525838,0.00095132034,0.0010200387,0.000025828167,0.0010167245],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985447,0.0004154417,0.0002344657,0.00023960417,0.00045471787,0.00011109089],"domain_scores_gemma":[0.99443495,0.0015750548,0.0015760614,0.00037170353,0.0016842815,0.00035795008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037039097,0.00088552514,0.00055093155,0.0012248071,0.00030788127,0.0004922246,0.0004951105,0.00048144796,0.0017908324],"category_scores_gemma":[0.0092525175,0.0003649408,0.0009026436,0.00070504635,0.00059644785,0.000613831,0.0010155627,0.0006705927,0.00056133076],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042473194,0.001251485,0.89507794,0.00045396146,0.0010194733,0.00025118043,0.0033252446,0.0014064243,0.010283082,0.00037795646,0.0021458974,0.080160014],"study_design_scores_gemma":[0.00016515797,0.0016092359,0.9945623,0.00002098911,0.0000685938,0.0002578367,0.00034997036,0.00084580196,0.0012767802,0.00011569316,0.0006998723,0.000027741638],"about_ca_topic_score_codex":0.0021232732,"about_ca_topic_score_gemma":0.0031108013,"teacher_disagreement_score":0.0037039097,"about_ca_system_score_codex":0.00049095426,"about_ca_system_score_gemma":0.0006686026,"threshold_uncertainty_score":0.019588351},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035569273,0.03008988,0.497026,0.39743927,0.008689503,0.009536188,0.00023146719,0.0013917686,0.020026568],"genre_scores_gemma":[0.1567288,0.014421245,0.76822746,0.04144674,0.0014131817,0.010045737,0.00023842744,0.0011397585,0.0063387193],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.3691778,0.5525138,0.026763523,0.01306238,0.033619754,0.0048627863],"domain_scores_gemma":[0.2404796,0.5914722,0.015986517,0.026441991,0.10460866,0.021011027],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5355895,0.0019885388,0.0034573593,0.011781084,0.01895926,0.029969435,0.009745809,0.014124504,0.0042710863],"category_scores_gemma":[0.55468434,0.002681474,0.003456012,0.012731743,0.031375054,0.0317538,0.041622695,0.028359704,0.0017033817],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013229655,0.00031576405,0.0017558624,0.0059895352,0.00020217706,0.0027184854,0.74987465,0.0015763454,0.002294359,0.031855665,0.050334956,0.15294985],"study_design_scores_gemma":[0.00016767373,0.00030943827,0.001286738,0.035759803,0.00019247552,0.0032654516,0.27499834,0.0037300133,0.001698576,0.07403508,0.60402113,0.0005352894],"about_ca_topic_score_codex":0.011327961,"about_ca_topic_score_gemma":0.019949066,"teacher_disagreement_score":0.46441048,"about_ca_system_score_codex":0.022789825,"about_ca_system_score_gemma":0.07712346,"threshold_uncertainty_score":0.57270086},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02764668,0.00028073278,0.96142477,0.00035329038,0.00007818861,0.004126267,0.0004995614,0.0028659003,0.0027246156],"genre_scores_gemma":[0.15531485,0.00014994729,0.8353669,0.00029024854,0.000043064276,0.0072527723,0.00053798145,0.000347391,0.00069685397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9722654,0.019962339,0.0033284163,0.001479428,0.0025575121,0.0004068926],"domain_scores_gemma":[0.80525017,0.17095377,0.010828717,0.004428797,0.0075457036,0.0009928601],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05701211,0.0020271528,0.0013885358,0.0028848092,0.0005595536,0.0024251277,0.0018625091,0.0019552389,0.0028292856],"category_scores_gemma":[0.1642898,0.0010232326,0.0015604292,0.0013581307,0.00073323946,0.0012849077,0.0009694966,0.002861221,0.00070153933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052587064,0.00064892,0.019560967,0.0017778821,0.0010192825,0.0007673701,0.0016151102,0.56195277,0.006067078,0.04951192,0.011956371,0.33986366],"study_design_scores_gemma":[0.0016026594,0.0011639441,0.001907748,0.0005653007,0.0004476287,0.00041384937,0.000057336485,0.938485,0.011424062,0.033272266,0.010555182,0.000104934246],"about_ca_topic_score_codex":0.0006953418,"about_ca_topic_score_gemma":0.00076924823,"teacher_disagreement_score":0.9429879,"about_ca_system_score_codex":0.0015031749,"about_ca_system_score_gemma":0.002923799,"threshold_uncertainty_score":0.30151248},"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":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12414374,0.026320817,0.6961196,0.010136011,0.003042367,0.10578271,0.017677488,0.004285973,0.012491364],"genre_scores_gemma":[0.0753646,0.0029240523,0.8470699,0.0006936859,0.000212756,0.07111725,0.0022401812,0.00011806901,0.0002594425],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.52263796,0.25677937,0.15844038,0.0068618385,0.053369775,0.0019107502],"domain_scores_gemma":[0.32733694,0.4491354,0.08914601,0.017142965,0.11421607,0.0030226677],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3607968,0.0021769581,0.004791025,0.03299159,0.0015552901,0.005359479,0.002823856,0.0018874059,0.0037627458],"category_scores_gemma":[0.56334716,0.0018730611,0.012828415,0.017586,0.00237412,0.007865029,0.009215215,0.003740998,0.00080975087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018780743,0.00050991547,0.09192929,0.093266256,0.015223765,0.00025244596,0.01002047,0.006193798,0.0031429247,0.010783299,0.030004937,0.7367949],"study_design_scores_gemma":[0.00855141,0.015680794,0.42033538,0.11209301,0.035101168,0.0037534048,0.015530146,0.07555295,0.014782898,0.08215819,0.21398464,0.00247611],"about_ca_topic_score_codex":0.0008099535,"about_ca_topic_score_gemma":0.001785037,"teacher_disagreement_score":0.6392032,"about_ca_system_score_codex":0.00572067,"about_ca_system_score_gemma":0.016658649,"threshold_uncertainty_score":0.78825134},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88373876,0.0053988793,0.042782307,0.016780723,0.0011788948,0.0031319782,0.0008672739,0.000116779935,0.0460044],"genre_scores_gemma":[0.97113377,0.0006814209,0.023523875,0.0013091712,0.00015082119,0.002001031,0.00027275286,0.000025504725,0.0009016215],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.85173255,0.09108843,0.008152493,0.0056259898,0.03963683,0.0037637958],"domain_scores_gemma":[0.60144526,0.27297148,0.020737732,0.019076975,0.08211678,0.0036517556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14660041,0.00085909176,0.0008472323,0.0065321163,0.0046988227,0.006028777,0.004539341,0.0022633409,0.0016956829],"category_scores_gemma":[0.36670518,0.0008857416,0.001797077,0.006519135,0.0126819955,0.0048661907,0.008414039,0.0033236486,0.00032037523],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006658543,0.0003755576,0.7679899,0.0012364938,0.00044248824,0.00038120232,0.035237484,0.0025120622,0.00046694014,0.024830533,0.0042400733,0.16162145],"study_design_scores_gemma":[0.00038683892,0.0012982956,0.8433437,0.008631354,0.00060863124,0.00062415464,0.046261992,0.021169065,0.003054436,0.032244682,0.04202457,0.00035220772],"about_ca_topic_score_codex":0.27891862,"about_ca_topic_score_gemma":0.29024318,"teacher_disagreement_score":0.27891862,"about_ca_system_score_codex":0.016333539,"about_ca_system_score_gemma":0.034855068,"threshold_uncertainty_score":0.77530634},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008062385,0.17925595,0.56279534,0.14679876,0.02775531,0.050102517,0.0010255394,0.0011859582,0.023018239],"genre_scores_gemma":[0.23143342,0.035253063,0.5296068,0.06436407,0.012953137,0.1231184,0.0005588781,0.00079338235,0.0019188605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.03658195,0.87342167,0.0475639,0.008289164,0.033281397,0.0008619436],"domain_scores_gemma":[0.02388983,0.9024955,0.020762747,0.032904282,0.018571878,0.0013757795],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.86487913,0.005154097,0.023198329,0.014528027,0.006785155,0.026545586,0.011619586,0.023152526,0.0056220996],"category_scores_gemma":[0.91179955,0.005714611,0.0073754303,0.018002741,0.06553046,0.020642413,0.01523282,0.025847424,0.0018388045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069258166,0.0007393655,0.011251028,0.09352103,0.016969793,0.0011041727,0.015307137,0.009867526,0.00070420146,0.4882327,0.038497817,0.31687948],"study_design_scores_gemma":[0.008521035,0.0029713337,0.006677517,0.09117609,0.0040253513,0.0011990673,0.0024256408,0.023268886,0.0012510199,0.78365797,0.07395046,0.0008757459],"about_ca_topic_score_codex":0.005381083,"about_ca_topic_score_gemma":0.0034693386,"teacher_disagreement_score":0.13512087,"about_ca_system_score_codex":0.029653128,"about_ca_system_score_gemma":0.04306285,"threshold_uncertainty_score":0.21514952},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81182885,0.0006012304,0.1651654,0.0013246813,0.00014594241,0.00022152133,0.0007524668,0.00020151751,0.019758383],"genre_scores_gemma":[0.9847143,0.00023977908,0.010841111,0.00008280981,0.000029246332,0.00022439739,0.00017176782,0.00001942856,0.0036771437],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995832,0.00017028599,0.000019425537,0.00010363177,0.000045750716,0.00007767599],"domain_scores_gemma":[0.99787486,0.0013921319,0.00025620052,0.00008530123,0.00021410949,0.00017734867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005776698,0.000703686,0.00094368303,0.0009433199,0.0011842054,0.0018023314,0.0016893679,0.0019171989,0.0040114303],"category_scores_gemma":[0.003169567,0.00053848996,0.0015350019,0.00070603716,0.0014314723,0.0012294457,0.0013423759,0.0011647552,0.00030847243],"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":[0.000039311522,0.00006254459,0.008355109,0.00003249797,0.00007616647,0.00015989503,0.0002632259,0.97918975,0.0005295845,0.009250256,0.00026727986,0.001774362],"study_design_scores_gemma":[0.000008684563,0.000022687931,0.00090062706,0.0000067533856,0.000021851672,0.000015884685,0.00008646973,0.9960563,0.000046203728,0.002597436,0.00022769898,0.000009393233],"about_ca_topic_score_codex":0.053314257,"about_ca_topic_score_gemma":0.026826711,"teacher_disagreement_score":0.053314257,"about_ca_system_score_codex":0.0023308874,"about_ca_system_score_gemma":0.0016188349,"threshold_uncertainty_score":0.106007874},"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":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027176563,0.10159424,0.8193164,0.008292196,0.0065467893,0.022402428,0.0036367811,0.0023166563,0.008717937],"genre_scores_gemma":[0.26034078,0.014887365,0.67837656,0.0040313667,0.0021363413,0.036465622,0.001858568,0.0010476012,0.0008557986],"study_design_codex":"meta_analysis","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.2451612,0.5943972,0.10874122,0.017792435,0.032867067,0.0010408774],"domain_scores_gemma":[0.18550251,0.66527927,0.05612739,0.075263314,0.016783873,0.0010436424],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.55568403,0.0046726987,0.0225077,0.016068552,0.0028154736,0.013520334,0.008544864,0.0071545807,0.004187142],"category_scores_gemma":[0.8295765,0.004775481,0.034638014,0.019351447,0.004851152,0.014005722,0.0074106664,0.007901298,0.0009599476],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013703746,0.0007546655,0.045046013,0.17945647,0.36055517,0.0010893185,0.0042024916,0.02069317,0.0026483636,0.041592907,0.012678541,0.31757915],"study_design_scores_gemma":[0.023566445,0.0052630575,0.024381181,0.0798037,0.50703543,0.0018832604,0.0007401799,0.04200753,0.008407483,0.23440209,0.070873335,0.0016363617],"about_ca_topic_score_codex":0.00094246643,"about_ca_topic_score_gemma":0.0014457427,"teacher_disagreement_score":0.44431597,"about_ca_system_score_codex":0.0028833777,"about_ca_system_score_gemma":0.008578016,"threshold_uncertainty_score":0.5479207},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29042038,0.0055190385,0.6902064,0.0020434044,0.00030265222,0.004941569,0.0015608758,0.0007868648,0.0042187823],"genre_scores_gemma":[0.79377294,0.0013874776,0.19553514,0.000747883,0.00006869786,0.006720825,0.00088145764,0.0001127215,0.00077279715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.88574255,0.10791375,0.0015341921,0.0023892864,0.0016391651,0.00078111235],"domain_scores_gemma":[0.45629117,0.50962704,0.014272471,0.010741086,0.0072604246,0.0018078454],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13562527,0.0016926071,0.0035122493,0.0021661546,0.00064976787,0.0019608205,0.0036363895,0.0032060412,0.0037732024],"category_scores_gemma":[0.26674107,0.0009493885,0.0052569536,0.002452356,0.0014324649,0.002363052,0.0019053383,0.0040278593,0.00034410128],"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":[0.005868522,0.0004332179,0.009583408,0.00077350845,0.002892413,0.00021072944,0.00031015568,0.94495326,0.00011864003,0.017956514,0.0015810113,0.015318763],"study_design_scores_gemma":[0.0013391706,0.0012773783,0.0013322924,0.00028660294,0.0006425956,0.00012875895,0.00007990297,0.98037845,0.00015061762,0.01347483,0.0008441485,0.00006529724],"about_ca_topic_score_codex":0.006895062,"about_ca_topic_score_gemma":0.004224677,"teacher_disagreement_score":0.86437476,"about_ca_system_score_codex":0.0034802528,"about_ca_system_score_gemma":0.004553958,"threshold_uncertainty_score":0.7172636},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964336,0.00007690505,0.0020746926,0.00013797742,0.0000073308574,0.00061106187,0.00017604163,0.000017944194,0.00046443907],"genre_scores_gemma":[0.9964812,0.00004511376,0.0022297394,0.0001434964,0.0000072478288,0.0008097394,0.00016196401,0.000006952668,0.00011451075],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9621013,0.029857589,0.0021121942,0.001672937,0.0024052907,0.0018507589],"domain_scores_gemma":[0.96048456,0.013059435,0.013347309,0.007157878,0.0032243242,0.0027264678],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032217093,0.0004508116,0.00040022822,0.0010483713,0.001746299,0.0010593039,0.0011623756,0.0011538079,0.000819134],"category_scores_gemma":[0.05005582,0.00057391875,0.0007569556,0.0011582931,0.0010782948,0.0012801107,0.001999066,0.0014512042,0.0004808602],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002232539,0.0012220087,0.98282003,0.00005178306,0.000058711485,0.00013205197,0.0075327423,0.000070040296,0.00045271343,0.00009499924,0.0004406344,0.006900913],"study_design_scores_gemma":[0.00008095441,0.0023114278,0.9861313,0.000052013453,0.00004473836,0.00031781895,0.008534527,0.00055690063,0.000590049,0.000093322466,0.0012553169,0.000031546067],"about_ca_topic_score_codex":0.0059299953,"about_ca_topic_score_gemma":0.0071579516,"teacher_disagreement_score":0.9677829,"about_ca_system_score_codex":0.001016953,"about_ca_system_score_gemma":0.0028325242,"threshold_uncertainty_score":0.17038232},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9688098,0.00062876975,0.024011806,0.000604494,0.000073383046,0.0015824405,0.0012124537,0.00016823871,0.0029086347],"genre_scores_gemma":[0.95133966,0.00023452853,0.044791233,0.0001244561,0.000031484327,0.0011459269,0.0021090594,0.000036522808,0.0001869744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9346322,0.04672435,0.0075007244,0.0032493055,0.0072293053,0.0006641399],"domain_scores_gemma":[0.79994994,0.11474266,0.046613585,0.014551167,0.022988975,0.0011537494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.089249656,0.00058935006,0.00080840633,0.0035388798,0.0005644371,0.0024907922,0.0015616786,0.0006945927,0.0007042338],"category_scores_gemma":[0.20026688,0.00034247836,0.0010890882,0.0025876556,0.00071086304,0.0017137905,0.0018715496,0.0010439771,0.00023937762],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005861276,0.00019611938,0.9581891,0.00013843973,0.00029083222,0.000024271489,0.0005675374,0.0045670737,0.00020751903,0.000773311,0.00070117874,0.033758458],"study_design_scores_gemma":[0.000582642,0.0023517548,0.84300995,0.00069937104,0.0010178803,0.0006560407,0.0016953124,0.13438362,0.004976057,0.0031312208,0.0073742387,0.00012195142],"about_ca_topic_score_codex":0.0032132934,"about_ca_topic_score_gemma":0.0028683587,"teacher_disagreement_score":0.089249656,"about_ca_system_score_codex":0.0023930704,"about_ca_system_score_gemma":0.004378845,"threshold_uncertainty_score":0.47200292},"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":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030434603,0.0014672565,0.00892914,0.0023292864,0.0017987243,0.9784743,0.0052483096,0.00028323295,0.0011653926],"genre_scores_gemma":[0.00039381717,0.00057087315,0.022479692,0.00044947673,0.000083165774,0.97521985,0.0004698871,0.00003199234,0.00030129368],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.7218143,0.15071782,0.08680318,0.013387648,0.021951113,0.005325964],"domain_scores_gemma":[0.6214106,0.14425656,0.0553868,0.030275246,0.13828759,0.010383119],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27037862,0.007534708,0.01738077,0.024397312,0.0077226837,0.014475765,0.0068992563,0.01645894,0.07748408],"category_scores_gemma":[0.4245497,0.0070272675,0.022122644,0.02076354,0.010449445,0.015897334,0.010377898,0.016220111,0.025817417],"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":[0.0061199083,0.0005876285,0.0013059521,0.61460036,0.0025905017,0.00091779884,0.008677777,0.0030243937,0.0030784118,0.025391823,0.18048847,0.15321702],"study_design_scores_gemma":[0.016517151,0.0013413598,0.0030374024,0.5424261,0.0036687332,0.00051003636,0.004645639,0.004134643,0.0049576503,0.0478782,0.37000418,0.0008788861],"about_ca_topic_score_codex":0.004447721,"about_ca_topic_score_gemma":0.005915512,"teacher_disagreement_score":0.7296214,"about_ca_system_score_codex":0.020809844,"about_ca_system_score_gemma":0.08461033,"threshold_uncertainty_score":0.8997531},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5064818,0.020821938,0.42496926,0.022576313,0.0008624402,0.013298683,0.002711459,0.00028086774,0.007997299],"genre_scores_gemma":[0.90666276,0.0013997579,0.08164802,0.0016887605,0.00018692572,0.0071419994,0.00042776234,0.000032145253,0.0008118761],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6978582,0.25667432,0.012688015,0.008392838,0.02233887,0.0020478657],"domain_scores_gemma":[0.6937566,0.203442,0.060991652,0.025720574,0.01457522,0.0015139659],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1998687,0.0009926746,0.001278316,0.0035360693,0.0041119754,0.0027958187,0.0042038565,0.0017876705,0.0008185058],"category_scores_gemma":[0.37107378,0.0009582302,0.002565341,0.0053330576,0.005789236,0.0012337639,0.0036906416,0.0014137311,0.00007221081],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010119984,0.00020849858,0.86258924,0.0027153795,0.009742434,0.0006123072,0.013998138,0.013436464,0.0006127179,0.033385392,0.0030168537,0.058670424],"study_design_scores_gemma":[0.0015893233,0.0009646667,0.86032313,0.0024777832,0.005890504,0.00066334783,0.0054219235,0.047126204,0.0014816792,0.056097705,0.017596439,0.0003673052],"about_ca_topic_score_codex":0.41742426,"about_ca_topic_score_gemma":0.39862347,"teacher_disagreement_score":0.8001313,"about_ca_system_score_codex":0.020249095,"about_ca_system_score_gemma":0.02840294,"threshold_uncertainty_score":0.98670435},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06147048,0.9044094,0.004907851,0.013746804,0.000931064,0.0062332116,0.0011029661,0.00004539981,0.007152884],"genre_scores_gemma":[0.22147961,0.7456043,0.011138345,0.007826073,0.00040399414,0.012010867,0.00082455686,0.00003487538,0.0006773696],"study_design_codex":"systematic_review","study_design_gemma":"qualitative","domain_scores_codex":[0.89152354,0.076547,0.018070526,0.002832102,0.009136947,0.0018899046],"domain_scores_gemma":[0.6977133,0.25336084,0.017395793,0.0026530158,0.027043229,0.0018337409],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11814126,0.0012883027,0.0036675907,0.036668688,0.0038847572,0.005727585,0.0025379092,0.0035890753,0.003706376],"category_scores_gemma":[0.1926962,0.0015008092,0.003556811,0.028837781,0.0032314155,0.010617481,0.0054034265,0.0024831623,0.00063839054],"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":[0.00035140442,0.00023320434,0.008434085,0.6038317,0.0017240952,0.0026920664,0.17974776,0.00033704663,0.0009560197,0.006646051,0.011452377,0.18359418],"study_design_scores_gemma":[0.00012363704,0.00037592935,0.00886682,0.7511063,0.0039293477,0.0016293925,0.1555605,0.0001983848,0.00052846264,0.001920538,0.07563483,0.00012581013],"about_ca_topic_score_codex":0.0069035375,"about_ca_topic_score_gemma":0.0152005935,"teacher_disagreement_score":0.8818587,"about_ca_system_score_codex":0.0133088445,"about_ca_system_score_gemma":0.029821444,"threshold_uncertainty_score":0.6247982},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57055986,0.028426513,0.061438315,0.00493614,0.012710626,0.3078125,0.001960082,0.0020159462,0.010139977],"genre_scores_gemma":[0.7086195,0.0032579661,0.06881666,0.002487597,0.0012767124,0.21303628,0.0004533518,0.00006775248,0.0019841518],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.90762913,0.07685909,0.006801575,0.0035066747,0.0039464296,0.0012572173],"domain_scores_gemma":[0.87715244,0.09339362,0.015948215,0.0061956565,0.004545664,0.0027644578],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07523524,0.0027218743,0.0048053176,0.0019901234,0.0013675373,0.0022745132,0.0022707474,0.0065708575,0.012603959],"category_scores_gemma":[0.11498793,0.0012355478,0.0040479526,0.0019217061,0.0036828525,0.0038222608,0.0015665524,0.0037939653,0.00094925694],"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":[0.9286784,0.012791424,0.0010658976,0.009139239,0.00425601,0.000084019026,0.0003634121,0.00081940443,0.0008579418,0.0023937568,0.0009803826,0.03857014],"study_design_scores_gemma":[0.78425163,0.2045864,0.0011579498,0.001274835,0.0024957117,0.000043181717,0.000103611565,0.0017835307,0.0007102274,0.0019463341,0.0015937428,0.000052853535],"about_ca_topic_score_codex":0.0009793269,"about_ca_topic_score_gemma":0.00081840367,"teacher_disagreement_score":0.92476475,"about_ca_system_score_codex":0.002115947,"about_ca_system_score_gemma":0.0048696697,"threshold_uncertainty_score":0.39788675},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011664946,0.93473756,0.016802296,0.0036715565,0.0016529807,0.029570265,0.010085373,0.00035982372,0.00195363],"genre_scores_gemma":[0.01841623,0.7767292,0.06395203,0.0029209151,0.00065320096,0.13121039,0.005143618,0.00020972366,0.0007646669],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.63420826,0.16560143,0.15897901,0.010373973,0.028316045,0.0025213491],"domain_scores_gemma":[0.48589876,0.39126065,0.06926795,0.012724164,0.03911122,0.0017372876],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19799879,0.005980721,0.023383602,0.05860134,0.0023131212,0.010911722,0.0067838696,0.005617708,0.016624706],"category_scores_gemma":[0.48231146,0.005369611,0.025776273,0.042292904,0.004005822,0.010560842,0.009614418,0.0044997744,0.0025782234],"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":[0.0001302313,0.0000073692167,0.00024203288,0.9668423,0.0047430717,0.00003171567,0.0003047887,0.00016890206,0.00009724487,0.0006297481,0.0016877535,0.025114829],"study_design_scores_gemma":[0.00018594891,0.00007136547,0.00061481557,0.96322787,0.017553654,0.00007660634,0.00019988236,0.0001432499,0.00020106275,0.001193176,0.016491374,0.000040821],"about_ca_topic_score_codex":0.009206469,"about_ca_topic_score_gemma":0.015316922,"teacher_disagreement_score":0.80200124,"about_ca_system_score_codex":0.019663312,"about_ca_system_score_gemma":0.043948933,"threshold_uncertainty_score":0.9890103},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040248767,0.0051872027,0.9470964,0.0018597845,0.00037322703,0.0014902367,0.0007901751,0.00076352083,0.0021907168],"genre_scores_gemma":[0.28100735,0.0049849907,0.7009546,0.00053415104,0.00022457939,0.010241939,0.00090080634,0.00032412424,0.0008274498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.7942211,0.19417389,0.0026569185,0.002892907,0.0055662594,0.0004889179],"domain_scores_gemma":[0.5644608,0.41165653,0.0067999745,0.009242053,0.007057455,0.0007830975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12291811,0.0020723063,0.0029580393,0.0074458877,0.0011886231,0.0041314657,0.0029637686,0.0018020553,0.00331162],"category_scores_gemma":[0.28965235,0.0015092497,0.0041261935,0.010508058,0.0030428143,0.0052326946,0.0033307835,0.0038646355,0.0005705699],"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":[0.002183481,0.001396607,0.15146087,0.006232923,0.00927265,0.00053363625,0.024874512,0.051447008,0.00094535894,0.17444041,0.0074171196,0.56979537],"study_design_scores_gemma":[0.00105514,0.0027634862,0.08811013,0.005808139,0.0022131908,0.0007903349,0.018062854,0.46614808,0.0014781088,0.39494777,0.017911127,0.000711544],"about_ca_topic_score_codex":0.010213401,"about_ca_topic_score_gemma":0.012392109,"teacher_disagreement_score":0.12291811,"about_ca_system_score_codex":0.0040856106,"about_ca_system_score_gemma":0.007007451,"threshold_uncertainty_score":0.6500609},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026198877,0.10052605,0.63378054,0.18878347,0.011703869,0.021157281,0.0020877412,0.0009709888,0.0147912325],"genre_scores_gemma":[0.17977603,0.041811477,0.6859818,0.03043996,0.0019683342,0.055003762,0.00084140175,0.0008903138,0.00328701],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3049161,0.6259978,0.037573125,0.009246296,0.019999178,0.0022674813],"domain_scores_gemma":[0.14730687,0.7525789,0.01162427,0.050454255,0.03571403,0.002321744],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58287126,0.0032177689,0.008971084,0.01790925,0.011754922,0.024906727,0.0072430773,0.0075636315,0.008714597],"category_scores_gemma":[0.63578254,0.0047191507,0.006675123,0.018063642,0.020102233,0.03761851,0.019794025,0.015048749,0.0015491298],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053966005,0.00017253241,0.00302582,0.05948411,0.0031462589,0.0012194328,0.54401904,0.0024221384,0.002770792,0.140535,0.028087413,0.21457782],"study_design_scores_gemma":[0.00043247023,0.000483424,0.0017590155,0.15729046,0.0017455607,0.00062272715,0.2348999,0.0038915735,0.002530048,0.3141451,0.28162768,0.0005720654],"about_ca_topic_score_codex":0.007647564,"about_ca_topic_score_gemma":0.012177034,"teacher_disagreement_score":0.41712874,"about_ca_system_score_codex":0.020278057,"about_ca_system_score_gemma":0.04959109,"threshold_uncertainty_score":0.51439404},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46162102,0.004126369,0.48027977,0.019575164,0.00071454904,0.009996843,0.00060284964,0.00026103054,0.022822358],"genre_scores_gemma":[0.8629808,0.0006591946,0.12192771,0.0033689712,0.00028091832,0.009459567,0.00026171957,0.00008591605,0.00097512256],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.2762717,0.663109,0.018113915,0.009598632,0.030442622,0.002464142],"domain_scores_gemma":[0.11641482,0.7897462,0.047925975,0.024656765,0.019923883,0.00133222],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.55013794,0.00086122187,0.001011353,0.0017917583,0.0021980926,0.0067102644,0.0033675982,0.0037888056,0.003366443],"category_scores_gemma":[0.7514048,0.00073128275,0.0020385298,0.0030846158,0.009714332,0.008989277,0.0068406803,0.0038793895,0.00060652994],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042963754,0.0011000766,0.51090866,0.004574879,0.0012039953,0.00032381818,0.10138123,0.0057068774,0.0013660332,0.10320694,0.0045061694,0.26142505],"study_design_scores_gemma":[0.0011799554,0.011652559,0.56258136,0.009022051,0.0015438318,0.0014012078,0.04620798,0.09649904,0.008693567,0.20836632,0.052250143,0.0006019845],"about_ca_topic_score_codex":0.002862089,"about_ca_topic_score_gemma":0.0025911273,"teacher_disagreement_score":0.44986206,"about_ca_system_score_codex":0.006292379,"about_ca_system_score_gemma":0.005946842,"threshold_uncertainty_score":0.5547601},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89348406,0.003026146,0.04771646,0.020435633,0.00031575953,0.026946362,0.00013586736,0.00020280218,0.007736878],"genre_scores_gemma":[0.82216483,0.002492581,0.13356027,0.0044732005,0.00032153857,0.03523457,0.000099688776,0.00006337547,0.001589954],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.86097187,0.12817802,0.0023899751,0.0018177143,0.004493601,0.0021488236],"domain_scores_gemma":[0.86561066,0.11165152,0.007654271,0.0050993054,0.0032030737,0.0067811627],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2209998,0.00087822316,0.0008651905,0.0015361038,0.0037272077,0.002629487,0.002877326,0.0018096329,0.0030616056],"category_scores_gemma":[0.15230973,0.00064406026,0.00093426136,0.0010250298,0.0018904534,0.0021854744,0.0037849846,0.0015844739,0.0005684691],"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":[0.004466715,0.011041839,0.20812166,0.002646132,0.00044720768,0.0004225086,0.044905547,0.001531576,0.002880043,0.004342138,0.00503107,0.7141635],"study_design_scores_gemma":[0.013226048,0.06548354,0.6829392,0.01029064,0.0019988099,0.0014480568,0.10489879,0.029769007,0.009565907,0.026583442,0.052754886,0.0010417515],"about_ca_topic_score_codex":0.003973053,"about_ca_topic_score_gemma":0.012253349,"teacher_disagreement_score":0.77900016,"about_ca_system_score_codex":0.0022716399,"about_ca_system_score_gemma":0.009896998,"threshold_uncertainty_score":0.9606459},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0452807,0.101977736,0.33520645,0.49311528,0.009347826,0.00076151744,0.0019201065,0.0010493282,0.011341049],"genre_scores_gemma":[0.46126723,0.040681712,0.44849852,0.040128507,0.0032545414,0.0035441334,0.00096861745,0.0006098332,0.0010467705],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7665657,0.19634967,0.0125858355,0.008021927,0.014671106,0.0018058524],"domain_scores_gemma":[0.46879274,0.41821265,0.034510277,0.032140102,0.04152459,0.0048196614],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25747967,0.0017762706,0.0041774902,0.007120336,0.0024193171,0.008777756,0.0040082694,0.0050252466,0.00348789],"category_scores_gemma":[0.60553294,0.0018777559,0.0023413172,0.016309736,0.009656526,0.01903723,0.0034331833,0.008730528,0.0015678201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077619054,0.00034927277,0.060024396,0.012666635,0.0013466416,0.00017895405,0.011076394,0.002998991,0.00042104232,0.26360762,0.07650662,0.5700472],"study_design_scores_gemma":[0.00055093213,0.00060094346,0.018506017,0.031398743,0.0011215978,0.00035866234,0.011685016,0.016866097,0.0013759899,0.8480015,0.06899107,0.00054333784],"about_ca_topic_score_codex":0.0055975798,"about_ca_topic_score_gemma":0.009159629,"teacher_disagreement_score":0.25747967,"about_ca_system_score_codex":0.0048625832,"about_ca_system_score_gemma":0.012285658,"threshold_uncertainty_score":0.9156598},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041130323,0.060521595,0.7836183,0.051866785,0.00489481,0.038578745,0.002719755,0.0019408732,0.0147288125],"genre_scores_gemma":[0.33617726,0.0050766943,0.609319,0.006902858,0.0011862296,0.03927366,0.0012582474,0.000321825,0.00048427485],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.06642537,0.7025526,0.15836611,0.02152501,0.049687143,0.0014437158],"domain_scores_gemma":[0.020167312,0.85868967,0.049868055,0.03287412,0.037490122,0.00091074756],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8639553,0.0041093966,0.012623053,0.023853203,0.0056371065,0.02018976,0.008714514,0.008253846,0.002710441],"category_scores_gemma":[0.9490649,0.005053938,0.015517103,0.016055726,0.014528922,0.02137797,0.017079713,0.014232571,0.0011325248],"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":[0.0059343176,0.00046144347,0.10768901,0.16077378,0.04786348,0.0005991065,0.04071382,0.018937098,0.002199877,0.10995886,0.032159477,0.47270975],"study_design_scores_gemma":[0.004702935,0.0029018046,0.0731442,0.16730362,0.0226188,0.0026064923,0.0089190705,0.12875628,0.0062331185,0.47754493,0.10260733,0.0026613998],"about_ca_topic_score_codex":0.005308913,"about_ca_topic_score_gemma":0.004776648,"teacher_disagreement_score":0.13604468,"about_ca_system_score_codex":0.014316271,"about_ca_system_score_gemma":0.024924388,"threshold_uncertainty_score":0.1677674},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053908974,0.00392879,0.8812939,0.008432646,0.0007859989,0.09388542,0.001590424,0.0009784992,0.0037135324],"genre_scores_gemma":[0.0074586724,0.00056540524,0.9285536,0.00057793205,0.00004995011,0.062276077,0.00025535305,0.00008625405,0.00017671872],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.25078052,0.62449676,0.07695955,0.015824907,0.029204728,0.0027334872],"domain_scores_gemma":[0.1996499,0.6219445,0.041041404,0.06666778,0.06833393,0.0023625197],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5503491,0.0027969596,0.009521995,0.050074052,0.007843868,0.017876253,0.009534853,0.0071218973,0.009775661],"category_scores_gemma":[0.71060026,0.004810433,0.013139913,0.047118325,0.0137667265,0.017995317,0.021469548,0.0078217555,0.0027169164],"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":[0.0014922264,0.00036247028,0.007025145,0.12515813,0.0048811794,0.0011231853,0.12923212,0.0053834077,0.0039950255,0.26485506,0.03572813,0.42076397],"study_design_scores_gemma":[0.0035876057,0.0016306917,0.007046197,0.11954851,0.00561292,0.0018845393,0.04725436,0.023746356,0.0072937952,0.5449483,0.23604563,0.0014011426],"about_ca_topic_score_codex":0.0079557,"about_ca_topic_score_gemma":0.011909595,"teacher_disagreement_score":0.44965088,"about_ca_system_score_codex":0.018481985,"about_ca_system_score_gemma":0.06921861,"threshold_uncertainty_score":0.5544996},"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":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001880343,0.0006617024,0.009981124,0.0008735393,0.0004747992,0.9810712,0.0036977702,0.00007609915,0.0012833695],"genre_scores_gemma":[0.0019172394,0.00009413387,0.0069020023,0.00025787798,0.00001870729,0.9904212,0.00022760626,0.000009603788,0.00015166242],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.6973951,0.20573348,0.05815696,0.011539817,0.022732262,0.004442354],"domain_scores_gemma":[0.5860751,0.24109879,0.045717556,0.058869272,0.06373392,0.0045053633],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3448243,0.0033935017,0.0060358993,0.007818308,0.0038065186,0.0061342767,0.006002787,0.010472558,0.059399728],"category_scores_gemma":[0.49654984,0.0038670315,0.0072229747,0.009952377,0.007272235,0.008261199,0.0046799853,0.008358173,0.012290298],"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":[0.059737258,0.005510287,0.023036215,0.36095122,0.0068647834,0.0015547697,0.019973107,0.008239938,0.0015319802,0.071095414,0.16615905,0.27534598],"study_design_scores_gemma":[0.091959395,0.016753098,0.050991803,0.27975455,0.008278961,0.0008241095,0.0150823295,0.01623603,0.0049356488,0.084169425,0.42990053,0.0011140889],"about_ca_topic_score_codex":0.004849677,"about_ca_topic_score_gemma":0.00444063,"teacher_disagreement_score":0.6551757,"about_ca_system_score_codex":0.01014121,"about_ca_system_score_gemma":0.05965029,"threshold_uncertainty_score":0.8079483},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3446251,0.007823347,0.4881274,0.0071601737,0.0026170264,0.09307067,0.017765064,0.0045100893,0.034301024],"genre_scores_gemma":[0.27250937,0.0025744317,0.6490241,0.00042016766,0.0003693458,0.063464426,0.008961803,0.00041669043,0.002259565],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8484887,0.03734692,0.061931726,0.003033266,0.047689095,0.0015102205],"domain_scores_gemma":[0.56438124,0.11562183,0.07173636,0.012743816,0.22952592,0.005990802],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18043575,0.0014228527,0.0032954563,0.028768552,0.001611787,0.004781399,0.002785903,0.0010445009,0.003087212],"category_scores_gemma":[0.33430055,0.0009329751,0.005127547,0.016486768,0.0015585307,0.004415709,0.004465286,0.0021872115,0.0013693372],"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":[0.0015464331,0.00070365274,0.14780663,0.008972643,0.0014090461,0.00023557685,0.005269189,0.0031227085,0.005200575,0.0033999651,0.02597716,0.79635644],"study_design_scores_gemma":[0.0018985118,0.007920347,0.7508965,0.009321874,0.0033037015,0.0019732337,0.0101771895,0.037470266,0.0243689,0.011856554,0.13986851,0.0009444664],"about_ca_topic_score_codex":0.0017854848,"about_ca_topic_score_gemma":0.0024792016,"teacher_disagreement_score":0.8195642,"about_ca_system_score_codex":0.0067032375,"about_ca_system_score_gemma":0.013520143,"threshold_uncertainty_score":0.9542468},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12226544,0.2723828,0.50755644,0.031374354,0.0026145645,0.041707784,0.0057410127,0.0063645313,0.009993068],"genre_scores_gemma":[0.22479035,0.03785581,0.68756306,0.0023133724,0.00070380734,0.044057786,0.001327393,0.0008790571,0.00050938095],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.16027455,0.6321101,0.15056989,0.007179274,0.049030647,0.00083545817],"domain_scores_gemma":[0.02659621,0.8741821,0.054490842,0.019047132,0.025058312,0.00062540034],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6702735,0.002455058,0.0069468576,0.049146827,0.0025452334,0.012730838,0.004366234,0.0032979068,0.002713189],"category_scores_gemma":[0.89665735,0.0035789672,0.013178249,0.057488367,0.0054788357,0.01677984,0.010467174,0.0049227024,0.00058296364],"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":[0.0016663979,0.0002514333,0.04542112,0.25552946,0.02414686,0.00047701003,0.05069423,0.0024964986,0.0024551714,0.011137466,0.013407261,0.59231716],"study_design_scores_gemma":[0.0033778131,0.0042118668,0.10592814,0.61379427,0.046918686,0.0044594277,0.01935152,0.036113843,0.0053583197,0.05461507,0.10352861,0.002342546],"about_ca_topic_score_codex":0.0019573523,"about_ca_topic_score_gemma":0.004590949,"teacher_disagreement_score":0.32972652,"about_ca_system_score_codex":0.009273177,"about_ca_system_score_gemma":0.020710332,"threshold_uncertainty_score":0.40661156},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.138954,0.0012308114,0.8529088,0.0014550748,0.00029783408,0.0012858048,0.0014936193,0.0009213047,0.0014527577],"genre_scores_gemma":[0.70754164,0.0015455519,0.2724969,0.00038593228,0.0003865686,0.004153078,0.0024572732,0.00024626587,0.010786791],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.988664,0.008389785,0.00037265656,0.0014003565,0.00063080806,0.0005424547],"domain_scores_gemma":[0.96560895,0.027828358,0.0024045534,0.0017542111,0.0017528894,0.0006510153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03128432,0.002478441,0.0032393623,0.0033018778,0.0016501845,0.0029557562,0.0056144805,0.003398335,0.0055143503],"category_scores_gemma":[0.049804512,0.0017943265,0.004769309,0.0029105728,0.0025694196,0.0024430347,0.0026903972,0.0039230026,0.0012193919],"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":[0.0024139124,0.000796454,0.095931716,0.00074839627,0.0030399081,0.0027480244,0.0026420122,0.6826813,0.0015536255,0.12326038,0.005087709,0.07909653],"study_design_scores_gemma":[0.00019131547,0.0003797197,0.0074007837,0.00007068116,0.00035537785,0.0002479835,0.00024415075,0.9663274,0.00013651839,0.0229802,0.0015840338,0.00008188436],"about_ca_topic_score_codex":0.023938198,"about_ca_topic_score_gemma":0.01542579,"teacher_disagreement_score":0.96871567,"about_ca_system_score_codex":0.0023702562,"about_ca_system_score_gemma":0.002759165,"threshold_uncertainty_score":0.16544926},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27955365,0.0029890737,0.7084165,0.0023251341,0.00017841223,0.00035563932,0.0008854905,0.0011010149,0.0041951053],"genre_scores_gemma":[0.79251283,0.0016551752,0.20197918,0.00019335432,0.00014792594,0.00044966477,0.0005776619,0.0002713472,0.0022128432],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980489,0.0015608788,0.00006167393,0.0001269566,0.00013291734,0.00006875095],"domain_scores_gemma":[0.98125976,0.016404517,0.00073140237,0.00037741684,0.0010037036,0.00022321599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068659177,0.0009094064,0.0013266128,0.0012756967,0.00053877843,0.0011968389,0.0010637712,0.0010753983,0.0026117656],"category_scores_gemma":[0.022584822,0.0004515484,0.0011333061,0.0016922809,0.00035789135,0.0004980362,0.0010326004,0.0019414204,0.00051925983],"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":[0.00029765646,0.00031932155,0.033784334,0.00023437144,0.0005856256,0.0010853567,0.00053597405,0.84992033,0.0005303523,0.010787632,0.0048355786,0.09708345],"study_design_scores_gemma":[0.000017359918,0.000059776306,0.002623393,0.00002112211,0.00003533468,0.00006656057,0.00004511709,0.9936754,0.000097501914,0.0027497902,0.0005952155,0.000013483606],"about_ca_topic_score_codex":0.015768657,"about_ca_topic_score_gemma":0.008200474,"teacher_disagreement_score":0.015768657,"about_ca_system_score_codex":0.00097368937,"about_ca_system_score_gemma":0.0012105919,"threshold_uncertainty_score":0.03631091},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11086574,0.019009229,0.82725877,0.010896584,0.0020140016,0.014307766,0.0023284752,0.0009690695,0.012350421],"genre_scores_gemma":[0.7963409,0.0027160319,0.17548363,0.0031769092,0.00059028604,0.019736601,0.0010592914,0.0002058874,0.0006904659],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.49036652,0.43826786,0.025018701,0.016696634,0.028053325,0.0015969978],"domain_scores_gemma":[0.15895459,0.7818875,0.034960613,0.018287148,0.005081413,0.0008287421],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4233748,0.0011605998,0.0033559343,0.003914619,0.0009778785,0.005143667,0.004183988,0.0040442073,0.0070781037],"category_scores_gemma":[0.6490687,0.0006194055,0.01005171,0.0048594764,0.005549357,0.004165809,0.0026633486,0.0040619755,0.00059881055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021761062,0.0013547969,0.17653409,0.043440577,0.08443376,0.0021507351,0.0060762353,0.06980622,0.0032161255,0.18607304,0.020427857,0.38472554],"study_design_scores_gemma":[0.01197771,0.010570523,0.069778584,0.020270273,0.037602607,0.0025623394,0.0011177284,0.15846239,0.008256627,0.65274894,0.025971733,0.00068051333],"about_ca_topic_score_codex":0.0007527697,"about_ca_topic_score_gemma":0.0005324074,"teacher_disagreement_score":0.4233748,"about_ca_system_score_codex":0.0027271772,"about_ca_system_score_gemma":0.006640361,"threshold_uncertainty_score":0.7110815},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99518496,0.0005007796,0.0013434252,0.0001579557,0.000029559737,0.00062235957,0.00065271446,0.000011748747,0.0014964583],"genre_scores_gemma":[0.99261636,0.00028492857,0.0045333994,0.00012899742,0.00001821543,0.0008220829,0.0011734796,0.00000787882,0.00041456864],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99736625,0.001313613,0.0003903323,0.0001716474,0.0006274022,0.000130721],"domain_scores_gemma":[0.99628735,0.0011998902,0.00069541874,0.00025862604,0.0012648613,0.0002938697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053147227,0.0003183915,0.00037541246,0.0009794394,0.00046376922,0.00033918922,0.00035804455,0.00028661516,0.001383562],"category_scores_gemma":[0.008260196,0.00013542494,0.00051536463,0.00061069184,0.00040102794,0.0002968597,0.0007945547,0.00054307457,0.00022561479],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054461946,0.0005812053,0.9336867,0.0002001196,0.0003057306,0.00032925213,0.0034703533,0.0005886135,0.0029269436,0.00021981272,0.0014215874,0.055725023],"study_design_scores_gemma":[0.00012239421,0.0006194081,0.9932094,0.00006496329,0.00005440516,0.00080330163,0.0007142219,0.0007401543,0.0007138906,0.0001267205,0.002810156,0.000021073363],"about_ca_topic_score_codex":0.0013985004,"about_ca_topic_score_gemma":0.0017900944,"teacher_disagreement_score":0.0053147227,"about_ca_system_score_codex":0.0004650171,"about_ca_system_score_gemma":0.00058018265,"threshold_uncertainty_score":0.028107285},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014913008,0.038587313,0.9283416,0.009820803,0.0012259941,0.0040918007,0.001085438,0.00039741836,0.0015365741],"genre_scores_gemma":[0.21644373,0.00872875,0.7648637,0.00210303,0.00050577085,0.0060472786,0.00053166837,0.00015857791,0.00061736285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.38414294,0.56136394,0.026628237,0.009256363,0.017229028,0.0013795038],"domain_scores_gemma":[0.19596906,0.7382303,0.034276016,0.019543225,0.010954185,0.0010273046],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42796156,0.0037728853,0.00786353,0.008017032,0.0019236798,0.0070440965,0.005099281,0.0063831136,0.0036084123],"category_scores_gemma":[0.71771395,0.0028649906,0.020926047,0.008089447,0.004465333,0.007227397,0.008045432,0.0065199784,0.00039389444],"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":[0.0071849464,0.0003460587,0.033650164,0.06032448,0.11273632,0.00082322804,0.008747833,0.16048445,0.001786733,0.12332519,0.008375906,0.48221472],"study_design_scores_gemma":[0.0052612606,0.00202471,0.013591451,0.023326049,0.06729174,0.0008049229,0.00090274756,0.2837664,0.0027700155,0.5817906,0.017362578,0.0011074721],"about_ca_topic_score_codex":0.014879318,"about_ca_topic_score_gemma":0.015464853,"teacher_disagreement_score":0.5720384,"about_ca_system_score_codex":0.006372921,"about_ca_system_score_gemma":0.012022594,"threshold_uncertainty_score":0.70542526},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9431124,0.0063633155,0.03955929,0.0017435725,0.00015806769,0.000103799546,0.003438926,0.00032534113,0.0051952414],"genre_scores_gemma":[0.9858431,0.0006591296,0.01023596,0.0004024336,0.00003386005,0.00010107472,0.0020911475,0.000042970398,0.0005903071],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9660346,0.028794449,0.0010463343,0.001984931,0.0016342958,0.0005054066],"domain_scores_gemma":[0.8746094,0.10406878,0.010158746,0.005209388,0.005516781,0.00043688234],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.039071925,0.00097550894,0.0011206164,0.0012749915,0.0002866944,0.0017766469,0.001825697,0.0015790164,0.00085916417],"category_scores_gemma":[0.101545714,0.0005076581,0.0022492956,0.00212772,0.0009881604,0.0016450235,0.0017359136,0.001310066,0.00024773995],"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":[0.0049500535,0.00021502504,0.34154195,0.00053974637,0.002906101,0.0005598009,0.0005670298,0.54866594,0.00041859626,0.008058281,0.0040109335,0.0875667],"study_design_scores_gemma":[0.00037294233,0.0017992536,0.5243373,0.0006805426,0.0020483057,0.0013153186,0.0009944944,0.43772632,0.0045038257,0.013603833,0.01233665,0.0002812232],"about_ca_topic_score_codex":0.020538542,"about_ca_topic_score_gemma":0.005444439,"teacher_disagreement_score":0.9609281,"about_ca_system_score_codex":0.003636061,"about_ca_system_score_gemma":0.0011719508,"threshold_uncertainty_score":0.20663458},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09064022,0.002510123,0.9038879,0.00023992718,0.00005317778,0.00027436184,0.000675756,0.00029688966,0.0014215446],"genre_scores_gemma":[0.7117128,0.0012770677,0.28521144,0.0001230358,0.00009120296,0.00046791736,0.0007140449,0.00008433182,0.0003182789],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98042107,0.013487823,0.0012412163,0.0018026399,0.0027898804,0.00025736055],"domain_scores_gemma":[0.8177476,0.16692676,0.0058731926,0.005872215,0.0033677954,0.00021247781],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03635077,0.0012084191,0.0014352048,0.005454694,0.00050956896,0.0019109087,0.0017640819,0.0012672517,0.0012276898],"category_scores_gemma":[0.16682477,0.0006448602,0.0023126088,0.0019910054,0.0013426631,0.0014501453,0.002225711,0.0011779632,0.00019026214],"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":[0.00079675287,0.00020979582,0.1853823,0.0019116014,0.0058623,0.00050972146,0.0017264553,0.4994226,0.0035684188,0.037603702,0.0015892403,0.26141712],"study_design_scores_gemma":[0.00016074316,0.00090272893,0.11782391,0.001570075,0.0018334537,0.0017357538,0.0008844247,0.6537877,0.014966068,0.19652548,0.00936398,0.00044565392],"about_ca_topic_score_codex":0.0044662426,"about_ca_topic_score_gemma":0.0025257021,"teacher_disagreement_score":0.9636492,"about_ca_system_score_codex":0.0012031466,"about_ca_system_score_gemma":0.001390015,"threshold_uncertainty_score":0.19224358},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058653153,0.0023001018,0.9313868,0.0017303374,0.000098392804,0.0005336189,0.0012374971,0.00029037672,0.003769622],"genre_scores_gemma":[0.80649656,0.0010317351,0.18877137,0.0003592068,0.00013138405,0.00082791125,0.0006055967,0.00008319974,0.0016930462],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9840316,0.011907003,0.00041582595,0.0015217108,0.0018039579,0.000319894],"domain_scores_gemma":[0.9197697,0.06896418,0.0040873694,0.004827281,0.0020909535,0.0002604914],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.031220144,0.00088030176,0.0010842951,0.003251918,0.0004722058,0.0013723694,0.0019933889,0.0014414857,0.0030728446],"category_scores_gemma":[0.11430238,0.00035132284,0.0030741084,0.0022253436,0.0018509236,0.0019118786,0.0013081353,0.0015997025,0.00023412665],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009544735,0.00032921313,0.19363433,0.0020297808,0.00362438,0.0004157104,0.0022173747,0.2465223,0.0023895495,0.19934678,0.006582086,0.3419541],"study_design_scores_gemma":[0.00023922315,0.0006919145,0.12133396,0.00072620943,0.0016383622,0.0005404276,0.0004103334,0.5652957,0.0049952096,0.28801396,0.01592276,0.00019204979],"about_ca_topic_score_codex":0.02597823,"about_ca_topic_score_gemma":0.011561838,"teacher_disagreement_score":0.96877986,"about_ca_system_score_codex":0.0033104145,"about_ca_system_score_gemma":0.002624406,"threshold_uncertainty_score":0.16510987},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011816497,0.5699668,0.1572156,0.016395066,0.0076368526,0.029157352,0.16422571,0.0022789298,0.041307196],"genre_scores_gemma":[0.10652906,0.3666718,0.37531745,0.006698884,0.0022870658,0.07823933,0.058111217,0.0018093929,0.0043358393],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.69819736,0.10748242,0.07653032,0.010477275,0.10308629,0.0042263702],"domain_scores_gemma":[0.4395608,0.3293648,0.048046168,0.024301535,0.15658447,0.002142195],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21062604,0.003567423,0.0037288317,0.07506874,0.005355165,0.010313789,0.0070275664,0.0020934967,0.014272888],"category_scores_gemma":[0.5186048,0.0020346912,0.008484321,0.117647946,0.004950515,0.0033772064,0.004632538,0.00332962,0.0024754675],"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":[0.0006922867,0.00013145502,0.076514386,0.18982986,0.007538166,0.0005591574,0.009194189,0.0021568656,0.0011001703,0.016268872,0.15719266,0.538822],"study_design_scores_gemma":[0.00028769905,0.00027635865,0.13559598,0.15897858,0.006895515,0.0010606961,0.0070557296,0.0025070785,0.0027068483,0.009762513,0.6742617,0.00061135466],"about_ca_topic_score_codex":0.4741085,"about_ca_topic_score_gemma":0.4619655,"teacher_disagreement_score":0.9670049,"about_ca_system_score_codex":0.03299512,"about_ca_system_score_gemma":0.092727005,"threshold_uncertainty_score":0.9734386},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6440118,0.0018279244,0.31996575,0.0056550046,0.00009799395,0.0022774881,0.02111294,0.0010683252,0.003982815],"genre_scores_gemma":[0.6524359,0.0003952271,0.33476102,0.00023464975,0.000104111285,0.00051017065,0.011281534,0.000029064475,0.00024830108],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9904633,0.004100396,0.0017248921,0.0013976783,0.002012204,0.00030154787],"domain_scores_gemma":[0.92533106,0.05577189,0.008737011,0.0033637213,0.0059127156,0.00088360003],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014663144,0.0008406778,0.0014023382,0.01540439,0.0012845045,0.0036207687,0.0022510022,0.0011017753,0.00041443485],"category_scores_gemma":[0.040659647,0.0004929479,0.0017867143,0.01385543,0.00091011805,0.0016171334,0.0015359451,0.00150288,0.0002341729],"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":[0.00026508115,0.0010710814,0.79234123,0.0007345358,0.00083490164,0.0004220561,0.0015022713,0.035236206,0.001390519,0.0025688738,0.003725465,0.15990771],"study_design_scores_gemma":[0.0001263173,0.00038821402,0.27026674,0.00067933666,0.00063744775,0.00079189474,0.004872572,0.69203913,0.0039110314,0.016655609,0.009505877,0.00012583229],"about_ca_topic_score_codex":0.024797922,"about_ca_topic_score_gemma":0.022215752,"teacher_disagreement_score":0.98533684,"about_ca_system_score_codex":0.0024676966,"about_ca_system_score_gemma":0.00410446,"threshold_uncertainty_score":0.07754707},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13766144,0.7171376,0.05664575,0.04647044,0.0037509582,0.001652543,0.00047216017,0.000096317686,0.03611279],"genre_scores_gemma":[0.79847527,0.12661281,0.0607416,0.009327756,0.0013116851,0.0027248536,0.00039508595,0.000094291936,0.00031667855],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6703051,0.26496235,0.024472248,0.0072412784,0.031040747,0.0019782654],"domain_scores_gemma":[0.27161407,0.6197833,0.06299653,0.013919684,0.028210532,0.0034760272],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20470981,0.00070200715,0.0016347279,0.011799579,0.004084567,0.014010798,0.0055859243,0.0038252028,0.0020057068],"category_scores_gemma":[0.40043664,0.0008600348,0.0019878244,0.01841343,0.02776949,0.015915068,0.011460659,0.0047747553,0.00031820274],"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":[0.00086236524,0.0004118515,0.22836186,0.059645087,0.0013555122,0.00033337265,0.059011597,0.001777561,0.00019634765,0.1538938,0.010441046,0.48370948],"study_design_scores_gemma":[0.00057064724,0.002160368,0.28830233,0.3118594,0.0028413376,0.003052044,0.11463038,0.005160767,0.0011952254,0.101717755,0.16793607,0.00057367206],"about_ca_topic_score_codex":0.016723065,"about_ca_topic_score_gemma":0.019768257,"teacher_disagreement_score":0.7952902,"about_ca_system_score_codex":0.012843805,"about_ca_system_score_gemma":0.021491218,"threshold_uncertainty_score":0.9807344},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998723,0.00022567625,0.000059241418,0.000047535406,0.000005642194,0.00003609381,0.0007024879,0.0000025731238,0.00019780218],"genre_scores_gemma":[0.9983126,0.00017594939,0.00008768785,0.000043900178,0.000029162946,0.00007727025,0.0011895781,0.0000022483566,0.00008147071],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99859184,0.0006022281,0.00011568211,0.00023981712,0.0001547794,0.0002956157],"domain_scores_gemma":[0.99737996,0.0006526051,0.001168926,0.00027732988,0.00013627626,0.00038493966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015654243,0.0006128632,0.00065633934,0.001775084,0.00064691814,0.0009429483,0.0007867212,0.00088982267,0.001626295],"category_scores_gemma":[0.0038741818,0.00048075043,0.00072593556,0.0027399606,0.0006439378,0.00055946904,0.001130003,0.000811461,0.00037505064],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021218695,0.00015822746,0.9978198,0.0000343696,0.00012032787,0.0002362687,0.00033721435,0.000069817324,0.00008024958,0.000015847987,0.00025938798,0.00065628067],"study_design_scores_gemma":[0.000031497006,0.00012135855,0.99906176,0.00001759588,0.000043531993,0.00012880683,0.00024727837,0.00016435087,0.0000117843965,0.0000069994244,0.00015969679,0.0000054002317],"about_ca_topic_score_codex":0.0426374,"about_ca_topic_score_gemma":0.035611436,"teacher_disagreement_score":0.0426374,"about_ca_system_score_codex":0.0016533486,"about_ca_system_score_gemma":0.0010421592,"threshold_uncertainty_score":0.08477849},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002579388,0.9969279,0.00076812337,0.0011198422,0.0002199807,0.0000697331,0.000063026615,0.0000032020007,0.0005701881],"genre_scores_gemma":[0.007375939,0.98908186,0.0019380641,0.00096892717,0.00015663529,0.0003157301,0.000056702167,0.000004797548,0.00010141529],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.95424634,0.027043113,0.009402349,0.0015952021,0.0071637537,0.0005492412],"domain_scores_gemma":[0.81022125,0.17377496,0.008075385,0.0019483733,0.0057056267,0.00027444502],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041417703,0.0014113158,0.005174779,0.01565405,0.0009733217,0.0048935884,0.0019459659,0.0024565542,0.003047483],"category_scores_gemma":[0.14225017,0.0014262132,0.0043622414,0.023155067,0.0028078905,0.0058737383,0.0030228328,0.002220934,0.00031414942],"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":[0.00010998116,0.000027533782,0.0008249216,0.6779596,0.003878532,0.000271856,0.0028250914,0.000448324,0.00037590152,0.015493015,0.008317505,0.28946775],"study_design_scores_gemma":[0.000063641986,0.00008381888,0.0031274867,0.85261226,0.0070152255,0.00064718846,0.0016301682,0.00016678836,0.0003174163,0.0075720223,0.12671526,0.000048811646],"about_ca_topic_score_codex":0.006767328,"about_ca_topic_score_gemma":0.014564766,"teacher_disagreement_score":0.9585823,"about_ca_system_score_codex":0.0063273804,"about_ca_system_score_gemma":0.013597633,"threshold_uncertainty_score":0.2190404},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1288565,0.011845019,0.013281265,0.79834,0.0022743768,0.0012362801,0.00015189192,0.00017945252,0.04383511],"genre_scores_gemma":[0.82278305,0.015873954,0.020862352,0.13006225,0.0038233304,0.0017004915,0.00010243196,0.000084572035,0.004707645],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.5827696,0.38060352,0.0090349205,0.0037067467,0.013130984,0.0107542705],"domain_scores_gemma":[0.40411478,0.3904342,0.046071097,0.0153531395,0.04239884,0.10162794],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23926781,0.0004878383,0.00068061077,0.001515536,0.008096801,0.015591989,0.002998681,0.0052126828,0.0061073373],"category_scores_gemma":[0.35036632,0.0006640665,0.00064397336,0.0023959102,0.010550703,0.009421717,0.012702545,0.008060478,0.0017198873],"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":[0.0010280202,0.002479506,0.1583031,0.0059954915,0.00041587852,0.0030847266,0.19965985,0.0018763224,0.002549142,0.05939274,0.19440132,0.37081388],"study_design_scores_gemma":[0.00061570294,0.0037924368,0.03416053,0.005302781,0.00029074555,0.0045473403,0.26183352,0.0011223856,0.0025943068,0.0340249,0.65147406,0.00024126499],"about_ca_topic_score_codex":0.002724515,"about_ca_topic_score_gemma":0.003672713,"teacher_disagreement_score":0.7607322,"about_ca_system_score_codex":0.0076067224,"about_ca_system_score_gemma":0.08781078,"threshold_uncertainty_score":0.9381182},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024298394,0.016407927,0.73426795,0.037166364,0.0054111965,0.1651489,0.0051525654,0.0019580165,0.010188711],"genre_scores_gemma":[0.024783367,0.002210909,0.83537376,0.0029865978,0.00039861238,0.13255641,0.0010080807,0.00021329611,0.00046893183],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.2871682,0.47179347,0.19474867,0.0031484058,0.040391073,0.0027502044],"domain_scores_gemma":[0.13318437,0.6636469,0.050053123,0.029521694,0.120601386,0.0029925888],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5940288,0.0033744485,0.004915989,0.026163781,0.0053705173,0.006123782,0.0058615725,0.005468979,0.0038981948],"category_scores_gemma":[0.69209206,0.0026930675,0.0072355545,0.013117968,0.00939098,0.0065130545,0.012235921,0.008819433,0.0009019446],"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":[0.0020265293,0.000872253,0.026552966,0.12695043,0.0028382973,0.0013290202,0.07069218,0.005774688,0.0104362285,0.058570042,0.19814529,0.49581203],"study_design_scores_gemma":[0.0031490838,0.0030836738,0.07648878,0.1518871,0.0031436605,0.0048835455,0.033468567,0.0208631,0.01493162,0.086516745,0.59913194,0.0024522166],"about_ca_topic_score_codex":0.002991624,"about_ca_topic_score_gemma":0.0048132893,"teacher_disagreement_score":0.40597123,"about_ca_system_score_codex":0.013059269,"about_ca_system_score_gemma":0.03885622,"threshold_uncertainty_score":0.50063485},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012808823,0.0028183726,0.81714255,0.0020634683,0.0014695238,0.15017518,0.010304966,0.0013279635,0.001889115],"genre_scores_gemma":[0.026311671,0.00047043426,0.6162728,0.00052908843,0.00018620351,0.3534203,0.0019867022,0.00024263916,0.0005801821],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.50233275,0.4576549,0.021015344,0.008267533,0.009425328,0.0013041502],"domain_scores_gemma":[0.71797407,0.15504864,0.02974497,0.07325199,0.021235386,0.0027449555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3445218,0.0031123247,0.0043081027,0.004032384,0.0014599978,0.00274921,0.004587153,0.0035787427,0.00980853],"category_scores_gemma":[0.42167285,0.0023957174,0.009658547,0.0068154866,0.0023677533,0.0015585292,0.006137749,0.002724147,0.0017166015],"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":[0.06361492,0.0017527136,0.065833025,0.06046785,0.094645925,0.00092118327,0.006232464,0.028024929,0.0063813464,0.06714008,0.08844735,0.51653826],"study_design_scores_gemma":[0.09200653,0.021928469,0.11677067,0.022362791,0.084318675,0.0015022942,0.001652924,0.10820613,0.01880321,0.21975528,0.3109527,0.0017403716],"about_ca_topic_score_codex":0.0023570915,"about_ca_topic_score_gemma":0.002171526,"teacher_disagreement_score":0.3445218,"about_ca_system_score_codex":0.0022095416,"about_ca_system_score_gemma":0.010321137,"threshold_uncertainty_score":0.80832136},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.993718,0.0006495569,0.0031123476,0.00008911248,0.000060743132,0.0005908291,0.00031852906,0.000027989005,0.0014329413],"genre_scores_gemma":[0.99261063,0.00029951322,0.0053856936,0.00008202703,0.000043607455,0.00071520207,0.00052598247,0.000012554397,0.0003246473],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99054,0.0036337082,0.00154533,0.001126022,0.0028725967,0.0002823772],"domain_scores_gemma":[0.97343224,0.010745342,0.0052588545,0.0018110021,0.008134571,0.00061807426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017031165,0.0005468511,0.00075843616,0.0023349149,0.0005092907,0.0006548773,0.00062637415,0.00096854556,0.00067916844],"category_scores_gemma":[0.025831759,0.00040307944,0.0011866677,0.0015187605,0.00067096343,0.0010023849,0.00106113,0.00069805107,0.00050091784],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033721223,0.0003718625,0.97593385,0.00016881013,0.0002226813,0.000039512746,0.0014191093,0.00015044326,0.001026174,0.000065145316,0.00020133317,0.020063842],"study_design_scores_gemma":[0.000084757165,0.0018116818,0.9939614,0.00011924531,0.00012579678,0.00035204453,0.00071231765,0.00120114,0.0005163189,0.000096010495,0.000997569,0.000021697513],"about_ca_topic_score_codex":0.0012470192,"about_ca_topic_score_gemma":0.0022575238,"teacher_disagreement_score":0.9829688,"about_ca_system_score_codex":0.00042531925,"about_ca_system_score_gemma":0.00066755526,"threshold_uncertainty_score":0.090070486},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014574158,0.98399746,0.0024238855,0.006034962,0.0013462872,0.0032906139,0.0005273741,0.000044267374,0.0008776204],"genre_scores_gemma":[0.023351202,0.9442272,0.01954353,0.0039100694,0.00038028695,0.007660711,0.00040827037,0.00003199665,0.00048659064],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.78718007,0.11676508,0.057316545,0.0056072823,0.031130927,0.0019999607],"domain_scores_gemma":[0.60666406,0.27847692,0.03810309,0.0066163344,0.06707572,0.0030638862],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14781441,0.003476268,0.010845123,0.044309273,0.002467003,0.010362654,0.004093274,0.0068555656,0.0047938246],"category_scores_gemma":[0.40927666,0.0029305513,0.01163499,0.03239187,0.002737421,0.012763284,0.0068922588,0.0037951476,0.00091204175],"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":[0.0001996869,0.000026050178,0.0011561919,0.87734354,0.005017402,0.00023548103,0.0015340765,0.00017692258,0.00033647564,0.0010530812,0.0053877407,0.107533276],"study_design_scores_gemma":[0.00013531793,0.00008769003,0.0014391033,0.96632886,0.012082329,0.0002108509,0.0009497213,0.00014310547,0.00013338859,0.00090317446,0.01754407,0.00004243018],"about_ca_topic_score_codex":0.011228418,"about_ca_topic_score_gemma":0.043909553,"teacher_disagreement_score":0.8521856,"about_ca_system_score_codex":0.017516254,"about_ca_system_score_gemma":0.05540941,"threshold_uncertainty_score":0.78172666},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9994906,0.00012839047,0.0001708571,0.000017312626,0.00000468263,0.000008799043,0.00007077189,0.0000023173075,0.00010632227],"genre_scores_gemma":[0.99960023,0.000060419454,0.00017027023,0.000007170982,0.0000046401005,0.000012700091,0.00010299045,0.0000012785065,0.00004025805],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986368,0.0006614855,0.00014361124,0.00022387745,0.00021940451,0.0001148776],"domain_scores_gemma":[0.9956507,0.0013432434,0.0017574854,0.00043130998,0.000666383,0.00015098443],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032237666,0.0002507807,0.00033316537,0.0006094833,0.00037017182,0.00052954507,0.00033182485,0.00028258582,0.00046084856],"category_scores_gemma":[0.008424179,0.00027270318,0.00025510346,0.00055038155,0.00035322536,0.00035439024,0.0005673914,0.00036880528,0.00014876101],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012815486,0.000018547942,0.9974698,0.000010326537,0.000029296789,0.000039515056,0.00043322795,0.000039125185,0.00032370392,0.000007919412,0.000036393463,0.0014641739],"study_design_scores_gemma":[0.0000051167312,0.00019723746,0.9985678,0.000011916617,0.000024483534,0.00016459468,0.0004209378,0.00032087977,0.00014430628,0.000012989511,0.00012622426,0.0000034923603],"about_ca_topic_score_codex":0.0032204906,"about_ca_topic_score_gemma":0.0026654494,"teacher_disagreement_score":0.9967762,"about_ca_system_score_codex":0.00023187557,"about_ca_system_score_gemma":0.00024466633,"threshold_uncertainty_score":0.017049074},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86654365,0.0006503906,0.12570968,0.0006206929,0.00020045166,0.000517436,0.0022125663,0.00046338627,0.0030817443],"genre_scores_gemma":[0.95898753,0.0001807711,0.03900508,0.00003707868,0.000062514715,0.00028594275,0.0010696965,0.000059570437,0.00031186375],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9914812,0.006041245,0.00039820728,0.0011095122,0.0007109768,0.0002589178],"domain_scores_gemma":[0.975502,0.018648114,0.0017508275,0.0016056548,0.0019226528,0.0005707582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008915895,0.0013495975,0.0010218131,0.004548369,0.0009258082,0.0015283455,0.0007718219,0.00045906735,0.0032119132],"category_scores_gemma":[0.029089108,0.00028786887,0.0024851416,0.0057276553,0.00085760886,0.0007074606,0.0013827216,0.0011217843,0.0003870453],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045303957,0.00030001826,0.8948487,0.0002867844,0.0036442645,0.00058493,0.00093562197,0.02008597,0.0017214977,0.0051864376,0.0035768573,0.068375826],"study_design_scores_gemma":[0.00006350152,0.0009894687,0.65302765,0.00013979031,0.0011402755,0.0008464189,0.0014414309,0.32211044,0.0016187476,0.013727066,0.0047060195,0.0001891563],"about_ca_topic_score_codex":0.008125765,"about_ca_topic_score_gemma":0.0057032052,"teacher_disagreement_score":0.008915895,"about_ca_system_score_codex":0.0007224525,"about_ca_system_score_gemma":0.0023073095,"threshold_uncertainty_score":0.04715234},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28420678,0.027030962,0.37047875,0.010006363,0.0037137014,0.2786207,0.01019019,0.0028777695,0.012874736],"genre_scores_gemma":[0.24086924,0.0026651097,0.5203695,0.00093227107,0.00028682142,0.23130046,0.00281828,0.00030441326,0.00045380247],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.19893907,0.4414651,0.2695458,0.01567391,0.07080263,0.003573537],"domain_scores_gemma":[0.09453659,0.5886511,0.10591383,0.048441518,0.16018921,0.0022677146],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.67226416,0.0032456352,0.0063805194,0.02261969,0.0040114266,0.007901948,0.004844791,0.0037664676,0.0014982219],"category_scores_gemma":[0.79826754,0.0037178088,0.013976817,0.019919101,0.0063842568,0.008773293,0.0121787945,0.0055988217,0.0006691502],"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":[0.0037079677,0.0008568267,0.22220314,0.16942742,0.015882276,0.0008334355,0.09191768,0.0071799816,0.0058923336,0.009343271,0.028896114,0.44385958],"study_design_scores_gemma":[0.0072779935,0.00791169,0.5196844,0.16996902,0.01850281,0.0027981147,0.040854305,0.051502895,0.020777281,0.030084679,0.1275032,0.0031337102],"about_ca_topic_score_codex":0.0034958574,"about_ca_topic_score_gemma":0.010670934,"teacher_disagreement_score":0.32773584,"about_ca_system_score_codex":0.012258954,"about_ca_system_score_gemma":0.03302401,"threshold_uncertainty_score":0.40415668},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9604303,0.0012226136,0.012129072,0.0043453895,0.0000737592,0.008690805,0.0032289901,0.000052059262,0.009826933],"genre_scores_gemma":[0.95930666,0.002048136,0.02070459,0.005965477,0.000103719816,0.006741594,0.0020431983,0.00006578953,0.0030209417],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9452202,0.024760697,0.0034470886,0.0018754118,0.01995067,0.004745867],"domain_scores_gemma":[0.90924174,0.034948893,0.0077919844,0.0074810786,0.036923736,0.0036126557],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.046912115,0.0008966458,0.00075658713,0.0028534688,0.008365607,0.003297098,0.00268351,0.0014852061,0.001370206],"category_scores_gemma":[0.13506803,0.00061480846,0.0006797172,0.006156871,0.0029623653,0.0009768226,0.006394701,0.0010672305,0.0004191883],"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":[0.0003339054,0.00037806085,0.8448497,0.0011956363,0.00026292214,0.0018589429,0.083052464,0.00051821664,0.0023675407,0.0009476134,0.005828122,0.05840686],"study_design_scores_gemma":[0.0001262064,0.00075899827,0.84740365,0.0011219,0.00040847203,0.0015656549,0.121440075,0.0022106264,0.0033350154,0.0007879638,0.020720873,0.00012054121],"about_ca_topic_score_codex":0.83372885,"about_ca_topic_score_gemma":0.90211433,"teacher_disagreement_score":0.95308787,"about_ca_system_score_codex":0.016861545,"about_ca_system_score_gemma":0.043953244,"threshold_uncertainty_score":0.33450067},"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":"review","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21537967,0.29465693,0.2046496,0.024690103,0.017293254,0.14617224,0.06482149,0.00372184,0.028615015],"genre_scores_gemma":[0.63975406,0.016809093,0.17604427,0.0028784617,0.0014869866,0.15166427,0.00935854,0.0006667854,0.0013375423],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.16955736,0.33054072,0.3961063,0.025104634,0.07605773,0.0026332114],"domain_scores_gemma":[0.069124304,0.6383225,0.17071775,0.026450444,0.09215636,0.0032286453],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5426323,0.0029750313,0.013894746,0.033131603,0.0043609636,0.009850033,0.0097626345,0.005029607,0.004722144],"category_scores_gemma":[0.8531419,0.0041792644,0.022141736,0.024842063,0.010228891,0.012827613,0.010414509,0.0053187246,0.0012123632],"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":[0.009682045,0.00032337158,0.23474948,0.4267201,0.11246057,0.0005167588,0.024342045,0.005011109,0.0010511748,0.0072403965,0.03495703,0.14294596],"study_design_scores_gemma":[0.01925859,0.0060214014,0.44584924,0.19581833,0.0982449,0.0036576209,0.018856643,0.025780175,0.004230517,0.05870987,0.118581176,0.004991493],"about_ca_topic_score_codex":0.009983631,"about_ca_topic_score_gemma":0.013761405,"teacher_disagreement_score":0.45736772,"about_ca_system_score_codex":0.01502715,"about_ca_system_score_gemma":0.026849465,"threshold_uncertainty_score":0.56401587},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73298234,0.004799262,0.23375365,0.010346954,0.00080790033,0.0007388484,0.0025447968,0.00049630477,0.013530001],"genre_scores_gemma":[0.9718365,0.0003534833,0.025305357,0.0005957072,0.00014465826,0.00035872523,0.0009956193,0.0000822887,0.00032763835],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.81868315,0.11678722,0.012823118,0.022250175,0.026954906,0.0025014277],"domain_scores_gemma":[0.25742498,0.6507077,0.039093018,0.034341067,0.017203068,0.0012301515],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.123645045,0.00073541235,0.0013238953,0.0048285504,0.0020136693,0.0055189203,0.0020054355,0.0024032095,0.0028914968],"category_scores_gemma":[0.45872182,0.00066750596,0.0024504706,0.0045628333,0.008628958,0.0057061724,0.0028892418,0.0026391165,0.00072376657],"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":[0.0007686592,0.0003165381,0.80199486,0.0017772806,0.0028982626,0.0016387982,0.009939405,0.011601379,0.0028369895,0.0518089,0.0066785105,0.10774046],"study_design_scores_gemma":[0.00016943565,0.0012242722,0.662786,0.0015313579,0.0012542867,0.0053459094,0.008688691,0.07098308,0.007932391,0.22558132,0.014136112,0.00036719866],"about_ca_topic_score_codex":0.0015582199,"about_ca_topic_score_gemma":0.0016922969,"teacher_disagreement_score":0.9975968,"about_ca_system_score_codex":0.003102772,"about_ca_system_score_gemma":0.0024529533,"threshold_uncertainty_score":0.6539053},"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":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014282733,0.048587732,0.51870763,0.090348326,0.026559623,0.13206317,0.10875559,0.010463826,0.0630859],"genre_scores_gemma":[0.013146229,0.03686103,0.6119611,0.015660683,0.004282803,0.2555472,0.050106544,0.0035155339,0.008918806],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.2604649,0.39473298,0.28806207,0.011843471,0.04149128,0.003405247],"domain_scores_gemma":[0.10917009,0.5022729,0.10495912,0.09960074,0.18022694,0.0037703188],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.44536048,0.00616824,0.009054686,0.035433035,0.005188285,0.024679448,0.019578306,0.020057824,0.060397517],"category_scores_gemma":[0.7942872,0.0062118564,0.014583298,0.0418902,0.007950512,0.018806301,0.015651817,0.018745035,0.03822244],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076727447,0.00015865952,0.002012472,0.14971569,0.0015071827,0.00078330573,0.006684085,0.0035793774,0.00073003146,0.10285298,0.5254288,0.20578016],"study_design_scores_gemma":[0.0004588837,0.00013436502,0.00077368127,0.13073784,0.0007258442,0.00037860507,0.001222383,0.0017861276,0.00085816986,0.061481677,0.80120564,0.0002368132],"about_ca_topic_score_codex":0.007974712,"about_ca_topic_score_gemma":0.0050272974,"teacher_disagreement_score":0.5546395,"about_ca_system_score_codex":0.014470092,"about_ca_system_score_gemma":0.07506641,"threshold_uncertainty_score":0.6839693},"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":"empirical","domain_codex":"methods","domain_gemma":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72893995,0.07904899,0.03434845,0.12939161,0.0009422496,0.015220667,0.00075683295,0.00019473556,0.011156502],"genre_scores_gemma":[0.91178906,0.008207595,0.048215423,0.019152047,0.0003346062,0.0117250495,0.00010463845,0.00008923464,0.00038248883],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.12789045,0.81652296,0.02678735,0.0049215094,0.018393723,0.005484029],"domain_scores_gemma":[0.093690686,0.7987956,0.066713065,0.01585285,0.018969873,0.005977831],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.66568744,0.00087845954,0.003429521,0.0077048875,0.00674644,0.018224183,0.004837924,0.006649136,0.002875023],"category_scores_gemma":[0.7766903,0.002661477,0.0029584104,0.011331866,0.01124674,0.016266089,0.012946045,0.004865004,0.00036537764],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026785326,0.0010710187,0.1728843,0.027739609,0.0032693679,0.0007037342,0.57749677,0.0005621515,0.0005585156,0.017788803,0.0038341691,0.19141302],"study_design_scores_gemma":[0.0029399116,0.007829419,0.13643391,0.106944814,0.0053157653,0.0014922444,0.64083093,0.0059497,0.0018296645,0.024956942,0.064878315,0.0005983365],"about_ca_topic_score_codex":0.0063254167,"about_ca_topic_score_gemma":0.009167538,"teacher_disagreement_score":0.33431256,"about_ca_system_score_codex":0.02368097,"about_ca_system_score_gemma":0.061044604,"threshold_uncertainty_score":0.41226697},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007107434,0.00018729271,0.99200916,0.00012640932,0.000031215008,0.00004856097,0.00005306581,0.000100117766,0.00033675737],"genre_scores_gemma":[0.23957926,0.0003530037,0.7573547,0.00021602117,0.00017195694,0.00083591964,0.00034282476,0.000086612694,0.0010597806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9854848,0.010633742,0.00051273336,0.0013158855,0.0017467975,0.00030616752],"domain_scores_gemma":[0.9272217,0.06225408,0.0033340335,0.0037592081,0.0030509557,0.00038004713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021848215,0.0008851793,0.0015433723,0.003092713,0.00066457526,0.0018075119,0.0027222952,0.0019280877,0.001904149],"category_scores_gemma":[0.1066879,0.00056820584,0.0017026529,0.0021219028,0.0022337895,0.0019063452,0.0024515768,0.0028449555,0.0003720412],"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":[0.0007956353,0.000522624,0.026179956,0.00079019833,0.0006806513,0.00092384336,0.0008236761,0.2604984,0.003946021,0.18267925,0.0031878722,0.51897186],"study_design_scores_gemma":[0.000085395586,0.00031821703,0.006672231,0.00011831381,0.000090155816,0.0005648162,0.00012173676,0.8877994,0.0011121917,0.100359075,0.00268367,0.000074749],"about_ca_topic_score_codex":0.0022579087,"about_ca_topic_score_gemma":0.0016072661,"teacher_disagreement_score":0.9781518,"about_ca_system_score_codex":0.0011248913,"about_ca_system_score_gemma":0.0015962146,"threshold_uncertainty_score":0.11554581},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001238731,0.27657026,0.4049792,0.21681875,0.04673064,0.012047394,0.0019058659,0.0049430723,0.034766126],"genre_scores_gemma":[0.010721471,0.25067008,0.5547452,0.108400345,0.029239524,0.019090746,0.0011037755,0.0028397248,0.023189157],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9169811,0.068996824,0.00636037,0.001516393,0.0055703595,0.00057502626],"domain_scores_gemma":[0.59723264,0.36958742,0.009437559,0.008140951,0.011285137,0.0043163095],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12765408,0.003752038,0.0036213913,0.00529166,0.0015767749,0.006053191,0.004529472,0.008119676,0.024115229],"category_scores_gemma":[0.23500635,0.0026386129,0.004057329,0.0057401354,0.0074364417,0.016667727,0.0051802434,0.015186103,0.0178303],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043124732,0.00027084886,0.0005502075,0.018338844,0.00027930905,0.00071658,0.0033755219,0.0011901382,0.0012444501,0.034731973,0.56768364,0.37118724],"study_design_scores_gemma":[0.00028152927,0.0004405129,0.00080416736,0.013529619,0.00013776246,0.0013243598,0.0009963827,0.0006510073,0.00063674233,0.075404696,0.90564233,0.00015079987],"about_ca_topic_score_codex":0.0019438945,"about_ca_topic_score_gemma":0.0037332524,"teacher_disagreement_score":0.8723459,"about_ca_system_score_codex":0.003053762,"about_ca_system_score_gemma":0.007583716,"threshold_uncertainty_score":0.67510736},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98401916,0.00012528933,0.0144887455,0.0002837789,0.00003381456,0.00009241129,0.00040878274,0.00005364139,0.0004944031],"genre_scores_gemma":[0.9969131,0.00002857015,0.0025570828,0.000019309493,0.000011554023,0.000053032916,0.00032111182,0.0000036055742,0.00009265234],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984131,0.0011056709,0.0000774517,0.0001508476,0.00012354895,0.00012934329],"domain_scores_gemma":[0.99066365,0.0071891895,0.0009162939,0.00035956848,0.0005684788,0.00030273187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072960057,0.00073964975,0.0006915547,0.001229643,0.00027452008,0.0010713424,0.00065841153,0.00048750264,0.0013394252],"category_scores_gemma":[0.016549738,0.00019167404,0.0009507653,0.00060848583,0.00034533846,0.00038118724,0.00064982206,0.001123998,0.00025974697],"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":[0.0013006132,0.00054380664,0.8809887,0.000053805135,0.00041070918,0.00018768164,0.00024218997,0.09365766,0.00022873757,0.00056697545,0.0009819814,0.020837164],"study_design_scores_gemma":[0.000095116986,0.0008866423,0.12867895,0.000036405032,0.00016566753,0.00012853897,0.00016080524,0.8677558,0.00023722972,0.0014946624,0.00032320828,0.000036933918],"about_ca_topic_score_codex":0.0028657028,"about_ca_topic_score_gemma":0.0017074553,"teacher_disagreement_score":0.0072960057,"about_ca_system_score_codex":0.00057746476,"about_ca_system_score_gemma":0.00081375573,"threshold_uncertainty_score":0.038585484},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5919242,0.00078636885,0.40405005,0.00072100596,0.000036130215,0.00017984059,0.0010155564,0.00031639633,0.0009705305],"genre_scores_gemma":[0.94771165,0.00035845852,0.04907755,0.00008749197,0.000042042087,0.00018554438,0.0015345636,0.000025275811,0.0009775046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981896,0.0011618618,0.0000798588,0.0003599213,0.000109479726,0.00009921496],"domain_scores_gemma":[0.9805046,0.016214091,0.0012656022,0.0009264351,0.00076692033,0.00032235586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009191353,0.0006921184,0.0010653808,0.0013480374,0.00055958476,0.0010025392,0.0011731889,0.00090779096,0.0017385929],"category_scores_gemma":[0.032703,0.00062636787,0.0014315977,0.00079598353,0.0006277146,0.00091043505,0.0010544725,0.0014518595,0.0003549664],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015272516,0.00040535923,0.5238563,0.00019536553,0.0012978041,0.0002302387,0.0009322387,0.2912446,0.0019338185,0.021847798,0.0028171178,0.15371211],"study_design_scores_gemma":[0.00009221373,0.00020092599,0.06219179,0.00008041336,0.00021087732,0.00011019479,0.0001401053,0.9171261,0.00038398066,0.018561624,0.00085901096,0.000042733416],"about_ca_topic_score_codex":0.020776536,"about_ca_topic_score_gemma":0.01463166,"teacher_disagreement_score":0.020776536,"about_ca_system_score_codex":0.000801262,"about_ca_system_score_gemma":0.0015345337,"threshold_uncertainty_score":0.048609078},"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":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029454492,0.3000214,0.22548689,0.22500436,0.058934767,0.12588952,0.0063129864,0.0028307096,0.05257398],"genre_scores_gemma":[0.02186366,0.3770181,0.35244626,0.030916443,0.015040766,0.18925773,0.006426836,0.0011617459,0.0058684973],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.21609603,0.47332552,0.22236305,0.014011637,0.07026133,0.003942423],"domain_scores_gemma":[0.095860876,0.5015094,0.10334967,0.03422196,0.25859278,0.0064653675],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6345983,0.0058389506,0.014161637,0.062013444,0.010926542,0.034302782,0.010758228,0.026797062,0.023952417],"category_scores_gemma":[0.81962526,0.009233671,0.01392438,0.055651784,0.021178612,0.03843994,0.02403961,0.02310911,0.02113321],"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":[0.0006129136,0.00017437675,0.0014144327,0.29612347,0.0016766003,0.00082995085,0.010803445,0.0016280577,0.0016405061,0.04083685,0.26136407,0.38289538],"study_design_scores_gemma":[0.00032355226,0.00016789633,0.000809424,0.7190991,0.0009883624,0.00033059818,0.0017274728,0.00084754685,0.0005572631,0.016825318,0.25807598,0.00024749624],"about_ca_topic_score_codex":0.006510678,"about_ca_topic_score_gemma":0.005704844,"teacher_disagreement_score":0.3654017,"about_ca_system_score_codex":0.025112018,"about_ca_system_score_gemma":0.16938022,"threshold_uncertainty_score":0.4506054},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5642731,0.00057985773,0.4080348,0.0004960304,0.0005699235,0.019161366,0.0024866958,0.0010767829,0.0033213827],"genre_scores_gemma":[0.33020842,0.0003095579,0.62082314,0.0005323072,0.0001215924,0.04374537,0.0013256222,0.0007212949,0.0022127347],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.97980714,0.012834474,0.0013023353,0.0025024794,0.0029427756,0.00061072625],"domain_scores_gemma":[0.959828,0.012718613,0.0071407235,0.010940205,0.00752752,0.0018449426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032514255,0.0016429338,0.0013886258,0.0015141224,0.0012262231,0.0013214251,0.0021829908,0.0016053834,0.004032118],"category_scores_gemma":[0.02321543,0.00090608693,0.0015261691,0.0007589972,0.0021323164,0.00078305625,0.0016019074,0.0021663876,0.001045615],"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":[0.06330638,0.02075267,0.05148204,0.002782913,0.0021288563,0.000947576,0.004679836,0.009147906,0.7189302,0.01605894,0.005367943,0.10441484],"study_design_scores_gemma":[0.010499616,0.20526758,0.1152566,0.001114444,0.002885651,0.0012231836,0.0012800129,0.037290353,0.5577165,0.012686578,0.054199077,0.0005804431],"about_ca_topic_score_codex":0.0008055169,"about_ca_topic_score_gemma":0.0015862816,"teacher_disagreement_score":0.9674857,"about_ca_system_score_codex":0.0008651385,"about_ca_system_score_gemma":0.0011785149,"threshold_uncertainty_score":0.17195392},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3990645,0.021591762,0.55401254,0.0038592368,0.001947349,0.0031456328,0.0057885274,0.0006282589,0.009962205],"genre_scores_gemma":[0.89200646,0.0028771188,0.09873526,0.00074027217,0.0005388025,0.0013955722,0.0017480373,0.0001114184,0.0018470482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8819967,0.10673842,0.0026967959,0.0032486843,0.0047949296,0.0005245271],"domain_scores_gemma":[0.78302836,0.18210107,0.012972644,0.0141735505,0.006623055,0.0011013262],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10477198,0.0009215609,0.0016522038,0.00266767,0.0005465517,0.0019852861,0.0015327454,0.0011918367,0.0083257565],"category_scores_gemma":[0.19904582,0.0003749105,0.0035039014,0.0029991928,0.0010592141,0.0015883974,0.002396691,0.0011269496,0.0007898039],"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":[0.043056123,0.00059934123,0.31121206,0.0053868336,0.0633897,0.00020509533,0.00086633506,0.03287555,0.0015977435,0.041655418,0.012852598,0.48630312],"study_design_scores_gemma":[0.010820942,0.018690791,0.51182663,0.0028741085,0.021019848,0.00092322234,0.0016570422,0.31181675,0.005531991,0.08833746,0.026016112,0.0004851932],"about_ca_topic_score_codex":0.0038327312,"about_ca_topic_score_gemma":0.0031080744,"teacher_disagreement_score":0.895228,"about_ca_system_score_codex":0.0014231537,"about_ca_system_score_gemma":0.0023021288,"threshold_uncertainty_score":0.55409384},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057581085,0.98469305,0.007004745,0.0013868945,0.0006395547,0.0032986715,0.0009332629,0.000062548876,0.0014055202],"genre_scores_gemma":[0.017830322,0.93179435,0.028748216,0.0020965158,0.0004708942,0.017671868,0.00091654615,0.00009185684,0.00037946727],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.729147,0.17548835,0.06328252,0.0074863313,0.023471266,0.001124443],"domain_scores_gemma":[0.29879764,0.63761616,0.033540267,0.0107281925,0.018750133,0.0005676973],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19295327,0.003964629,0.01285931,0.039489374,0.0020477576,0.0097215,0.005721942,0.00597519,0.01083474],"category_scores_gemma":[0.57075673,0.0032679446,0.019853614,0.03766879,0.0034559583,0.008459942,0.00528746,0.004025995,0.0012618382],"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":[0.00025690693,0.00002507393,0.0006032381,0.8939181,0.014123024,0.00007935232,0.0004540103,0.0005731754,0.000077063334,0.0026700646,0.002908491,0.08431139],"study_design_scores_gemma":[0.0002436108,0.00012922734,0.0009274362,0.93828684,0.032959107,0.00014628649,0.00023950505,0.00039488994,0.00020666565,0.0035943175,0.022820707,0.00005139999],"about_ca_topic_score_codex":0.005765235,"about_ca_topic_score_gemma":0.010166562,"teacher_disagreement_score":0.8070467,"about_ca_system_score_codex":0.012108882,"about_ca_system_score_gemma":0.027136987,"threshold_uncertainty_score":0.9952323},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010871141,0.0018072999,0.9091192,0.010385625,0.00057264057,0.000575825,0.0014806057,0.0005910061,0.06459667],"genre_scores_gemma":[0.57615256,0.0049256496,0.38123608,0.0030856973,0.00073415454,0.004391949,0.0018006258,0.00062688097,0.027046455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99767965,0.0012112972,0.00014588595,0.0003734039,0.0003985912,0.00019117713],"domain_scores_gemma":[0.9908922,0.0062669353,0.00097411417,0.0006229306,0.000971234,0.00027259186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035598946,0.0014560283,0.0013269122,0.0012189095,0.00085966126,0.0031001538,0.0025473358,0.0035165912,0.01341718],"category_scores_gemma":[0.022263909,0.000740488,0.0025938498,0.0010015969,0.0024280502,0.0041298023,0.0025494315,0.0035525865,0.0020252909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005009516,0.000069029804,0.0017721424,0.0005613485,0.00011026219,0.00020172751,0.00046389477,0.49730363,0.00045719167,0.47460893,0.0074321367,0.016969634],"study_design_scores_gemma":[0.000043687924,0.000059066482,0.0007854263,0.00030982585,0.00008802206,0.00014917486,0.00016185289,0.5012526,0.00025796398,0.44679946,0.050043136,0.000049793685],"about_ca_topic_score_codex":0.010997684,"about_ca_topic_score_gemma":0.004975209,"teacher_disagreement_score":0.01341718,"about_ca_system_score_codex":0.0029888889,"about_ca_system_score_gemma":0.004144069,"threshold_uncertainty_score":0.04488498},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99788386,0.00045790873,0.00023228921,0.00041632925,0.000006932468,0.00009269703,0.00044343594,0.000008544534,0.0004581627],"genre_scores_gemma":[0.99853337,0.0002840723,0.0004703147,0.00017877675,0.000021329695,0.00009151563,0.00034672284,0.0000028274333,0.00007100933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9889347,0.005560322,0.002654649,0.00060419296,0.0017019802,0.0005441584],"domain_scores_gemma":[0.94151586,0.015937285,0.03358336,0.0015580322,0.003600664,0.0038047745],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012631275,0.00023044959,0.0005091162,0.0024013573,0.00063721975,0.0010608743,0.0005402193,0.00090522825,0.0015698919],"category_scores_gemma":[0.0316307,0.0005423726,0.0005694865,0.0022819007,0.000533832,0.0016930609,0.001193389,0.0009932138,0.00036328778],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002603312,0.00005710398,0.9984133,0.000027372309,0.000027436781,0.00002881771,0.00024069916,0.00001389914,0.000035142784,0.0000067073606,0.0001280734,0.0009953387],"study_design_scores_gemma":[0.0000069143994,0.00018562422,0.99816704,0.000034719225,0.000017904578,0.00028183748,0.000860202,0.0001254269,0.000037589227,0.000012273558,0.00026307852,0.000007457911],"about_ca_topic_score_codex":0.0011596207,"about_ca_topic_score_gemma":0.0013062704,"teacher_disagreement_score":0.9873687,"about_ca_system_score_codex":0.00053098885,"about_ca_system_score_gemma":0.000921233,"threshold_uncertainty_score":0.06680143},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018330712,0.0021872316,0.96750045,0.00043819894,0.0006730774,0.0062421258,0.0023874925,0.0012700238,0.00097074755],"genre_scores_gemma":[0.16610062,0.0007068864,0.80082023,0.00040655193,0.00019805258,0.028397487,0.0017450673,0.00047682557,0.0011483066],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8173689,0.14742805,0.009479134,0.011686654,0.012939149,0.001098015],"domain_scores_gemma":[0.7624749,0.19027647,0.012107147,0.026787082,0.0077093965,0.00064495683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11871526,0.0016675617,0.004192808,0.004849847,0.0008527203,0.0016214355,0.0041874144,0.0025180504,0.008862815],"category_scores_gemma":[0.32451397,0.00088762515,0.009202172,0.0067572393,0.0023527169,0.0012998087,0.0023428726,0.0042162845,0.0012282594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0137888165,0.0010821711,0.13933942,0.024743127,0.08805463,0.0021151158,0.0023725478,0.051812008,0.015634725,0.066319175,0.03665244,0.5580859],"study_design_scores_gemma":[0.0042396183,0.019388916,0.22649452,0.00521993,0.035687327,0.0019780227,0.0014387624,0.42157283,0.024024043,0.116291694,0.14278053,0.0008837901],"about_ca_topic_score_codex":0.0020122267,"about_ca_topic_score_gemma":0.00096719427,"teacher_disagreement_score":0.11871526,"about_ca_system_score_codex":0.001307543,"about_ca_system_score_gemma":0.00302027,"threshold_uncertainty_score":0.6278338},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98519933,0.00068561774,0.004052319,0.0004937281,0.000098433695,0.0014882718,0.0014340982,0.00004387725,0.0065043676],"genre_scores_gemma":[0.9819743,0.0006824528,0.013193463,0.00016496649,0.000019498617,0.0016973513,0.0012218104,0.00002852991,0.0010175051],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973948,0.0012285286,0.00044482434,0.00019301745,0.00059952296,0.00013933916],"domain_scores_gemma":[0.99632853,0.0013183455,0.00048204913,0.00035670088,0.001334417,0.0001798826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004614552,0.00027972358,0.00034788233,0.0010060981,0.00047655718,0.00045836053,0.00040733814,0.00020331703,0.0014811779],"category_scores_gemma":[0.011000879,0.00021526321,0.00071905414,0.0008313567,0.00036815225,0.00035296028,0.0008057776,0.0005446009,0.00023776197],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020935845,0.0005656219,0.77934736,0.00063855626,0.00020069393,0.0005192792,0.022160366,0.00048046,0.006165015,0.0009212796,0.0028894416,0.18590254],"study_design_scores_gemma":[0.000052937445,0.00047172687,0.9763812,0.000284633,0.00007281794,0.00082249445,0.0049754656,0.0008865379,0.0013781377,0.00036740158,0.014266072,0.00004059555],"about_ca_topic_score_codex":0.00829583,"about_ca_topic_score_gemma":0.01562842,"teacher_disagreement_score":0.00829583,"about_ca_system_score_codex":0.0006821137,"about_ca_system_score_gemma":0.0015769912,"threshold_uncertainty_score":0.024404347},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27384284,0.001231173,0.5036318,0.0069786105,0.0010215279,0.18090674,0.0009291627,0.0005626495,0.030895531],"genre_scores_gemma":[0.21229652,0.00050990714,0.68886536,0.0009754407,0.00008862143,0.09569114,0.0004382092,0.000054312863,0.0010804344],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6012497,0.3432488,0.02944493,0.006850507,0.015218717,0.0039873496],"domain_scores_gemma":[0.7502913,0.17595057,0.011576525,0.009106115,0.050504386,0.0025710869],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25040698,0.00220263,0.0019340826,0.010872037,0.0043506115,0.0040136585,0.0037807275,0.0031263744,0.0051103146],"category_scores_gemma":[0.24854642,0.0016225245,0.003213376,0.005253424,0.00515047,0.0052260817,0.012643281,0.0034530347,0.0010263787],"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":[0.0030395302,0.0016943965,0.026215086,0.014854454,0.0014381768,0.0013730412,0.33389014,0.0117117595,0.01082026,0.05012659,0.022277601,0.5225589],"study_design_scores_gemma":[0.0044804765,0.009596644,0.06205107,0.016045745,0.0016925809,0.0034796621,0.4244821,0.14102353,0.019208275,0.18361205,0.13192134,0.0024065934],"about_ca_topic_score_codex":0.0022266114,"about_ca_topic_score_gemma":0.0036782064,"teacher_disagreement_score":0.25040698,"about_ca_system_score_codex":0.007804164,"about_ca_system_score_gemma":0.020644657,"threshold_uncertainty_score":0.9243817},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13492708,0.0022898768,0.84368557,0.0022549303,0.00031243777,0.010903222,0.00035154633,0.0004915383,0.004783809],"genre_scores_gemma":[0.42482552,0.00065401435,0.562654,0.00079007016,0.00007362357,0.009659471,0.00018451421,0.000058464026,0.0011003278],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.92559457,0.06972879,0.0009054374,0.0011704459,0.002199249,0.00040144566],"domain_scores_gemma":[0.85837835,0.12364282,0.0061900173,0.005418243,0.004989207,0.0013813246],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09597893,0.001227684,0.0017366656,0.00073165155,0.00045203028,0.0013973375,0.0015472134,0.0028335792,0.004017163],"category_scores_gemma":[0.12695777,0.00086150056,0.002563436,0.00056098955,0.0011780888,0.0012015112,0.0012823397,0.002542256,0.00045176514],"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":[0.04961657,0.0031035254,0.0072369697,0.0032686251,0.002595762,0.0003194296,0.0007058358,0.5769533,0.0054135625,0.06659968,0.0033590728,0.28082764],"study_design_scores_gemma":[0.020420644,0.03196132,0.0035633114,0.0008735711,0.0012022862,0.00025531813,0.000095695,0.8715641,0.004081075,0.057121806,0.008640917,0.00022006461],"about_ca_topic_score_codex":0.00090461184,"about_ca_topic_score_gemma":0.000830705,"teacher_disagreement_score":0.9040211,"about_ca_system_score_codex":0.0016652151,"about_ca_system_score_gemma":0.0035451471,"threshold_uncertainty_score":0.5075911},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91015506,0.03256243,0.005825686,0.005902457,0.0057711485,0.03283942,0.0010568252,0.0005528036,0.00533417],"genre_scores_gemma":[0.9570312,0.003716771,0.006151452,0.002065239,0.0015452888,0.028137373,0.00025269194,0.000028322336,0.0010715679],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9549328,0.036877383,0.0027238352,0.0024153749,0.0017792932,0.0012713257],"domain_scores_gemma":[0.95306486,0.033608228,0.0076144394,0.0016866768,0.0011088747,0.002917015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02421944,0.0020291554,0.0054849084,0.001709574,0.0011975658,0.0021104298,0.0022411465,0.0070483643,0.010265956],"category_scores_gemma":[0.058002055,0.0011672727,0.005208597,0.0013591613,0.0030864081,0.0027876906,0.0014514745,0.0049668616,0.0008067341],"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":[0.95913684,0.0090937205,0.0012453756,0.004380235,0.002643709,0.000037697842,0.000089839734,0.00032868216,0.00019601348,0.0003535532,0.0007368281,0.021757537],"study_design_scores_gemma":[0.94316083,0.050701138,0.0016953934,0.0006992091,0.001745881,0.000024572697,0.000038385944,0.00075515546,0.00019352934,0.0004608812,0.000500153,0.000024896852],"about_ca_topic_score_codex":0.0008237455,"about_ca_topic_score_gemma":0.00071280566,"teacher_disagreement_score":0.97578055,"about_ca_system_score_codex":0.002032302,"about_ca_system_score_gemma":0.003473337,"threshold_uncertainty_score":0.12808615},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7258213,0.0015271123,0.26782602,0.00079325575,0.00015403327,0.0011980066,0.00093272375,0.00048714827,0.001260373],"genre_scores_gemma":[0.9205508,0.00034062148,0.076437555,0.00010770921,0.00003403631,0.0012574794,0.0006957875,0.00004709611,0.0005288343],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9580939,0.038325302,0.00079199456,0.001371874,0.0008537417,0.00056323176],"domain_scores_gemma":[0.66267323,0.30914682,0.0057390453,0.01575192,0.005679025,0.0010099602],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08347904,0.0011304569,0.001943323,0.0020336495,0.0010176372,0.0016483504,0.0023346783,0.0028058698,0.0018938908],"category_scores_gemma":[0.14847507,0.00095265906,0.0043147164,0.0024080228,0.0011607617,0.0017907593,0.0017384611,0.003101495,0.0003106718],"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":[0.0031099024,0.00078188156,0.12607849,0.00048094633,0.0032011853,0.00056530925,0.0018572654,0.8093263,0.00066696096,0.012306626,0.0017270424,0.039898146],"study_design_scores_gemma":[0.00027623255,0.00084802974,0.012301725,0.00012605905,0.00041014334,0.00012541238,0.00036460697,0.97819126,0.00043090762,0.005913614,0.0009464457,0.000065551874],"about_ca_topic_score_codex":0.029313266,"about_ca_topic_score_gemma":0.014414966,"teacher_disagreement_score":0.91652095,"about_ca_system_score_codex":0.0017579828,"about_ca_system_score_gemma":0.0020405953,"threshold_uncertainty_score":0.44148463},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64351016,0.005642463,0.06929156,0.039553933,0.0024618285,0.17485377,0.01697461,0.00047337185,0.0472383],"genre_scores_gemma":[0.60074985,0.0022650533,0.24939717,0.011164171,0.00032480562,0.12619202,0.0051957495,0.00019938078,0.0045118085],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9235039,0.043125246,0.0043718494,0.0044548404,0.018165488,0.0063786176],"domain_scores_gemma":[0.9123822,0.018429102,0.0044846167,0.0070713377,0.045069158,0.012563668],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17215152,0.0010282829,0.001010789,0.00724816,0.021723624,0.0065759267,0.0056594657,0.0016061089,0.0026451652],"category_scores_gemma":[0.11014697,0.0009210509,0.00091815036,0.006920456,0.008352717,0.0027612401,0.010782213,0.002916285,0.0004662399],"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":[0.0005215444,0.0008957572,0.5143853,0.0033997796,0.0003006258,0.0011828698,0.21167761,0.00081453094,0.0054362533,0.025310514,0.050243203,0.18583198],"study_design_scores_gemma":[0.00035219602,0.00086613814,0.6125996,0.0046881787,0.00031354904,0.00027527715,0.22115932,0.002365643,0.0017225879,0.0060414113,0.14925447,0.00036162525],"about_ca_topic_score_codex":0.9260049,"about_ca_topic_score_gemma":0.96638376,"teacher_disagreement_score":0.9387442,"about_ca_system_score_codex":0.061255798,"about_ca_system_score_gemma":0.23885322,"threshold_uncertainty_score":0.91043514},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9752858,0.00021274808,0.02244867,0.00039802355,0.000016462434,0.00025314215,0.00048563143,0.000060703205,0.0008387799],"genre_scores_gemma":[0.98660094,0.00010514756,0.0124294665,0.00006168963,0.000009527094,0.0002219786,0.00041449437,0.000007683372,0.000149172],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965239,0.00276948,0.00015774161,0.00021511839,0.00015302378,0.0001806579],"domain_scores_gemma":[0.8948608,0.09835705,0.0020614031,0.0014882418,0.0025076303,0.0007248323],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016142502,0.0009827174,0.00097643875,0.0007669948,0.0006269182,0.0009886468,0.001044389,0.0013661985,0.0013402693],"category_scores_gemma":[0.051559135,0.00063433644,0.0016753976,0.0007222693,0.0007113639,0.0011108456,0.0008947828,0.0019262101,0.00013686462],"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":[0.0013813067,0.0006517756,0.10802939,0.000122971,0.00034254979,0.00023632274,0.00026298966,0.8785662,0.0003131139,0.0015214414,0.00054323446,0.008028772],"study_design_scores_gemma":[0.00019026965,0.00046751078,0.0072320225,0.00004144269,0.00014435471,0.0000707165,0.000121753634,0.9896729,0.00031812978,0.0015396249,0.00018186487,0.000019492458],"about_ca_topic_score_codex":0.02310107,"about_ca_topic_score_gemma":0.015027644,"teacher_disagreement_score":0.9838575,"about_ca_system_score_codex":0.0018766992,"about_ca_system_score_gemma":0.0028568057,"threshold_uncertainty_score":0.08537072},"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":"review","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023148833,0.8267936,0.15594499,0.0039150966,0.0020011305,0.0044530933,0.001281173,0.00029651306,0.0029995195],"genre_scores_gemma":[0.09131377,0.46645933,0.40159178,0.004625345,0.0049612676,0.028123716,0.0018204235,0.0005162556,0.0005881095],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.2874201,0.57429606,0.089313515,0.016541896,0.031503055,0.0009252911],"domain_scores_gemma":[0.10615728,0.8198795,0.04491143,0.01645489,0.012160982,0.000436017],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5303099,0.0037769815,0.015031132,0.04065981,0.0010065914,0.011281221,0.012310668,0.006352551,0.004223093],"category_scores_gemma":[0.7525079,0.0038025628,0.019624462,0.033760794,0.007850427,0.00901457,0.006471585,0.0074870484,0.0008978272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013727923,0.0002730401,0.035026245,0.3157728,0.04369841,0.001133857,0.0047864392,0.006200593,0.00059386744,0.088637896,0.014841393,0.48766264],"study_design_scores_gemma":[0.0015702739,0.0030712588,0.03504197,0.46981147,0.042452626,0.011609135,0.0039843847,0.020396013,0.0031796275,0.1648823,0.2428394,0.0011615441],"about_ca_topic_score_codex":0.0032297738,"about_ca_topic_score_gemma":0.0018284129,"teacher_disagreement_score":0.46969008,"about_ca_system_score_codex":0.008180703,"about_ca_system_score_gemma":0.008344483,"threshold_uncertainty_score":0.57921153},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33762497,0.59998393,0.028342007,0.00837881,0.000829609,0.011133564,0.007026305,0.00019005484,0.006490732],"genre_scores_gemma":[0.89535934,0.053273126,0.030306261,0.0045106583,0.00035316832,0.013598042,0.0021593843,0.0001623576,0.00027776175],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.2270231,0.3804368,0.30038854,0.01893815,0.071195856,0.002017621],"domain_scores_gemma":[0.06261252,0.7514549,0.12269242,0.02568521,0.03624196,0.0013129892],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4605903,0.0015542087,0.006640377,0.028452624,0.0029396077,0.013551551,0.003726588,0.004144344,0.0030317728],"category_scores_gemma":[0.8019162,0.0039061736,0.009646131,0.03694949,0.0042634364,0.015739333,0.010692351,0.0030922014,0.00054596126],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004825107,0.00059229304,0.6464594,0.15627109,0.07299167,0.00079576875,0.019331701,0.0006005203,0.0007490428,0.0024299696,0.0024595468,0.09249388],"study_design_scores_gemma":[0.0030137103,0.0051527116,0.60559565,0.16741124,0.15298101,0.007869658,0.021102823,0.0030658364,0.0025870549,0.0075463457,0.022904623,0.00076934265],"about_ca_topic_score_codex":0.0045375917,"about_ca_topic_score_gemma":0.006919132,"teacher_disagreement_score":0.5394097,"about_ca_system_score_codex":0.0073449435,"about_ca_system_score_gemma":0.010314509,"threshold_uncertainty_score":0.6651882},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013925869,0.009536851,0.0037179624,0.08837836,0.8971835,0.000055195633,0.000039531387,0.0001597943,0.0007895834],"genre_scores_gemma":[0.002191661,0.0107831415,0.0044675553,0.03133487,0.948433,0.00010755467,0.000039733266,0.00018752036,0.0024550052],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.94528997,0.022912018,0.009370886,0.0039070747,0.017782716,0.0007373293],"domain_scores_gemma":[0.59102035,0.28985804,0.009239017,0.00993755,0.093949564,0.0059954766],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.072541624,0.0036465845,0.0035618069,0.005910587,0.0049861856,0.010977968,0.006407709,0.014163022,0.0035927028],"category_scores_gemma":[0.30012414,0.0016702677,0.002291132,0.003104346,0.011749578,0.009294922,0.0038292229,0.026749872,0.0033538868],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000392158,0.000021006746,0.00015984208,0.0011415072,0.000049195183,0.00016497546,0.0005227452,0.00009573139,0.00014944514,0.0029268605,0.9625304,0.032199096],"study_design_scores_gemma":[0.00007452522,0.00006930738,0.000846546,0.0035357678,0.00013205684,0.00067763677,0.00080386974,0.0009936352,0.00047346612,0.014014485,0.9782956,0.000083110506],"about_ca_topic_score_codex":0.0021965434,"about_ca_topic_score_gemma":0.005827831,"teacher_disagreement_score":0.9274584,"about_ca_system_score_codex":0.0046243947,"about_ca_system_score_gemma":0.008494298,"threshold_uncertainty_score":0.38364136},"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":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067462966,0.064649954,0.049015798,0.75767803,0.011198928,0.0008943464,0.00045917262,0.0001793597,0.04846137],"genre_scores_gemma":[0.83379096,0.020545254,0.020810919,0.11441214,0.005215347,0.002013282,0.0001460042,0.00027589075,0.0027901686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.64637136,0.2955599,0.015488223,0.010082335,0.026894383,0.005603851],"domain_scores_gemma":[0.29764622,0.6294822,0.028820047,0.016670413,0.019802017,0.007579037],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30331331,0.0005796308,0.0015386612,0.0027262464,0.0046222773,0.011408697,0.0029867778,0.0052567087,0.01558367],"category_scores_gemma":[0.50524586,0.0008570865,0.0015784394,0.00359405,0.030894278,0.019300053,0.006556564,0.0055100815,0.0012433555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008325659,0.00031742005,0.08086016,0.009635095,0.00050684053,0.0006049287,0.09134011,0.0006214499,0.00043578903,0.43067566,0.035511784,0.3486581],"study_design_scores_gemma":[0.00037966348,0.00083227124,0.05294245,0.039808348,0.0005210868,0.0011607149,0.09456495,0.001448394,0.0017555965,0.6370687,0.16928217,0.00023569257],"about_ca_topic_score_codex":0.0044387607,"about_ca_topic_score_gemma":0.003862015,"teacher_disagreement_score":0.6966867,"about_ca_system_score_codex":0.0076119583,"about_ca_system_score_gemma":0.016811362,"threshold_uncertainty_score":0.8591387},"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":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041360088,0.0022700154,0.94778126,0.0022019376,0.00045898248,0.0022077104,0.0008138317,0.000893602,0.002012687],"genre_scores_gemma":[0.6555062,0.0008578253,0.3295508,0.0016717565,0.00034980083,0.008690291,0.00094548287,0.00014565412,0.0022822325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8148047,0.17313115,0.0029871366,0.0043092635,0.0036195444,0.0011482672],"domain_scores_gemma":[0.4808081,0.4931005,0.011497217,0.009970435,0.0032896318,0.0013340764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16630106,0.0018605456,0.004196714,0.0026929998,0.00060691766,0.0026282957,0.0039281673,0.0031817819,0.00988501],"category_scores_gemma":[0.3226643,0.00078115094,0.0053083086,0.0023332515,0.0034977396,0.0033045246,0.0029517892,0.005429136,0.001098695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011789169,0.0011419553,0.036773004,0.0047198087,0.00684413,0.0008743522,0.0012470287,0.46373966,0.0014222696,0.24278359,0.009001312,0.21966375],"study_design_scores_gemma":[0.0011936933,0.0030796677,0.0050039934,0.00037680336,0.00095376634,0.00017686334,0.000113181944,0.86249197,0.0007073603,0.12232895,0.0034886296,0.00008515529],"about_ca_topic_score_codex":0.0014831532,"about_ca_topic_score_gemma":0.0007856259,"teacher_disagreement_score":0.16630106,"about_ca_system_score_codex":0.0017329899,"about_ca_system_score_gemma":0.003243621,"threshold_uncertainty_score":0.87949455},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8897006,0.0062127123,0.08454816,0.0022228176,0.00030818078,0.0060167024,0.003639687,0.00020367329,0.007147369],"genre_scores_gemma":[0.9888629,0.00018369344,0.008378598,0.00049929396,0.000014924611,0.0011069136,0.0004480645,0.000033171113,0.00047245197],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.6880767,0.27787113,0.008362155,0.01153203,0.010861959,0.0032960856],"domain_scores_gemma":[0.29613006,0.6356863,0.020886816,0.029671552,0.015616255,0.0020090763],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36706138,0.0010852112,0.0018940134,0.0018127545,0.0019541227,0.002674406,0.0034506775,0.0017902538,0.0033842209],"category_scores_gemma":[0.47318524,0.0009618583,0.00653397,0.0023597484,0.0038736353,0.0016815757,0.0030739813,0.002626143,0.00017262126],"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":[0.012660768,0.0004842314,0.80140376,0.0033701265,0.041560188,0.0012204322,0.009946311,0.05925924,0.0014138022,0.020791197,0.00561322,0.042276733],"study_design_scores_gemma":[0.0014264713,0.004490676,0.68096316,0.003455527,0.04509101,0.0007604756,0.0073955073,0.2018702,0.004535394,0.02781766,0.02146416,0.0007298268],"about_ca_topic_score_codex":0.20233081,"about_ca_topic_score_gemma":0.12140565,"teacher_disagreement_score":0.7976692,"about_ca_system_score_codex":0.009922909,"about_ca_system_score_gemma":0.0072180727,"threshold_uncertainty_score":0.78052604},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5252372,0.00352199,0.051964443,0.39469847,0.0011366906,0.0052167634,0.001189018,0.00027944415,0.016756056],"genre_scores_gemma":[0.9048696,0.002239676,0.027651843,0.054566074,0.00045159284,0.00865799,0.00046993254,0.00006959497,0.001023731],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.625708,0.32497868,0.016917557,0.008521008,0.016661683,0.0072130538],"domain_scores_gemma":[0.41778728,0.43677044,0.06013099,0.02813782,0.036267944,0.020905439],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26350677,0.0006358557,0.0010079684,0.002000047,0.0057351766,0.006737956,0.0036720799,0.0056528305,0.004936519],"category_scores_gemma":[0.30427665,0.0008008097,0.00079643726,0.0029701132,0.0056229443,0.009762911,0.008367225,0.005591264,0.0009951025],"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":[0.0006904512,0.001343441,0.38830814,0.004094941,0.000289518,0.001981016,0.22942175,0.000932789,0.003109156,0.014754536,0.05846396,0.29661036],"study_design_scores_gemma":[0.0003502527,0.0018862156,0.19616525,0.008592653,0.00015040481,0.0020595489,0.6345807,0.0058356086,0.0020590727,0.048209313,0.09957479,0.00053623936],"about_ca_topic_score_codex":0.004978862,"about_ca_topic_score_gemma":0.006232602,"teacher_disagreement_score":0.73649323,"about_ca_system_score_codex":0.004735998,"about_ca_system_score_gemma":0.017308893,"threshold_uncertainty_score":0.90822726},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91363466,0.0010589531,0.015875543,0.0004637912,0.00016325053,0.061032817,0.0012797798,0.00005295573,0.0064382437],"genre_scores_gemma":[0.82754,0.0009220541,0.04515254,0.0005454145,0.00007058451,0.12276987,0.0018220432,0.0000715836,0.0011059032],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9247113,0.05767376,0.0081660785,0.0026015316,0.005131159,0.0017162202],"domain_scores_gemma":[0.8813423,0.07975169,0.008381194,0.010513185,0.018724252,0.0012874348],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11881831,0.0008084417,0.0010929946,0.0033408965,0.0018451911,0.0017838896,0.0015276007,0.00086855644,0.0029220367],"category_scores_gemma":[0.10288598,0.0010096321,0.0014361221,0.003484699,0.00283691,0.0017137186,0.0039977445,0.0016267761,0.00064165273],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028552737,0.0049719936,0.52864856,0.0074011125,0.0003942606,0.0008850642,0.23437324,0.0007643364,0.0050669773,0.0028399976,0.002554246,0.2092449],"study_design_scores_gemma":[0.0019276609,0.0143915545,0.68208826,0.004152521,0.00090242596,0.0010848276,0.24528581,0.0012439014,0.008176772,0.0016296594,0.03894479,0.00017180169],"about_ca_topic_score_codex":0.003895396,"about_ca_topic_score_gemma":0.006527798,"teacher_disagreement_score":0.8811817,"about_ca_system_score_codex":0.0027066052,"about_ca_system_score_gemma":0.007867742,"threshold_uncertainty_score":0.6283788},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8117333,0.0051113074,0.16116782,0.007990398,0.0010523683,0.004196617,0.0042983233,0.0003406076,0.004109301],"genre_scores_gemma":[0.94996434,0.000515837,0.042210966,0.000996527,0.00013263566,0.0038909486,0.0014473196,0.00008640354,0.00075501244],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.77093023,0.19894813,0.009104244,0.0077722077,0.010073185,0.0031719618],"domain_scores_gemma":[0.77364564,0.15043081,0.032618366,0.030215144,0.011068187,0.0020217802],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2292263,0.0008129168,0.0011277127,0.0022896118,0.0022067819,0.0016459728,0.0029251084,0.0014260949,0.0016179319],"category_scores_gemma":[0.33695897,0.00079365465,0.0027559353,0.0038049698,0.0011920512,0.0017798397,0.0027307835,0.0026439654,0.00023453396],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023041769,0.0000906734,0.96621376,0.00027137177,0.0018268253,0.00013392637,0.0018178317,0.0008524874,0.000091147645,0.0015445764,0.0028945634,0.02403248],"study_design_scores_gemma":[0.000087803965,0.0007064562,0.96815854,0.0006797053,0.0012045784,0.000276762,0.002332997,0.011822535,0.0007508019,0.0048783403,0.009011419,0.00009014422],"about_ca_topic_score_codex":0.024004174,"about_ca_topic_score_gemma":0.023381734,"teacher_disagreement_score":0.7707737,"about_ca_system_score_codex":0.0019160596,"about_ca_system_score_gemma":0.0063691507,"threshold_uncertainty_score":0.9505012},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05449849,0.00037567902,0.92868876,0.0010790492,0.000084418505,0.00033186108,0.0031266264,0.0021700407,0.00964508],"genre_scores_gemma":[0.57737917,0.0012942733,0.3910954,0.0007106514,0.00020427858,0.0020897908,0.005159101,0.00034314656,0.021724112],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994209,0.00026046904,0.000039369148,0.00011579626,0.00010988198,0.000053654032],"domain_scores_gemma":[0.9935695,0.0054201847,0.00026758813,0.00013365626,0.0005317116,0.00007741203],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018996096,0.00084330625,0.0008234478,0.0012395557,0.00047407573,0.0012732435,0.0019962976,0.0018394102,0.012869834],"category_scores_gemma":[0.008147073,0.00062529545,0.0009851631,0.0012230043,0.00035025371,0.0012563027,0.00069500593,0.0012994411,0.0019632033],"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":[0.00010098825,0.00010828961,0.0036478296,0.000052646246,0.00006024576,0.00009657166,0.000040778817,0.9671611,0.0002242615,0.0045143142,0.002428196,0.02156483],"study_design_scores_gemma":[0.000020647558,0.00001671481,0.00033975093,0.0000124815615,0.000013674574,0.000025943447,0.000005875273,0.99629694,0.00008999752,0.0025066074,0.0006649447,0.0000064364745],"about_ca_topic_score_codex":0.027470462,"about_ca_topic_score_gemma":0.015477105,"teacher_disagreement_score":0.9981004,"about_ca_system_score_codex":0.0010771095,"about_ca_system_score_gemma":0.0018338382,"threshold_uncertainty_score":0.05462116},"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":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18988106,0.00784942,0.19970337,0.011676415,0.0017151586,0.5742453,0.0015839828,0.0011731847,0.01217205],"genre_scores_gemma":[0.19278978,0.0025670992,0.5674654,0.0025904528,0.0001238931,0.23311536,0.0003196018,0.00007313633,0.0009552185],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.5543097,0.32991865,0.06372306,0.009133724,0.039285004,0.0036297848],"domain_scores_gemma":[0.43239063,0.3889791,0.04689387,0.03100515,0.096917324,0.003813956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38301307,0.0023003432,0.0031271013,0.0075403973,0.002872969,0.004544776,0.0032235472,0.0024091422,0.002863227],"category_scores_gemma":[0.4534557,0.002069551,0.004148932,0.0063414,0.00327817,0.0066736178,0.0058161314,0.0023392965,0.0008634816],"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":[0.0024530264,0.0032416917,0.062265117,0.070854,0.0029040994,0.00045689187,0.08081631,0.0019667454,0.0042798845,0.0073252944,0.008272153,0.75516474],"study_design_scores_gemma":[0.025806807,0.07350674,0.18107313,0.2310026,0.014991225,0.0015368151,0.18814956,0.03941315,0.04308099,0.04360151,0.1554549,0.002382614],"about_ca_topic_score_codex":0.0067763943,"about_ca_topic_score_gemma":0.021169761,"teacher_disagreement_score":0.38301307,"about_ca_system_score_codex":0.009219962,"about_ca_system_score_gemma":0.08182382,"threshold_uncertainty_score":0.7608547},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06986409,0.19842292,0.0964501,0.6081716,0.0064111045,0.010013713,0.0012362135,0.0005203666,0.008909965],"genre_scores_gemma":[0.5196918,0.07286253,0.33371815,0.05507228,0.003999769,0.0131618325,0.00074130396,0.00018214395,0.0005701887],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.5583294,0.34033954,0.05666063,0.007533806,0.033255678,0.0038809308],"domain_scores_gemma":[0.08352304,0.8015373,0.04382881,0.0206171,0.04546576,0.0050279936],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.47533783,0.0014633635,0.0030667009,0.015805887,0.0018740766,0.01682785,0.008879949,0.005535831,0.0037149026],"category_scores_gemma":[0.7471808,0.0012662086,0.0034921218,0.0075128283,0.006652513,0.02293794,0.01119047,0.0071584326,0.00057373336],"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":[0.00094118464,0.00090702984,0.080669224,0.09659368,0.0037845175,0.0007406257,0.04375175,0.0034355868,0.00058459665,0.028580787,0.029721506,0.7102895],"study_design_scores_gemma":[0.0010597616,0.0023537348,0.06702036,0.64441836,0.0035910523,0.0011093487,0.059879392,0.0107948985,0.0017251933,0.10386315,0.10364061,0.00054409157],"about_ca_topic_score_codex":0.007074355,"about_ca_topic_score_gemma":0.011639904,"teacher_disagreement_score":0.47533783,"about_ca_system_score_codex":0.013475874,"about_ca_system_score_gemma":0.050403696,"threshold_uncertainty_score":0.64700186},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010810754,0.30764037,0.67101574,0.0035947345,0.00081518176,0.0021091138,0.0015935039,0.00080510706,0.0016154813],"genre_scores_gemma":[0.152013,0.093700476,0.74093705,0.0018943137,0.00038362484,0.008094488,0.0015853673,0.00064584083,0.00074584136],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8405931,0.14422005,0.006412846,0.0039771628,0.0044951243,0.00030169883],"domain_scores_gemma":[0.7504673,0.22672532,0.0060230116,0.011696102,0.0047330423,0.00035525806],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14326479,0.003056067,0.0068066516,0.007883055,0.0006626826,0.005247237,0.0036674177,0.0021495845,0.0026234614],"category_scores_gemma":[0.30534598,0.0014983518,0.02518631,0.0070476267,0.0009580686,0.003760212,0.0030241017,0.0039043357,0.0004617315],"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":[0.0045910478,0.00019298116,0.009032377,0.071685374,0.44746765,0.00026991643,0.00093229173,0.069429636,0.0019090847,0.037434205,0.0077659306,0.3492895],"study_design_scores_gemma":[0.0059380457,0.002828881,0.015012052,0.029855674,0.4723324,0.0009024073,0.0007548716,0.18212478,0.0052336846,0.2335577,0.050598506,0.00086106337],"about_ca_topic_score_codex":0.0022362256,"about_ca_topic_score_gemma":0.0038342134,"teacher_disagreement_score":0.8567352,"about_ca_system_score_codex":0.0027005547,"about_ca_system_score_gemma":0.0030909404,"threshold_uncertainty_score":0.75766563},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05403775,0.005193455,0.92307365,0.0017137119,0.000334305,0.010221353,0.00047815972,0.00024735727,0.004700266],"genre_scores_gemma":[0.52383834,0.0015067655,0.4525721,0.0017670026,0.00020143818,0.018327517,0.0005361086,0.00007363052,0.0011770304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.24606189,0.7006791,0.019316077,0.011886554,0.020276757,0.0017796765],"domain_scores_gemma":[0.124353945,0.8268928,0.026330873,0.018268382,0.0034958306,0.000658188],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.54880565,0.003354459,0.0072117746,0.0054630223,0.0010501347,0.0055399598,0.0044979486,0.008131398,0.005471555],"category_scores_gemma":[0.76557714,0.0024306388,0.011576164,0.0040691597,0.013859223,0.007996251,0.005689874,0.007864948,0.00064114813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028047511,0.0013421018,0.0505606,0.017141309,0.01802573,0.0021885235,0.004682124,0.13423602,0.0029812553,0.40981638,0.003501407,0.3274771],"study_design_scores_gemma":[0.0065783532,0.012169693,0.025097234,0.00580122,0.006800938,0.002317834,0.00074266474,0.28799593,0.007158091,0.63377273,0.010880654,0.00068464834],"about_ca_topic_score_codex":0.0008084629,"about_ca_topic_score_gemma":0.0005634014,"teacher_disagreement_score":0.45119435,"about_ca_system_score_codex":0.0047067977,"about_ca_system_score_gemma":0.0041010315,"threshold_uncertainty_score":0.55640304},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016593123,0.023120461,0.81943464,0.061628707,0.0015087972,0.032876454,0.004135228,0.0009198216,0.039782755],"genre_scores_gemma":[0.048515033,0.0033419759,0.9238534,0.002630522,0.000113231625,0.019645624,0.0012669372,0.000059416176,0.0005737843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.63028914,0.28024992,0.05076282,0.010074316,0.02514929,0.0034746032],"domain_scores_gemma":[0.7672095,0.14753565,0.020713981,0.023739152,0.03605317,0.0047484646],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28773353,0.0034275365,0.0038794929,0.025694333,0.0053243334,0.0124505805,0.00868893,0.0058677886,0.0026526998],"category_scores_gemma":[0.24021018,0.0025982675,0.010902672,0.011209545,0.0176261,0.01090061,0.018236034,0.008695455,0.00095975643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032546988,0.0004393967,0.012013469,0.04077891,0.000998537,0.00034663506,0.045452967,0.009838116,0.0025850998,0.5557063,0.021968132,0.30954692],"study_design_scores_gemma":[0.0007107412,0.001193794,0.016722223,0.106766395,0.0026227836,0.001450508,0.019333657,0.014940138,0.004650456,0.42693105,0.4040974,0.00058088556],"about_ca_topic_score_codex":0.01420108,"about_ca_topic_score_gemma":0.01623143,"teacher_disagreement_score":0.71226645,"about_ca_system_score_codex":0.037966438,"about_ca_system_score_gemma":0.09989538,"threshold_uncertainty_score":0.8783514},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15736982,0.008378635,0.6318938,0.14080933,0.013565438,0.032965414,0.0012756475,0.0013702468,0.012371737],"genre_scores_gemma":[0.6056707,0.0016331264,0.3216029,0.031973585,0.003827766,0.033202123,0.00060558016,0.00046485587,0.0010194205],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.26201624,0.635143,0.03152687,0.016371414,0.053061217,0.0018813143],"domain_scores_gemma":[0.102901414,0.83134997,0.020728698,0.017267598,0.025784958,0.0019673507],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6213381,0.001688682,0.0024885705,0.0043566884,0.005033161,0.00526636,0.0048880256,0.0049827946,0.0030157722],"category_scores_gemma":[0.8618037,0.0015450484,0.0027546985,0.0057270555,0.017750835,0.0073265224,0.0040048477,0.0053800824,0.00081097404],"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":[0.00392235,0.0014322915,0.24142607,0.00674232,0.0028391182,0.0022602044,0.086040385,0.007222349,0.0023153983,0.07993187,0.14723934,0.41862828],"study_design_scores_gemma":[0.0065110954,0.007210391,0.33232036,0.024158396,0.001850705,0.0036014938,0.036205977,0.15807098,0.0070460327,0.32370797,0.098088555,0.0012279856],"about_ca_topic_score_codex":0.008918378,"about_ca_topic_score_gemma":0.01048834,"teacher_disagreement_score":0.37866187,"about_ca_system_score_codex":0.0049080784,"about_ca_system_score_gemma":0.010793744,"threshold_uncertainty_score":0.46695757},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006958599,0.059770737,0.0025213426,0.1172724,0.8188249,0.0001282009,0.000073198484,0.00017574381,0.0011639722],"genre_scores_gemma":[0.0009366652,0.04354328,0.003255354,0.06458529,0.8846541,0.00028425848,0.000040148447,0.00016493013,0.0025359504],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8453566,0.07716049,0.022846391,0.007129693,0.045765854,0.0017409715],"domain_scores_gemma":[0.32270545,0.58129674,0.017141638,0.00850939,0.062038984,0.0083078835],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12712121,0.0038308415,0.005037999,0.0069005406,0.0048446646,0.016578253,0.008707507,0.032388147,0.0044769133],"category_scores_gemma":[0.353876,0.0024182897,0.0042631123,0.0053922087,0.012718947,0.0131491115,0.0036544204,0.038140997,0.0049351747],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109572225,0.000033103177,0.000119486496,0.005763595,0.00012863986,0.00028742923,0.0004724313,0.00012478279,0.00010665566,0.003813555,0.9385512,0.050489526],"study_design_scores_gemma":[0.00014269889,0.00009487853,0.00035351538,0.011283891,0.00014932724,0.000477674,0.00040557672,0.0003638287,0.00013948316,0.006994417,0.9795289,0.00006591597],"about_ca_topic_score_codex":0.00219078,"about_ca_topic_score_gemma":0.0054636984,"teacher_disagreement_score":0.8728788,"about_ca_system_score_codex":0.0076756305,"about_ca_system_score_gemma":0.014163368,"threshold_uncertainty_score":0.67228925},"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":"review","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29000634,0.4173486,0.04659103,0.0063990727,0.0020173448,0.17423981,0.050940186,0.0014346767,0.011022939],"genre_scores_gemma":[0.41884005,0.17999555,0.18880235,0.0055741547,0.0011668373,0.16695978,0.03521649,0.0007815623,0.0026632613],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.3515312,0.13698739,0.42590573,0.011304685,0.071828365,0.0024425688],"domain_scores_gemma":[0.11512839,0.46486738,0.29088864,0.041853927,0.08515038,0.0021113795],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31067207,0.002332782,0.009087578,0.10326271,0.0025546665,0.008077423,0.0036062251,0.0036241037,0.0032106997],"category_scores_gemma":[0.698716,0.002310416,0.0048085907,0.08569303,0.0049672653,0.010700318,0.0073294607,0.0024223689,0.0014563287],"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":[0.015108614,0.00087690155,0.15358213,0.41968027,0.006103813,0.002443617,0.021664066,0.0008296591,0.009808217,0.0034764814,0.011857764,0.35456854],"study_design_scores_gemma":[0.0106514655,0.010544207,0.36001027,0.40339077,0.037582796,0.008869643,0.014273337,0.004799579,0.018682096,0.0069000465,0.1230286,0.0012672853],"about_ca_topic_score_codex":0.002782671,"about_ca_topic_score_gemma":0.0049617435,"teacher_disagreement_score":0.68932796,"about_ca_system_score_codex":0.007052069,"about_ca_system_score_gemma":0.021200644,"threshold_uncertainty_score":0.85006404},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.115995646,0.061914813,0.653299,0.02894897,0.0015650622,0.06924506,0.0075795124,0.0004178081,0.061034154],"genre_scores_gemma":[0.1836464,0.013295105,0.6815718,0.002197344,0.00011179112,0.11506817,0.0023093186,0.00009451673,0.0017057323],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8892969,0.08373129,0.01375309,0.003780185,0.008535434,0.0009030354],"domain_scores_gemma":[0.79245037,0.16548397,0.017453227,0.008047546,0.015547491,0.0010174146],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.12389744,0.0016341101,0.0013450269,0.02004716,0.0028216052,0.005445836,0.0035892613,0.002005012,0.0041189035],"category_scores_gemma":[0.16030666,0.0009948807,0.0033197321,0.0151432175,0.010271215,0.009202228,0.009097787,0.0033641416,0.00063260546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021076936,0.00018337587,0.028880252,0.041355833,0.0004810938,0.00073679374,0.38927767,0.0009550992,0.0017998872,0.13591754,0.012962546,0.3872392],"study_design_scores_gemma":[0.0003231483,0.0005977432,0.05360393,0.08861198,0.0013027125,0.0020467492,0.3377182,0.0032826893,0.003030839,0.21032223,0.2987728,0.00038702425],"about_ca_topic_score_codex":0.00734365,"about_ca_topic_score_gemma":0.013675828,"teacher_disagreement_score":0.87610257,"about_ca_system_score_codex":0.010780376,"about_ca_system_score_gemma":0.021222053,"threshold_uncertainty_score":0.6552401},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11950702,0.25915065,0.3310985,0.018337531,0.008245696,0.20271021,0.03432075,0.003627818,0.023001788],"genre_scores_gemma":[0.33421236,0.01293127,0.3908209,0.0022446143,0.000790328,0.25311995,0.004720804,0.000455423,0.00070427125],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.13989447,0.40067145,0.37757823,0.015477082,0.06432452,0.0020543407],"domain_scores_gemma":[0.05175774,0.7313998,0.11259846,0.024896426,0.07775519,0.0015924675],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.741162,0.0048779934,0.0195864,0.042239707,0.0045463364,0.013040396,0.006273275,0.005430988,0.0068066036],"category_scores_gemma":[0.85857,0.0044376124,0.044958968,0.038941883,0.00802885,0.010426315,0.0123605775,0.0051389597,0.0009844261],"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":[0.008097285,0.00021485185,0.08165959,0.58890367,0.13302442,0.00056055875,0.011762783,0.0052235797,0.001256288,0.009508941,0.012701695,0.14708626],"study_design_scores_gemma":[0.013272021,0.0066996724,0.1830655,0.39080733,0.20807004,0.0023298208,0.010155815,0.03663897,0.0076939655,0.050367065,0.08831318,0.0025866725],"about_ca_topic_score_codex":0.0033621406,"about_ca_topic_score_gemma":0.0071176295,"teacher_disagreement_score":0.258838,"about_ca_system_score_codex":0.014016801,"about_ca_system_score_gemma":0.023144342,"threshold_uncertainty_score":0.31919336},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99232435,0.0027401287,0.0025313438,0.0003961922,0.000050819057,0.00009643377,0.0011907459,0.000014737265,0.00065516506],"genre_scores_gemma":[0.99750155,0.0004617987,0.0010511292,0.00018807699,0.00003468761,0.00007389099,0.0005704272,0.000006992707,0.000111446265],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98913294,0.0050552227,0.001433048,0.0017344389,0.0021298185,0.00051463564],"domain_scores_gemma":[0.9690662,0.006964216,0.015133473,0.0059271813,0.0022777354,0.00063124544],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017470267,0.00034995834,0.0006485487,0.0009870774,0.0007348011,0.0011610631,0.001102136,0.00081193977,0.00074226415],"category_scores_gemma":[0.025522383,0.0005128221,0.0012131822,0.0024200664,0.00075998914,0.00069221575,0.0007087772,0.0010008181,0.00019420093],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010670682,0.000018615796,0.99807775,0.00002551938,0.00033155954,0.00003069015,0.00008723954,0.000025408692,0.00007126479,0.000055217777,0.00007934771,0.0010907694],"study_design_scores_gemma":[0.0000144084115,0.00014815238,0.9981964,0.000039761773,0.0003258123,0.00028294485,0.0001326624,0.00029268558,0.00009020815,0.000070365284,0.00039532944,0.000011330538],"about_ca_topic_score_codex":0.014871031,"about_ca_topic_score_gemma":0.015584136,"teacher_disagreement_score":0.98252976,"about_ca_system_score_codex":0.0006373273,"about_ca_system_score_gemma":0.0012371154,"threshold_uncertainty_score":0.09239274},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07484647,0.883992,0.018516291,0.004768174,0.0011815211,0.009708215,0.003547761,0.00016416104,0.0032753977],"genre_scores_gemma":[0.7678807,0.16659518,0.029177623,0.0065499973,0.0010268055,0.02543741,0.002338732,0.00034606617,0.00064756535],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.23941937,0.38423243,0.28515154,0.02593242,0.06317963,0.0020845593],"domain_scores_gemma":[0.058138445,0.7830277,0.11466776,0.019193502,0.024034375,0.00093824643],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5409521,0.002628473,0.012202711,0.032498974,0.0031587158,0.0120979175,0.0045940336,0.0052508726,0.0056966413],"category_scores_gemma":[0.8453652,0.0051819026,0.026023472,0.035628136,0.008066512,0.014528913,0.014069447,0.005345644,0.00084509805],"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":[0.0028866741,0.000268739,0.17073423,0.5355445,0.18030404,0.0008328207,0.033545546,0.0006061078,0.00044078674,0.0030599511,0.0039329873,0.06784361],"study_design_scores_gemma":[0.0022361344,0.0019116997,0.11696098,0.57685363,0.25431275,0.0037547962,0.015387941,0.0014676269,0.0009933956,0.005511287,0.020124726,0.00048500416],"about_ca_topic_score_codex":0.0060482672,"about_ca_topic_score_gemma":0.00790755,"teacher_disagreement_score":0.98779726,"about_ca_system_score_codex":0.012204246,"about_ca_system_score_gemma":0.014621981,"threshold_uncertainty_score":0.56608784},"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":"reporting","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026587695,0.03602089,0.67709184,0.0250424,0.0035142552,0.19954732,0.013663786,0.007509002,0.01102286],"genre_scores_gemma":[0.020595253,0.0028620579,0.8972047,0.0008590616,0.00022560237,0.076307505,0.0016045191,0.00016428503,0.00017695577],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.2463922,0.32345968,0.33284262,0.014643044,0.08053421,0.002128248],"domain_scores_gemma":[0.07971947,0.72546047,0.07030262,0.035984147,0.08648638,0.0020469243],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5703085,0.0049826647,0.012055216,0.07910931,0.0041734357,0.01745308,0.0066899573,0.005623569,0.0053520924],"category_scores_gemma":[0.82838094,0.005776962,0.0263061,0.05035644,0.0075226435,0.026707925,0.021607846,0.0099614,0.0014187314],"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":[0.0007565295,0.00029965412,0.014736083,0.22784796,0.010399078,0.00031489134,0.018008677,0.0050984845,0.0017166759,0.015600328,0.023960497,0.6812612],"study_design_scores_gemma":[0.006582201,0.0035964407,0.0607446,0.3841923,0.040041417,0.003534786,0.013189796,0.062085334,0.009391831,0.15205069,0.2604548,0.004135767],"about_ca_topic_score_codex":0.0028163358,"about_ca_topic_score_gemma":0.0056717526,"teacher_disagreement_score":0.4296915,"about_ca_system_score_codex":0.020295031,"about_ca_system_score_gemma":0.06508214,"threshold_uncertainty_score":0.5298861},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031888925,0.0005892638,0.96565294,0.0005447534,0.000114581395,0.00036709447,0.0000696229,0.0003500978,0.0004227745],"genre_scores_gemma":[0.51142853,0.00023806223,0.4863264,0.00038428314,0.00010957647,0.0008301976,0.00017274855,0.0001652647,0.00034504058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95534694,0.035284743,0.002519446,0.0032890635,0.0027958278,0.00076404895],"domain_scores_gemma":[0.89377993,0.084838755,0.008100331,0.010040668,0.002545616,0.000694756],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06941801,0.0009543284,0.0017375934,0.0014024663,0.0008438102,0.0015650406,0.0020648432,0.0016198277,0.0018197118],"category_scores_gemma":[0.17762883,0.0006040176,0.002167034,0.0017397716,0.0018809385,0.0021167083,0.0025137425,0.0021567426,0.0002565408],"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":[0.0050741923,0.00067122024,0.15290485,0.0026710238,0.004823809,0.0013917957,0.0027463397,0.12836537,0.01785288,0.10354469,0.0072714672,0.5726824],"study_design_scores_gemma":[0.0010560883,0.0022762024,0.035777766,0.0006992397,0.0018129756,0.0014558516,0.0003686956,0.666053,0.020897735,0.25619805,0.013137339,0.0002670366],"about_ca_topic_score_codex":0.0013631294,"about_ca_topic_score_gemma":0.0012995506,"teacher_disagreement_score":0.930582,"about_ca_system_score_codex":0.00088557875,"about_ca_system_score_gemma":0.0022364182,"threshold_uncertainty_score":0.36712193},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9506038,0.0013621073,0.013945644,0.0008050448,0.00025414734,0.0024610641,0.0074788206,0.00008812439,0.02300127],"genre_scores_gemma":[0.9642433,0.0005541015,0.026814869,0.00017674394,0.000037429807,0.0027647917,0.0038013894,0.000036582973,0.0015707104],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97939086,0.0077834697,0.0038585425,0.0011913399,0.0073332307,0.0004425822],"domain_scores_gemma":[0.94093907,0.030455416,0.007361577,0.0031680115,0.017200246,0.00087565574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023207288,0.00038068864,0.0005531452,0.0023097312,0.001065194,0.0021222986,0.00065256184,0.00067083846,0.0025809435],"category_scores_gemma":[0.06841913,0.0004136681,0.0013969903,0.0027463213,0.0007807342,0.00073277805,0.001671129,0.0008321346,0.00063934893],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009349144,0.00044979362,0.8328496,0.0015295594,0.00086239877,0.0001674319,0.009497136,0.0029501505,0.0019464488,0.0040899413,0.007383075,0.13733944],"study_design_scores_gemma":[0.00012325867,0.00066451164,0.96908826,0.00050868065,0.00035924665,0.0004121781,0.004440364,0.0030348187,0.001590022,0.0018866904,0.017794544,0.00009738529],"about_ca_topic_score_codex":0.0077202064,"about_ca_topic_score_gemma":0.0073686326,"teacher_disagreement_score":0.023207288,"about_ca_system_score_codex":0.0017585995,"about_ca_system_score_gemma":0.0026970664,"threshold_uncertainty_score":0.122733355},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09553581,0.036997255,0.12857117,0.6888762,0.013723397,0.001972899,0.0052669425,0.0004818461,0.028574409],"genre_scores_gemma":[0.6271799,0.016296567,0.17740236,0.1568064,0.013061014,0.0030995053,0.0026235036,0.00049933535,0.0030312994],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.72034353,0.17565425,0.0393619,0.00892465,0.053650077,0.002065494],"domain_scores_gemma":[0.30322477,0.5501723,0.05134942,0.04248601,0.04983699,0.0029305005],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30773792,0.0011871606,0.0017213484,0.0066493466,0.001882736,0.009314553,0.0072139157,0.0037200225,0.0017845961],"category_scores_gemma":[0.6536948,0.0012617048,0.0013633702,0.0099891005,0.007677306,0.013605661,0.0055586556,0.0073252465,0.0010288218],"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":[0.0007039622,0.00018920859,0.32984984,0.0038125187,0.0009715296,0.0008968691,0.013639087,0.0022259646,0.00056973816,0.054054253,0.13546397,0.45762298],"study_design_scores_gemma":[0.0003930157,0.000950689,0.23702422,0.062147845,0.0009811576,0.006151389,0.028708529,0.026044043,0.003123863,0.1909087,0.44286776,0.0006987919],"about_ca_topic_score_codex":0.015409438,"about_ca_topic_score_gemma":0.01018727,"teacher_disagreement_score":0.69226205,"about_ca_system_score_codex":0.0044724587,"about_ca_system_score_gemma":0.0064538084,"threshold_uncertainty_score":0.8536824},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043439935,0.15487616,0.73815405,0.04532926,0.0030779168,0.04168536,0.00067565165,0.0006356516,0.011222004],"genre_scores_gemma":[0.04639259,0.037870787,0.80109507,0.009369461,0.0019525844,0.101992935,0.000296198,0.0002909066,0.0007394503],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.07660539,0.803065,0.07746097,0.0074739065,0.03407848,0.0013162954],"domain_scores_gemma":[0.038941324,0.8754633,0.036057368,0.028429829,0.020031318,0.001076775],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.79637265,0.0038486284,0.007468751,0.016839292,0.0038660178,0.017198917,0.010560853,0.012219874,0.0072019654],"category_scores_gemma":[0.8569364,0.0041863467,0.012247601,0.015292166,0.017753977,0.018170932,0.013185823,0.014719884,0.0019006061],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017101442,0.00058816746,0.014470263,0.098193765,0.004992846,0.0019483161,0.013565899,0.0043214527,0.0006650461,0.31477845,0.019667579,0.52509815],"study_design_scores_gemma":[0.0025049304,0.003016202,0.0062897354,0.34197974,0.00515894,0.009162346,0.004441935,0.027318783,0.004075653,0.3338935,0.26136717,0.00079100946],"about_ca_topic_score_codex":0.002164086,"about_ca_topic_score_gemma":0.0021061122,"teacher_disagreement_score":0.20362735,"about_ca_system_score_codex":0.02137975,"about_ca_system_score_gemma":0.04328767,"threshold_uncertainty_score":0.25110883},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014172719,0.0014812412,0.97703403,0.0032198576,0.00019772496,0.0005712474,0.00065396854,0.00034120813,0.0023279558],"genre_scores_gemma":[0.4705843,0.0015847916,0.51800364,0.0024347352,0.0007453292,0.0041865082,0.0009502149,0.00020639124,0.0013041199],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.75906754,0.20580292,0.010112654,0.011892709,0.011601151,0.0015229665],"domain_scores_gemma":[0.52805245,0.29873392,0.038412303,0.12637286,0.0066147354,0.0018138675],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19137058,0.0013099643,0.0027768605,0.0031253714,0.002072325,0.0074842772,0.0053520314,0.0032817023,0.0042920313],"category_scores_gemma":[0.38618475,0.0016967787,0.0036241862,0.00614783,0.0071162623,0.009392936,0.012975857,0.0033660093,0.0008567154],"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":[0.002680634,0.00017808343,0.02486356,0.003486528,0.0031863763,0.001727736,0.0055452012,0.050306328,0.0048308154,0.45863307,0.008092116,0.43646958],"study_design_scores_gemma":[0.0004762987,0.00058164983,0.0031346446,0.0008640503,0.0010519493,0.0013228211,0.0005847809,0.071222655,0.00861816,0.8902766,0.021748923,0.000117449934],"about_ca_topic_score_codex":0.00067132997,"about_ca_topic_score_gemma":0.0003729972,"teacher_disagreement_score":0.8086294,"about_ca_system_score_codex":0.0024052146,"about_ca_system_score_gemma":0.0061355648,"threshold_uncertainty_score":0.99718404},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022818274,0.98901516,0.001890181,0.00185691,0.0005853875,0.002690436,0.0010706419,0.000045822457,0.0005635681],"genre_scores_gemma":[0.081139416,0.8864156,0.010081451,0.0063138725,0.0005816008,0.013805867,0.001182924,0.00007124233,0.00040795878],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.805058,0.09815657,0.0616587,0.007725556,0.025559803,0.0018413825],"domain_scores_gemma":[0.47521928,0.42194837,0.07129034,0.010182343,0.02027861,0.0010809567],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.107769445,0.002052879,0.011837047,0.0155774895,0.0017864029,0.0068951477,0.0033585904,0.004604058,0.0044692117],"category_scores_gemma":[0.42400256,0.00280466,0.011312021,0.015593629,0.0034315686,0.0064296466,0.003397576,0.002562808,0.00062643236],"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":[0.00020249876,0.000018334717,0.0031426682,0.9507652,0.020067507,0.00010226196,0.00045675578,0.00011941014,0.00009556994,0.0005458053,0.002566483,0.02191749],"study_design_scores_gemma":[0.000248342,0.00009185657,0.0040369146,0.9320068,0.052969962,0.00021180019,0.00035711282,0.0001452683,0.00020426126,0.001029667,0.008649317,0.000048643382],"about_ca_topic_score_codex":0.0089679435,"about_ca_topic_score_gemma":0.021038476,"teacher_disagreement_score":0.8922306,"about_ca_system_score_codex":0.009195535,"about_ca_system_score_gemma":0.023568181,"threshold_uncertainty_score":0.5699461},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004003612,0.9957748,0.0013607471,0.00058034493,0.00028587607,0.0006454789,0.00063306483,0.00001780731,0.0003014401],"genre_scores_gemma":[0.01274119,0.97687733,0.0056209443,0.0010938282,0.0002369949,0.0026157042,0.0006603162,0.00002100781,0.00013280803],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9043862,0.046779413,0.030767808,0.0039116675,0.0132908635,0.0008640273],"domain_scores_gemma":[0.6452802,0.3083816,0.02759722,0.0044645485,0.013702031,0.0005744384],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0677409,0.0028531323,0.012655008,0.025463514,0.0012268838,0.0047307843,0.004735938,0.003284038,0.0055527072],"category_scores_gemma":[0.28312954,0.0019321165,0.016055642,0.023766853,0.0024138591,0.005121843,0.0030243348,0.0025905112,0.0005830464],"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":[0.00009021375,0.000008720985,0.00077972596,0.9488094,0.014051782,0.000051966956,0.00014273338,0.00019123,0.000045594836,0.0006887248,0.0014722223,0.03366766],"study_design_scores_gemma":[0.00015240327,0.0001034503,0.002570436,0.92318344,0.0557289,0.00015787997,0.00017837946,0.00017626009,0.00013455148,0.0012077191,0.016362386,0.000044150835],"about_ca_topic_score_codex":0.0106730545,"about_ca_topic_score_gemma":0.024216741,"teacher_disagreement_score":0.9322591,"about_ca_system_score_codex":0.0077912705,"about_ca_system_score_gemma":0.025656758,"threshold_uncertainty_score":0.3582524},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015151923,0.00102112,0.0010615871,0.10712652,0.88633794,0.000038073897,0.0023885588,0.00030358037,0.0015712016],"genre_scores_gemma":[0.021515952,0.013298834,0.013867712,0.30513257,0.4944346,0.0006491832,0.007167587,0.0037248235,0.14020874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9864631,0.0040188464,0.0029637213,0.0014048874,0.0043371413,0.00081219675],"domain_scores_gemma":[0.89033103,0.0471371,0.0068223136,0.004605727,0.048610985,0.0024928926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013037966,0.002993791,0.002206599,0.0036623266,0.0032355662,0.0045080613,0.0043523447,0.0064367447,0.06089699],"category_scores_gemma":[0.19809054,0.0012497028,0.0019874764,0.0036832218,0.0027048218,0.002624028,0.002776689,0.014934069,0.030157994],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038502,0.000005882637,0.00009458164,0.00015055925,0.000014922633,0.00011787794,0.00005171084,0.000030441097,0.000018621302,0.0007532638,0.99460864,0.0041148835],"study_design_scores_gemma":[0.00012468478,0.00003599239,0.0012086726,0.0018624999,0.000097283504,0.0007224055,0.00024627626,0.00043274072,0.00038596752,0.0028511456,0.99194133,0.000091006616],"about_ca_topic_score_codex":0.027695041,"about_ca_topic_score_gemma":0.026688239,"teacher_disagreement_score":0.06089699,"about_ca_system_score_codex":0.0053886166,"about_ca_system_score_gemma":0.010626051,"threshold_uncertainty_score":0.20372075},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98758554,0.0013635067,0.000630001,0.0039715217,0.00029329077,0.00025886102,0.0014079112,0.000027072148,0.004462275],"genre_scores_gemma":[0.9931532,0.001502104,0.0015311278,0.0011609901,0.00014048777,0.0005109811,0.0007481753,0.000010403544,0.0012423812],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9966761,0.0014066385,0.0006152253,0.00025606144,0.0007744887,0.0002714558],"domain_scores_gemma":[0.987661,0.0025670761,0.007224682,0.00023428068,0.0013144305,0.0009985138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036137786,0.00020651934,0.0005555925,0.0007677444,0.0007158932,0.0011319488,0.00038695842,0.0007163795,0.0056335363],"category_scores_gemma":[0.018889047,0.0002686257,0.0006743749,0.00065978436,0.00072824367,0.0010081053,0.00083309977,0.00094361836,0.0009251551],"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":[0.0009930193,0.00035550795,0.92594784,0.0010944783,0.0003537051,0.00022129783,0.014355439,0.00008411109,0.0007946186,0.00033738645,0.0092907455,0.046171907],"study_design_scores_gemma":[0.00005988354,0.00038761942,0.98249626,0.00052657153,0.00013461338,0.0004585914,0.011151342,0.000102166545,0.000408432,0.0003145241,0.003902723,0.00005717158],"about_ca_topic_score_codex":0.0025801775,"about_ca_topic_score_gemma":0.0042678593,"teacher_disagreement_score":0.0056335363,"about_ca_system_score_codex":0.0008822179,"about_ca_system_score_gemma":0.00064629107,"threshold_uncertainty_score":0.019111753},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005167409,0.02134188,0.5535184,0.09479657,0.023726258,0.2474711,0.02217412,0.0067687253,0.025035594],"genre_scores_gemma":[0.007187977,0.0033562141,0.75603426,0.004329445,0.00091617776,0.22305706,0.0032867729,0.0004690342,0.0013631084],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.27615774,0.45877033,0.20811485,0.008674098,0.045762,0.002521084],"domain_scores_gemma":[0.071778566,0.56598616,0.057359036,0.13185614,0.16974144,0.0032785186],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6328035,0.00707738,0.017110609,0.06886112,0.011340229,0.02482518,0.013376138,0.013878461,0.045204118],"category_scores_gemma":[0.86960346,0.007437839,0.01523174,0.061648447,0.013674323,0.046039533,0.026377624,0.021109924,0.017335817],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011432869,0.00047035184,0.002491014,0.104130104,0.0011474711,0.0002964788,0.030097956,0.0012410292,0.0013920557,0.08733156,0.26847374,0.50178504],"study_design_scores_gemma":[0.00293426,0.00066444906,0.0036559934,0.2582184,0.0018356491,0.00046986857,0.015377081,0.006791278,0.0019461336,0.17474823,0.53233117,0.0010274438],"about_ca_topic_score_codex":0.0056614922,"about_ca_topic_score_gemma":0.0073223654,"teacher_disagreement_score":0.3671965,"about_ca_system_score_codex":0.020298814,"about_ca_system_score_gemma":0.07309832,"threshold_uncertainty_score":0.4528187},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59543777,0.026726695,0.07636766,0.04406613,0.0035144931,0.19682586,0.0034619353,0.00136409,0.052235283],"genre_scores_gemma":[0.5554829,0.0117365,0.15787554,0.021250961,0.0024737807,0.23553848,0.0020734204,0.00071465364,0.012853709],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8227325,0.15642871,0.0075106355,0.0024108766,0.0072361864,0.0036811067],"domain_scores_gemma":[0.79959744,0.14276499,0.010730604,0.013563816,0.023551809,0.009791323],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20640397,0.0015843072,0.0025917115,0.0014012173,0.0056058215,0.0041674217,0.004537206,0.005332863,0.013673167],"category_scores_gemma":[0.23660631,0.0012497517,0.0018400442,0.0021381197,0.0038185967,0.004139382,0.0049297544,0.0029502583,0.00635169],"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":[0.030730894,0.02149471,0.032051034,0.020276275,0.0017509075,0.003731906,0.050766207,0.002082296,0.0074158874,0.0032100552,0.07285618,0.7536337],"study_design_scores_gemma":[0.10002635,0.19955616,0.10232887,0.019745732,0.005584147,0.0059941206,0.053415902,0.007982704,0.021762706,0.022328047,0.4594654,0.0018098728],"about_ca_topic_score_codex":0.003026039,"about_ca_topic_score_gemma":0.006280809,"teacher_disagreement_score":0.793596,"about_ca_system_score_codex":0.0018825507,"about_ca_system_score_gemma":0.01238056,"threshold_uncertainty_score":0.9786452},"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":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018173581,0.012206766,0.39878598,0.026166767,0.0039228755,0.5102581,0.013335022,0.0031143147,0.014036579],"genre_scores_gemma":[0.010965462,0.00191387,0.68238646,0.0015749914,0.0002204449,0.29899576,0.002538512,0.00022950849,0.0011750006],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.56980616,0.27755904,0.11597013,0.005563189,0.027505837,0.0035956379],"domain_scores_gemma":[0.28411388,0.42636132,0.04290722,0.027422152,0.21300729,0.0061880327],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37266424,0.0066495137,0.0065250583,0.02743026,0.0063242936,0.009179245,0.01022866,0.0075578704,0.01094113],"category_scores_gemma":[0.541418,0.0054744435,0.011818299,0.012385406,0.007933136,0.013200399,0.013459224,0.009330358,0.0044801957],"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":[0.0025135898,0.00075375265,0.010933859,0.16704248,0.0013570247,0.0018450728,0.08918011,0.004835624,0.008676128,0.033985473,0.18905224,0.48982468],"study_design_scores_gemma":[0.0033723263,0.0021624092,0.018969739,0.17760731,0.002198628,0.0019917341,0.037255093,0.009987266,0.0075370087,0.06740171,0.66988164,0.001635145],"about_ca_topic_score_codex":0.0045991717,"about_ca_topic_score_gemma":0.009508643,"teacher_disagreement_score":0.6273358,"about_ca_system_score_codex":0.015206641,"about_ca_system_score_gemma":0.08378152,"threshold_uncertainty_score":0.7736167},"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":"reporting","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006460205,0.9567992,0.008608553,0.003706297,0.00251378,0.014834946,0.004068339,0.000115043425,0.002893724],"genre_scores_gemma":[0.08979187,0.78251743,0.041228924,0.004171283,0.0014223097,0.07451171,0.005686754,0.00018089917,0.00048872223],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.297003,0.3038766,0.31620583,0.013173633,0.0677229,0.0020180305],"domain_scores_gemma":[0.13942422,0.62189835,0.14460771,0.01881219,0.07366112,0.0015963818],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42549863,0.0036537538,0.0140086375,0.09489745,0.004464305,0.01849698,0.006014518,0.0063076215,0.007857915],"category_scores_gemma":[0.810638,0.0044148895,0.020427395,0.0903157,0.0066825473,0.019341806,0.010812964,0.0045721973,0.0014461756],"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":[0.0005025212,0.000041177682,0.0029376936,0.9186149,0.01242721,0.00012791684,0.0023951572,0.00019774695,0.00023924735,0.0016568522,0.0033596563,0.057499826],"study_design_scores_gemma":[0.0002862523,0.0002536014,0.0043639424,0.95721555,0.022911677,0.00021791906,0.0011761701,0.0001663298,0.00025642075,0.0014517268,0.01162856,0.000071877985],"about_ca_topic_score_codex":0.0060551544,"about_ca_topic_score_gemma":0.012120906,"teacher_disagreement_score":0.5745014,"about_ca_system_score_codex":0.022096034,"about_ca_system_score_gemma":0.056446716,"threshold_uncertainty_score":0.7084625},"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":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015723433,0.9095888,0.015594811,0.003951493,0.0024372877,0.043224365,0.006466752,0.00020361067,0.002809451],"genre_scores_gemma":[0.21017525,0.5395193,0.082849726,0.0042492016,0.00073669764,0.15610646,0.005639078,0.00016916063,0.00055509876],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.20624068,0.44445157,0.27012262,0.016111258,0.06130224,0.0017716839],"domain_scores_gemma":[0.1462898,0.614919,0.16129705,0.024655389,0.051169407,0.001669361],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.46341702,0.0030217522,0.014979084,0.041010935,0.0029921345,0.010086039,0.0063483263,0.0043561193,0.0048892507],"category_scores_gemma":[0.7992236,0.0042336476,0.016627721,0.050654538,0.0074513378,0.015686486,0.008332614,0.0037246589,0.00087116804],"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":[0.00046959808,0.000028680384,0.003746561,0.9439069,0.017487157,0.00006871699,0.0017867503,0.00020514106,0.00016252976,0.0010727169,0.0015764256,0.029488895],"study_design_scores_gemma":[0.0010554509,0.00040686812,0.007897742,0.9303652,0.045706354,0.00019512253,0.0013902786,0.00032126397,0.00044033022,0.0017929648,0.010320555,0.000107770575],"about_ca_topic_score_codex":0.0067972676,"about_ca_topic_score_gemma":0.013487543,"teacher_disagreement_score":0.53658295,"about_ca_system_score_codex":0.020739561,"about_ca_system_score_gemma":0.06386475,"threshold_uncertainty_score":0.66170233},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011568591,0.8984523,0.07894062,0.0028602595,0.0012025628,0.0032488771,0.0019519371,0.00025950136,0.0015154348],"genre_scores_gemma":[0.56210625,0.2480425,0.15711209,0.007107999,0.0019302858,0.019897524,0.0025758003,0.00036062195,0.00086694036],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.59986085,0.32523108,0.048054762,0.011694592,0.014054739,0.0011040091],"domain_scores_gemma":[0.45458513,0.47707006,0.03822935,0.019586822,0.009673994,0.0008546504],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30741432,0.0037080492,0.016446201,0.009840081,0.00077368016,0.0065172645,0.0043665757,0.00454566,0.0030796006],"category_scores_gemma":[0.5258327,0.002536485,0.05613639,0.010698283,0.0024394882,0.005747529,0.0033020158,0.005200615,0.00040320546],"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":[0.003060394,0.000040995812,0.015093044,0.1043211,0.8504348,0.00021083838,0.00016277573,0.0030824724,0.00021123968,0.002265261,0.0010492447,0.020067833],"study_design_scores_gemma":[0.0018553212,0.00066907593,0.008306611,0.030082023,0.9426791,0.0003368299,0.0001373565,0.0028327715,0.0005083332,0.0070986203,0.0054043,0.000089748995],"about_ca_topic_score_codex":0.0023378145,"about_ca_topic_score_gemma":0.0035316937,"teacher_disagreement_score":0.9835538,"about_ca_system_score_codex":0.0038870252,"about_ca_system_score_gemma":0.0034125147,"threshold_uncertainty_score":0.85408145},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39219934,0.0016391217,0.35092527,0.011602867,0.00028490185,0.095926724,0.001936023,0.00017809482,0.14530773],"genre_scores_gemma":[0.66508675,0.0008628607,0.2624458,0.0008802593,0.00002489738,0.06507702,0.0003987516,0.00006579182,0.005157841],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.92102283,0.07139706,0.0014497536,0.0016474457,0.0026806765,0.0018023248],"domain_scores_gemma":[0.93823004,0.05441817,0.0015657429,0.0017846506,0.003378465,0.00062302605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.050435454,0.0018207212,0.0009609579,0.005090527,0.0063212076,0.006007595,0.0036683308,0.0022172525,0.008290296],"category_scores_gemma":[0.055949565,0.0009999294,0.0010417263,0.0035927678,0.01310315,0.0037936121,0.0068754796,0.0029326852,0.00040439726],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047825323,0.00077091187,0.0028398205,0.007637128,0.00006834376,0.0022483477,0.6746572,0.009622228,0.0028303843,0.19070601,0.0036289783,0.104512446],"study_design_scores_gemma":[0.0010516074,0.0016762239,0.0070511177,0.009808567,0.00025290812,0.0006413669,0.67980695,0.016235165,0.0073272847,0.119597405,0.1563653,0.00018603193],"about_ca_topic_score_codex":0.014932559,"about_ca_topic_score_gemma":0.02306765,"teacher_disagreement_score":0.050435454,"about_ca_system_score_codex":0.031664915,"about_ca_system_score_gemma":0.02172811,"threshold_uncertainty_score":0.26673138},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035084505,0.24482934,0.64992535,0.016646296,0.010950667,0.028169584,0.004130251,0.0016755062,0.008588558],"genre_scores_gemma":[0.57178277,0.026961923,0.3236565,0.010295362,0.0027384872,0.060566477,0.0018789765,0.00094280514,0.0011767432],"study_design_codex":"meta_analysis","study_design_gemma":"observational","domain_scores_codex":[0.076267496,0.7479254,0.12103136,0.020421155,0.033175804,0.0011788204],"domain_scores_gemma":[0.032166347,0.8686815,0.053808633,0.034056183,0.010682772,0.0006045142],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7610331,0.0056300354,0.016131563,0.010647748,0.0029330617,0.010127835,0.0062243002,0.009673381,0.004766655],"category_scores_gemma":[0.8988537,0.004303736,0.027176334,0.01188628,0.013424536,0.010795571,0.0072941477,0.010283962,0.0010225786],"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":[0.036065996,0.0005967734,0.06667067,0.21321307,0.3056592,0.00093033334,0.0071154195,0.022450186,0.0023304473,0.052703284,0.0121218795,0.28014272],"study_design_scores_gemma":[0.040566083,0.008897645,0.07217264,0.12975408,0.21651545,0.002568036,0.0011088626,0.07279775,0.011641545,0.39153844,0.050108336,0.002331133],"about_ca_topic_score_codex":0.0023170565,"about_ca_topic_score_gemma":0.0018014001,"teacher_disagreement_score":0.9838684,"about_ca_system_score_codex":0.008993954,"about_ca_system_score_gemma":0.011915791,"threshold_uncertainty_score":0.29468876},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79527664,0.0016022796,0.18827167,0.0018261189,0.00013191673,0.0015435234,0.004904891,0.0012292985,0.0052136607],"genre_scores_gemma":[0.77965575,0.00033901754,0.21553494,0.00022280244,0.000059137747,0.00037444851,0.0035159788,0.00006136207,0.00023653949],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98248327,0.010060727,0.002147063,0.002255773,0.002598181,0.00045500146],"domain_scores_gemma":[0.96441823,0.020844636,0.005008247,0.0020993962,0.007048886,0.00058066886],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024357757,0.0009852172,0.0012599203,0.00504021,0.0006791189,0.0034698232,0.0017460337,0.0012327777,0.00081740296],"category_scores_gemma":[0.06242185,0.0003877553,0.0011539629,0.0043984754,0.0004526607,0.0017930946,0.0013576244,0.0008811632,0.00033480037],"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":[0.0003714438,0.00019029024,0.911795,0.00013740212,0.000611236,0.00002857234,0.0001421802,0.017818833,0.00042368463,0.0005681665,0.001618924,0.06629425],"study_design_scores_gemma":[0.00019778131,0.00068331877,0.4392058,0.00016936375,0.00048579066,0.00030690752,0.00037830928,0.5506954,0.002411985,0.0023901968,0.0029750597,0.000100017765],"about_ca_topic_score_codex":0.021438226,"about_ca_topic_score_gemma":0.015039889,"teacher_disagreement_score":0.97564226,"about_ca_system_score_codex":0.0021395688,"about_ca_system_score_gemma":0.0029693183,"threshold_uncertainty_score":0.12881762},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965636,0.00009558517,0.00052847597,0.000049519185,0.000029064777,0.0011166596,0.0007836422,0.000017545688,0.0008157601],"genre_scores_gemma":[0.9960517,0.000071498376,0.00059764576,0.00010143156,0.000026709884,0.0020131755,0.0006436465,0.000011548181,0.0004826732],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97466916,0.016288564,0.0022700788,0.0017615655,0.0034624338,0.0015481963],"domain_scores_gemma":[0.945555,0.03192002,0.009412579,0.004367425,0.006657309,0.0020876694],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026346184,0.0008615604,0.00083149015,0.0016748506,0.00046952176,0.00084578,0.0010992064,0.0014957822,0.004146232],"category_scores_gemma":[0.05631646,0.0006187205,0.0020285791,0.0013421695,0.0008160625,0.0012910197,0.0013594804,0.00091030233,0.0013474257],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03270727,0.0035979208,0.93216014,0.00047668134,0.0005839367,0.00013276516,0.0038369107,0.00025101443,0.0016300037,0.00008858264,0.0010670641,0.023467576],"study_design_scores_gemma":[0.0013428178,0.023347558,0.97086024,0.000082426,0.00023700153,0.0001247558,0.0016215558,0.00092815876,0.0007489915,0.000045641373,0.00062285975,0.00003794271],"about_ca_topic_score_codex":0.006281595,"about_ca_topic_score_gemma":0.0046480433,"teacher_disagreement_score":0.9736538,"about_ca_system_score_codex":0.0012984303,"about_ca_system_score_gemma":0.0010228554,"threshold_uncertainty_score":0.13933367},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0740458,0.7118211,0.12484736,0.053294998,0.0035572604,0.0045913714,0.01697344,0.0005623752,0.010306226],"genre_scores_gemma":[0.6667717,0.21250834,0.073108055,0.024538983,0.0024648209,0.012740823,0.006834605,0.0003944885,0.0006382254],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.28639707,0.42504653,0.19570531,0.024821758,0.065675855,0.002353551],"domain_scores_gemma":[0.04176605,0.8024784,0.105078444,0.022746122,0.027264796,0.00066624035],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52193016,0.0016987273,0.0079122195,0.015959833,0.0019803923,0.0075427494,0.0039519914,0.0041415524,0.0050500436],"category_scores_gemma":[0.82654846,0.0029556719,0.008710779,0.018981757,0.0058191735,0.013827527,0.006295051,0.004211942,0.0009455308],"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":[0.0020220948,0.0001451951,0.12807788,0.48738372,0.04423707,0.00034933715,0.01006353,0.0028240492,0.0008160879,0.0149429785,0.021646151,0.2874919],"study_design_scores_gemma":[0.0012071326,0.0014549341,0.121347524,0.65822387,0.061244614,0.0025415174,0.0076975077,0.0054323194,0.0029521505,0.049649835,0.0873814,0.00086716213],"about_ca_topic_score_codex":0.007553633,"about_ca_topic_score_gemma":0.007785146,"teacher_disagreement_score":0.47806984,"about_ca_system_score_codex":0.008224639,"about_ca_system_score_gemma":0.01706659,"threshold_uncertainty_score":0.58954525},"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":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07520429,0.01872604,0.16199164,0.6466865,0.0027459005,0.0015801416,0.00032446234,0.00015174416,0.092589274],"genre_scores_gemma":[0.8181609,0.00518715,0.14783438,0.02484959,0.000493716,0.0013805074,0.00019292929,0.000039696894,0.0018611416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9572233,0.03492592,0.0013930316,0.0022390482,0.0029015075,0.0013172184],"domain_scores_gemma":[0.95849115,0.028861864,0.003952237,0.0009798019,0.004735302,0.0029795975],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04961098,0.00075881137,0.00077443215,0.0045619695,0.0071967174,0.009747195,0.003706089,0.004403425,0.0031257933],"category_scores_gemma":[0.038326442,0.0003894338,0.0012119198,0.0029382021,0.036849346,0.009823253,0.0061276173,0.0067941784,0.00034687325],"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":[0.000045518726,0.00017490247,0.009951444,0.00065959606,0.000032863198,0.0003603547,0.06745828,0.00087556377,0.00018488237,0.86421406,0.009961566,0.04608097],"study_design_scores_gemma":[0.00011454123,0.00019171255,0.0062736217,0.0028718202,0.00007595047,0.0008373848,0.12646961,0.0038999172,0.00031824867,0.756546,0.10228538,0.00011579132],"about_ca_topic_score_codex":0.017169088,"about_ca_topic_score_gemma":0.02060028,"teacher_disagreement_score":0.950389,"about_ca_system_score_codex":0.021358913,"about_ca_system_score_gemma":0.04440419,"threshold_uncertainty_score":0.26237112},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007491433,0.0004348355,0.013695764,0.0005917193,0.0002129785,0.83850694,0.13442941,0.0011733206,0.0034636173],"genre_scores_gemma":[0.0054383306,0.000119268756,0.013410974,0.0001646014,0.000017356522,0.96137697,0.018614754,0.00014211304,0.0007156323],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9599057,0.023248794,0.00942326,0.0026359442,0.0033239287,0.0014624038],"domain_scores_gemma":[0.8956472,0.039421543,0.008843194,0.021907141,0.031611796,0.0025691488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08644835,0.0031868734,0.004703609,0.0029818052,0.003972083,0.003596139,0.009190654,0.0035272308,0.09635186],"category_scores_gemma":[0.14932697,0.0040877108,0.0058028894,0.0046095676,0.0021406962,0.0019438112,0.003530952,0.003855825,0.012050991],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16007109,0.0080627855,0.024713432,0.04438364,0.0059938845,0.0006411892,0.003916677,0.01611659,0.0018158532,0.0075934837,0.60705227,0.11963906],"study_design_scores_gemma":[0.3069104,0.011382132,0.0937079,0.026685782,0.0067647877,0.0005890322,0.0021343918,0.03133376,0.005412687,0.011492401,0.5020031,0.001583739],"about_ca_topic_score_codex":0.08570573,"about_ca_topic_score_gemma":0.13357466,"teacher_disagreement_score":0.09635186,"about_ca_system_score_codex":0.01155578,"about_ca_system_score_gemma":0.048514917,"threshold_uncertainty_score":0.457188},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10417858,0.34151483,0.024707058,0.0042788116,0.0007117312,0.10426689,0.40689903,0.0007088878,0.012734112],"genre_scores_gemma":[0.26047316,0.1416437,0.052151427,0.0072976253,0.00044943247,0.44804832,0.085890844,0.0005408409,0.0035046174],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.79976195,0.034177694,0.124154165,0.008921384,0.028482469,0.0045024054],"domain_scores_gemma":[0.58609724,0.26611444,0.08537987,0.010225987,0.050360117,0.001822349],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.07309956,0.0027585155,0.009017284,0.09895005,0.0018831788,0.0057825875,0.0028561347,0.00214584,0.011761742],"category_scores_gemma":[0.3254703,0.0026762888,0.012978086,0.096662894,0.00236991,0.0074849296,0.0065658824,0.002144712,0.0022662815],"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":[0.002895511,0.00020401725,0.07668647,0.7730047,0.017897967,0.001889409,0.014961713,0.0006603244,0.0013932281,0.004524793,0.02395339,0.08192832],"study_design_scores_gemma":[0.0016898242,0.0014994818,0.20301199,0.5169793,0.039818924,0.0049235066,0.025913987,0.0009485385,0.0029839303,0.0048222975,0.19682066,0.0005875063],"about_ca_topic_score_codex":0.0069832546,"about_ca_topic_score_gemma":0.016446756,"teacher_disagreement_score":0.92690045,"about_ca_system_score_codex":0.0096776495,"about_ca_system_score_gemma":0.023515945,"threshold_uncertainty_score":0.38659203},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045183897,0.02005705,0.64325744,0.13484676,0.023313962,0.13578176,0.016642502,0.010352792,0.011229333],"genre_scores_gemma":[0.013746871,0.0031967354,0.78401643,0.012949309,0.0011417246,0.18112092,0.0017038534,0.0009324987,0.0011917592],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.056496557,0.68365675,0.21881983,0.010844789,0.028449131,0.001732904],"domain_scores_gemma":[0.021152286,0.66511405,0.09200342,0.11157952,0.107823856,0.0023268918],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8284384,0.009084071,0.011476585,0.03025342,0.0060398765,0.019855484,0.013553967,0.019532956,0.013459751],"category_scores_gemma":[0.9448705,0.011497604,0.0228066,0.020165877,0.012656938,0.024042754,0.020645222,0.022718817,0.009534352],"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":[0.0030514156,0.00035104516,0.008846117,0.24120595,0.009167937,0.0011791021,0.03704052,0.0048004864,0.00293103,0.06754058,0.3030552,0.32083067],"study_design_scores_gemma":[0.0048988494,0.0007788722,0.006116745,0.3717299,0.0062605278,0.0011797403,0.006882654,0.016571576,0.009446932,0.10722909,0.46763125,0.0012738602],"about_ca_topic_score_codex":0.005461292,"about_ca_topic_score_gemma":0.005221052,"teacher_disagreement_score":0.1715616,"about_ca_system_score_codex":0.015414628,"about_ca_system_score_gemma":0.06185028,"threshold_uncertainty_score":0.21156603},"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":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00050437264,0.99570674,0.0015639728,0.0013876256,0.00019767327,0.00015542077,0.0001785138,0.000016084654,0.00028971312],"genre_scores_gemma":[0.022210378,0.9660672,0.007897286,0.001580956,0.00034675,0.0015212811,0.00025743808,0.000040635077,0.0000780112],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.66459846,0.21516421,0.0782921,0.011034739,0.029223414,0.001687133],"domain_scores_gemma":[0.19168249,0.7358685,0.04427584,0.010521269,0.016930398,0.00072153565],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26287284,0.0017519781,0.0070621604,0.030606642,0.0020093387,0.007530968,0.0054622036,0.0048473435,0.003910163],"category_scores_gemma":[0.56578267,0.0026228027,0.009100031,0.042912133,0.005972571,0.008713995,0.0054233745,0.0032903715,0.000598458],"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":[0.0003376366,0.000041434727,0.005131373,0.73694843,0.0069539794,0.00015387926,0.00340455,0.0003976154,0.00027588254,0.0061561945,0.006103826,0.23409517],"study_design_scores_gemma":[0.00013865813,0.00019047374,0.0064686076,0.9039332,0.014449564,0.0006196469,0.0019193258,0.000391738,0.000589376,0.0063775047,0.06478418,0.00013769262],"about_ca_topic_score_codex":0.006045779,"about_ca_topic_score_gemma":0.0074225035,"teacher_disagreement_score":0.7371272,"about_ca_system_score_codex":0.009387077,"about_ca_system_score_gemma":0.021930717,"threshold_uncertainty_score":0.90900904},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79207927,0.00062023546,0.13835354,0.017382497,0.000559622,0.017613366,0.000400431,0.0011194154,0.03187165],"genre_scores_gemma":[0.66200876,0.00070223695,0.3121765,0.0026416392,0.00014307965,0.017965434,0.00021101565,0.00014567586,0.0040057143],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9748541,0.019540073,0.00093794387,0.0016325015,0.0016440592,0.0013913246],"domain_scores_gemma":[0.95605975,0.032675,0.0021715523,0.0031330276,0.0028028304,0.0031577812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03909073,0.0010338303,0.00067488477,0.001732101,0.0047619273,0.0042260196,0.0025091292,0.0019165804,0.0063335146],"category_scores_gemma":[0.058804035,0.0007005629,0.0011077779,0.0010282829,0.0029055038,0.0046747574,0.009767328,0.0023000238,0.0012495446],"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":[0.00073422084,0.005773932,0.008951476,0.002143599,0.00007350657,0.001939743,0.40159163,0.0009184621,0.0059296694,0.002865292,0.0076084137,0.56147015],"study_design_scores_gemma":[0.0039264327,0.017594432,0.035880562,0.0077821263,0.0012141952,0.0037544004,0.5845037,0.020995494,0.022747125,0.03869835,0.2621909,0.0007122814],"about_ca_topic_score_codex":0.0025713572,"about_ca_topic_score_gemma":0.0057196803,"teacher_disagreement_score":0.03909073,"about_ca_system_score_codex":0.002886357,"about_ca_system_score_gemma":0.014386717,"threshold_uncertainty_score":0.20673406},"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":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044874478,0.0007001846,0.0035185795,0.0004083169,0.00023125405,0.93655634,0.01143611,0.00008714757,0.002187639],"genre_scores_gemma":[0.014531307,0.00025609648,0.0041514086,0.00027337114,0.00003418353,0.9781693,0.0017281247,0.0000057202246,0.0008505746],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951984,0.0021661595,0.0010670266,0.00059198926,0.0003541634,0.0006222416],"domain_scores_gemma":[0.995262,0.0011860307,0.00084652414,0.0004966107,0.0016539881,0.0005547875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014315652,0.002098169,0.0030753769,0.0022806104,0.0021458552,0.0013966145,0.0015409323,0.002662176,0.024672396],"category_scores_gemma":[0.007124275,0.0020920169,0.0025166199,0.001575897,0.0011233316,0.0017068362,0.0017802337,0.002235162,0.0056417696],"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":[0.08910116,0.06475273,0.22824766,0.090789214,0.002836632,0.0044014887,0.036293797,0.009008275,0.010558189,0.013347508,0.20140551,0.2492578],"study_design_scores_gemma":[0.06151894,0.05758352,0.5433488,0.02122123,0.0017552954,0.0012559674,0.028109567,0.007107151,0.0035484736,0.006100417,0.26758873,0.0008617883],"about_ca_topic_score_codex":0.0044216434,"about_ca_topic_score_gemma":0.0068540885,"teacher_disagreement_score":0.024672396,"about_ca_system_score_codex":0.0032000244,"about_ca_system_score_gemma":0.008192969,"threshold_uncertainty_score":0.08253735},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995786,0.0002896588,0.0007176978,0.00070530956,0.000008649421,0.00044874082,0.000049556573,0.000004542346,0.0019898356],"genre_scores_gemma":[0.9968238,0.00045992015,0.0014484036,0.00020848567,0.000008681048,0.000472224,0.000034683515,0.000008847177,0.0005349277],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8843913,0.091709346,0.005896996,0.0029585871,0.00890055,0.006143287],"domain_scores_gemma":[0.76035845,0.20021577,0.016455801,0.005195442,0.0136132585,0.004161309],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07743685,0.0005830425,0.00083968666,0.0040426557,0.010761192,0.0060211783,0.003121072,0.0028500303,0.0023506193],"category_scores_gemma":[0.13166952,0.0009440162,0.00091933116,0.0045019216,0.005704655,0.006040438,0.008172686,0.002161929,0.0002798655],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000155373,0.00074206496,0.06620854,0.00034198118,0.000045816963,0.0037663018,0.9079663,0.00006804478,0.00024317417,0.0005766501,0.00037708948,0.019508744],"study_design_scores_gemma":[0.000028602857,0.00043569895,0.031288102,0.00040974357,0.000060506645,0.0019100906,0.9617464,0.00028499454,0.00043231904,0.00025708912,0.0031060888,0.000040367126],"about_ca_topic_score_codex":0.028837042,"about_ca_topic_score_gemma":0.054041374,"teacher_disagreement_score":0.92256314,"about_ca_system_score_codex":0.016158156,"about_ca_system_score_gemma":0.012246067,"threshold_uncertainty_score":0.4095301},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30560112,0.014453428,0.5183769,0.0057095727,0.0011908018,0.113723375,0.008631151,0.0011579373,0.031155704],"genre_scores_gemma":[0.29943666,0.0030584505,0.5708424,0.000859441,0.00021038171,0.12255591,0.0017988012,0.000110085624,0.0011278887],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.68148726,0.20715125,0.05793069,0.007697306,0.04417163,0.0015619098],"domain_scores_gemma":[0.4510829,0.34587076,0.10956182,0.019216698,0.072192885,0.0020749848],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22297724,0.0018485448,0.0018824993,0.016473297,0.0019843206,0.0034146444,0.003258947,0.0012470442,0.0037199163],"category_scores_gemma":[0.36626303,0.0011126656,0.0049024806,0.008626058,0.0025015848,0.0041194493,0.0055973916,0.0018309368,0.00067040353],"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":[0.0018862856,0.0011271634,0.28926846,0.02771833,0.0023062518,0.00029091406,0.053051412,0.0023663642,0.0017986725,0.008484842,0.009607619,0.6020937],"study_design_scores_gemma":[0.002824246,0.011164814,0.6343047,0.049116053,0.0042419536,0.0035097376,0.09331009,0.031605206,0.017152017,0.040262017,0.11078722,0.0017220256],"about_ca_topic_score_codex":0.0028703914,"about_ca_topic_score_gemma":0.00549625,"teacher_disagreement_score":0.22297724,"about_ca_system_score_codex":0.0054533826,"about_ca_system_score_gemma":0.009390243,"threshold_uncertainty_score":0.9582074},"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":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005665679,0.00075544656,0.028822182,0.0025157968,0.0010033011,0.9579893,0.005436936,0.00058167824,0.0023288708],"genre_scores_gemma":[0.00034771202,0.00018827966,0.036110483,0.00025012845,0.000038744623,0.9624203,0.00030608173,0.00002518971,0.00031312043],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.6169017,0.22690068,0.11501596,0.013282863,0.023258567,0.004640193],"domain_scores_gemma":[0.36047426,0.37566343,0.049858548,0.0924518,0.11192468,0.009627255],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41217765,0.005577304,0.008642204,0.023567922,0.0066319397,0.012259755,0.0069041913,0.015891792,0.10561582],"category_scores_gemma":[0.56246006,0.010665861,0.01352833,0.023515541,0.007790773,0.0115424,0.015072742,0.016327746,0.027985293],"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":[0.013352486,0.001624464,0.002294481,0.3569317,0.003464611,0.0016391873,0.0192809,0.0035360353,0.003988625,0.06431479,0.20350127,0.32607144],"study_design_scores_gemma":[0.04531735,0.0018069295,0.005502794,0.20513488,0.0044390876,0.0006421005,0.005295279,0.0059168697,0.005521521,0.10065181,0.61838996,0.0013813896],"about_ca_topic_score_codex":0.0030150684,"about_ca_topic_score_gemma":0.0049094222,"teacher_disagreement_score":0.5878223,"about_ca_system_score_codex":0.01095705,"about_ca_system_score_gemma":0.0824909,"threshold_uncertainty_score":0.72488964},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09486468,0.012365343,0.69627243,0.091633834,0.0011237845,0.0048326664,0.00033674395,0.0003586583,0.09821189],"genre_scores_gemma":[0.83373564,0.0015828243,0.15679379,0.0019374683,0.0001817969,0.0050036036,0.000069028065,0.00007895004,0.0006169158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6578507,0.30050743,0.008694351,0.014746174,0.013303552,0.004897837],"domain_scores_gemma":[0.5149488,0.4071427,0.030740768,0.03354853,0.00992592,0.0036933573],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26593128,0.0026155543,0.0032741216,0.016091766,0.012089503,0.03168847,0.0091010155,0.010623097,0.0089682145],"category_scores_gemma":[0.31511104,0.0033285855,0.0042397147,0.0076315743,0.1434877,0.049713288,0.02591665,0.01040968,0.0006180851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056728593,0.000052588704,0.0028023995,0.00084495463,0.00012359837,0.00016568844,0.02465305,0.0018740934,0.00010462752,0.9587155,0.0003367255,0.010270131],"study_design_scores_gemma":[0.00007927878,0.00007786798,0.0012499538,0.0014964653,0.00013322843,0.00011658085,0.016747683,0.0031461213,0.00027515707,0.97046834,0.0061603175,0.000048901158],"about_ca_topic_score_codex":0.003551633,"about_ca_topic_score_gemma":0.0035385925,"teacher_disagreement_score":0.73406875,"about_ca_system_score_codex":0.02922233,"about_ca_system_score_gemma":0.03263493,"threshold_uncertainty_score":0.90523744},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53419816,0.12340928,0.31822252,0.0073806844,0.0015707446,0.00079341617,0.001928738,0.00044263032,0.01205371],"genre_scores_gemma":[0.8817291,0.010780733,0.10480419,0.00070460694,0.00062519324,0.00030148702,0.00039501503,0.00003624998,0.0006233179],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98395765,0.012489387,0.0009004789,0.00084326963,0.0016293256,0.00017980694],"domain_scores_gemma":[0.94556814,0.04715717,0.0038561183,0.001215894,0.0019177138,0.00028486334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029918188,0.0009464045,0.0010464146,0.0025942074,0.00023678307,0.0020628308,0.00057226175,0.0011285342,0.0010523665],"category_scores_gemma":[0.042943776,0.00017773327,0.0009366919,0.0022527312,0.0006811117,0.0014152298,0.0008112562,0.0011877844,0.00041248364],"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":[0.003229879,0.00039199548,0.27482623,0.003716754,0.0028914344,0.00025711858,0.00048271473,0.041242927,0.0024164724,0.0077154413,0.0027493336,0.66007966],"study_design_scores_gemma":[0.0010785667,0.016157208,0.38059142,0.008302463,0.0037491363,0.0029559673,0.0018587788,0.4431834,0.013769703,0.094312645,0.03357819,0.00046262392],"about_ca_topic_score_codex":0.0006509592,"about_ca_topic_score_gemma":0.0007532042,"teacher_disagreement_score":0.029918188,"about_ca_system_score_codex":0.0005322724,"about_ca_system_score_gemma":0.00079695164,"threshold_uncertainty_score":0.1582244},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038060434,0.0013163222,0.95588535,0.00089958886,0.0006901289,0.033626556,0.0013262561,0.00045157838,0.0019981486],"genre_scores_gemma":[0.030594215,0.0005007457,0.8625024,0.0005283512,0.00016448613,0.104651794,0.00057134434,0.00014031818,0.00034627487],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.33674034,0.5929276,0.03653918,0.010554557,0.022223685,0.0010146004],"domain_scores_gemma":[0.16634977,0.7375192,0.032248344,0.041645635,0.021416789,0.0008203007],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5459851,0.0032407052,0.003971564,0.010191617,0.0015381632,0.004023967,0.0071107754,0.0035006497,0.0060472554],"category_scores_gemma":[0.7746489,0.0023618068,0.00549881,0.00863865,0.0047833915,0.0037257262,0.0055987295,0.0058898013,0.0011330815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005142243,0.0007264561,0.051126875,0.020396605,0.0078096925,0.00090225117,0.0077272393,0.04009015,0.0015724304,0.18682028,0.0395279,0.63815796],"study_design_scores_gemma":[0.007837471,0.009037616,0.036740143,0.026824182,0.006679337,0.0020082346,0.003520346,0.27412003,0.015490778,0.37422785,0.24260715,0.0009067815],"about_ca_topic_score_codex":0.0019284931,"about_ca_topic_score_gemma":0.0018130253,"teacher_disagreement_score":0.4540149,"about_ca_system_score_codex":0.0035378593,"about_ca_system_score_gemma":0.007503539,"threshold_uncertainty_score":0.5598812},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40697566,0.0015782721,0.4974227,0.0013367918,0.0007355732,0.0024198254,0.01729667,0.05257028,0.01966418],"genre_scores_gemma":[0.44507372,0.0004980133,0.5223694,0.0004389094,0.000101104604,0.006556545,0.009953244,0.009865291,0.0051437225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9737742,0.016386312,0.0026359598,0.00297681,0.0037714115,0.00045524735],"domain_scores_gemma":[0.8811861,0.08992039,0.006665797,0.00780657,0.013695418,0.00072569697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037710264,0.0016876517,0.00123848,0.0042702514,0.00050982233,0.00254265,0.0016636242,0.0007884454,0.010853464],"category_scores_gemma":[0.15408258,0.00080490345,0.0023447524,0.0029989304,0.0007604691,0.0014841018,0.0023245465,0.0012248323,0.004669819],"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":[0.012176737,0.0009809926,0.1325267,0.0038133226,0.0031248017,0.00050765736,0.0061265132,0.0119725065,0.008709254,0.009002883,0.054631006,0.7564276],"study_design_scores_gemma":[0.0020029931,0.0053207804,0.62227714,0.0026910042,0.0025559822,0.0022549625,0.0041591655,0.21998835,0.02709031,0.017996818,0.092786506,0.0008759405],"about_ca_topic_score_codex":0.0030668003,"about_ca_topic_score_gemma":0.004007264,"teacher_disagreement_score":0.037710264,"about_ca_system_score_codex":0.0008635659,"about_ca_system_score_gemma":0.0018712877,"threshold_uncertainty_score":0.19943333},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026746068,0.87109226,0.1144439,0.0048008543,0.0016182406,0.0001339801,0.0010022437,0.0013365436,0.005304567],"genre_scores_gemma":[0.0033487682,0.9182253,0.06929962,0.002037794,0.0024815176,0.0005684694,0.0011573199,0.000939187,0.0019420591],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98770845,0.006514472,0.0016686807,0.0010424388,0.002853433,0.00021257119],"domain_scores_gemma":[0.95809156,0.034159586,0.0017707611,0.0017837611,0.003840757,0.00035354664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014936299,0.002391054,0.0031420814,0.0077116634,0.0006480801,0.0021984787,0.0036633967,0.0031473837,0.013364275],"category_scores_gemma":[0.042858448,0.0013995257,0.0041098865,0.011422302,0.0027028956,0.0023020788,0.0015396836,0.005448965,0.015198459],"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":[0.00007652606,0.000059356356,0.0004379016,0.02629793,0.00032234442,0.00016855664,0.00023938366,0.0037227012,0.0005941755,0.035003677,0.08982168,0.8432557],"study_design_scores_gemma":[0.000041088813,0.000116793104,0.0010766686,0.0110019585,0.00018134508,0.0009115448,0.00006635038,0.001998233,0.00063143,0.04126847,0.9425708,0.00013534562],"about_ca_topic_score_codex":0.0031300606,"about_ca_topic_score_gemma":0.0019161471,"teacher_disagreement_score":0.014936299,"about_ca_system_score_codex":0.0013682538,"about_ca_system_score_gemma":0.004586164,"threshold_uncertainty_score":0.07899165},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4590501,0.035287265,0.19815752,0.21015887,0.014665623,0.03709024,0.014873618,0.00084672915,0.029870002],"genre_scores_gemma":[0.60452217,0.0068493034,0.26781258,0.05155797,0.004820601,0.055627197,0.0056123477,0.0003580754,0.0028397883],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.47775882,0.4728794,0.018249767,0.008919869,0.018209524,0.0039826445],"domain_scores_gemma":[0.4623114,0.3584493,0.035639502,0.065931104,0.061077658,0.016591046],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5158493,0.0014070476,0.0029869669,0.0036195384,0.0030435494,0.00497229,0.007838541,0.0035735029,0.001992889],"category_scores_gemma":[0.433051,0.0014641812,0.0022877706,0.0041961023,0.0035701036,0.0035033105,0.010852737,0.004055493,0.0009513466],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003238053,0.0008484626,0.6981168,0.0068571293,0.0025580956,0.00080373697,0.036122415,0.0027818782,0.0015854278,0.008236995,0.044688452,0.19416262],"study_design_scores_gemma":[0.0011187281,0.0063437656,0.76087886,0.0160214,0.0013976542,0.0013967422,0.037104443,0.010014667,0.0016962304,0.028503941,0.1350553,0.00046830377],"about_ca_topic_score_codex":0.03669233,"about_ca_topic_score_gemma":0.048917744,"teacher_disagreement_score":0.4841507,"about_ca_system_score_codex":0.003714437,"about_ca_system_score_gemma":0.016376466,"threshold_uncertainty_score":0.59704405},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053723884,0.0005241608,0.9920859,0.0011339037,0.00024142988,0.00021523736,0.0011635488,0.0029241294,0.0011744369],"genre_scores_gemma":[0.011131641,0.00056094734,0.9833323,0.0003076597,0.00017438582,0.0016241088,0.00089280424,0.0011616483,0.0008145414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97729594,0.016990509,0.0013744716,0.0015239673,0.0024630583,0.0003519671],"domain_scores_gemma":[0.868559,0.11215026,0.004389492,0.008382407,0.0055391435,0.0009797657],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026298357,0.004419914,0.0024538331,0.01366312,0.0014745283,0.008377046,0.0052441373,0.004956508,0.02761154],"category_scores_gemma":[0.17490338,0.002361236,0.008902767,0.007860373,0.002516147,0.0066954195,0.008640285,0.008796666,0.004598868],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006746821,0.00023012463,0.0028024828,0.005004819,0.0018876508,0.0008194512,0.004163674,0.13895872,0.0033136366,0.45781687,0.09701452,0.28731337],"study_design_scores_gemma":[0.00040237748,0.00009900864,0.0008462285,0.001121863,0.00032620408,0.0007114889,0.00034563363,0.34670487,0.0017611015,0.5508949,0.096509084,0.0002771546],"about_ca_topic_score_codex":0.006079957,"about_ca_topic_score_gemma":0.0073373024,"teacher_disagreement_score":0.97370166,"about_ca_system_score_codex":0.0026842682,"about_ca_system_score_gemma":0.0036809545,"threshold_uncertainty_score":0.1390807},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99013054,0.0006592489,0.0020925477,0.00031151454,0.00014252003,0.00072888186,0.001803286,0.000023882858,0.004107643],"genre_scores_gemma":[0.9886932,0.0004941259,0.0069816727,0.00011244505,0.000024747798,0.0010010571,0.0019686779,0.000016562346,0.0007074588],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9951763,0.002090372,0.0007306541,0.00039638826,0.0013272091,0.00027911467],"domain_scores_gemma":[0.98894715,0.0050902017,0.0015151552,0.0005950489,0.0033457098,0.00050660333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010670521,0.00032485276,0.00034891898,0.0009746992,0.0004872179,0.0008333173,0.0005237158,0.00035272734,0.0020377259],"category_scores_gemma":[0.023663413,0.00023406907,0.00082019466,0.0007967452,0.00059331383,0.0005961725,0.0011684368,0.0006133368,0.00024684353],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039567103,0.0005900152,0.89255655,0.000506858,0.00032746082,0.00026385035,0.008875531,0.0013208474,0.0016337151,0.0007137945,0.00521259,0.08760311],"study_design_scores_gemma":[0.00006733625,0.00047946273,0.9907849,0.00022968078,0.00006527581,0.00022139432,0.0022413472,0.0010395377,0.00030776014,0.00025187616,0.004277105,0.000034293116],"about_ca_topic_score_codex":0.008577951,"about_ca_topic_score_gemma":0.011231204,"teacher_disagreement_score":0.010670521,"about_ca_system_score_codex":0.0011444308,"about_ca_system_score_gemma":0.0022568677,"threshold_uncertainty_score":0.05643183},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008415863,0.046976145,0.5497062,0.20551296,0.010928001,0.1562063,0.0036974398,0.0020138475,0.01654322],"genre_scores_gemma":[0.015134056,0.0067047477,0.93309927,0.0052487827,0.0004842223,0.03803885,0.0007307949,0.00016113269,0.00039811808],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.14201461,0.63887393,0.16885778,0.009461738,0.037994664,0.0027973566],"domain_scores_gemma":[0.048119754,0.75056493,0.043509945,0.045192,0.10713756,0.005475799],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.72158647,0.008107918,0.011307371,0.070274055,0.009651206,0.03376677,0.020548992,0.01858338,0.008102141],"category_scores_gemma":[0.8720837,0.007066174,0.015018062,0.038045563,0.013594287,0.029946398,0.031119544,0.021255525,0.0034475797],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004597781,0.00056689855,0.0047812965,0.18501358,0.005350512,0.002137122,0.121417545,0.004607145,0.0024635792,0.068216234,0.06963698,0.53534937],"study_design_scores_gemma":[0.0011859731,0.00063902535,0.0028049813,0.4682392,0.007063036,0.0007321632,0.050389394,0.010607116,0.004018651,0.20276298,0.25043216,0.0011254287],"about_ca_topic_score_codex":0.011829558,"about_ca_topic_score_gemma":0.019875525,"teacher_disagreement_score":0.27841353,"about_ca_system_score_codex":0.04013695,"about_ca_system_score_gemma":0.16985132,"threshold_uncertainty_score":0.34333348},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9626825,0.002735189,0.0017938475,0.013971858,0.00024953604,0.004292089,0.00055402395,0.000075601296,0.013645435],"genre_scores_gemma":[0.97473645,0.0024628465,0.0062210946,0.004223048,0.000042092503,0.003446648,0.00027840224,0.000033144726,0.008556352],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9930381,0.002881624,0.00026663337,0.0004375968,0.00085669575,0.002519403],"domain_scores_gemma":[0.9907244,0.00279638,0.0010122623,0.00024501584,0.0023861066,0.0028357885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013619369,0.00070391974,0.00064301817,0.0018222098,0.024045415,0.004712933,0.0037724106,0.0016456101,0.005705556],"category_scores_gemma":[0.022178799,0.0005136149,0.00048284145,0.0021832678,0.0039113536,0.0014893231,0.005322371,0.0011325728,0.00045069153],"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":[0.00036081203,0.00033172205,0.13432379,0.0016870159,0.000044933233,0.004417388,0.7408466,0.0003785456,0.0023623027,0.004152832,0.018216463,0.09287757],"study_design_scores_gemma":[0.00006854356,0.00034573206,0.106613345,0.0023762996,0.00005095401,0.00031236061,0.8408561,0.0005687327,0.0005452814,0.00081958214,0.04734332,0.00009982973],"about_ca_topic_score_codex":0.93747103,"about_ca_topic_score_gemma":0.9721439,"teacher_disagreement_score":0.06252897,"about_ca_system_score_codex":0.049150247,"about_ca_system_score_gemma":0.16574617,"threshold_uncertainty_score":0.35661167},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049510494,0.00058277143,0.94400895,0.0012644514,0.000065993125,0.0005166554,0.00012161329,0.00036720253,0.0035617806],"genre_scores_gemma":[0.66427743,0.000472717,0.33192605,0.00034466278,0.00006445596,0.0020824547,0.0001544432,0.00018023672,0.0004975418],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9282547,0.06467404,0.0012656067,0.0019016864,0.003407959,0.0004960469],"domain_scores_gemma":[0.5264463,0.4541779,0.007282035,0.007094158,0.0043258118,0.00067380315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.072849885,0.0006925935,0.001352351,0.0019857944,0.0007429935,0.0025075234,0.0025955515,0.0022159342,0.004641956],"category_scores_gemma":[0.30822593,0.0007606735,0.0022785487,0.0017494855,0.002498228,0.0026549578,0.0028540373,0.0027492323,0.0004561741],"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":[0.0010956653,0.00038542564,0.07106851,0.001791243,0.0020051913,0.00064242556,0.002361814,0.64578545,0.0019038917,0.13704696,0.0037409228,0.13217247],"study_design_scores_gemma":[0.00013676946,0.0003579888,0.004653884,0.00037402587,0.00022611492,0.00020722656,0.00016235287,0.91903824,0.0009488958,0.0717715,0.0020838531,0.00003907875],"about_ca_topic_score_codex":0.00239342,"about_ca_topic_score_gemma":0.0017157823,"teacher_disagreement_score":0.072849885,"about_ca_system_score_codex":0.0018448541,"about_ca_system_score_gemma":0.0024103285,"threshold_uncertainty_score":0.3852716},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99467754,0.00078843016,0.002925582,0.00012048769,0.00006304442,0.00007630646,0.0002599944,0.00004137004,0.0010471463],"genre_scores_gemma":[0.9981621,0.000108670654,0.001391105,0.000027959202,0.000024872837,0.000049971124,0.00017157807,0.00000517031,0.000058542413],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9598678,0.026216058,0.0029204986,0.0028237852,0.0075693047,0.000602614],"domain_scores_gemma":[0.883986,0.072617106,0.01816342,0.0069885836,0.017404921,0.0008400208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028001148,0.00034590898,0.0005783695,0.0009983396,0.00044133683,0.001039582,0.00077307137,0.000558021,0.00046166833],"category_scores_gemma":[0.09323257,0.00045952754,0.0004351968,0.00083930674,0.0009199967,0.00039876733,0.00092332356,0.0005750807,0.00019447184],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032896266,0.00006034002,0.9855047,0.00013545014,0.00020524737,0.00007042451,0.0021873238,0.0002358648,0.0005424246,0.000028330714,0.00026792366,0.010433063],"study_design_scores_gemma":[0.000022714548,0.00059495773,0.9962543,0.00009448712,0.00010043704,0.0002484703,0.0005707897,0.0011268381,0.00056362565,0.000048495378,0.00036473034,0.0000101196065],"about_ca_topic_score_codex":0.0035853942,"about_ca_topic_score_gemma":0.003204868,"teacher_disagreement_score":0.028001148,"about_ca_system_score_codex":0.000676721,"about_ca_system_score_gemma":0.0007297672,"threshold_uncertainty_score":0.14808595},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012739221,0.0006076916,0.97238094,0.0023904145,0.00014138628,0.0019336358,0.0013157044,0.0071493853,0.0013417471],"genre_scores_gemma":[0.027101066,0.00015288488,0.96987265,0.00015565114,0.000038190177,0.0012585693,0.00045866802,0.0007107194,0.00025159575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8622901,0.108180076,0.010192542,0.0061011454,0.012362728,0.00087341334],"domain_scores_gemma":[0.5041586,0.3964302,0.021736136,0.040848054,0.032683853,0.004143118],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26154345,0.0022385463,0.0023013044,0.0061805528,0.0018957938,0.006104504,0.0038390409,0.0021195998,0.0054923915],"category_scores_gemma":[0.3659699,0.0014397969,0.0039189183,0.006553713,0.0021383325,0.0030372026,0.009449063,0.0037736206,0.0011823598],"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":[0.0017237639,0.00061977963,0.077433124,0.00304588,0.0032862767,0.000982009,0.007020927,0.046760496,0.0059221652,0.03100567,0.03319997,0.789],"study_design_scores_gemma":[0.0017903121,0.0018492314,0.056632925,0.0019368362,0.0012310129,0.0015230569,0.002435556,0.7527584,0.012670735,0.09719331,0.06943769,0.0005409335],"about_ca_topic_score_codex":0.006974491,"about_ca_topic_score_gemma":0.008782038,"teacher_disagreement_score":0.73845655,"about_ca_system_score_codex":0.0024998412,"about_ca_system_score_gemma":0.007689696,"threshold_uncertainty_score":0.9106484},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67264444,0.001843195,0.3144305,0.0024311107,0.00029569378,0.0009162766,0.004856991,0.00044401386,0.0021377152],"genre_scores_gemma":[0.9316317,0.0009154598,0.054253943,0.00024630947,0.00021154541,0.0017213017,0.0053001777,0.00010256727,0.005616992],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871731,0.0101352,0.0003631549,0.0012829695,0.00034360657,0.00070196885],"domain_scores_gemma":[0.96966547,0.024671964,0.0024564185,0.0011668404,0.0013057503,0.0007334829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021274446,0.0020510734,0.0036663518,0.0024108044,0.0013544628,0.002678191,0.0048838714,0.002616281,0.008251122],"category_scores_gemma":[0.02703344,0.0016408883,0.0051347297,0.0018594885,0.0018274542,0.0013532032,0.0026507452,0.003687902,0.0009940767],"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":[0.0070997435,0.0016125103,0.24970287,0.0006468364,0.007971372,0.0017594754,0.001814364,0.62669545,0.0019165085,0.047446232,0.005903442,0.04743126],"study_design_scores_gemma":[0.00047414046,0.00058980926,0.012565958,0.00011153039,0.0008055853,0.00015172227,0.00026738324,0.9750704,0.00013144963,0.008251895,0.0014943399,0.00008571686],"about_ca_topic_score_codex":0.042010292,"about_ca_topic_score_gemma":0.021147754,"teacher_disagreement_score":0.042010292,"about_ca_system_score_codex":0.0016805106,"about_ca_system_score_gemma":0.0029731507,"threshold_uncertainty_score":0.1125114},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5105961,0.103278406,0.013698256,0.004846722,0.008846463,0.3338619,0.012157022,0.00075469835,0.011960432],"genre_scores_gemma":[0.51079303,0.01616519,0.016294783,0.0023723177,0.0016047426,0.44750604,0.0019895013,0.00010321333,0.0031712106],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.93163,0.04527851,0.011481011,0.004797253,0.0045198887,0.0022933003],"domain_scores_gemma":[0.91762656,0.047431428,0.020947171,0.0044472907,0.0073194974,0.002228171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044584118,0.005118892,0.010115876,0.0026896936,0.0019455927,0.0047914456,0.0020083303,0.0085969595,0.011766803],"category_scores_gemma":[0.1304252,0.0023461138,0.0103902845,0.0032225563,0.0034008666,0.004837548,0.0021215717,0.0053128,0.0011759188],"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":[0.91868645,0.006052737,0.0013279575,0.026753062,0.021402407,0.000087669265,0.0004031871,0.0004950799,0.0006823504,0.00055044953,0.001523908,0.02203474],"study_design_scores_gemma":[0.9101597,0.06094272,0.0027241257,0.0021767137,0.018945802,0.00006122006,0.00013002467,0.00048264573,0.00088734896,0.0009470568,0.0024595198,0.00008317461],"about_ca_topic_score_codex":0.00164623,"about_ca_topic_score_gemma":0.002743649,"teacher_disagreement_score":0.044584118,"about_ca_system_score_codex":0.0030733268,"about_ca_system_score_gemma":0.005369366,"threshold_uncertainty_score":0.23578614},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42184415,0.004625704,0.54369503,0.01005275,0.0009011981,0.00075623736,0.0023738393,0.0018656205,0.0138854645],"genre_scores_gemma":[0.8308516,0.00078015367,0.16528441,0.0006429473,0.00026111124,0.00044997805,0.0011471836,0.00022526846,0.00035732056],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.91626394,0.06115297,0.00488523,0.005023015,0.011008149,0.0016667636],"domain_scores_gemma":[0.5593716,0.26607352,0.06624526,0.064727105,0.038679488,0.004903087],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10689983,0.0019226786,0.003516688,0.0069765453,0.00082818297,0.006312417,0.0024357513,0.001840729,0.001870594],"category_scores_gemma":[0.39435187,0.0009854711,0.0028895359,0.008409514,0.003007977,0.006476802,0.004807158,0.0033363993,0.0007752336],"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":[0.0015457846,0.0003510109,0.56063133,0.0014259734,0.0023119007,0.00011269812,0.002483325,0.09260464,0.000826488,0.02933737,0.00979123,0.29857826],"study_design_scores_gemma":[0.00047996728,0.0024257898,0.3184136,0.00227168,0.0013377805,0.0003609874,0.0020107704,0.45242342,0.0043878886,0.1929175,0.022163885,0.0008067391],"about_ca_topic_score_codex":0.004609384,"about_ca_topic_score_gemma":0.0043521672,"teacher_disagreement_score":0.89310014,"about_ca_system_score_codex":0.002751601,"about_ca_system_score_gemma":0.0037531024,"threshold_uncertainty_score":0.5653471},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021997627,0.99618983,0.0001867072,0.0003885238,0.00014222696,0.00038015342,0.0002896362,0.000006913957,0.00021617411],"genre_scores_gemma":[0.030516185,0.96626765,0.0009804526,0.0007724535,0.00014617808,0.0009784914,0.00024341728,0.0000063297457,0.00008881567],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9788382,0.007895071,0.007954058,0.0014499804,0.0034011833,0.00046153812],"domain_scores_gemma":[0.9021613,0.07517015,0.014986128,0.0011085998,0.0060665356,0.00050729216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019251753,0.0015464511,0.008242445,0.012521615,0.00082657376,0.0034525208,0.00210497,0.0023446556,0.0027601751],"category_scores_gemma":[0.10233467,0.0014475066,0.0066151544,0.01352672,0.0013475765,0.0032852902,0.001777113,0.0011279796,0.00028193244],"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":[0.00010679905,0.000013931048,0.0022943253,0.9647462,0.007943492,0.00010121237,0.00036407867,0.000069612746,0.00011316097,0.00018013793,0.0008663198,0.023200769],"study_design_scores_gemma":[0.0001188471,0.00018325636,0.008563556,0.9335413,0.0480526,0.00040733616,0.00057099975,0.000077567805,0.0001547149,0.00024462916,0.008050077,0.000035176196],"about_ca_topic_score_codex":0.0073958975,"about_ca_topic_score_gemma":0.020632345,"teacher_disagreement_score":0.019251753,"about_ca_system_score_codex":0.004568329,"about_ca_system_score_gemma":0.015905637,"threshold_uncertainty_score":0.10181421},"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":"incentives","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"incentives","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99363685,0.0014639217,0.00035185472,0.0026677928,0.00002539435,0.00011862426,0.000214015,0.000010815411,0.0015108015],"genre_scores_gemma":[0.9984586,0.00031189137,0.00025145087,0.00068987126,0.000039278388,0.00005276868,0.00008758808,0.0000050897897,0.00010355349],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97601783,0.014480116,0.0019089764,0.0020297393,0.003921173,0.0016421662],"domain_scores_gemma":[0.82033163,0.06801467,0.07837461,0.009256627,0.010617796,0.013404718],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02627945,0.00020678496,0.00040839394,0.0011566795,0.0017535323,0.0020605705,0.0010761598,0.0011293477,0.0017255414],"category_scores_gemma":[0.10031535,0.00033022574,0.00081232167,0.0031129655,0.001979421,0.0014366426,0.0017551582,0.0016195248,0.00010762302],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018812269,0.00019086245,0.9888812,0.000087151835,0.00014258597,0.000053906486,0.0045049516,0.000019262989,0.00008413239,0.000074904216,0.00043141723,0.0053414674],"study_design_scores_gemma":[0.000035696947,0.00012311505,0.997004,0.000053061278,0.000056862034,0.000037991227,0.0021073131,0.00003963323,0.000019025609,0.000033811502,0.00048349256,0.000005989426],"about_ca_topic_score_codex":0.069335535,"about_ca_topic_score_gemma":0.07465236,"teacher_disagreement_score":0.97372055,"about_ca_system_score_codex":0.0024018178,"about_ca_system_score_gemma":0.00680024,"threshold_uncertainty_score":0.13898069},"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":"protocol","genre_gemma":"methods","domain_codex":"reporting","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0125228595,0.058266785,0.31407753,0.0916976,0.021060212,0.43377176,0.042855695,0.0037003693,0.022047186],"genre_scores_gemma":[0.031420045,0.012864568,0.54122734,0.009694656,0.0011644593,0.3896202,0.012046506,0.0004795842,0.0014826007],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.11426545,0.40296093,0.42338976,0.008932121,0.0446278,0.0058239633],"domain_scores_gemma":[0.06830081,0.46123168,0.16972603,0.0649721,0.22797802,0.007791404],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7249626,0.005999877,0.016147334,0.03836315,0.010607357,0.023568861,0.020872096,0.024423532,0.0047500893],"category_scores_gemma":[0.8044734,0.008076801,0.031078087,0.03672797,0.017251117,0.010865254,0.02079739,0.023345888,0.003133084],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027739205,0.00057706685,0.02151267,0.4308018,0.010194935,0.001859302,0.030341655,0.0062432536,0.0037855853,0.066420935,0.20110887,0.22438005],"study_design_scores_gemma":[0.0031518543,0.0008954388,0.025744429,0.42016947,0.0076604127,0.0013128665,0.01052162,0.009116775,0.005852988,0.044013664,0.46961874,0.0019416483],"about_ca_topic_score_codex":0.015812868,"about_ca_topic_score_gemma":0.01023202,"teacher_disagreement_score":0.2750374,"about_ca_system_score_codex":0.028088793,"about_ca_system_score_gemma":0.14507638,"threshold_uncertainty_score":0.33917016},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8976694,0.0031353747,0.05890909,0.022663476,0.000076805736,0.0012617769,0.00042573054,0.000074340016,0.015784008],"genre_scores_gemma":[0.9648703,0.0012209535,0.031205598,0.0016054858,0.00008303386,0.00026715844,0.00013702796,0.000025468147,0.0005849745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.94870615,0.04458725,0.0021059818,0.0009852941,0.002510263,0.0011050958],"domain_scores_gemma":[0.76747024,0.21145226,0.010585922,0.002855687,0.0055117137,0.0021242094],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056434296,0.00047597048,0.0005047613,0.0010428886,0.0018718785,0.0020688442,0.0012642954,0.004030324,0.0026383672],"category_scores_gemma":[0.12483666,0.0004158193,0.00093346497,0.0011311199,0.0014188639,0.0020252457,0.0018894324,0.0024802312,0.00029910548],"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":[0.0032685858,0.0033203147,0.24300835,0.0047480534,0.00074799795,0.152075,0.107956715,0.070494324,0.0044458653,0.033468887,0.016928189,0.3595378],"study_design_scores_gemma":[0.0020119196,0.008056566,0.122096546,0.0067868573,0.001404301,0.1209523,0.17478804,0.27411157,0.01699553,0.082294695,0.18975866,0.0007430896],"about_ca_topic_score_codex":0.0040657157,"about_ca_topic_score_gemma":0.009688724,"teacher_disagreement_score":0.9435657,"about_ca_system_score_codex":0.003774461,"about_ca_system_score_gemma":0.0032139213,"threshold_uncertainty_score":0.2984566},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08232613,0.0034816782,0.85303944,0.0031383194,0.0011729744,0.0007001325,0.024986966,0.014156221,0.016998203],"genre_scores_gemma":[0.6890635,0.002137164,0.2892531,0.00091032777,0.0007267372,0.0015294678,0.0103874,0.0011379954,0.0048544263],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99572057,0.002712882,0.00023368622,0.0006217012,0.000569639,0.00014146669],"domain_scores_gemma":[0.9540332,0.038258318,0.003688751,0.0019334569,0.0017971512,0.00028914225],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063657537,0.0014495441,0.0010319523,0.0055627483,0.000297012,0.0030414476,0.0013981488,0.0010568887,0.03405811],"category_scores_gemma":[0.053997938,0.00044137955,0.0019117884,0.0027334862,0.0011869288,0.0021811074,0.0016571782,0.0014545323,0.0022343656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042096083,0.0004453589,0.063101724,0.006377343,0.0021391665,0.0014255985,0.0024876373,0.1559124,0.0092937695,0.15496245,0.08968981,0.5099552],"study_design_scores_gemma":[0.0010070164,0.0019023905,0.11594446,0.002434576,0.0015815172,0.0034150737,0.0022999563,0.4516063,0.008748414,0.31892025,0.091490276,0.0006497126],"about_ca_topic_score_codex":0.0017906433,"about_ca_topic_score_gemma":0.0013938101,"teacher_disagreement_score":0.9936342,"about_ca_system_score_codex":0.0008263435,"about_ca_system_score_gemma":0.00062112755,"threshold_uncertainty_score":0.11393577},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23452197,0.054367483,0.6920521,0.010028028,0.00068057165,0.001978217,0.000986626,0.00047746074,0.004907543],"genre_scores_gemma":[0.84608364,0.003320257,0.14776984,0.00094061694,0.00015495007,0.0011029218,0.00025672486,0.00008355375,0.0002875289],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.68992114,0.2861822,0.00811574,0.0067154183,0.008090454,0.00097502896],"domain_scores_gemma":[0.42077973,0.5328739,0.021448057,0.0206428,0.0038750318,0.00038038255],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22969307,0.0016736344,0.002926309,0.0033962685,0.0011214804,0.0036932721,0.0025832225,0.0041036694,0.001284132],"category_scores_gemma":[0.43601897,0.0011287464,0.014951432,0.003999404,0.0016723203,0.0032940877,0.0024071087,0.0038518875,0.0001504024],"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":[0.009658954,0.0006238898,0.23582613,0.012823119,0.2099841,0.004096235,0.002711817,0.24273014,0.0032887766,0.031332042,0.004321668,0.24260305],"study_design_scores_gemma":[0.003529617,0.0031028492,0.07416846,0.0065530017,0.18046427,0.0035541484,0.0008646387,0.57244736,0.0053027333,0.13774787,0.011660515,0.0006045801],"about_ca_topic_score_codex":0.0054991753,"about_ca_topic_score_gemma":0.0064045647,"teacher_disagreement_score":0.77030694,"about_ca_system_score_codex":0.0023295716,"about_ca_system_score_gemma":0.0024737017,"threshold_uncertainty_score":0.9499256},"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":"software","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025914889,0.0043823873,0.5791824,0.0064152908,0.0017862839,0.0026440863,0.19214249,0.20197488,0.008880702],"genre_scores_gemma":[0.025442941,0.003768592,0.8115101,0.0032732761,0.000716582,0.017789494,0.06052947,0.072314404,0.0046551703],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97358614,0.017185142,0.0034688034,0.0024797656,0.0028750233,0.0004051064],"domain_scores_gemma":[0.7521542,0.20605157,0.01450839,0.014848227,0.011112179,0.0013254168],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037282165,0.0039376584,0.003616819,0.009028365,0.0008108921,0.0053891945,0.0054630274,0.002307709,0.13427946],"category_scores_gemma":[0.26131782,0.003210048,0.0060776398,0.0071566906,0.0015203637,0.003933619,0.0050532143,0.004192438,0.04088491],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007432233,0.00005540679,0.0034406437,0.018688776,0.004695587,0.00047078726,0.0006246508,0.009148693,0.0009363826,0.022158748,0.8292866,0.10975044],"study_design_scores_gemma":[0.0030944832,0.00026037602,0.0068358383,0.008388082,0.005196433,0.0013296836,0.00016657806,0.050875414,0.0036729872,0.14266305,0.77694476,0.00057232357],"about_ca_topic_score_codex":0.0043073543,"about_ca_topic_score_gemma":0.0061928285,"teacher_disagreement_score":0.96271783,"about_ca_system_score_codex":0.0019977363,"about_ca_system_score_gemma":0.009688724,"threshold_uncertainty_score":0.44920957},"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":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05471914,0.08703388,0.83431363,0.0047458797,0.0018933553,0.009129263,0.0031949948,0.0024616027,0.002508262],"genre_scores_gemma":[0.5126241,0.017142685,0.44800636,0.002035326,0.00041338953,0.016275698,0.001987461,0.0009153796,0.00059960596],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.35959333,0.6075119,0.01755842,0.0066488427,0.0077743228,0.00091318117],"domain_scores_gemma":[0.15364766,0.81221694,0.012344487,0.015146285,0.006007835,0.0006368809],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.44286653,0.0054586846,0.015181667,0.010749138,0.0012253176,0.008267421,0.007043927,0.0063219834,0.0040000216],"category_scores_gemma":[0.70764613,0.004090528,0.056177486,0.00923845,0.002947509,0.0075067854,0.004789741,0.006514878,0.0006041888],"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":[0.03137712,0.00036348047,0.016398504,0.0543406,0.42341438,0.00047664464,0.0018262896,0.2879035,0.0010489068,0.019368233,0.006652018,0.15683031],"study_design_scores_gemma":[0.018879093,0.0064921537,0.01128071,0.018893735,0.31117678,0.0006268381,0.00061125617,0.51251024,0.0021301208,0.10861133,0.0076491744,0.0011385146],"about_ca_topic_score_codex":0.006705448,"about_ca_topic_score_gemma":0.0057107843,"teacher_disagreement_score":0.55713344,"about_ca_system_score_codex":0.006531018,"about_ca_system_score_gemma":0.007025856,"threshold_uncertainty_score":0.68704474},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62879753,0.0018288145,0.35963,0.0011903881,0.0001480712,0.0020364267,0.001146922,0.00045046103,0.0047714417],"genre_scores_gemma":[0.86416084,0.00077088596,0.1307003,0.0003568927,0.000043465534,0.0014458614,0.0010071561,0.0002313227,0.0012833914],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.88711584,0.10621365,0.0018725452,0.0020496298,0.0021080694,0.00064030016],"domain_scores_gemma":[0.33904284,0.62817013,0.010450647,0.012353351,0.009239786,0.00074331154],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.102205686,0.0012875741,0.0016584962,0.0013478204,0.00067498774,0.0015986831,0.002409847,0.0015655219,0.0048406115],"category_scores_gemma":[0.34164888,0.0007316602,0.0029148336,0.0023287092,0.0010404687,0.002957391,0.0014719962,0.0021845377,0.0007219748],"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":[0.0066493764,0.002476425,0.08474952,0.0021926344,0.0040438888,0.0006885328,0.003365947,0.75591886,0.0007125081,0.026018005,0.0052766423,0.10790768],"study_design_scores_gemma":[0.0006648823,0.0019776348,0.0093437135,0.00041108593,0.00059436023,0.00018339239,0.00062384614,0.97132486,0.0006084513,0.01216826,0.0020046416,0.000094977455],"about_ca_topic_score_codex":0.016093358,"about_ca_topic_score_gemma":0.007433504,"teacher_disagreement_score":0.8977943,"about_ca_system_score_codex":0.0017028741,"about_ca_system_score_gemma":0.0022995248,"threshold_uncertainty_score":0.5405218},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028497068,0.0015041782,0.9687618,0.00037523868,0.00003914143,0.0001192427,0.00010304863,0.00013916945,0.0004611867],"genre_scores_gemma":[0.33559462,0.003839147,0.6578241,0.00024575554,0.00013886917,0.0007815664,0.00045025395,0.00013758389,0.000988067],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9876615,0.010557402,0.00032138158,0.00060610304,0.0007141997,0.00013933517],"domain_scores_gemma":[0.9556848,0.04007299,0.0016004423,0.0011002301,0.0012707455,0.00027082185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022233974,0.0011189944,0.001680421,0.0021096095,0.00065937295,0.0018381918,0.0028575663,0.0014564263,0.0009877454],"category_scores_gemma":[0.059104227,0.0009938575,0.0030823026,0.0014266104,0.0007354026,0.0012581263,0.002146522,0.0016610223,0.00021358472],"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":[0.00039157987,0.00018518032,0.04175237,0.00052308803,0.0025259126,0.00032194494,0.00075869565,0.7239882,0.00074074854,0.07260949,0.0009799206,0.15522282],"study_design_scores_gemma":[0.00004424204,0.00008412495,0.0036951618,0.0001186946,0.00024852648,0.00011930972,0.00009859103,0.9561707,0.00032794173,0.03790161,0.001137253,0.00005386138],"about_ca_topic_score_codex":0.014450175,"about_ca_topic_score_gemma":0.012433612,"teacher_disagreement_score":0.022233974,"about_ca_system_score_codex":0.0012409519,"about_ca_system_score_gemma":0.002126119,"threshold_uncertainty_score":0.1175859},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008358368,0.9744039,0.009033696,0.008308431,0.0009275273,0.0012474854,0.00038691444,0.0000620137,0.004794146],"genre_scores_gemma":[0.02293255,0.9354404,0.028624963,0.004612375,0.0004627818,0.006657087,0.0005977467,0.00006361881,0.00060844375],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.86973274,0.070372075,0.0349888,0.004939926,0.017934512,0.0020320357],"domain_scores_gemma":[0.6402981,0.3062026,0.019461008,0.007194041,0.025187843,0.0016563516],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0968502,0.003323189,0.0063245064,0.060509294,0.004577663,0.015222187,0.004698718,0.006285969,0.005504558],"category_scores_gemma":[0.24011448,0.0017811108,0.009507893,0.049094565,0.008781486,0.017435001,0.011879824,0.0072280406,0.0010321793],"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":[0.0001064596,0.00006267959,0.001361873,0.5299851,0.0016797028,0.00035219293,0.02195571,0.0007553791,0.00036437667,0.071015395,0.014990783,0.35737038],"study_design_scores_gemma":[0.000037757265,0.00005466662,0.0013443806,0.81045383,0.002141151,0.0003285748,0.005957773,0.00031880933,0.0002278336,0.022803493,0.15624252,0.00008924637],"about_ca_topic_score_codex":0.009186438,"about_ca_topic_score_gemma":0.018486323,"teacher_disagreement_score":0.9031498,"about_ca_system_score_codex":0.024580032,"about_ca_system_score_gemma":0.059022125,"threshold_uncertainty_score":0.5121989},"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":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022560615,0.77291507,0.087975495,0.0070605357,0.0025439947,0.08619531,0.016197918,0.0007194411,0.0038315996],"genre_scores_gemma":[0.28098255,0.1896519,0.16731119,0.005778443,0.0011851275,0.34353134,0.010175097,0.00044537662,0.00093895814],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.16399384,0.38198698,0.38028342,0.016391259,0.0560317,0.0013128773],"domain_scores_gemma":[0.06733787,0.73338366,0.13757186,0.025031807,0.03567382,0.0010010608],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.57466537,0.00425303,0.022400148,0.03004323,0.002846761,0.008940257,0.0071321786,0.005337782,0.0045615495],"category_scores_gemma":[0.81745017,0.0047307326,0.029419478,0.030911615,0.0071218703,0.011368235,0.0074802553,0.004425423,0.000792782],"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":[0.0012596895,0.000059066922,0.011153591,0.8728928,0.065475084,0.00018072117,0.0021647105,0.00094068004,0.00026080123,0.0020164126,0.0034750141,0.040121436],"study_design_scores_gemma":[0.0033115367,0.00106033,0.022769568,0.7556748,0.16464625,0.0008158912,0.0016698786,0.0035461257,0.0019246249,0.010908735,0.033144437,0.0005278486],"about_ca_topic_score_codex":0.0048870565,"about_ca_topic_score_gemma":0.0062333676,"teacher_disagreement_score":0.42533463,"about_ca_system_score_codex":0.016054196,"about_ca_system_score_gemma":0.024970712,"threshold_uncertainty_score":0.52451336},"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":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008937174,0.0034278773,0.7144529,0.01786268,0.0039393026,0.006945011,0.0988969,0.13096169,0.022620007],"genre_scores_gemma":[0.0036342142,0.0015656101,0.94763166,0.0026004815,0.0004904916,0.011971915,0.009756922,0.018315086,0.0040336144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9195457,0.05510779,0.0134142,0.002565341,0.008412873,0.00095407607],"domain_scores_gemma":[0.58240676,0.33698335,0.016943248,0.020217277,0.041025467,0.0024238832],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.101009406,0.0043309242,0.0031998446,0.013818271,0.0023356737,0.013302016,0.009701112,0.007769699,0.28602692],"category_scores_gemma":[0.4266371,0.0070961425,0.0099415425,0.0129500255,0.002035116,0.011892207,0.010645031,0.008116183,0.09698503],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002931725,0.0001057085,0.0013858721,0.01141923,0.00039439948,0.00022752675,0.0024013447,0.0016272294,0.0003982912,0.033635475,0.82777464,0.1203371],"study_design_scores_gemma":[0.00065846846,0.00012614712,0.0017555541,0.018266996,0.00041236487,0.00031125374,0.00084425224,0.0078745475,0.0016688608,0.08499714,0.88273185,0.00035257716],"about_ca_topic_score_codex":0.007305748,"about_ca_topic_score_gemma":0.011794048,"teacher_disagreement_score":0.8989906,"about_ca_system_score_codex":0.003188995,"about_ca_system_score_gemma":0.010896179,"threshold_uncertainty_score":0.9568554},"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":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037684,0.8246015,0.042825636,0.031934403,0.0041931397,0.03169981,0.016005957,0.0008411815,0.010214393],"genre_scores_gemma":[0.24771227,0.4964346,0.12015857,0.04353602,0.0022547147,0.071112685,0.014514924,0.0011622942,0.0031139373],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.3083009,0.31397268,0.2973581,0.014624364,0.06351833,0.0022256551],"domain_scores_gemma":[0.08193702,0.6305155,0.17517582,0.030586278,0.078992836,0.002792653],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50301,0.0021291685,0.008291054,0.031510334,0.0018057405,0.008480298,0.0038965587,0.005189203,0.004844113],"category_scores_gemma":[0.78491175,0.0033433186,0.011248824,0.033862095,0.0052823937,0.012641866,0.0058450983,0.00549508,0.00189593],"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":[0.0028986307,0.000100506186,0.028999282,0.5741852,0.012894101,0.00035469004,0.004944751,0.0009843415,0.0013726521,0.008892784,0.028025586,0.33634746],"study_design_scores_gemma":[0.0019126312,0.0012484102,0.028903384,0.78450054,0.016549762,0.0013385046,0.0022944496,0.0011820792,0.00164061,0.012009222,0.1481073,0.00031307168],"about_ca_topic_score_codex":0.0023765315,"about_ca_topic_score_gemma":0.0050275694,"teacher_disagreement_score":0.99170893,"about_ca_system_score_codex":0.010250164,"about_ca_system_score_gemma":0.022452164,"threshold_uncertainty_score":0.61287725},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005995515,0.00029987536,0.9928474,0.00021829842,0.000054399075,0.00006258322,0.000035509795,0.000083911254,0.00040249043],"genre_scores_gemma":[0.27610755,0.0010986625,0.7202894,0.00024277814,0.00020689279,0.0005654815,0.00018188481,0.00014938894,0.0011580066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9803356,0.016670391,0.00040510806,0.00087611645,0.0014862749,0.00022661439],"domain_scores_gemma":[0.92212254,0.06682544,0.003933134,0.0042574145,0.0025632447,0.00029819293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040140748,0.0008671039,0.0007591636,0.0013424143,0.0005843432,0.0011380641,0.001973451,0.0014586924,0.0015256694],"category_scores_gemma":[0.14003138,0.00050861586,0.0015979969,0.0019397053,0.00139093,0.002106967,0.0019625,0.0022828379,0.0002214962],"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":[0.00038921458,0.00016619866,0.016926017,0.0005832152,0.00058372633,0.0009895223,0.0009016568,0.3778376,0.0018199815,0.39237896,0.0038188598,0.20360501],"study_design_scores_gemma":[0.00007475885,0.00012117849,0.0018759642,0.000114657516,0.00013939061,0.00019910556,0.00007818225,0.8295343,0.00097242894,0.16269407,0.0041510025,0.000045010325],"about_ca_topic_score_codex":0.0052378625,"about_ca_topic_score_gemma":0.0036837398,"teacher_disagreement_score":0.040140748,"about_ca_system_score_codex":0.0009137187,"about_ca_system_score_gemma":0.0016108834,"threshold_uncertainty_score":0.21228713},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005784717,0.99857926,0.00013220082,0.00025638918,0.00006623087,0.00010159008,0.00018158363,0.0000060860757,0.000098210985],"genre_scores_gemma":[0.009002821,0.98890334,0.0011157254,0.00027712132,0.00009739515,0.0003820015,0.00018123194,0.000006310131,0.000034116896],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.95249814,0.014570912,0.021827497,0.0029491202,0.0072460775,0.00090820796],"domain_scores_gemma":[0.8312755,0.12079408,0.030707864,0.0023677975,0.013858529,0.0009962403],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.041290294,0.0022430762,0.008935594,0.04627792,0.00096440245,0.0046364823,0.0019496982,0.002380923,0.002391244],"category_scores_gemma":[0.1338058,0.0022682932,0.010446678,0.040238533,0.0014305435,0.0047257557,0.0032408854,0.001572099,0.00033257637],"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":[0.00020802133,0.00002090827,0.0040425295,0.91008335,0.008858056,0.000113085975,0.00046155203,0.00017108234,0.0002781648,0.00044224435,0.0015772851,0.07374376],"study_design_scores_gemma":[0.00013500807,0.00022538664,0.017652202,0.9169591,0.04143156,0.00072667724,0.00068035297,0.0001993179,0.00031388356,0.00055595767,0.021062937,0.00005765379],"about_ca_topic_score_codex":0.010254307,"about_ca_topic_score_gemma":0.02367985,"teacher_disagreement_score":0.9910644,"about_ca_system_score_codex":0.0074456795,"about_ca_system_score_gemma":0.017886912,"threshold_uncertainty_score":0.21836656},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73927,0.0020082344,0.23913293,0.0011414443,0.00022962647,0.004775799,0.005969509,0.002347828,0.0051245023],"genre_scores_gemma":[0.60139567,0.00048432834,0.38900137,0.00037933612,0.000072786075,0.0019234722,0.0061012157,0.00009130804,0.00055049884],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9854032,0.007280945,0.0024193185,0.002269915,0.0020872026,0.0005394874],"domain_scores_gemma":[0.93627363,0.038365003,0.00594375,0.002949372,0.015581666,0.0008866378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0336495,0.0015746265,0.0013308561,0.00539471,0.00082525675,0.0028805456,0.0020036974,0.001485566,0.0012744174],"category_scores_gemma":[0.06872748,0.00057317916,0.0020230273,0.0023814964,0.0005960881,0.0019139788,0.0016784566,0.0012517858,0.00058323756],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016211602,0.0010230449,0.7524583,0.00042635915,0.0011253955,0.00011267341,0.00039525825,0.03011195,0.0015007497,0.0013510982,0.0044894237,0.20538469],"study_design_scores_gemma":[0.0010729783,0.0011111167,0.24996278,0.0007468911,0.0012140627,0.0006174937,0.0006862609,0.7274846,0.00761315,0.004361526,0.004989772,0.00013938844],"about_ca_topic_score_codex":0.0112761175,"about_ca_topic_score_gemma":0.0070717935,"teacher_disagreement_score":0.0336495,"about_ca_system_score_codex":0.0020450845,"about_ca_system_score_gemma":0.0043987404,"threshold_uncertainty_score":0.17795771},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16787821,0.0003849454,0.8295413,0.0003290277,0.000045230503,0.0001288979,0.00026347634,0.00021381429,0.0012150533],"genre_scores_gemma":[0.9442252,0.0002843104,0.053618845,0.0001612944,0.00006696324,0.0002463427,0.00036889807,0.000026573822,0.001001697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956905,0.002934057,0.00013616249,0.0005034718,0.000530096,0.00020575164],"domain_scores_gemma":[0.9706133,0.024423033,0.002843928,0.0011095306,0.0007127431,0.00029742456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008997202,0.0010609967,0.0010707664,0.0014115389,0.00020027776,0.0011408667,0.0010683058,0.0015427462,0.0014673454],"category_scores_gemma":[0.023371028,0.0003679414,0.0018132543,0.0004536698,0.0012876923,0.0009529364,0.0013014668,0.0009875783,0.00020616403],"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":[0.00054592843,0.00044858526,0.03542659,0.0002502837,0.0005371424,0.00028879076,0.00010070319,0.8941572,0.0068599973,0.025711942,0.00046537025,0.035207544],"study_design_scores_gemma":[0.000021079399,0.0004227802,0.004564084,0.000014935222,0.00009805379,0.00012779541,0.000017861914,0.98182386,0.0013063028,0.0112898955,0.00029221326,0.000021089414],"about_ca_topic_score_codex":0.0009848347,"about_ca_topic_score_gemma":0.00052724016,"teacher_disagreement_score":0.008997202,"about_ca_system_score_codex":0.00084380014,"about_ca_system_score_gemma":0.0012948298,"threshold_uncertainty_score":0.04758233},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034128267,0.000264422,0.9953147,0.00016280303,0.00003681305,0.00023782134,0.00014030763,0.00012452924,0.00030569878],"genre_scores_gemma":[0.22032589,0.0010673095,0.7707893,0.00028071267,0.00024432776,0.0041028424,0.0008320261,0.00024973377,0.0021079117],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9343352,0.059590604,0.0011342925,0.0020454505,0.0023145785,0.00057981216],"domain_scores_gemma":[0.7756071,0.20985776,0.004982837,0.0058288807,0.0030876196,0.00063580385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06923937,0.002008789,0.0019930871,0.0037323923,0.00077049795,0.0022675898,0.004736531,0.0020066088,0.0062785954],"category_scores_gemma":[0.15335678,0.0012244205,0.0055759866,0.0027491956,0.0022105195,0.0018073941,0.0031792088,0.0043453416,0.00059887447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065229804,0.0002751422,0.028121604,0.001202569,0.0033719037,0.0010669448,0.0018400692,0.41469097,0.0012129381,0.34604698,0.005281576,0.19623697],"study_design_scores_gemma":[0.00012945659,0.0003633478,0.0033001075,0.0002749092,0.00040638575,0.00040730994,0.00023583726,0.81189775,0.0005790615,0.17717876,0.005107776,0.000119331766],"about_ca_topic_score_codex":0.0048409603,"about_ca_topic_score_gemma":0.0028486687,"teacher_disagreement_score":0.06923937,"about_ca_system_score_codex":0.0013915309,"about_ca_system_score_gemma":0.0031176184,"threshold_uncertainty_score":0.36617714},"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":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25626525,0.010644299,0.014084412,0.0016510562,0.0036945348,0.7059447,0.002526924,0.0006480846,0.004540792],"genre_scores_gemma":[0.2524782,0.0017707222,0.017803777,0.0009913353,0.0006195837,0.72353524,0.00041185864,0.000029375766,0.0023598466],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.98345906,0.0113709895,0.0013395624,0.0014928927,0.001102157,0.0012353545],"domain_scores_gemma":[0.99276274,0.0031788812,0.0011548812,0.00081636844,0.0010721845,0.0010148984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018270507,0.003640318,0.00930569,0.0014856672,0.0016132839,0.0021888337,0.0021839286,0.005083116,0.010852169],"category_scores_gemma":[0.018099679,0.0015858638,0.004192908,0.0018631393,0.0031807276,0.0022752415,0.0016374104,0.002875194,0.0017296497],"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":[0.96820027,0.00816468,0.00038212104,0.0061361804,0.0025335485,0.000049369017,0.00011821684,0.0010070703,0.0008328337,0.00076387887,0.0007730136,0.011038822],"study_design_scores_gemma":[0.9521925,0.04409964,0.00045923167,0.00024723227,0.00084646296,0.000014095638,0.000029616547,0.0005653566,0.00020073578,0.00052475417,0.0007997777,0.00002066626],"about_ca_topic_score_codex":0.0021623776,"about_ca_topic_score_gemma":0.0031522766,"teacher_disagreement_score":0.018270507,"about_ca_system_score_codex":0.002235716,"about_ca_system_score_gemma":0.0057922723,"threshold_uncertainty_score":0.09662485},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006267275,0.95106053,0.014461088,0.003996497,0.0008368122,0.019870926,0.0012946199,0.00009136511,0.0021208785],"genre_scores_gemma":[0.08745287,0.8032247,0.05789375,0.0020847167,0.0003274702,0.047527004,0.0011369886,0.00004813502,0.00030430077],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8399196,0.09603345,0.039300535,0.006709456,0.016810024,0.001226926],"domain_scores_gemma":[0.6593948,0.29151082,0.022034822,0.005685444,0.020177161,0.0011969664],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13501066,0.003097028,0.010985217,0.03660454,0.002411364,0.010249758,0.0050518117,0.003346248,0.004860355],"category_scores_gemma":[0.37774116,0.0028987003,0.011636887,0.025281716,0.0040089623,0.016465334,0.005448146,0.003017133,0.00060989463],"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":[0.00013399801,0.000061982835,0.0022195287,0.84268373,0.004757906,0.00013564284,0.0041537182,0.00046944915,0.00012942638,0.0032063504,0.0017896747,0.14025868],"study_design_scores_gemma":[0.00017118291,0.0001659535,0.0021856646,0.9646734,0.011902001,0.00017199898,0.00400744,0.00059738156,0.00020626398,0.0036995243,0.012135537,0.00008365263],"about_ca_topic_score_codex":0.009167521,"about_ca_topic_score_gemma":0.016457228,"teacher_disagreement_score":0.86498934,"about_ca_system_score_codex":0.016232185,"about_ca_system_score_gemma":0.06083142,"threshold_uncertainty_score":0.71401316},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91859514,0.001174423,0.06507194,0.0009006112,0.00019976588,0.0015454168,0.006972465,0.0012444346,0.0042959],"genre_scores_gemma":[0.9043203,0.00019833371,0.089460425,0.00018097763,0.000050974795,0.00040361797,0.005075796,0.000041355714,0.0002681866],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98733425,0.005752164,0.0019499807,0.002080036,0.0024185926,0.0004650616],"domain_scores_gemma":[0.9438606,0.029684186,0.0055999453,0.0028666563,0.017280148,0.00070848764],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02562251,0.0010478621,0.0011090422,0.0051930966,0.00080989714,0.0025977793,0.002125851,0.0012091536,0.0007874622],"category_scores_gemma":[0.07484033,0.00039302272,0.0011721445,0.0022726269,0.0004364028,0.0007967242,0.0010526764,0.0007967584,0.0004621721],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081078085,0.0002826786,0.9291205,0.00015137912,0.00059969665,0.000078278885,0.00016669295,0.014506358,0.0010354747,0.00031060388,0.0026051549,0.050332412],"study_design_scores_gemma":[0.0005403221,0.000738618,0.47377765,0.00029604454,0.0008756178,0.00081333256,0.00033384498,0.511875,0.005752761,0.0010213674,0.0038692106,0.000106230575],"about_ca_topic_score_codex":0.03358431,"about_ca_topic_score_gemma":0.028231267,"teacher_disagreement_score":0.9743775,"about_ca_system_score_codex":0.0020204806,"about_ca_system_score_gemma":0.0055269157,"threshold_uncertainty_score":0.13550633},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020517063,0.001773989,0.006433826,0.06670473,0.88593245,0.00031260404,0.030364327,0.0017319422,0.006540924],"genre_scores_gemma":[0.023007726,0.011517663,0.06417351,0.14986289,0.34525898,0.0061515635,0.045871213,0.017863428,0.3362931],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95371413,0.0177196,0.011610568,0.0032319236,0.012189617,0.0015341793],"domain_scores_gemma":[0.63621753,0.19777705,0.018210342,0.024007,0.11869336,0.0050947242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041040648,0.004522108,0.0041033183,0.009478672,0.0033708885,0.007872575,0.005805892,0.008136488,0.28511402],"category_scores_gemma":[0.46208587,0.0028604716,0.0035922148,0.0103411,0.0032753604,0.0047696736,0.004461481,0.01417665,0.11359055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008055882,0.0000057986754,0.000050506165,0.0006088005,0.000029186658,0.000054151005,0.00003739255,0.000059803977,0.000018240487,0.00080385304,0.9926963,0.005555329],"study_design_scores_gemma":[0.0005692531,0.000049507424,0.001082663,0.003940508,0.00022508054,0.00035941432,0.00011678283,0.0007510982,0.00027998586,0.0077704983,0.98473537,0.000119789634],"about_ca_topic_score_codex":0.027888238,"about_ca_topic_score_gemma":0.03277534,"teacher_disagreement_score":0.28511402,"about_ca_system_score_codex":0.008022252,"about_ca_system_score_gemma":0.018884316,"threshold_uncertainty_score":0.9538014},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9949527,0.00050043094,0.0002288826,0.0005338665,0.000014939502,0.00019024048,0.0012971918,0.000005787751,0.0022760043],"genre_scores_gemma":[0.996624,0.00043719454,0.00053276157,0.0002948554,0.000009193011,0.00008355678,0.00063631847,0.0000047437507,0.0013774115],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975647,0.00066995254,0.00009798432,0.00026309106,0.0006727918,0.0007315225],"domain_scores_gemma":[0.99477637,0.00088327075,0.0006310029,0.00018394289,0.0026777384,0.0008477139],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025696445,0.00036200846,0.0004100089,0.0013182277,0.0033347337,0.0011070574,0.0012850607,0.0008759838,0.0018190295],"category_scores_gemma":[0.0059689037,0.00026905455,0.00047557632,0.003944622,0.00074616546,0.00045189846,0.00084401126,0.00093757093,0.00020090664],"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":[0.0001242081,0.00019888737,0.98153037,0.00009853145,0.00005168252,0.00088441145,0.005152455,0.00016153061,0.00037021778,0.00012721778,0.0016098315,0.009690714],"study_design_scores_gemma":[0.000020762514,0.00010945694,0.98848224,0.000058575788,0.00003618399,0.00022119326,0.008842306,0.0008884948,0.00007797769,0.000016718855,0.0012310279,0.000015124207],"about_ca_topic_score_codex":0.9957682,"about_ca_topic_score_gemma":0.99774665,"teacher_disagreement_score":0.9974304,"about_ca_system_score_codex":0.02849593,"about_ca_system_score_gemma":0.028855028,"threshold_uncertainty_score":0.20675343},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043199062,0.8995014,0.047517996,0.02417363,0.0044157733,0.01524848,0.0020288376,0.00022874541,0.002565141],"genre_scores_gemma":[0.19628829,0.49799722,0.2027798,0.020251464,0.0035835179,0.07677413,0.001506124,0.00026432253,0.00055514683],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.13345684,0.6326429,0.16711998,0.015607717,0.04961649,0.0015560527],"domain_scores_gemma":[0.10250608,0.7115786,0.09352616,0.03506068,0.055755846,0.0015725616],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.62581927,0.0037226656,0.01748395,0.040328927,0.0037701589,0.022612503,0.007813212,0.007955369,0.00528393],"category_scores_gemma":[0.86300534,0.0074651893,0.021857267,0.039521985,0.012326919,0.024824765,0.009163352,0.005938068,0.0011818464],"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":[0.00076153583,0.000101341386,0.012189439,0.778769,0.0638136,0.00024233038,0.004478867,0.0010275898,0.00034904695,0.020282838,0.0074449107,0.11053946],"study_design_scores_gemma":[0.0010505386,0.00043131213,0.005446959,0.88777924,0.046487592,0.0005672103,0.002420112,0.0013906748,0.0005161362,0.026618225,0.027056787,0.00023528907],"about_ca_topic_score_codex":0.0056256354,"about_ca_topic_score_gemma":0.008220587,"teacher_disagreement_score":0.98251605,"about_ca_system_score_codex":0.02619974,"about_ca_system_score_gemma":0.041559316,"threshold_uncertainty_score":0.4614315},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72421217,0.00033211132,0.25295794,0.0032745595,0.0005198017,0.0064749587,0.0050048633,0.0023467748,0.0048768534],"genre_scores_gemma":[0.8015713,0.000070587455,0.18397287,0.000772953,0.000089822584,0.0045586335,0.008166605,0.00035297836,0.00044426677],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.838124,0.13377889,0.006618415,0.010841795,0.00900754,0.0016293151],"domain_scores_gemma":[0.6639186,0.20631814,0.0136150215,0.072029576,0.0395342,0.004584508],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24186942,0.0018106514,0.0010211373,0.0015087409,0.0020258422,0.0039110137,0.0057314313,0.0023336424,0.0016971156],"category_scores_gemma":[0.32605192,0.00090984756,0.0023105566,0.0022686548,0.00261614,0.0039539346,0.0068822005,0.0034423347,0.0008211398],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00658125,0.006063998,0.66079956,0.0011128044,0.00466683,0.0006826701,0.0065977494,0.15670335,0.007510918,0.0112812845,0.019031554,0.11896798],"study_design_scores_gemma":[0.0035320225,0.005895277,0.21999694,0.0007736215,0.0012201439,0.00060488423,0.0030677365,0.719171,0.013800602,0.014622559,0.017021418,0.0002938486],"about_ca_topic_score_codex":0.012207983,"about_ca_topic_score_gemma":0.009479318,"teacher_disagreement_score":0.75813055,"about_ca_system_score_codex":0.0022283494,"about_ca_system_score_gemma":0.00690207,"threshold_uncertainty_score":0.93491},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10179225,0.65849507,0.1946638,0.013767034,0.003552124,0.008881196,0.010780866,0.0010744162,0.00699329],"genre_scores_gemma":[0.8054944,0.041681897,0.13679397,0.003228318,0.0017260372,0.007274585,0.003037691,0.0003180273,0.00044505368],"study_design_codex":"meta_analysis","study_design_gemma":"observational","domain_scores_codex":[0.42896926,0.30051017,0.20149687,0.02080914,0.047035277,0.0011792704],"domain_scores_gemma":[0.10988067,0.6887183,0.11638021,0.038460787,0.045078587,0.0014814337],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.48334616,0.0023536056,0.008335964,0.02340696,0.0015970613,0.010385461,0.0038969396,0.0026040906,0.0032524585],"category_scores_gemma":[0.7472464,0.0018744568,0.017554913,0.018429974,0.003929337,0.005501442,0.0044886298,0.0025635299,0.0003827459],"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":[0.0044602524,0.00018073207,0.2904862,0.2251888,0.32265764,0.00036565537,0.0026603974,0.003883977,0.0013339075,0.00420271,0.005408292,0.13917151],"study_design_scores_gemma":[0.003621763,0.0039601056,0.2690288,0.1449812,0.46995813,0.0031289272,0.0024226657,0.018261727,0.0051450157,0.03485147,0.04372838,0.0009117984],"about_ca_topic_score_codex":0.0015958081,"about_ca_topic_score_gemma":0.003104826,"teacher_disagreement_score":0.51665384,"about_ca_system_score_codex":0.0039117825,"about_ca_system_score_gemma":0.006015969,"threshold_uncertainty_score":0.6371262},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039342092,0.004754667,0.98379356,0.0019648192,0.0005473382,0.0022610915,0.00076514547,0.00061680545,0.0013623663],"genre_scores_gemma":[0.2934621,0.0045197634,0.66687226,0.0033189093,0.0010684291,0.02523223,0.0014568252,0.00052890746,0.0035406034],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.68367314,0.29246068,0.005415822,0.008555405,0.008605344,0.0012895842],"domain_scores_gemma":[0.4359079,0.52398854,0.021364115,0.012054238,0.0054358453,0.0012492848],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2648448,0.0042883037,0.005136416,0.0052645616,0.000747094,0.0052051,0.007815989,0.0046920255,0.011552622],"category_scores_gemma":[0.44405743,0.0020425771,0.009527294,0.004178895,0.004194513,0.0060507134,0.0041558016,0.01047765,0.0015782199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005885473,0.0005284166,0.016333068,0.008963987,0.013792976,0.0007656674,0.0011370232,0.43117726,0.0007095377,0.33046496,0.013875517,0.1763661],"study_design_scores_gemma":[0.0017193481,0.0010390059,0.0021800587,0.0011939865,0.0023626625,0.00026575275,0.0001127427,0.7135389,0.0005794947,0.26564443,0.011215872,0.00014769152],"about_ca_topic_score_codex":0.002462644,"about_ca_topic_score_gemma":0.0016868848,"teacher_disagreement_score":0.7351552,"about_ca_system_score_codex":0.0036463889,"about_ca_system_score_gemma":0.0049674064,"threshold_uncertainty_score":0.9065772},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015855823,0.13842441,0.49839804,0.020211576,0.002269462,0.25741953,0.042517204,0.004767958,0.020136004],"genre_scores_gemma":[0.036457375,0.03986613,0.5459519,0.0038784328,0.000362941,0.36327496,0.008334478,0.0007052502,0.0011684948],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.2670049,0.38418517,0.2628861,0.012993662,0.07064168,0.0022885238],"domain_scores_gemma":[0.111135654,0.5467242,0.13703121,0.051145986,0.15008457,0.0038783797],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5872356,0.003944498,0.0055250847,0.055927835,0.0018443202,0.011091715,0.004770226,0.0036519177,0.020330122],"category_scores_gemma":[0.787796,0.004138641,0.011281983,0.050079994,0.003236783,0.011956648,0.008658512,0.00485007,0.008490311],"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":[0.0011598128,0.00031873156,0.021158746,0.28545737,0.0049213483,0.00015297903,0.007037868,0.0011785323,0.0017220847,0.008091838,0.034039106,0.6347616],"study_design_scores_gemma":[0.0031061745,0.0017363033,0.054768655,0.50002134,0.013716421,0.0010112432,0.0053468877,0.0050649703,0.004937311,0.01635589,0.3931038,0.0008310362],"about_ca_topic_score_codex":0.0026479065,"about_ca_topic_score_gemma":0.0043209055,"teacher_disagreement_score":0.41276437,"about_ca_system_score_codex":0.011322366,"about_ca_system_score_gemma":0.053922478,"threshold_uncertainty_score":0.509012},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027036802,0.22721264,0.38909486,0.11000153,0.011474549,0.21090451,0.023186034,0.005878244,0.019544043],"genre_scores_gemma":[0.0075989105,0.07437454,0.77001923,0.0062557557,0.0015298843,0.13359895,0.00371019,0.00058064004,0.0023319386],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.5226603,0.27983016,0.15282091,0.009181428,0.033792783,0.001714434],"domain_scores_gemma":[0.14902143,0.6674116,0.039074115,0.04517634,0.09576903,0.0035474754],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.485374,0.006403202,0.013396417,0.06643814,0.0051939613,0.01613602,0.015183544,0.012441648,0.024107441],"category_scores_gemma":[0.69039834,0.007401084,0.018306503,0.04542758,0.007919383,0.018467935,0.015833989,0.011407504,0.0099359825],"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":[0.00039095193,0.00015983057,0.0013895038,0.45261806,0.0037343288,0.0011963083,0.012834457,0.002307207,0.0015516077,0.017026141,0.13082717,0.37596443],"study_design_scores_gemma":[0.0005770819,0.00020403341,0.0011861286,0.6639276,0.0036106152,0.00072024367,0.004731866,0.002403913,0.0012789216,0.047767382,0.27314922,0.0004429382],"about_ca_topic_score_codex":0.009592268,"about_ca_topic_score_gemma":0.018980136,"teacher_disagreement_score":0.514626,"about_ca_system_score_codex":0.011263217,"about_ca_system_score_gemma":0.10811895,"threshold_uncertainty_score":0.63462543},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8956024,0.0007748774,0.03192327,0.0031749115,0.00003285593,0.000113710856,0.00024911767,0.000060250324,0.06806859],"genre_scores_gemma":[0.9945469,0.00012986621,0.004232152,0.000024898856,0.0000058114247,0.000026414911,0.000038133905,0.0000019383103,0.0009938407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9994475,0.00029367377,0.000022988515,0.000089809895,0.0000628846,0.0000830731],"domain_scores_gemma":[0.9979018,0.0013947316,0.00026558936,0.00011424643,0.00021874264,0.00010477665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015883293,0.00032745846,0.00020736086,0.0024934642,0.0016914175,0.0030126413,0.00065976585,0.000496486,0.0027704216],"category_scores_gemma":[0.0043601748,0.00012959709,0.00063069287,0.0012268202,0.0028625736,0.0021906663,0.0016043481,0.00040649733,0.00007187555],"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":[0.00039354194,0.0002812858,0.05403544,0.00042269268,0.00021293867,0.0019897637,0.09864752,0.063095406,0.001327593,0.6812385,0.0024977978,0.09585761],"study_design_scores_gemma":[0.00007864541,0.00016370349,0.06995046,0.0005552551,0.00020791823,0.00047451985,0.118643515,0.26691982,0.00086914044,0.5221547,0.019873071,0.00010932546],"about_ca_topic_score_codex":0.07454293,"about_ca_topic_score_gemma":0.052206088,"teacher_disagreement_score":0.07454293,"about_ca_system_score_codex":0.005019235,"about_ca_system_score_gemma":0.0019512865,"threshold_uncertainty_score":0.1482181},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8638124,0.0031772575,0.008514133,0.0041145324,0.0058062864,0.105619356,0.0010272214,0.0008882437,0.007040672],"genre_scores_gemma":[0.8551857,0.0007932897,0.016102532,0.0035309861,0.0018459831,0.1189064,0.00041032388,0.00008281978,0.003142052],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.86692846,0.11435721,0.006674017,0.0058615603,0.0029893513,0.003189382],"domain_scores_gemma":[0.88206536,0.08215863,0.017573461,0.007582787,0.002965982,0.0076538455],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05496262,0.00354399,0.0044326833,0.0027204342,0.0016022972,0.0030926734,0.0030101486,0.0092820125,0.026580952],"category_scores_gemma":[0.09373927,0.0022123712,0.0037194905,0.0018486873,0.0049722875,0.005649452,0.0038217905,0.006689954,0.0035153213],"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":[0.9529435,0.022611089,0.0014301417,0.00066434016,0.0006573585,0.000019885747,0.00021853921,0.00045261002,0.00018376418,0.00050490804,0.0008077254,0.01950613],"study_design_scores_gemma":[0.8648272,0.1297982,0.001208997,0.00017066581,0.00041461294,0.000015026319,0.000073510404,0.0019079208,0.0002268408,0.0005780243,0.000743493,0.000035406625],"about_ca_topic_score_codex":0.0011049828,"about_ca_topic_score_gemma":0.0007957337,"teacher_disagreement_score":0.94503736,"about_ca_system_score_codex":0.0031313554,"about_ca_system_score_gemma":0.00530483,"threshold_uncertainty_score":0.2906736},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27412954,0.0067768125,0.6061837,0.02080347,0.002360567,0.021776212,0.003007301,0.0005838343,0.0643785],"genre_scores_gemma":[0.69850576,0.00237738,0.25117293,0.0053088497,0.00047529195,0.038138516,0.0017324878,0.0005222207,0.0017665714],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.4090275,0.4702822,0.038775697,0.016734261,0.0631242,0.0020561402],"domain_scores_gemma":[0.24310891,0.5072871,0.07036159,0.095500566,0.0823287,0.0014131288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3636621,0.0011118265,0.0023289653,0.0066937194,0.0038370756,0.007561441,0.0020283253,0.0020235432,0.005081505],"category_scores_gemma":[0.64158744,0.001371486,0.0024990148,0.010674933,0.015006844,0.007293702,0.007489433,0.003522672,0.0020231584],"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":[0.001375537,0.00076968776,0.1815943,0.02519419,0.0028235037,0.0009522425,0.239238,0.0014746124,0.0047110706,0.102570735,0.019925619,0.41937056],"study_design_scores_gemma":[0.001867688,0.0053212233,0.25304887,0.068688996,0.0039790054,0.0035629699,0.13113603,0.014428921,0.020593474,0.24934055,0.24711455,0.0009177578],"about_ca_topic_score_codex":0.0016888926,"about_ca_topic_score_gemma":0.001619789,"teacher_disagreement_score":0.3636621,"about_ca_system_score_codex":0.0038043244,"about_ca_system_score_gemma":0.017041594,"threshold_uncertainty_score":0.7847179},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3435417,0.0047835875,0.6324938,0.003935442,0.0002705743,0.0009927844,0.008878049,0.0006842792,0.0044198087],"genre_scores_gemma":[0.8732531,0.0007587684,0.11907836,0.0005525864,0.00029888056,0.0012734634,0.0043749246,0.00007473418,0.00033520072],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9112971,0.065972015,0.010142574,0.0056649367,0.005908421,0.0010149155],"domain_scores_gemma":[0.543725,0.36543632,0.050234657,0.02866774,0.010629994,0.0013062472],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.113389015,0.0006113866,0.0011185607,0.006662232,0.0010166358,0.0031226287,0.0017652881,0.0010972279,0.001268626],"category_scores_gemma":[0.2900028,0.00051856367,0.0017917635,0.0073703346,0.0023368262,0.0036223393,0.002970424,0.0015659558,0.00016106007],"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":[0.0005243465,0.0001081933,0.814669,0.0017810082,0.0025702014,0.00022830375,0.005266639,0.014599273,0.00069609226,0.023958988,0.003788519,0.13180946],"study_design_scores_gemma":[0.0001021406,0.0012906992,0.73584074,0.0024648185,0.0016792226,0.0011166881,0.006078408,0.087123245,0.0023341663,0.13506249,0.026568547,0.00033886216],"about_ca_topic_score_codex":0.0031976083,"about_ca_topic_score_gemma":0.0036305941,"teacher_disagreement_score":0.886611,"about_ca_system_score_codex":0.0017550245,"about_ca_system_score_gemma":0.0016752755,"threshold_uncertainty_score":0.5996656},"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":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0184837,0.17947505,0.48894012,0.13148977,0.02935791,0.12254928,0.012905497,0.0030596692,0.013738898],"genre_scores_gemma":[0.12108604,0.044466756,0.57238734,0.034364786,0.006914594,0.21354476,0.0047342954,0.0013114482,0.0011900059],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.047229756,0.5879894,0.3165402,0.010174291,0.036968112,0.0010982169],"domain_scores_gemma":[0.023310687,0.703837,0.10572773,0.08466541,0.081055045,0.0014041568],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8489353,0.00413971,0.014975033,0.024804352,0.0042279423,0.026260087,0.013186896,0.008526524,0.004318539],"category_scores_gemma":[0.9323656,0.004689221,0.019370308,0.026794849,0.016629227,0.017591562,0.013613688,0.017372742,0.0027498298],"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":[0.0029644808,0.0003321209,0.02356271,0.36216572,0.017999148,0.00043756294,0.022304136,0.0040769195,0.0016535019,0.051226903,0.052562166,0.4607146],"study_design_scores_gemma":[0.0041645397,0.0014642691,0.025565917,0.57370496,0.013394624,0.0011554775,0.006678127,0.009597336,0.0044480655,0.16655952,0.1918651,0.0014021469],"about_ca_topic_score_codex":0.005109185,"about_ca_topic_score_gemma":0.0042450144,"teacher_disagreement_score":0.1510647,"about_ca_system_score_codex":0.019529749,"about_ca_system_score_gemma":0.046036717,"threshold_uncertainty_score":0.18628973},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21108904,0.025573302,0.6852036,0.0093952725,0.0010016878,0.030150069,0.011382872,0.019707127,0.0064970166],"genre_scores_gemma":[0.32491297,0.0023591937,0.6559332,0.0010624272,0.00018834755,0.01264758,0.0018716702,0.0005956923,0.00042899663],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.46940148,0.43362522,0.06569802,0.010886498,0.019259805,0.0011289639],"domain_scores_gemma":[0.07610664,0.7904215,0.052249003,0.04914393,0.031216616,0.0008623448],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45518884,0.0024938793,0.0035623247,0.011167053,0.0015564471,0.0058508287,0.0042509725,0.0018093927,0.0036787568],"category_scores_gemma":[0.7226175,0.0038480035,0.0063097375,0.009257533,0.0018484365,0.00703612,0.0050596334,0.0022250314,0.0015940107],"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":[0.008983875,0.0005507283,0.0544428,0.08237221,0.008711024,0.0005624517,0.014467269,0.032536842,0.008057072,0.005100168,0.01626705,0.76794845],"study_design_scores_gemma":[0.013203981,0.014232251,0.1029918,0.06892812,0.029204745,0.0047704745,0.007128073,0.5250101,0.040699568,0.055999894,0.13382185,0.004009214],"about_ca_topic_score_codex":0.0046513733,"about_ca_topic_score_gemma":0.011343571,"teacher_disagreement_score":0.5448111,"about_ca_system_score_codex":0.0038548326,"about_ca_system_score_gemma":0.01769142,"threshold_uncertainty_score":0.67184913},"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":"review","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.115583815,0.40894058,0.22835433,0.0045889933,0.0012931584,0.20530735,0.01980442,0.0019331855,0.014194159],"genre_scores_gemma":[0.16901805,0.0656873,0.5728245,0.0011938292,0.00044505476,0.18378149,0.0061201192,0.00031868933,0.00061098643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.35178196,0.39280778,0.19831358,0.01221654,0.04308484,0.0017953307],"domain_scores_gemma":[0.20355065,0.67198247,0.053057417,0.030312402,0.03919044,0.0019066118],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3060412,0.0053028357,0.015663832,0.06598104,0.0028196417,0.011800197,0.004539225,0.004231887,0.010254272],"category_scores_gemma":[0.68519473,0.0056510083,0.026632996,0.0835071,0.0021089602,0.015833208,0.012061033,0.0031106106,0.002393305],"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":[0.01137676,0.0010771471,0.033005126,0.4089605,0.06458194,0.0007275684,0.0075939777,0.004670536,0.0028376079,0.006199209,0.0056305192,0.45333913],"study_design_scores_gemma":[0.031841658,0.018233921,0.054472223,0.33530957,0.4009984,0.004805478,0.010120519,0.026297063,0.008091881,0.030949347,0.07693837,0.0019415568],"about_ca_topic_score_codex":0.0017550697,"about_ca_topic_score_gemma":0.0033851487,"teacher_disagreement_score":0.69395876,"about_ca_system_score_codex":0.006711466,"about_ca_system_score_gemma":0.014206523,"threshold_uncertainty_score":0.85577476},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95674914,0.00047153234,0.03961929,0.0012081534,0.000013044566,0.00008874815,0.00058187364,0.00007703994,0.0011911289],"genre_scores_gemma":[0.99046665,0.00010235985,0.008698642,0.00010279655,0.000010983509,0.000014661554,0.0003255624,0.000015603942,0.00026275514],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922597,0.00485952,0.00029443786,0.00092706387,0.0011098814,0.00054940965],"domain_scores_gemma":[0.93659884,0.047984853,0.0065247216,0.0033878747,0.004754173,0.000749503],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029879602,0.0006066964,0.0007340043,0.0018427392,0.00077005394,0.0019299798,0.0023127683,0.0015178886,0.00088304543],"category_scores_gemma":[0.07594081,0.00043306453,0.0011129439,0.0018704952,0.0016703106,0.00096331874,0.0011448712,0.0014824867,0.00009725979],"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":[0.0002919153,0.0000960581,0.87068695,0.00008701895,0.00047082306,0.0013427885,0.0015451966,0.09637028,0.00056767405,0.0043627108,0.0011089288,0.023069667],"study_design_scores_gemma":[0.00004486853,0.00012707994,0.28519532,0.0001017657,0.00026312118,0.0010610931,0.0015611002,0.6976462,0.0010946896,0.011232426,0.0015705415,0.00010184386],"about_ca_topic_score_codex":0.36238143,"about_ca_topic_score_gemma":0.2683549,"teacher_disagreement_score":0.9701204,"about_ca_system_score_codex":0.004749507,"about_ca_system_score_gemma":0.0032140452,"threshold_uncertainty_score":0.7205443},"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":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030649846,0.020226352,0.94987935,0.013271169,0.00375168,0.0016834651,0.00089703064,0.004437332,0.0055469912],"genre_scores_gemma":[0.0027786843,0.015867308,0.9657905,0.003992304,0.0023787064,0.004652568,0.0004630288,0.0017153926,0.0023615032],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9147992,0.060495,0.009523525,0.002798112,0.011822731,0.0005614527],"domain_scores_gemma":[0.54271424,0.4043837,0.009474179,0.011236601,0.030301519,0.0018897385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11275549,0.005298162,0.0034118271,0.011170613,0.0015168489,0.0053774095,0.007489451,0.0074494095,0.027403688],"category_scores_gemma":[0.30816746,0.0038980243,0.0051182946,0.00689824,0.0053493744,0.011252357,0.004451348,0.0151299955,0.022678407],"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":[0.00019098278,0.0003208034,0.001267667,0.012919667,0.0004461607,0.0008374805,0.005272673,0.0034833779,0.0025045886,0.051316924,0.38537976,0.5360599],"study_design_scores_gemma":[0.00021164495,0.00038699192,0.0019663812,0.014597695,0.00016511149,0.003003834,0.0019092268,0.012348949,0.002034667,0.1909147,0.771984,0.00047689647],"about_ca_topic_score_codex":0.0023190668,"about_ca_topic_score_gemma":0.0030403417,"teacher_disagreement_score":0.11275549,"about_ca_system_score_codex":0.0026905008,"about_ca_system_score_gemma":0.0054100472,"threshold_uncertainty_score":0.59631515},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2274117,0.0031673107,0.64027715,0.06482314,0.0019743855,0.029826064,0.00028544044,0.00070518017,0.03152964],"genre_scores_gemma":[0.49386242,0.0006478811,0.46848452,0.008835906,0.00027490265,0.026583217,0.000088342334,0.00018264727,0.0010402274],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.092499286,0.8760531,0.012371659,0.0050806724,0.011021771,0.002973383],"domain_scores_gemma":[0.17429483,0.7393603,0.019731864,0.03733908,0.02494372,0.004330231],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6821989,0.0019902948,0.0021515654,0.0038505867,0.010157493,0.010666657,0.007173573,0.01251044,0.0055474434],"category_scores_gemma":[0.6391788,0.0024348835,0.0022742231,0.003812438,0.016172921,0.011478522,0.015846483,0.0077069434,0.0015031706],"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":[0.0023844352,0.0013670399,0.015771393,0.014663263,0.0006362354,0.009152659,0.57939434,0.009735832,0.004603047,0.10200263,0.021710914,0.23857822],"study_design_scores_gemma":[0.0022428897,0.0079334155,0.017619396,0.031567138,0.00058817,0.011994384,0.31563303,0.060231213,0.010909347,0.31224903,0.22768016,0.0013518914],"about_ca_topic_score_codex":0.0016419792,"about_ca_topic_score_gemma":0.0019303829,"teacher_disagreement_score":0.31780112,"about_ca_system_score_codex":0.008545139,"about_ca_system_score_gemma":0.014921489,"threshold_uncertainty_score":0.39190543},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04200118,0.00255061,0.82723045,0.037258778,0.0009442817,0.006061333,0.0007689181,0.0005716971,0.082612775],"genre_scores_gemma":[0.2923421,0.0020914879,0.6830664,0.003059414,0.00014611614,0.012194388,0.00059512316,0.00033426183,0.0061706575],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8747931,0.10586018,0.0047680065,0.004013299,0.007934678,0.0026307036],"domain_scores_gemma":[0.8532735,0.119503304,0.0052364403,0.007019796,0.011486221,0.0034806977],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13774201,0.0028692002,0.0021635725,0.022631353,0.0120872585,0.021944048,0.0060810777,0.005274637,0.011565594],"category_scores_gemma":[0.10318048,0.0017130736,0.004306585,0.011542748,0.040800255,0.02956945,0.028391961,0.011602331,0.0015054424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008626751,0.000109365,0.0030563332,0.0019381066,0.00007457747,0.0006244562,0.3589006,0.001065704,0.0010749795,0.5463333,0.0074319667,0.07930439],"study_design_scores_gemma":[0.00007679639,0.0001363407,0.0018753897,0.0051085977,0.00009193227,0.00066469755,0.32580137,0.004866277,0.0014011601,0.5070707,0.1527115,0.00019523464],"about_ca_topic_score_codex":0.011141534,"about_ca_topic_score_gemma":0.012231011,"teacher_disagreement_score":0.86225796,"about_ca_system_score_codex":0.02690917,"about_ca_system_score_gemma":0.040489707,"threshold_uncertainty_score":0.7284581},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011188065,0.030184476,0.6023218,0.1888745,0.0020681357,0.0015215039,0.0014403819,0.0004491882,0.16195193],"genre_scores_gemma":[0.65313417,0.019350067,0.2890982,0.018432168,0.0034744916,0.0069871005,0.0011122403,0.00018040146,0.00823125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9267724,0.059861913,0.0028753467,0.004057086,0.0047453404,0.001687892],"domain_scores_gemma":[0.84459364,0.12508655,0.009695834,0.005798452,0.0117566455,0.0030689153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07809777,0.0019761417,0.0015606255,0.0106775565,0.005037552,0.012373367,0.005060923,0.005983191,0.011187206],"category_scores_gemma":[0.08805794,0.000880785,0.0021517465,0.011257323,0.038660746,0.028184844,0.008089042,0.006526935,0.0015508818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007943383,0.000009814326,0.00035700598,0.00013662741,0.000013485283,0.00002928648,0.0013332682,0.00028702218,0.000010097555,0.99275416,0.0012085381,0.0038528014],"study_design_scores_gemma":[0.000030240224,0.00003052336,0.00033881512,0.00051608717,0.000026288324,0.00009612761,0.0012759074,0.0015079086,0.00003477798,0.96931475,0.026809858,0.000018766163],"about_ca_topic_score_codex":0.004450741,"about_ca_topic_score_gemma":0.0017941283,"teacher_disagreement_score":0.92190224,"about_ca_system_score_codex":0.014338479,"about_ca_system_score_gemma":0.015399755,"threshold_uncertainty_score":0.41302544},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.429257,0.003869872,0.5582558,0.0015850147,0.00022724118,0.0022108697,0.00054439827,0.0003978924,0.0036519957],"genre_scores_gemma":[0.96852154,0.00019861532,0.028865285,0.00038711898,0.00003367737,0.0014064916,0.00017154447,0.000078529876,0.00033724087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8752029,0.10460735,0.0047843587,0.008242318,0.005992067,0.0011709079],"domain_scores_gemma":[0.4349083,0.51382583,0.023787515,0.022377364,0.004248359,0.0008526504],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20386481,0.0007960075,0.0017632178,0.0011371684,0.0003635835,0.0014986565,0.0020512433,0.0016461696,0.0026779708],"category_scores_gemma":[0.3820038,0.00072493387,0.0023856892,0.0009976104,0.0031023428,0.0017262183,0.0015173929,0.0021563424,0.00032301864],"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":[0.028456202,0.0010392802,0.26135638,0.0051602195,0.012012505,0.0014863432,0.0047555105,0.25138918,0.007878625,0.07638744,0.006894984,0.34318337],"study_design_scores_gemma":[0.0040734196,0.008119912,0.21181794,0.0016684724,0.00413433,0.0015176894,0.0004100934,0.561383,0.011347029,0.18868046,0.0065798545,0.00026780355],"about_ca_topic_score_codex":0.0004936666,"about_ca_topic_score_gemma":0.00030907177,"teacher_disagreement_score":0.7961352,"about_ca_system_score_codex":0.0011569792,"about_ca_system_score_gemma":0.0012398089,"threshold_uncertainty_score":0.9817764},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8463901,0.0640271,0.03750843,0.0016816838,0.0010123409,0.0025126173,0.020041177,0.0005581988,0.026268365],"genre_scores_gemma":[0.9636137,0.006158648,0.021729184,0.00024895556,0.00018446681,0.001463911,0.0056250812,0.00006221734,0.0009138213],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9213323,0.035603236,0.020120109,0.0064489143,0.015897604,0.0005977875],"domain_scores_gemma":[0.7503559,0.18098888,0.023433117,0.009212922,0.035373114,0.0006360821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06759255,0.000542109,0.001649655,0.009545753,0.00038391768,0.0021629774,0.0011136949,0.0006095073,0.0020664916],"category_scores_gemma":[0.17696637,0.00036268082,0.0019461772,0.0060119927,0.0010299525,0.0017133126,0.0018013974,0.000600975,0.00049422716],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030059617,0.00020093565,0.664298,0.022388117,0.007261899,0.00041083584,0.008801231,0.0015484849,0.0029507237,0.0027542445,0.006656049,0.2797236],"study_design_scores_gemma":[0.00045092247,0.0014923298,0.94557637,0.0056527886,0.0038404844,0.0015083182,0.0057708696,0.004280186,0.0029230493,0.00455991,0.023691416,0.00025335644],"about_ca_topic_score_codex":0.0010112595,"about_ca_topic_score_gemma":0.0024270525,"teacher_disagreement_score":0.06759255,"about_ca_system_score_codex":0.00089367427,"about_ca_system_score_gemma":0.0015013146,"threshold_uncertainty_score":0.35746783},"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":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001114639,0.00026278777,0.00601582,0.0015204219,0.0005218337,0.9705585,0.013491083,0.0002948517,0.0062200087],"genre_scores_gemma":[0.0011747797,0.00018027217,0.0074539394,0.00060162804,0.00007583002,0.98642635,0.003039054,0.000036104222,0.0010121377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.91427517,0.055992264,0.018186754,0.003096621,0.0051199193,0.0033293653],"domain_scores_gemma":[0.86487937,0.043608554,0.012911752,0.023288906,0.049018305,0.0062931026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14534655,0.0021213577,0.0030790076,0.0052509,0.004379712,0.0044929506,0.0033086687,0.005652788,0.117086135],"category_scores_gemma":[0.112882264,0.002655857,0.0032569636,0.0053542326,0.0026066776,0.0049456083,0.0047109965,0.006733777,0.036953397],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020325957,0.003435872,0.0047285142,0.034901742,0.00039507746,0.0009165838,0.008173175,0.0029523284,0.0023650588,0.027278826,0.74755883,0.14696804],"study_design_scores_gemma":[0.01907901,0.0024748843,0.0144052375,0.024525633,0.0002277715,0.00043005272,0.0038472512,0.0017268268,0.0015201394,0.011034129,0.92036986,0.00035918818],"about_ca_topic_score_codex":0.0026784637,"about_ca_topic_score_gemma":0.0041378117,"teacher_disagreement_score":0.14534655,"about_ca_system_score_codex":0.00653228,"about_ca_system_score_gemma":0.033849914,"threshold_uncertainty_score":0.7686752},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024372524,0.0028866008,0.9547202,0.0036602453,0.0003968775,0.0049467185,0.00033208064,0.00011607838,0.008568647],"genre_scores_gemma":[0.3354588,0.00088780065,0.6480709,0.001320369,0.00046758336,0.013247046,0.0002090498,0.000078034085,0.00026040338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.12471981,0.8027306,0.033856083,0.009515649,0.02831176,0.00086613744],"domain_scores_gemma":[0.037576318,0.900021,0.02775506,0.02232605,0.011664699,0.0006567942],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.68116885,0.0024347398,0.004864898,0.017361114,0.0032127635,0.011122899,0.0061296993,0.0050659287,0.0043995427],"category_scores_gemma":[0.8225554,0.0018358782,0.008371887,0.009918408,0.019957453,0.011018579,0.014576926,0.0070913574,0.0005920691],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028163472,0.0009451091,0.118485466,0.019304378,0.014776055,0.0009194945,0.056915108,0.03449877,0.0024229565,0.40539512,0.005881393,0.3376397],"study_design_scores_gemma":[0.0011818515,0.004381032,0.03438101,0.008003972,0.0038485897,0.0020702179,0.009937885,0.09443217,0.006446561,0.80863976,0.025617173,0.0010597308],"about_ca_topic_score_codex":0.0013561926,"about_ca_topic_score_gemma":0.0010682803,"teacher_disagreement_score":0.31883115,"about_ca_system_score_codex":0.00738526,"about_ca_system_score_gemma":0.012008532,"threshold_uncertainty_score":0.3931756},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14039405,0.0019137562,0.85443735,0.0012936051,0.000087333676,0.00013140518,0.00042854686,0.00019359069,0.0011203865],"genre_scores_gemma":[0.91822803,0.000566996,0.07966637,0.00022868848,0.00012747406,0.00023450253,0.00044825152,0.000037163572,0.00046251476],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98505396,0.010861997,0.0005831864,0.0017502533,0.0012975358,0.00045312147],"domain_scores_gemma":[0.7094734,0.2682718,0.011796931,0.006788441,0.0028031257,0.00086642266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052401714,0.0009418682,0.0016600112,0.0023426064,0.00050656276,0.001991612,0.0020859763,0.0017077846,0.0015797798],"category_scores_gemma":[0.20006986,0.00038738825,0.002162539,0.0015953652,0.002867479,0.0024086519,0.0021045613,0.0027600494,0.00015074812],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010660711,0.00021530103,0.21191011,0.0010152847,0.002555565,0.0009280029,0.0011394509,0.48917273,0.0016285233,0.1344635,0.0021677446,0.15373763],"study_design_scores_gemma":[0.000097000615,0.00046341948,0.029364856,0.0002662791,0.00065405807,0.0005317987,0.00023970638,0.762163,0.0015511555,0.20323479,0.001350627,0.00008324889],"about_ca_topic_score_codex":0.0023866212,"about_ca_topic_score_gemma":0.0011760113,"teacher_disagreement_score":0.052401714,"about_ca_system_score_codex":0.0013343939,"about_ca_system_score_gemma":0.0013234231,"threshold_uncertainty_score":0.27713},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041771005,0.77509654,0.08367506,0.08931992,0.030213222,0.0017095612,0.0014185025,0.0007862542,0.017363228],"genre_scores_gemma":[0.0036103374,0.75802404,0.12700109,0.061318908,0.030860158,0.0039956905,0.0013587516,0.000838518,0.012992473],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9627934,0.025364736,0.0056163357,0.0012752055,0.004391805,0.00055846706],"domain_scores_gemma":[0.8313366,0.14745997,0.0068090963,0.0022624256,0.009921406,0.0022105437],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034560576,0.0030074122,0.0036455418,0.010547473,0.0016290405,0.0072419215,0.003597101,0.006807386,0.027272018],"category_scores_gemma":[0.111500666,0.0021670463,0.003938633,0.011646434,0.0050593936,0.016212339,0.0051409644,0.015467902,0.021817043],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001232064,0.0001032799,0.00038549528,0.044794235,0.00029324752,0.0003151038,0.0031094784,0.0007447046,0.0014288248,0.0803248,0.58647,0.28190753],"study_design_scores_gemma":[0.000030389983,0.00006974718,0.00036568212,0.024723465,0.00006831561,0.0006185849,0.0003812596,0.00019312104,0.00016371957,0.04303369,0.9303,0.000052102838],"about_ca_topic_score_codex":0.0019229971,"about_ca_topic_score_gemma":0.0034904776,"teacher_disagreement_score":0.96543944,"about_ca_system_score_codex":0.0045801187,"about_ca_system_score_gemma":0.0069790767,"threshold_uncertainty_score":0.18277597},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7831784,0.0058629797,0.013221327,0.005008757,0.0023781578,0.18745655,0.0006277439,0.00036294924,0.001903194],"genre_scores_gemma":[0.78613514,0.0028995103,0.040132806,0.0022758832,0.0008368076,0.16662899,0.00029781958,0.00003917388,0.00075397594],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9157089,0.07301999,0.0063679856,0.0013770257,0.002194622,0.0013314415],"domain_scores_gemma":[0.9160118,0.06311698,0.007324041,0.004506302,0.00609262,0.0029482055],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07939917,0.0014242823,0.0029390613,0.0011047997,0.0011037871,0.0016370782,0.0017429464,0.0035890825,0.0023677724],"category_scores_gemma":[0.10457348,0.00084982975,0.0038972264,0.0010526096,0.0019868768,0.0026953444,0.0014997778,0.0030444318,0.0002442845],"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":[0.650763,0.097490035,0.011628772,0.014652484,0.008600788,0.00073948526,0.0041476144,0.002612696,0.002162934,0.0016237978,0.0039025221,0.20167598],"study_design_scores_gemma":[0.63442063,0.34466872,0.0075261383,0.0021023161,0.0037818835,0.00010801267,0.00084596867,0.002398109,0.00092709274,0.0008512342,0.0022946226,0.00007517709],"about_ca_topic_score_codex":0.0018922997,"about_ca_topic_score_gemma":0.0034328455,"teacher_disagreement_score":0.92060083,"about_ca_system_score_codex":0.0021001268,"about_ca_system_score_gemma":0.006325492,"threshold_uncertainty_score":0.41990793},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9474245,0.0010108394,0.04691928,0.0013606709,0.00017423439,0.0004040081,0.0015776895,0.00028312393,0.0008456224],"genre_scores_gemma":[0.98079383,0.0005619104,0.01402493,0.0001859789,0.00012926699,0.0004448529,0.002035352,0.000074688316,0.0017491532],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98723245,0.009200986,0.000492808,0.0017196344,0.0003838066,0.00097038597],"domain_scores_gemma":[0.9143995,0.075002015,0.0051965485,0.0023131657,0.0016075742,0.0014811179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026628507,0.0023530526,0.002472422,0.002751852,0.0012382752,0.0035838578,0.0047515,0.0024757853,0.0050540846],"category_scores_gemma":[0.046739306,0.0016161597,0.0062892046,0.0019502902,0.0011585458,0.0020922488,0.002141871,0.0038201914,0.0006607862],"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":[0.0031613857,0.0010661839,0.5099171,0.00032392502,0.0039216056,0.0009119763,0.0012463669,0.4495807,0.00029267423,0.006043527,0.0022545964,0.021280007],"study_design_scores_gemma":[0.00013783091,0.0005035381,0.019228566,0.000067042274,0.00041852088,0.00012668717,0.00048298304,0.97625256,0.00006856685,0.0022144334,0.0004489446,0.000050329327],"about_ca_topic_score_codex":0.04964102,"about_ca_topic_score_gemma":0.017966436,"teacher_disagreement_score":0.04964102,"about_ca_system_score_codex":0.0021036752,"about_ca_system_score_gemma":0.0029089125,"threshold_uncertainty_score":0.1408267},"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":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46572202,0.004023596,0.0029501829,0.0014024343,0.0006750421,0.5199785,0.0007239448,0.00013056408,0.0043936027],"genre_scores_gemma":[0.56855065,0.0019832132,0.0089216465,0.002293082,0.0004971276,0.41614252,0.00030245076,0.000013240297,0.0012960262],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9755519,0.019657467,0.0016768104,0.0010335672,0.0009593337,0.0011209076],"domain_scores_gemma":[0.98889834,0.0049549793,0.0028458533,0.0009364571,0.00074039836,0.001623893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027797036,0.0015539512,0.002334415,0.0016817845,0.0015973648,0.001670712,0.0014208264,0.003843714,0.011201921],"category_scores_gemma":[0.027672503,0.0011995004,0.002092401,0.0014226097,0.0020216203,0.0017807658,0.0020976837,0.0020699992,0.0009927904],"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":[0.7723809,0.047138464,0.022503816,0.017565124,0.00433382,0.0007390714,0.006347759,0.00094535516,0.003103827,0.0012820825,0.0040231007,0.11963677],"study_design_scores_gemma":[0.79977554,0.17448922,0.016558351,0.001914858,0.0014410208,0.00009969839,0.001035784,0.00043739923,0.00039429276,0.0007422141,0.0030676336,0.000044028755],"about_ca_topic_score_codex":0.0023026152,"about_ca_topic_score_gemma":0.003907625,"teacher_disagreement_score":0.027797036,"about_ca_system_score_codex":0.0011210872,"about_ca_system_score_gemma":0.0070838067,"threshold_uncertainty_score":0.14700651},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62250584,0.012453221,0.2860247,0.010620607,0.0016566033,0.019522903,0.016232504,0.020713005,0.010270669],"genre_scores_gemma":[0.54425097,0.0010831965,0.43426895,0.0013643303,0.000156471,0.01292136,0.004516799,0.00063016213,0.00080776185],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9099356,0.07355731,0.0072881975,0.003173283,0.005436096,0.00060956174],"domain_scores_gemma":[0.5905296,0.3686234,0.014850818,0.008731207,0.015657865,0.0016070369],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11474901,0.001973905,0.003544967,0.0033532558,0.0009791604,0.002782855,0.003971755,0.002751533,0.005666393],"category_scores_gemma":[0.31678915,0.0015512052,0.0049792943,0.0035223337,0.0010135063,0.0033907,0.003236054,0.0020674851,0.0008880291],"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":[0.054574106,0.00362994,0.05965325,0.03522679,0.016982866,0.0005823089,0.00286847,0.34864774,0.004701922,0.008025964,0.03592048,0.4291862],"study_design_scores_gemma":[0.021461321,0.011823862,0.0141224535,0.0026173848,0.006654441,0.00049779867,0.00032580076,0.9171052,0.00571781,0.007486343,0.011594743,0.00059284875],"about_ca_topic_score_codex":0.007864475,"about_ca_topic_score_gemma":0.008664678,"teacher_disagreement_score":0.885251,"about_ca_system_score_codex":0.0044626608,"about_ca_system_score_gemma":0.010287213,"threshold_uncertainty_score":0.606858},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7825397,0.006911119,0.07972446,0.09209275,0.00087491213,0.010885914,0.0019577984,0.00032002482,0.024693327],"genre_scores_gemma":[0.91924006,0.0045359144,0.041406423,0.017451735,0.00025940535,0.012447687,0.00035537666,0.0001815243,0.0041219345],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.745741,0.22982004,0.0062484294,0.0035427436,0.009135004,0.0055126785],"domain_scores_gemma":[0.6041551,0.36100262,0.010385094,0.0038577667,0.014558814,0.006040554],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15169062,0.0008162188,0.001349108,0.0036927795,0.011337204,0.007168773,0.0031280885,0.0045117927,0.004741463],"category_scores_gemma":[0.24158683,0.0014194422,0.0015263081,0.003920845,0.010850526,0.0074852803,0.009258058,0.006119042,0.00071090134],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012148177,0.000075839875,0.0016129322,0.0012570078,0.00002808678,0.00080960547,0.97229654,0.0001301446,0.0009706936,0.0030838503,0.002116201,0.017497564],"study_design_scores_gemma":[0.000092448536,0.0001917768,0.0016285528,0.0022941835,0.000033578668,0.0006155975,0.9477739,0.00062354194,0.00093701016,0.0032904574,0.042445913,0.00007305146],"about_ca_topic_score_codex":0.003990527,"about_ca_topic_score_gemma":0.005193045,"teacher_disagreement_score":0.8483094,"about_ca_system_score_codex":0.015145216,"about_ca_system_score_gemma":0.0184635,"threshold_uncertainty_score":0.80222625},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019941147,0.03008288,0.9209804,0.0025170743,0.0012817237,0.0060911374,0.0077255717,0.003173085,0.008207093],"genre_scores_gemma":[0.26124698,0.009173358,0.7080421,0.0015725333,0.00065541564,0.015147772,0.0026166756,0.00059446733,0.00095074956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8797155,0.102577694,0.0035178917,0.004136579,0.009434966,0.0006173748],"domain_scores_gemma":[0.5833848,0.37740403,0.015352279,0.012666022,0.010329825,0.0008630085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14294171,0.0040693744,0.006778423,0.010685649,0.00097215164,0.0047790785,0.0030659328,0.0034449399,0.010849875],"category_scores_gemma":[0.34274057,0.001646672,0.013343248,0.0057408107,0.002756575,0.0049261414,0.004172673,0.0048393733,0.0006616382],"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":[0.013347341,0.000589244,0.021676445,0.032125756,0.04277799,0.0006806653,0.00095245463,0.24667096,0.0028266588,0.16343911,0.03912066,0.43579268],"study_design_scores_gemma":[0.008313602,0.007866755,0.012280233,0.012214686,0.034869045,0.0015584324,0.00049983343,0.68152815,0.008076498,0.16838777,0.06357199,0.00083291274],"about_ca_topic_score_codex":0.002781327,"about_ca_topic_score_gemma":0.001869139,"teacher_disagreement_score":0.14294171,"about_ca_system_score_codex":0.0029844104,"about_ca_system_score_gemma":0.0047641764,"threshold_uncertainty_score":0.75595707},"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":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08093826,0.0015964278,0.91013926,0.0003464353,0.0001734863,0.00040250827,0.0006272726,0.0042248294,0.0015515976],"genre_scores_gemma":[0.2859722,0.0008581508,0.71,0.00013864237,0.00006815394,0.00047143415,0.0012640723,0.00056688266,0.0006604371],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9719524,0.018441066,0.0026178532,0.0021628423,0.004323633,0.0005022102],"domain_scores_gemma":[0.75448143,0.21030872,0.010174897,0.007306103,0.01652115,0.0012077988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047733203,0.0019963668,0.0016323809,0.0060263174,0.0004434078,0.0021406107,0.0027066062,0.0019073099,0.0033078275],"category_scores_gemma":[0.16174793,0.00058460166,0.0027276403,0.0029659872,0.0011155141,0.0033650144,0.0023469834,0.002183753,0.00081466354],"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":[0.0035315836,0.000683478,0.0792289,0.0025783,0.0014043677,0.0005239822,0.0016779237,0.18839182,0.0053331177,0.03723123,0.007835863,0.67157936],"study_design_scores_gemma":[0.00021142536,0.0009913887,0.014949401,0.00028785126,0.00027487922,0.000370545,0.00060462614,0.96538645,0.004366425,0.008473811,0.0038902694,0.00019300886],"about_ca_topic_score_codex":0.0045796405,"about_ca_topic_score_gemma":0.0036718792,"teacher_disagreement_score":0.047733203,"about_ca_system_score_codex":0.0013375131,"about_ca_system_score_gemma":0.0020522284,"threshold_uncertainty_score":0.25244033},"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":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006544081,0.09029396,0.09233331,0.011146156,0.0016343362,0.019678542,0.71339214,0.04741471,0.017562756],"genre_scores_gemma":[0.028207717,0.07213766,0.5589439,0.003691618,0.00096795685,0.069692895,0.25670645,0.005858404,0.0037934035],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9327421,0.023507228,0.033462767,0.0041878787,0.0052267173,0.00087338797],"domain_scores_gemma":[0.7148342,0.19326447,0.039582826,0.023048561,0.020125976,0.0091439355],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.055633478,0.0034516316,0.010069275,0.06713319,0.002159369,0.012742746,0.0050489344,0.003929824,0.04533228],"category_scores_gemma":[0.26590818,0.0038455913,0.0060806107,0.0635713,0.0022170616,0.011148445,0.013111982,0.004529328,0.013698604],"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":[0.0031470177,0.00018970692,0.004963742,0.4500668,0.009308535,0.0007770284,0.0028257477,0.001890764,0.004416619,0.043016635,0.28794783,0.19144951],"study_design_scores_gemma":[0.005460148,0.0006550353,0.015363114,0.15189342,0.017602209,0.0012663098,0.0011102358,0.0047034174,0.002280475,0.04212309,0.7566824,0.00086011225],"about_ca_topic_score_codex":0.003058731,"about_ca_topic_score_gemma":0.0063702613,"teacher_disagreement_score":0.99495107,"about_ca_system_score_codex":0.004127162,"about_ca_system_score_gemma":0.032914877,"threshold_uncertainty_score":0.2942214},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9735449,0.003225158,0.018632937,0.0006654205,0.00013190413,0.000054873504,0.00047299816,0.00014375013,0.0031280492],"genre_scores_gemma":[0.99392724,0.0010524571,0.0039192494,0.000028658693,0.000025210658,0.000027334116,0.00042154954,0.000008372815,0.0005898631],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995926,0.00015300146,0.00004700695,0.000084532665,0.00007810288,0.00004481817],"domain_scores_gemma":[0.99827635,0.0011744745,0.00015750686,0.00004528974,0.0002932737,0.00005313725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023689487,0.0007828671,0.00062140526,0.0011300176,0.0002646019,0.0009177969,0.00056467875,0.00066109764,0.00075337116],"category_scores_gemma":[0.004244444,0.00020426059,0.0007130342,0.00072490727,0.00017085372,0.0009505846,0.00037245677,0.0006717786,0.00012112063],"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":[0.00061144197,0.000382275,0.08590313,0.00039680203,0.00036989863,0.00026664455,0.00018100272,0.83163536,0.0007953698,0.001305664,0.001420376,0.076732025],"study_design_scores_gemma":[0.000007581252,0.00011189335,0.009583844,0.000051643397,0.000059653572,0.000014786207,0.000100323035,0.9892257,0.00026758114,0.0003629541,0.00020469977,0.000009317304],"about_ca_topic_score_codex":0.023690281,"about_ca_topic_score_gemma":0.013633341,"teacher_disagreement_score":0.023690281,"about_ca_system_score_codex":0.00069348747,"about_ca_system_score_gemma":0.0008036275,"threshold_uncertainty_score":0.047104776},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7098987,0.000536409,0.21723151,0.0018053424,0.00019145558,0.0052331616,0.041571554,0.0011581628,0.02237379],"genre_scores_gemma":[0.8590181,0.0002955772,0.108996406,0.0003390387,0.00008781201,0.004177179,0.025967732,0.000114520706,0.001003699],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97542745,0.014327438,0.0027162016,0.0015419039,0.0054670903,0.0005199186],"domain_scores_gemma":[0.9518189,0.008732143,0.017258238,0.010092615,0.011303763,0.00079438323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02495097,0.00043495625,0.0005422553,0.0037113198,0.00029555307,0.00097417936,0.0009010509,0.00035246633,0.0009525021],"category_scores_gemma":[0.062773496,0.00023926744,0.0010567235,0.005182165,0.00026920077,0.0008352423,0.0019435707,0.00072296936,0.00046423008],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015093305,0.00018159702,0.87185746,0.00013908079,0.00074701925,0.000022861032,0.00040832843,0.006754416,0.00027417013,0.0033834574,0.013209349,0.1028713],"study_design_scores_gemma":[0.00006616517,0.00032398652,0.956546,0.00013385362,0.00020094978,0.00007345318,0.0002555327,0.026662862,0.0010765576,0.002719652,0.011888357,0.000052613406],"about_ca_topic_score_codex":0.015199524,"about_ca_topic_score_gemma":0.017939541,"teacher_disagreement_score":0.02495097,"about_ca_system_score_codex":0.0014089207,"about_ca_system_score_gemma":0.002408213,"threshold_uncertainty_score":0.13195491},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018856843,0.0004991815,0.9961952,0.00041316065,0.00006110235,0.000040275794,0.00024785232,0.00027190868,0.00038574197],"genre_scores_gemma":[0.122020796,0.0019171675,0.8682027,0.0006996935,0.0005332898,0.0012834672,0.0018619867,0.0008467144,0.002634178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9827855,0.013165784,0.00064023095,0.0014668917,0.0016243749,0.00031720888],"domain_scores_gemma":[0.96506006,0.027179126,0.003473838,0.0022361036,0.0016743364,0.00037646387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020326132,0.0015909403,0.0022456998,0.0013985777,0.0007346674,0.001928005,0.0027371426,0.00236719,0.004888058],"category_scores_gemma":[0.044704985,0.00093520276,0.0026693882,0.0025952293,0.0018926781,0.0012003862,0.0019673964,0.005053389,0.0014705607],"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":[0.00048460718,0.00013568733,0.0074186027,0.0020683722,0.00096430257,0.00055587565,0.00043887668,0.5358558,0.0050565563,0.21273173,0.02825309,0.20603648],"study_design_scores_gemma":[0.000074980766,0.000093310795,0.0011296568,0.00019834652,0.00007748672,0.00020429096,0.000026954562,0.8791492,0.0011693403,0.10637418,0.011441213,0.00006104433],"about_ca_topic_score_codex":0.0027468724,"about_ca_topic_score_gemma":0.0023600557,"teacher_disagreement_score":0.020326132,"about_ca_system_score_codex":0.0011250087,"about_ca_system_score_gemma":0.0030394054,"threshold_uncertainty_score":0.1074962},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2524322,0.0044364696,0.7331725,0.0013372386,0.0003399122,0.0007234896,0.003992653,0.0009466471,0.002618959],"genre_scores_gemma":[0.6992312,0.0011930709,0.29548547,0.00037505268,0.00020889143,0.0003293034,0.0023735422,0.00010529124,0.0006982964],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9907725,0.00551769,0.00078410516,0.0015800986,0.0010462416,0.00029942053],"domain_scores_gemma":[0.9288263,0.05456201,0.005664841,0.0069857053,0.003318857,0.00064240914],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016006188,0.0007955942,0.0012510224,0.004499255,0.0005886186,0.00162735,0.0016426586,0.0010312643,0.001599497],"category_scores_gemma":[0.094009325,0.00065281463,0.001571859,0.0033479198,0.00094074034,0.0023453115,0.0025600025,0.0022534365,0.00043653575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008306018,0.00021753667,0.38807818,0.0012952558,0.0012867202,0.0009914355,0.0026929765,0.2624724,0.002452584,0.022846857,0.0062495074,0.31058595],"study_design_scores_gemma":[0.00016118892,0.00061643176,0.27133155,0.00090012315,0.00071223563,0.0011596994,0.0022118893,0.5893003,0.004240411,0.10490097,0.024121305,0.00034383754],"about_ca_topic_score_codex":0.020503497,"about_ca_topic_score_gemma":0.021709204,"teacher_disagreement_score":0.9839938,"about_ca_system_score_codex":0.001094273,"about_ca_system_score_gemma":0.0022168136,"threshold_uncertainty_score":0.0846498},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88389647,0.031160245,0.05699507,0.002128525,0.0011316538,0.0023442083,0.019504614,0.0007777883,0.0020614145],"genre_scores_gemma":[0.9809528,0.00070035027,0.006978824,0.000685435,0.00018061485,0.001329719,0.008413129,0.00020175385,0.00055733364],"study_design_codex":"observational","study_design_gemma":"meta_analysis","domain_scores_codex":[0.82139343,0.12677832,0.021719234,0.016853198,0.01055206,0.002703666],"domain_scores_gemma":[0.5197734,0.32885244,0.060708765,0.07866494,0.009907829,0.0020925773],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22285339,0.001827054,0.005600535,0.0030202083,0.00063606875,0.0032342812,0.003685513,0.0019618163,0.0026942883],"category_scores_gemma":[0.29486427,0.0009647066,0.018652728,0.0037083114,0.0015222288,0.0024970174,0.0021386275,0.0040324456,0.00043166117],"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":[0.0703097,0.0007128071,0.6085755,0.006691703,0.20636548,0.0011255689,0.0008996191,0.035702243,0.0025662968,0.002186188,0.0069717015,0.0578932],"study_design_scores_gemma":[0.009703072,0.009045927,0.7377395,0.001616619,0.12830836,0.0016548707,0.00061598973,0.06958408,0.005575208,0.006036524,0.0296092,0.00051067],"about_ca_topic_score_codex":0.0034619623,"about_ca_topic_score_gemma":0.003604908,"teacher_disagreement_score":0.22285339,"about_ca_system_score_codex":0.0025586148,"about_ca_system_score_gemma":0.0024798398,"threshold_uncertainty_score":0.95836014},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27267122,0.054599356,0.6045532,0.041967504,0.0027381703,0.0046045827,0.004991463,0.00073660456,0.0131378425],"genre_scores_gemma":[0.8790533,0.0031912234,0.108490035,0.0056941677,0.00032541412,0.0019564074,0.00071690243,0.00015645132,0.0004161108],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.60913754,0.3732555,0.0061063804,0.0066828346,0.003917862,0.0008998935],"domain_scores_gemma":[0.14848283,0.8196183,0.012167831,0.014933396,0.0040152622,0.00078232266],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38872704,0.0017181255,0.0060107564,0.001863471,0.0009144133,0.005067828,0.0038450833,0.0045226915,0.0033126478],"category_scores_gemma":[0.65502036,0.0014972385,0.013801918,0.002980629,0.0033326645,0.0077679274,0.002736898,0.0054726214,0.0004179151],"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":[0.01723442,0.00054695515,0.09487767,0.009661392,0.09607561,0.0010265404,0.0013248692,0.6430271,0.00060779316,0.04677595,0.008077959,0.08076369],"study_design_scores_gemma":[0.010370731,0.0028531493,0.01153821,0.0053410125,0.03831536,0.00071452203,0.00047427765,0.6960685,0.0014433103,0.21857889,0.013935924,0.00036609775],"about_ca_topic_score_codex":0.0055511384,"about_ca_topic_score_gemma":0.0046794256,"teacher_disagreement_score":0.61127293,"about_ca_system_score_codex":0.002740453,"about_ca_system_score_gemma":0.004534644,"threshold_uncertainty_score":0.7538084},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6115893,0.013646274,0.20265923,0.075411454,0.0011945759,0.056154117,0.0020603326,0.0019126767,0.03537196],"genre_scores_gemma":[0.53781474,0.0072070267,0.4338429,0.0039828755,0.00017992429,0.013552035,0.0006374801,0.0002652341,0.0025178178],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.80155957,0.16279183,0.012528877,0.002657892,0.016499702,0.003962119],"domain_scores_gemma":[0.45923716,0.44158137,0.016375903,0.011799469,0.06538952,0.0056164884],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21249844,0.0022255545,0.002160877,0.007964722,0.006330613,0.008644186,0.0030784283,0.003975686,0.006439737],"category_scores_gemma":[0.3467583,0.0014185363,0.00294055,0.007886315,0.002617818,0.011735351,0.0072323703,0.0038846796,0.0012711763],"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":[0.0014858097,0.00262079,0.025245488,0.0291116,0.00030502304,0.0007936044,0.121477455,0.0033458883,0.0028086486,0.009282544,0.009677869,0.7938453],"study_design_scores_gemma":[0.0039469013,0.00986699,0.113298886,0.09889546,0.0043387087,0.0023588836,0.50550103,0.038841236,0.018234473,0.060963225,0.14253664,0.001217593],"about_ca_topic_score_codex":0.008585072,"about_ca_topic_score_gemma":0.011784022,"teacher_disagreement_score":0.7875016,"about_ca_system_score_codex":0.0115915695,"about_ca_system_score_gemma":0.05359423,"threshold_uncertainty_score":0.9711296},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9901157,0.00040060197,0.0023583008,0.00037958336,0.00007042066,0.00094084744,0.00075138337,0.00003143025,0.004951777],"genre_scores_gemma":[0.996795,0.00016519835,0.0015300288,0.00014120854,0.000020571944,0.00073783577,0.0003720502,0.000007434681,0.00023077012],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9654787,0.022521837,0.0030910533,0.0019449329,0.0058794655,0.00108398],"domain_scores_gemma":[0.9344608,0.03210826,0.017060589,0.0051613003,0.010117399,0.0010917068],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.040036127,0.00053359877,0.0005277915,0.0024743986,0.0006497146,0.0017142375,0.0011322524,0.0007487622,0.0008875309],"category_scores_gemma":[0.098518245,0.00040205897,0.000963961,0.0017434292,0.0012251298,0.0013198433,0.0020849016,0.00063331885,0.00044001464],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102036094,0.000087900735,0.9835165,0.00015224081,0.00013408695,0.000030333793,0.0020208855,0.00023031718,0.00015029163,0.00009167869,0.00030944898,0.01317429],"study_design_scores_gemma":[0.000021631511,0.00048090864,0.99015474,0.00034232027,0.0000621304,0.00009127057,0.0042785304,0.0022648615,0.0005718665,0.000202498,0.0015104102,0.000018860375],"about_ca_topic_score_codex":0.0043019075,"about_ca_topic_score_gemma":0.004886957,"teacher_disagreement_score":0.95996386,"about_ca_system_score_codex":0.0011546683,"about_ca_system_score_gemma":0.0012735031,"threshold_uncertainty_score":0.21173382},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010050683,0.1767894,0.44635347,0.26287,0.028810093,0.051952593,0.003075446,0.0043816953,0.015716651],"genre_scores_gemma":[0.0474236,0.03332994,0.79907745,0.032034386,0.006441749,0.077044874,0.0012131607,0.0013982931,0.0020365163],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.070299916,0.6395045,0.2235316,0.01176532,0.052422218,0.002476416],"domain_scores_gemma":[0.014140649,0.82569283,0.060406957,0.03605788,0.06125083,0.002450928],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.85171396,0.0071217488,0.025283229,0.06681444,0.013775819,0.046033062,0.02409686,0.024425358,0.009864185],"category_scores_gemma":[0.95008343,0.014374456,0.019386007,0.05164988,0.0273719,0.05975838,0.03997699,0.022491215,0.004697019],"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":[0.002380409,0.00023698117,0.008087153,0.24129662,0.010635447,0.0025877343,0.13197143,0.003332688,0.00217554,0.046293695,0.08993683,0.46106553],"study_design_scores_gemma":[0.002276067,0.0006378949,0.0046604667,0.49760652,0.009831018,0.0026935993,0.03363206,0.005551588,0.0027195725,0.17413686,0.2647385,0.0015158955],"about_ca_topic_score_codex":0.008078497,"about_ca_topic_score_gemma":0.016831748,"teacher_disagreement_score":0.14828604,"about_ca_system_score_codex":0.036267083,"about_ca_system_score_gemma":0.10870826,"threshold_uncertainty_score":0.26313734},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007871726,0.115628995,0.08087794,0.7353936,0.008697548,0.01557988,0.0031614103,0.000728,0.03206095],"genre_scores_gemma":[0.14762218,0.13572036,0.44684383,0.20235114,0.0049620713,0.050279956,0.002104955,0.0005709896,0.00954457],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.76527905,0.17808983,0.021214155,0.006751251,0.022982981,0.005682679],"domain_scores_gemma":[0.2736878,0.62103,0.024324197,0.018834071,0.055756625,0.00636738],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23420404,0.0044805976,0.008514233,0.007431042,0.010760024,0.020175701,0.009390532,0.02595802,0.032493584],"category_scores_gemma":[0.47541273,0.0027750018,0.009928545,0.006208428,0.021309264,0.04509337,0.01237895,0.020857556,0.0067926114],"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":[0.0010257906,0.0011165913,0.014697402,0.0665743,0.0013289523,0.002147902,0.043054573,0.0037350846,0.0015844533,0.13750003,0.2425806,0.48465437],"study_design_scores_gemma":[0.0004824118,0.0008229923,0.009244583,0.15353023,0.0013466375,0.0009710346,0.0686625,0.0026540267,0.0019434635,0.42272368,0.33692217,0.0006963525],"about_ca_topic_score_codex":0.023822788,"about_ca_topic_score_gemma":0.05076148,"teacher_disagreement_score":0.76579595,"about_ca_system_score_codex":0.013516855,"about_ca_system_score_gemma":0.12924318,"threshold_uncertainty_score":0.94436276},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004323168,0.07110726,0.8895413,0.0022808344,0.0011189285,0.019974638,0.0077116634,0.001532827,0.0024093352],"genre_scores_gemma":[0.107286185,0.01258555,0.8207374,0.0014718897,0.0004234646,0.052664198,0.0040583187,0.00030066332,0.00047231157],"study_design_codex":"meta_analysis","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.646728,0.26237833,0.04826969,0.01923236,0.022472475,0.000919055],"domain_scores_gemma":[0.43465748,0.52333593,0.014779869,0.01427513,0.012294893,0.0006566675],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.25801766,0.0054450487,0.015549785,0.0402033,0.0010856402,0.006792984,0.006548509,0.004810168,0.0090876],"category_scores_gemma":[0.51599145,0.0022472013,0.034020983,0.019968927,0.0021648451,0.0052942354,0.0055260905,0.0052055935,0.0012630286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027698402,0.00025965134,0.011339096,0.22399385,0.3353253,0.001156582,0.0013839543,0.05810834,0.0015493302,0.039490517,0.014135279,0.31048828],"study_design_scores_gemma":[0.011017333,0.001944074,0.0133438995,0.046191018,0.26425895,0.002061107,0.00063175126,0.23520361,0.0037018775,0.3483033,0.07217257,0.0011705905],"about_ca_topic_score_codex":0.00595485,"about_ca_topic_score_gemma":0.006052041,"teacher_disagreement_score":0.25801766,"about_ca_system_score_codex":0.0053042546,"about_ca_system_score_gemma":0.011299079,"threshold_uncertainty_score":0.9149963},"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":"commentary","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019421346,0.21742363,0.297515,0.31292453,0.026977398,0.09137475,0.019083612,0.010089724,0.022669222],"genre_scores_gemma":[0.011612211,0.07160186,0.76971436,0.027885433,0.005074623,0.10230169,0.006153199,0.0023521613,0.003304513],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.16899574,0.6065381,0.13899465,0.0152520435,0.0666137,0.0036058694],"domain_scores_gemma":[0.047047604,0.58114374,0.088959314,0.06830357,0.20285639,0.011689307],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.68902737,0.005720792,0.014685925,0.057815544,0.004877544,0.039893944,0.016061572,0.014464653,0.025085764],"category_scores_gemma":[0.84470826,0.0063028443,0.016775915,0.053475693,0.00690772,0.026973061,0.025865013,0.019505167,0.020565506],"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":[0.0005004986,0.00017911401,0.0021517875,0.20712295,0.0048359428,0.00039706132,0.005808981,0.0017021543,0.00086191535,0.020603132,0.2646272,0.49120936],"study_design_scores_gemma":[0.0012620756,0.0003298053,0.0027432176,0.34353095,0.002900412,0.00051789056,0.0024024965,0.0036432093,0.0009306441,0.035048097,0.60591483,0.0007763486],"about_ca_topic_score_codex":0.010346607,"about_ca_topic_score_gemma":0.019614842,"teacher_disagreement_score":0.31097263,"about_ca_system_score_codex":0.026040029,"about_ca_system_score_gemma":0.20330669,"threshold_uncertainty_score":0.38348466},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30635124,0.00533267,0.67861384,0.0022142937,0.00031404407,0.00027279442,0.0017839941,0.0030824714,0.0020345445],"genre_scores_gemma":[0.82810545,0.000977038,0.16773708,0.0004334621,0.00022929115,0.00024624605,0.0014436897,0.00010423999,0.00072343927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985268,0.0008967759,0.00007349877,0.0002609712,0.00015186949,0.000090029054],"domain_scores_gemma":[0.9945874,0.0037275103,0.0005185797,0.00026485597,0.0006910457,0.00021060914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005931179,0.0010154839,0.0012503106,0.0019304575,0.000447572,0.0010754152,0.001181512,0.0010166977,0.0012388622],"category_scores_gemma":[0.013906401,0.0006516526,0.0014569806,0.0012410153,0.00030967552,0.00075498206,0.0007776854,0.001632321,0.0007837218],"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":[0.0010740797,0.00046330527,0.100521974,0.0004428515,0.0009014642,0.00034562638,0.00020831209,0.68330574,0.0027811686,0.0021155411,0.007470957,0.20036902],"study_design_scores_gemma":[0.000032180338,0.00007314031,0.0048961365,0.00005788154,0.0000673145,0.00004171811,0.000014267837,0.9910978,0.00035548903,0.0028887498,0.00046305233,0.000012355759],"about_ca_topic_score_codex":0.0077944775,"about_ca_topic_score_gemma":0.009986893,"teacher_disagreement_score":0.0077944775,"about_ca_system_score_codex":0.0007143659,"about_ca_system_score_gemma":0.0012218108,"threshold_uncertainty_score":0.03136748},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03894208,0.26997352,0.6645258,0.005374493,0.00177655,0.006290403,0.0066106287,0.0009018986,0.005604616],"genre_scores_gemma":[0.57416,0.047885012,0.35857415,0.0021486771,0.0009271602,0.011183416,0.003233485,0.0006112541,0.0012768146],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.6157467,0.3609411,0.01055045,0.0068879137,0.0054204385,0.00045339626],"domain_scores_gemma":[0.45118234,0.510964,0.011724955,0.020278476,0.005339809,0.00051049463],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21582223,0.003761384,0.0064943493,0.0075524463,0.00058503344,0.005693204,0.003434389,0.0021071695,0.0051502744],"category_scores_gemma":[0.4535898,0.0014530122,0.03195939,0.0073926393,0.0010500272,0.0049231695,0.0037700438,0.0036410326,0.0004265208],"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":[0.006425498,0.00016181816,0.024305616,0.055169784,0.7187874,0.00020190576,0.00053513143,0.04871043,0.000432686,0.011671313,0.003571068,0.13002746],"study_design_scores_gemma":[0.0044729244,0.0029240192,0.017802319,0.021249918,0.730906,0.00046923992,0.00039353844,0.121474944,0.0018464798,0.075939916,0.022085091,0.00043568615],"about_ca_topic_score_codex":0.005125912,"about_ca_topic_score_gemma":0.0075561213,"teacher_disagreement_score":0.7841778,"about_ca_system_score_codex":0.0029389705,"about_ca_system_score_gemma":0.0033619602,"threshold_uncertainty_score":0.96703076},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2039296,0.6767402,0.06053619,0.007675882,0.0014666872,0.0063917274,0.03565189,0.000590585,0.007017211],"genre_scores_gemma":[0.90298367,0.043190937,0.030507768,0.0030289285,0.00047259603,0.0095457425,0.009540982,0.00028818304,0.00044122225],"study_design_codex":"meta_analysis","study_design_gemma":"observational","domain_scores_codex":[0.5783588,0.22958192,0.13237986,0.02770783,0.02922194,0.002749572],"domain_scores_gemma":[0.156736,0.73425925,0.07772528,0.017930072,0.012380016,0.00096932],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26367208,0.0024790778,0.008972449,0.031977687,0.002110937,0.0069330516,0.004902283,0.0035867335,0.0044913283],"category_scores_gemma":[0.633985,0.0024328516,0.022125589,0.029616624,0.0035808317,0.007055275,0.0072305766,0.0029784671,0.00038562383],"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":[0.0046142736,0.00017193535,0.31135303,0.18989365,0.3993447,0.00105759,0.0032332053,0.005223972,0.00053349236,0.005406803,0.0052692336,0.07389804],"study_design_scores_gemma":[0.002070148,0.000833292,0.21701258,0.10438137,0.6018902,0.002629907,0.0023272526,0.0097973235,0.002263192,0.02864006,0.027619163,0.00053557294],"about_ca_topic_score_codex":0.004764565,"about_ca_topic_score_gemma":0.006448967,"teacher_disagreement_score":0.99102753,"about_ca_system_score_codex":0.0046844766,"about_ca_system_score_gemma":0.005842819,"threshold_uncertainty_score":0.9080234},"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":"protocol","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015826654,0.26521567,0.14956099,0.14575972,0.022071823,0.37848413,0.012266154,0.0014082049,0.009406629],"genre_scores_gemma":[0.060038246,0.03631698,0.434013,0.043687157,0.0017112537,0.4197311,0.0030705004,0.00040447354,0.0010272003],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.1207546,0.56029844,0.27739128,0.0094876755,0.029904408,0.0021637157],"domain_scores_gemma":[0.069395706,0.6511069,0.09775153,0.07934802,0.099211656,0.0031861924],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.74621403,0.003835558,0.017135493,0.026682684,0.0079546245,0.022844622,0.011853753,0.016415754,0.009287131],"category_scores_gemma":[0.8706106,0.0071334722,0.025468402,0.03545655,0.009142127,0.034690965,0.01049833,0.010444712,0.0037008827],"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":[0.002727486,0.00084484386,0.022781726,0.6556892,0.02281119,0.0009838849,0.02625628,0.0016743806,0.0016064215,0.025669461,0.058349896,0.18060528],"study_design_scores_gemma":[0.0033977805,0.0009865114,0.01186382,0.8142206,0.017177764,0.00054385595,0.0092696445,0.0020553055,0.0009091489,0.029658709,0.109346524,0.0005703672],"about_ca_topic_score_codex":0.009288009,"about_ca_topic_score_gemma":0.019448921,"teacher_disagreement_score":0.25378597,"about_ca_system_score_codex":0.02124633,"about_ca_system_score_gemma":0.07541076,"threshold_uncertainty_score":0.3129633},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005205795,0.83626986,0.09152537,0.015240435,0.01230178,0.03139134,0.001905944,0.0006992945,0.00546016],"genre_scores_gemma":[0.31535378,0.22263241,0.2343766,0.045495182,0.00698681,0.17001697,0.0021773481,0.0009177146,0.0020431816],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.19128661,0.64101297,0.104188256,0.018306961,0.044084553,0.001120648],"domain_scores_gemma":[0.115544796,0.78016716,0.067465104,0.020331915,0.015809212,0.0006817823],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5223192,0.0046756202,0.023567177,0.016387684,0.002156804,0.013773733,0.0067455485,0.011078093,0.0061831544],"category_scores_gemma":[0.76080227,0.0039999494,0.032575693,0.017507933,0.009742377,0.015120755,0.0038230598,0.011639997,0.0014294983],"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":[0.0029383693,0.00013537597,0.0035673096,0.7288258,0.15840484,0.0002372103,0.0014762521,0.0017460717,0.00036695905,0.014833136,0.01005706,0.07741161],"study_design_scores_gemma":[0.012772388,0.0021590418,0.008099737,0.5683856,0.2674477,0.00070135214,0.0008084815,0.008911758,0.002300955,0.08492839,0.0426979,0.0007866504],"about_ca_topic_score_codex":0.0023833264,"about_ca_topic_score_gemma":0.0039338395,"teacher_disagreement_score":0.4776808,"about_ca_system_score_codex":0.012610329,"about_ca_system_score_gemma":0.015929494,"threshold_uncertainty_score":0.58906555},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08441767,0.0015053792,0.8874733,0.013428295,0.00023508891,0.00041408432,0.0025005676,0.0006084997,0.009417158],"genre_scores_gemma":[0.5641711,0.0012677624,0.42447075,0.0013583502,0.00030488934,0.0013482313,0.002394538,0.00019868971,0.0044858055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98420054,0.012406435,0.00052748795,0.0012384518,0.0012163427,0.0004107669],"domain_scores_gemma":[0.9259873,0.06151116,0.0038229062,0.005086913,0.0029529692,0.0006388141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031390127,0.000843569,0.0009150107,0.0026171308,0.0014519494,0.0021716766,0.0022680925,0.002765312,0.0025850786],"category_scores_gemma":[0.05942504,0.0005853695,0.0024868464,0.0061178734,0.002481395,0.0021754515,0.0037594922,0.004281133,0.0005686485],"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":[0.00046290868,0.00034224437,0.14186518,0.0005068399,0.0007283215,0.0034761073,0.007197797,0.17368309,0.00082377484,0.5518969,0.016220694,0.10279618],"study_design_scores_gemma":[0.000101706064,0.00014463413,0.02364698,0.00018860663,0.0001606155,0.0013426834,0.0012975768,0.6470433,0.00056977256,0.29807556,0.027271215,0.00015744193],"about_ca_topic_score_codex":0.028431574,"about_ca_topic_score_gemma":0.026298985,"teacher_disagreement_score":0.031390127,"about_ca_system_score_codex":0.002816,"about_ca_system_score_gemma":0.0030638638,"threshold_uncertainty_score":0.16600889},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21394831,0.11725806,0.60480934,0.0028647932,0.002728323,0.03495205,0.01432646,0.001238736,0.007873867],"genre_scores_gemma":[0.52760035,0.017337848,0.39236504,0.0007211059,0.00065365795,0.052967306,0.006966024,0.00043892616,0.0009497515],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.45231467,0.43390167,0.05883449,0.0121757835,0.041425657,0.0013476853],"domain_scores_gemma":[0.08555351,0.84980845,0.03284982,0.017138712,0.014015133,0.00063436426],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41353762,0.0023176915,0.005579103,0.019244405,0.0013111676,0.0056012254,0.004660057,0.00330479,0.0084797],"category_scores_gemma":[0.75597125,0.0012943094,0.020249743,0.022053706,0.0031251025,0.0052555744,0.0044108084,0.002963818,0.00072904985],"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":[0.028094018,0.0011534288,0.10998471,0.14648657,0.16115409,0.00089526107,0.009233447,0.035330936,0.0013702778,0.0242101,0.01019472,0.4718926],"study_design_scores_gemma":[0.015650189,0.03207581,0.2910154,0.09145404,0.18882276,0.0032690444,0.012324334,0.16308704,0.010045114,0.099474534,0.09079058,0.0019912587],"about_ca_topic_score_codex":0.0013490475,"about_ca_topic_score_gemma":0.0010792825,"teacher_disagreement_score":0.5864624,"about_ca_system_score_codex":0.0037056047,"about_ca_system_score_gemma":0.004161552,"threshold_uncertainty_score":0.72321254},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5770056,0.0035107634,0.40739325,0.0025087807,0.00033713554,0.0006010059,0.005400955,0.0014978572,0.0017445831],"genre_scores_gemma":[0.91983193,0.0005036358,0.07524698,0.00029902792,0.00014716065,0.00035861676,0.002837194,0.00007992902,0.0006955373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720734,0.002005166,0.000105930674,0.00036799168,0.0001228625,0.00019063248],"domain_scores_gemma":[0.98644,0.011363987,0.0010014911,0.0002624998,0.000688385,0.00024352671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012436558,0.0011241827,0.001225421,0.0011756888,0.00044063103,0.0009452975,0.0013153809,0.00072401215,0.0011845462],"category_scores_gemma":[0.020997994,0.00048557334,0.0016466986,0.0008891764,0.00037482328,0.0006186984,0.0006370914,0.0011631165,0.00037367397],"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":[0.0008458798,0.00027372222,0.105612345,0.0003261602,0.0010299493,0.0002921234,0.00028652663,0.81272304,0.00025297332,0.0024817302,0.0056816717,0.07019385],"study_design_scores_gemma":[0.00011122182,0.00013314367,0.0074102753,0.00011163148,0.00014060896,0.000054091786,0.00010107517,0.983984,0.00014792026,0.0067979954,0.0009777152,0.000030466235],"about_ca_topic_score_codex":0.0659258,"about_ca_topic_score_gemma":0.05971926,"teacher_disagreement_score":0.0659258,"about_ca_system_score_codex":0.0014599458,"about_ca_system_score_gemma":0.0019376405,"threshold_uncertainty_score":0.13108414},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98936963,0.00011204771,0.0076894644,0.000092556824,0.000018784916,0.0007369235,0.0012470261,0.000032503547,0.0007010453],"genre_scores_gemma":[0.9912509,0.000050272287,0.00634189,0.000059219416,0.000012016625,0.0005920702,0.0015067691,0.00000944102,0.00017750694],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961708,0.0017013622,0.00031398662,0.0007597357,0.000829337,0.00022471372],"domain_scores_gemma":[0.992875,0.0021895252,0.0018903944,0.0012319714,0.0015153154,0.0002976703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074544908,0.00047309723,0.00042020532,0.0020490852,0.00091003266,0.0011730945,0.00090598455,0.00051349105,0.00085338723],"category_scores_gemma":[0.022867471,0.00049659726,0.0008992245,0.0019560661,0.0003616678,0.00083049084,0.00087135937,0.00088881084,0.0003429547],"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":[0.00015066247,0.00029907082,0.9929979,0.00002182808,0.00010514164,0.00010991923,0.0004165716,0.000410393,0.00014840999,0.00021115654,0.0004831926,0.0046457676],"study_design_scores_gemma":[0.00020789028,0.0009909702,0.9705414,0.00005243702,0.00018644016,0.00070643774,0.0012979123,0.022904884,0.00025016998,0.00062557735,0.0021875917,0.00004816161],"about_ca_topic_score_codex":0.046573997,"about_ca_topic_score_gemma":0.047103494,"teacher_disagreement_score":0.046573997,"about_ca_system_score_codex":0.0027647114,"about_ca_system_score_gemma":0.0024506792,"threshold_uncertainty_score":0.09260583},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004433637,0.91720086,0.033840455,0.0055799256,0.0016015994,0.031113105,0.0044522784,0.0003811013,0.0013969778],"genre_scores_gemma":[0.13652094,0.47405216,0.20452604,0.0060405685,0.0010557381,0.17288554,0.004112321,0.0002819044,0.0005248342],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.34724346,0.33218178,0.25087005,0.012892027,0.054911442,0.0019012268],"domain_scores_gemma":[0.18967077,0.5961386,0.13215443,0.022814045,0.057496283,0.0017258797],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41302642,0.0046065277,0.019734325,0.050911736,0.0037025532,0.011622723,0.006342082,0.0045710495,0.004971186],"category_scores_gemma":[0.68367755,0.0040730364,0.024514625,0.039071586,0.0057337983,0.011182875,0.0076477774,0.0038185187,0.0008231445],"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":[0.00025189706,0.000030421448,0.0035316618,0.9291484,0.020859035,0.00011569315,0.0014131505,0.0004552136,0.0003314884,0.0012761584,0.0024081764,0.04017867],"study_design_scores_gemma":[0.0007505449,0.0002932533,0.0060378183,0.9068561,0.05937254,0.0003360983,0.0012296943,0.0009866821,0.0008052071,0.003983615,0.019103287,0.00024503682],"about_ca_topic_score_codex":0.0071916766,"about_ca_topic_score_gemma":0.015380093,"teacher_disagreement_score":0.58697355,"about_ca_system_score_codex":0.016842198,"about_ca_system_score_gemma":0.047394745,"threshold_uncertainty_score":0.723843},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16923602,0.020214079,0.628792,0.011389599,0.0011648164,0.13200322,0.009523176,0.020069601,0.007607541],"genre_scores_gemma":[0.1269009,0.0017590959,0.7993327,0.0016529671,0.00022318769,0.067024864,0.001394457,0.0012603047,0.00045153312],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.21147178,0.6162013,0.12008486,0.0149731655,0.035291366,0.0019775396],"domain_scores_gemma":[0.028076893,0.85752684,0.044207506,0.042836107,0.026015319,0.0013373285],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6903608,0.003311963,0.00580234,0.01659216,0.0026372317,0.009844128,0.0068952716,0.003339117,0.00619272],"category_scores_gemma":[0.85635346,0.004204028,0.010243984,0.01756941,0.0044523156,0.013670324,0.010936327,0.0037200525,0.0029628007],"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":[0.025702577,0.0028395492,0.029003544,0.073272064,0.010556904,0.0006827636,0.01195366,0.00894989,0.004745766,0.006049152,0.02332508,0.8029191],"study_design_scores_gemma":[0.10476429,0.047519144,0.13784613,0.093919836,0.051759634,0.0063290717,0.0099691115,0.22222067,0.066719614,0.047335893,0.20690444,0.004712268],"about_ca_topic_score_codex":0.0019635109,"about_ca_topic_score_gemma":0.002794197,"teacher_disagreement_score":0.30963922,"about_ca_system_score_codex":0.011464294,"about_ca_system_score_gemma":0.030437902,"threshold_uncertainty_score":0.38184035},"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":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8575697,0.11832463,0.0045544156,0.0042364104,0.0007308329,0.0019154006,0.0053809932,0.00015280001,0.0071347277],"genre_scores_gemma":[0.9874956,0.0067304554,0.0017693248,0.00047294842,0.0006561259,0.0009680884,0.0013370195,0.000058693153,0.0005116875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7657202,0.08944447,0.08713796,0.0109767625,0.044195432,0.0025251803],"domain_scores_gemma":[0.20505741,0.46618688,0.27867764,0.025231557,0.021647645,0.003198741],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.124916404,0.001194602,0.0037419046,0.038817614,0.001346086,0.00669444,0.0022696522,0.0026288868,0.0061309724],"category_scores_gemma":[0.52272624,0.0007832122,0.00730784,0.03252731,0.0029051627,0.006947222,0.006291881,0.0016886524,0.00073467754],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008282942,0.0005211217,0.8568399,0.023729147,0.032056067,0.000766125,0.005253182,0.0003620879,0.0007288898,0.0011539516,0.0019860894,0.06832044],"study_design_scores_gemma":[0.0010586872,0.002512703,0.939234,0.007708911,0.028911348,0.0033373109,0.0040679392,0.0011886092,0.0016240333,0.0035705403,0.0065442184,0.00024161594],"about_ca_topic_score_codex":0.0009799411,"about_ca_topic_score_gemma":0.0010926089,"teacher_disagreement_score":0.96118236,"about_ca_system_score_codex":0.0021561862,"about_ca_system_score_gemma":0.0025701295,"threshold_uncertainty_score":0.660629},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017082553,0.79737276,0.15041997,0.018169275,0.0044434955,0.0037286484,0.004441358,0.0012136851,0.003128133],"genre_scores_gemma":[0.53211963,0.19849865,0.22017725,0.029883811,0.00394677,0.009449385,0.0034133035,0.0014800262,0.0010310818],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.5259068,0.32465497,0.10343773,0.020118345,0.024544293,0.0013378303],"domain_scores_gemma":[0.17962602,0.7062419,0.0552487,0.04522016,0.012900437,0.00076272106],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41042277,0.0045531993,0.014045054,0.015028654,0.0019158316,0.008953203,0.0068605314,0.005818086,0.003926432],"category_scores_gemma":[0.70819384,0.0049152193,0.04467906,0.018685846,0.003777606,0.008994524,0.004863788,0.006255379,0.0010070292],"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":[0.002357275,0.00007962436,0.050217886,0.14853732,0.6908966,0.0010777724,0.0012165403,0.004095478,0.0006389419,0.005657465,0.011523817,0.08370131],"study_design_scores_gemma":[0.0021687704,0.0006679197,0.032823507,0.09263853,0.79011714,0.00210897,0.00072710967,0.0070230113,0.0019016458,0.035864595,0.033500303,0.000458515],"about_ca_topic_score_codex":0.0037233778,"about_ca_topic_score_gemma":0.007322231,"teacher_disagreement_score":0.9954468,"about_ca_system_score_codex":0.004207465,"about_ca_system_score_gemma":0.0058576553,"threshold_uncertainty_score":0.7270537},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15359421,0.081815235,0.7480682,0.003955765,0.0006164309,0.005435426,0.0028296446,0.0012278972,0.0024571286],"genre_scores_gemma":[0.69020045,0.007882346,0.29594103,0.00079074106,0.00022646903,0.003555206,0.0010188225,0.0001791034,0.00020584087],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.71916074,0.2638281,0.008127286,0.004228431,0.0041672303,0.00048826885],"domain_scores_gemma":[0.39534432,0.5690005,0.016359948,0.013380076,0.0050519556,0.00086316327],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2956173,0.003026921,0.0052956846,0.0072244518,0.0008041637,0.0036243242,0.0031262033,0.003012422,0.002303062],"category_scores_gemma":[0.40889233,0.0014802458,0.019546038,0.006941517,0.0011544786,0.0030114055,0.003368637,0.0027701792,0.00019546323],"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":[0.009834159,0.00033708685,0.06883846,0.011634544,0.3053182,0.0002924455,0.0005238409,0.47442466,0.0005586608,0.009182461,0.0021153756,0.11694014],"study_design_scores_gemma":[0.0054520657,0.0040388196,0.017903302,0.002824263,0.1330357,0.0004540709,0.00019778595,0.7859434,0.0019728362,0.04280564,0.0050187116,0.00035348546],"about_ca_topic_score_codex":0.0031401732,"about_ca_topic_score_gemma":0.0020538121,"teacher_disagreement_score":0.70438266,"about_ca_system_score_codex":0.0030273614,"about_ca_system_score_gemma":0.004067902,"threshold_uncertainty_score":0.8686293},"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":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082566656,0.023121428,0.8556878,0.0124715725,0.0020647026,0.014488354,0.0016828885,0.0012044302,0.0067120926],"genre_scores_gemma":[0.6986629,0.0036314342,0.27280146,0.004353289,0.00037069796,0.018294223,0.0006937395,0.00012751589,0.001064817],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.4468987,0.53315467,0.009797512,0.004693139,0.0043343673,0.00112158],"domain_scores_gemma":[0.13627443,0.8281072,0.017856859,0.010539105,0.0061021084,0.001120291],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.40546694,0.0027172654,0.0076515526,0.0037703323,0.00088842947,0.0051359576,0.0034769813,0.0059818528,0.007103582],"category_scores_gemma":[0.6627085,0.0018287053,0.013786783,0.002921956,0.0036700966,0.00537564,0.0033811566,0.00595734,0.0006080846],"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":[0.024438292,0.0013073821,0.034872413,0.015137472,0.037355058,0.0010755464,0.0012249417,0.7083104,0.00071711524,0.081789,0.008336588,0.08543581],"study_design_scores_gemma":[0.009868246,0.004546405,0.0030892254,0.0041647493,0.008368537,0.00037966733,0.00026135545,0.8715594,0.00054542394,0.09149822,0.0055521987,0.0001666052],"about_ca_topic_score_codex":0.0041317386,"about_ca_topic_score_gemma":0.0022591336,"teacher_disagreement_score":0.5945331,"about_ca_system_score_codex":0.0047274176,"about_ca_system_score_gemma":0.0058826166,"threshold_uncertainty_score":0.73316514},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9699267,0.016865361,0.007203546,0.00078830373,0.00014833048,0.0017465048,0.0020243616,0.0000738174,0.0012231186],"genre_scores_gemma":[0.98664725,0.0019918836,0.006738797,0.000321651,0.00011725812,0.0030231085,0.0009033744,0.00004611128,0.00021049572],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.75520235,0.10769379,0.08759628,0.012875209,0.034521867,0.0021104943],"domain_scores_gemma":[0.24474251,0.573856,0.13730615,0.017674932,0.02265648,0.003763938],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19293359,0.0007254664,0.0027544864,0.011181816,0.0014624601,0.00384378,0.0020462195,0.0019630212,0.0022923583],"category_scores_gemma":[0.44966462,0.0014418365,0.0061075776,0.014783289,0.0020143758,0.0059103156,0.0036378286,0.0016418892,0.00055715285],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097510533,0.00020764182,0.9745129,0.0042750817,0.0063063353,0.00010127754,0.0034733838,0.000194155,0.00026541538,0.00021740346,0.00052049477,0.008950933],"study_design_scores_gemma":[0.00031117848,0.0032732259,0.97851425,0.0023822812,0.006946583,0.00081542647,0.0033664776,0.0012278684,0.0004975184,0.0006939422,0.0018692284,0.00010201967],"about_ca_topic_score_codex":0.0012717708,"about_ca_topic_score_gemma":0.0018828624,"teacher_disagreement_score":0.80706644,"about_ca_system_score_codex":0.0018283118,"about_ca_system_score_gemma":0.003651626,"threshold_uncertainty_score":0.99525654},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03074076,0.0033440054,0.9380554,0.011040561,0.0012547808,0.009317206,0.0010221368,0.0004212122,0.0048039583],"genre_scores_gemma":[0.28620926,0.0011700134,0.67948365,0.008766887,0.0005603468,0.02219319,0.0005191883,0.00018752304,0.0009100284],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.27370086,0.66556007,0.02414305,0.009165214,0.025902743,0.001527994],"domain_scores_gemma":[0.28362802,0.5874827,0.03619486,0.059714474,0.031056585,0.001923423],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.57477593,0.0016090279,0.0023978837,0.0035881978,0.0021080321,0.0054652896,0.004855122,0.0029728413,0.0023466216],"category_scores_gemma":[0.6809764,0.0015012503,0.0034340187,0.004881566,0.0051879208,0.003826417,0.004801595,0.0039560576,0.0005786689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041995985,0.000527709,0.25633168,0.0074717086,0.006719156,0.00092857087,0.01736218,0.037604656,0.0026098515,0.12840414,0.03409441,0.5037463],"study_design_scores_gemma":[0.0024961026,0.0065365783,0.24110717,0.015701191,0.004296466,0.002917516,0.007150721,0.17113942,0.012784083,0.35200864,0.18310261,0.00075955037],"about_ca_topic_score_codex":0.0065455073,"about_ca_topic_score_gemma":0.008187802,"teacher_disagreement_score":0.42522407,"about_ca_system_score_codex":0.004975315,"about_ca_system_score_gemma":0.009065929,"threshold_uncertainty_score":0.524377},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28241324,0.008640558,0.6967626,0.0032911238,0.00042849334,0.00078091654,0.0012984282,0.0012743189,0.005110362],"genre_scores_gemma":[0.8177552,0.003549103,0.17242673,0.0006039551,0.00028847248,0.0009993088,0.0015515267,0.00034390806,0.0024818107],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9829266,0.01398996,0.00061539153,0.0012855288,0.00083897176,0.00034354418],"domain_scores_gemma":[0.8429002,0.14683217,0.0031664872,0.0019695265,0.0045285523,0.0006030304],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.042774376,0.0028215728,0.0023147287,0.004400395,0.0006526147,0.0024276657,0.0036498602,0.0020796817,0.0027058509],"category_scores_gemma":[0.080362126,0.0008985136,0.003985918,0.0025912665,0.00067586184,0.002816719,0.001911762,0.003247698,0.0009626536],"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":[0.00092422304,0.00037746236,0.03055335,0.00039393912,0.0016923136,0.00014696906,0.00031764215,0.8606077,0.0002132032,0.011288774,0.0021331385,0.09135132],"study_design_scores_gemma":[0.000036191814,0.00014717887,0.0013312848,0.000057617668,0.00010945597,0.00002264817,0.00008555788,0.9933241,0.00008208865,0.0044454453,0.00033734896,0.00002111702],"about_ca_topic_score_codex":0.017429978,"about_ca_topic_score_gemma":0.008281477,"teacher_disagreement_score":0.9572256,"about_ca_system_score_codex":0.002368854,"about_ca_system_score_gemma":0.002192053,"threshold_uncertainty_score":0.22621524},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20681065,0.0059733354,0.7689265,0.0021836064,0.00051449286,0.0075548384,0.0020985221,0.0007204005,0.005217668],"genre_scores_gemma":[0.55370134,0.0023468495,0.43167305,0.00046212188,0.000109562716,0.00995322,0.0010691264,0.00016130776,0.00052346167],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.78453225,0.20118406,0.0049114972,0.002681979,0.0058272127,0.00086301705],"domain_scores_gemma":[0.26944095,0.683264,0.017075783,0.010317292,0.018602585,0.0012993922],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22391586,0.0015263095,0.0025243089,0.0031667314,0.0009305377,0.002520561,0.0029937795,0.0028727138,0.0039443537],"category_scores_gemma":[0.40516636,0.00088120304,0.0043462864,0.0043293987,0.0013181368,0.0024245419,0.0022073707,0.0033490832,0.00038830607],"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":[0.005753479,0.0013635898,0.07311286,0.005097139,0.006429484,0.00087155704,0.0015738596,0.7335207,0.0010635884,0.041340046,0.005845805,0.12402788],"study_design_scores_gemma":[0.0011553754,0.0033467847,0.009456278,0.0019141375,0.001080683,0.00033976737,0.00048113338,0.9617132,0.0010942338,0.014559956,0.0046983445,0.00016018518],"about_ca_topic_score_codex":0.0058181887,"about_ca_topic_score_gemma":0.00311164,"teacher_disagreement_score":0.7760841,"about_ca_system_score_codex":0.003681684,"about_ca_system_score_gemma":0.005094327,"threshold_uncertainty_score":0.9570499},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31942537,0.0010619032,0.6723678,0.0014756274,0.000117090574,0.00049991556,0.0016528968,0.0018632166,0.0015361608],"genre_scores_gemma":[0.77105093,0.0002188246,0.22580184,0.00021202027,0.0001034519,0.00031639996,0.0017841966,0.00005374907,0.00045870576],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653155,0.0021018651,0.00026764977,0.0005716083,0.0002888301,0.00023861312],"domain_scores_gemma":[0.988204,0.0091579845,0.0007050346,0.00038109554,0.0012817177,0.00027012778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011333095,0.00094844826,0.0014880112,0.0022579546,0.0005606613,0.0012778826,0.0018286121,0.0010697473,0.0009099624],"category_scores_gemma":[0.019059291,0.0006600756,0.0012743658,0.0017702811,0.00043113148,0.0009412658,0.00086742325,0.0014217889,0.00045104354],"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":[0.0008624922,0.00071409484,0.086237095,0.0001210848,0.00047215985,0.00022041352,0.000098556695,0.7126836,0.0007410576,0.0016112763,0.0053803744,0.19085783],"study_design_scores_gemma":[0.000040363975,0.0000359989,0.0021261612,0.00001399635,0.000021521584,0.000024752419,0.00001179588,0.9959409,0.00014229993,0.0014982899,0.00013561493,0.000008281048],"about_ca_topic_score_codex":0.020507684,"about_ca_topic_score_gemma":0.012406789,"teacher_disagreement_score":0.020507684,"about_ca_system_score_codex":0.0010496861,"about_ca_system_score_gemma":0.0022143417,"threshold_uncertainty_score":0.059935868},"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":"methods","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007004232,0.101146944,0.75103015,0.044692606,0.010753008,0.07621604,0.007044826,0.003746901,0.0046691145],"genre_scores_gemma":[0.0012366017,0.016312905,0.9298281,0.0018629762,0.0006260273,0.04874499,0.00051694806,0.00032032075,0.0005511539],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.40509912,0.4459381,0.111813545,0.010261437,0.025761172,0.0011266106],"domain_scores_gemma":[0.22964469,0.61317605,0.0391257,0.042433623,0.072079435,0.0035404337],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50246936,0.0077923657,0.01689861,0.04196279,0.004044292,0.017427862,0.011638751,0.01189317,0.022569317],"category_scores_gemma":[0.6816752,0.0088753225,0.027075898,0.032512218,0.009095002,0.014549931,0.011594269,0.021356039,0.011976475],"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":[0.00080498477,0.00021490981,0.0010440185,0.27907687,0.008516921,0.00051208487,0.011992879,0.0032663892,0.0018889031,0.060264446,0.15520133,0.4772162],"study_design_scores_gemma":[0.0028247861,0.0005501947,0.0013794361,0.27646336,0.011046646,0.00089057063,0.0023225655,0.00792864,0.0028800676,0.26353204,0.42925185,0.0009298456],"about_ca_topic_score_codex":0.0041173543,"about_ca_topic_score_gemma":0.006618217,"teacher_disagreement_score":0.49753064,"about_ca_system_score_codex":0.009710141,"about_ca_system_score_gemma":0.058325417,"threshold_uncertainty_score":0.61354387},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919612,0.0010664464,0.0010080631,0.00057177094,0.00005229281,0.00016787599,0.0038664097,0.000025495108,0.0012805591],"genre_scores_gemma":[0.99199426,0.00069306424,0.003352848,0.00010885119,0.00003657052,0.00021951042,0.003373352,0.000008268805,0.00021334601],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99784493,0.00094924384,0.00023976256,0.00023888248,0.00049770006,0.00022944945],"domain_scores_gemma":[0.9892657,0.0035792484,0.004697875,0.0004511093,0.0012745273,0.0007315216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00516419,0.0005554217,0.0005109123,0.0019780246,0.0003835341,0.0012262897,0.0010975568,0.0004364517,0.0011700675],"category_scores_gemma":[0.018698746,0.0003261782,0.0012153091,0.0019766835,0.00038002705,0.0006947162,0.0012164059,0.0013624402,0.00018148315],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026618172,0.000024730194,0.99617285,0.000039853116,0.00004626293,0.000012571928,0.00014603086,0.00011858465,0.000009318034,0.000024121913,0.00031939815,0.0030596426],"study_design_scores_gemma":[0.0000060734683,0.00005650186,0.9971533,0.00012403498,0.000043934084,0.00003827346,0.00079356163,0.001120914,0.000046318266,0.000055801964,0.0005527686,0.000008592328],"about_ca_topic_score_codex":0.0723918,"about_ca_topic_score_gemma":0.14174807,"teacher_disagreement_score":0.0723918,"about_ca_system_score_codex":0.0013731205,"about_ca_system_score_gemma":0.0026605304,"threshold_uncertainty_score":0.14394087},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016413778,0.3406595,0.531388,0.007934604,0.017183792,0.03226822,0.041821465,0.0067190705,0.0056116115],"genre_scores_gemma":[0.26787895,0.049360555,0.558372,0.0030874156,0.002822635,0.09826403,0.015752885,0.0017307736,0.0027307037],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.47139075,0.3621028,0.094489366,0.023593541,0.04661077,0.001812733],"domain_scores_gemma":[0.31511423,0.522482,0.06298736,0.064424634,0.034059253,0.0009325739],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27522725,0.0042016893,0.01481257,0.027558014,0.0010742914,0.008442186,0.0055559655,0.0021203686,0.008784297],"category_scores_gemma":[0.6174312,0.0021651622,0.029246654,0.03431178,0.0031243376,0.0041894787,0.0040592295,0.0043029864,0.0019320907],"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":[0.0033410203,0.00013657862,0.021108968,0.42811278,0.28818968,0.0004068958,0.0015181975,0.005044244,0.0019174104,0.0117080975,0.035769343,0.20274685],"study_design_scores_gemma":[0.007365588,0.0036008735,0.06984213,0.12186891,0.41779098,0.0013707781,0.0018401332,0.032949563,0.0082390765,0.11579035,0.2179507,0.0013908426],"about_ca_topic_score_codex":0.002890062,"about_ca_topic_score_gemma":0.0034852903,"teacher_disagreement_score":0.72477275,"about_ca_system_score_codex":0.00366343,"about_ca_system_score_gemma":0.011047252,"threshold_uncertainty_score":0.89377385},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7191638,0.0032071192,0.19815472,0.023357524,0.0006747865,0.006489621,0.032649644,0.0057859486,0.010516843],"genre_scores_gemma":[0.60613096,0.0016069035,0.3256204,0.0030862123,0.00016655131,0.0030625693,0.058258023,0.0010547847,0.0010136131],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8486201,0.10071588,0.024525736,0.007057526,0.016938442,0.0021424005],"domain_scores_gemma":[0.64565176,0.1812595,0.02419239,0.09881069,0.04376717,0.006318462],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.203931,0.00069281465,0.0009429682,0.0036859103,0.0015928418,0.008018436,0.005117459,0.0014304828,0.0012486082],"category_scores_gemma":[0.3446447,0.00077783025,0.001982213,0.011954365,0.0021667494,0.0072594816,0.009996469,0.0033544097,0.0005962256],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033883231,0.0016080395,0.4428138,0.0025900903,0.001158949,0.0014202644,0.023862185,0.021752968,0.0032082812,0.04079985,0.04157869,0.41581866],"study_design_scores_gemma":[0.0023724155,0.0034174758,0.35815272,0.006662957,0.0018774844,0.0041574836,0.038641132,0.12165933,0.029059047,0.049984142,0.38314787,0.0008679334],"about_ca_topic_score_codex":0.022092944,"about_ca_topic_score_gemma":0.010360008,"teacher_disagreement_score":0.796069,"about_ca_system_score_codex":0.0062310845,"about_ca_system_score_gemma":0.0140100345,"threshold_uncertainty_score":0.9816948},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18402214,0.7042647,0.005767561,0.0075237663,0.0026617362,0.0057344153,0.07255464,0.0006301345,0.016840866],"genre_scores_gemma":[0.6547804,0.2626919,0.011878768,0.0033328712,0.0024240427,0.018766306,0.03891624,0.00067781203,0.006531693],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8509096,0.04668368,0.06604517,0.006629108,0.027774202,0.0019582876],"domain_scores_gemma":[0.47524962,0.30388284,0.15471584,0.01153685,0.046026014,0.008588891],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.055842973,0.0016508963,0.0029016633,0.037617523,0.0015660371,0.0056192847,0.0023556803,0.00223432,0.010278954],"category_scores_gemma":[0.37822273,0.0008923357,0.0046130875,0.03652323,0.0010871413,0.004853756,0.0040859855,0.0020342923,0.0027270075],"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":[0.0098085245,0.00031303306,0.22835113,0.24483308,0.009597571,0.0025543473,0.009682511,0.0010563296,0.0035666954,0.0040469444,0.15051362,0.33567622],"study_design_scores_gemma":[0.002011431,0.0018380084,0.6749728,0.089526996,0.005841769,0.012728022,0.008991558,0.00096543436,0.0020422053,0.004532066,0.19593273,0.00061693054],"about_ca_topic_score_codex":0.002455336,"about_ca_topic_score_gemma":0.0032062756,"teacher_disagreement_score":0.9623825,"about_ca_system_score_codex":0.005173471,"about_ca_system_score_gemma":0.0062232,"threshold_uncertainty_score":0.29532945},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004138955,0.00047422296,0.9930576,0.0036298472,0.00012570337,0.00017717079,0.00036592883,0.0007738406,0.0009817613],"genre_scores_gemma":[0.015855936,0.0006601116,0.9804474,0.0007727393,0.000263416,0.000674895,0.0008364105,0.00015985568,0.00032927317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9351719,0.04452966,0.005348885,0.0042824633,0.009759287,0.000907781],"domain_scores_gemma":[0.85737234,0.09595911,0.0046127914,0.031749662,0.0068642325,0.0034419396],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.075066045,0.001815351,0.0030710176,0.0064638047,0.0021626842,0.013468383,0.0074919504,0.003927281,0.004663409],"category_scores_gemma":[0.120210886,0.0018888488,0.007814761,0.008694357,0.009107593,0.011466127,0.019858636,0.009660088,0.0018899839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017777272,0.00014446826,0.0015491149,0.0006928473,0.00051547296,0.00024003471,0.00073406217,0.080637306,0.0007882611,0.7899067,0.012851675,0.111762375],"study_design_scores_gemma":[0.00008373503,0.000040218827,0.00018558657,0.00019620589,0.00005938116,0.00008297049,0.00009415803,0.15197511,0.00039115804,0.81667185,0.030172907,0.0000468056],"about_ca_topic_score_codex":0.008608484,"about_ca_topic_score_gemma":0.00649831,"teacher_disagreement_score":0.92493397,"about_ca_system_score_codex":0.0040449104,"about_ca_system_score_gemma":0.014492167,"threshold_uncertainty_score":0.3969919},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017269833,0.17892224,0.56892955,0.1233261,0.005032439,0.078891456,0.0036777854,0.0014403005,0.022510266],"genre_scores_gemma":[0.07025004,0.019060811,0.86187875,0.0033896342,0.0004925174,0.043179385,0.0012602975,0.00013783594,0.00035076204],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.264128,0.44338143,0.20970044,0.016644165,0.061180193,0.004965735],"domain_scores_gemma":[0.1449731,0.6711043,0.049210884,0.024425022,0.10510261,0.00518397],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.68872905,0.0072498727,0.011236945,0.13019347,0.012728687,0.031144567,0.01925308,0.009776727,0.0031072176],"category_scores_gemma":[0.7705693,0.004638355,0.016869389,0.056221135,0.0355782,0.0335557,0.037559967,0.012188241,0.0007887486],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035954267,0.00019560482,0.0132553335,0.18567516,0.0034635232,0.0007562018,0.06219131,0.0052691335,0.00082064426,0.23842378,0.024015233,0.4655745],"study_design_scores_gemma":[0.0006053722,0.00066860206,0.009265021,0.37157977,0.0059606098,0.0018086169,0.056248985,0.013369186,0.001540465,0.4148493,0.12319071,0.0009133248],"about_ca_topic_score_codex":0.0159714,"about_ca_topic_score_gemma":0.017311212,"teacher_disagreement_score":0.31127095,"about_ca_system_score_codex":0.05484915,"about_ca_system_score_gemma":0.16533302,"threshold_uncertainty_score":0.3979603},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22822861,0.4891457,0.15569292,0.017970482,0.003827297,0.06858062,0.025294483,0.001152512,0.010107329],"genre_scores_gemma":[0.6260317,0.04594074,0.1833856,0.0028483078,0.00063500024,0.1331617,0.0072305533,0.00030307414,0.00046339066],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.16314669,0.41947857,0.33564082,0.019472238,0.05999874,0.0022629576],"domain_scores_gemma":[0.08545679,0.75395817,0.09898982,0.023312114,0.03685814,0.0014249764],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.61237156,0.002194451,0.012778176,0.04231887,0.0025600307,0.008478831,0.0035823274,0.0033385106,0.0025635238],"category_scores_gemma":[0.8240412,0.0031273554,0.016609682,0.04204769,0.007741623,0.009602167,0.011993052,0.0034964986,0.00035103664],"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":[0.0017241781,0.00014945692,0.1336423,0.6374148,0.061569743,0.00040567212,0.027883671,0.0019038918,0.0011625511,0.009826984,0.0063197957,0.11799697],"study_design_scores_gemma":[0.0031861875,0.0020111136,0.24330918,0.55328876,0.08200042,0.0021275328,0.021586673,0.009650152,0.0023361421,0.036739845,0.042535596,0.0012284438],"about_ca_topic_score_codex":0.0036511943,"about_ca_topic_score_gemma":0.008240902,"teacher_disagreement_score":0.38762844,"about_ca_system_score_codex":0.010071101,"about_ca_system_score_gemma":0.026862355,"threshold_uncertainty_score":0.47801495},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.956324,0.0062616905,0.021109905,0.0023911833,0.00013123133,0.00022335017,0.008595264,0.00038984703,0.004573699],"genre_scores_gemma":[0.9788319,0.0018302286,0.012647771,0.0001837036,0.000030865554,0.0000623446,0.004996695,0.000032978453,0.0013835324],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99937695,0.00016372319,0.00004808608,0.00011944604,0.00017850936,0.00011329327],"domain_scores_gemma":[0.9976927,0.0006946356,0.0002919242,0.000076618984,0.0010048393,0.00023917336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022640345,0.00076901074,0.00048122156,0.0015557848,0.0007122362,0.000868297,0.00091956375,0.00043010255,0.0010717431],"category_scores_gemma":[0.0058342493,0.00016875457,0.0007065073,0.0014831404,0.0003449655,0.00040174252,0.0005203744,0.00069647783,0.00028583032],"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":[0.00083600666,0.00013768645,0.77251476,0.0004307631,0.00048504292,0.00028158413,0.0004085864,0.09202308,0.0010205084,0.0011047388,0.010418207,0.12033898],"study_design_scores_gemma":[0.000091655944,0.00018199321,0.47971445,0.00031131742,0.0002590408,0.00017814494,0.0009046718,0.5116527,0.0011430032,0.00083831674,0.0046473015,0.00007724368],"about_ca_topic_score_codex":0.9327708,"about_ca_topic_score_gemma":0.92947495,"teacher_disagreement_score":0.06722921,"about_ca_system_score_codex":0.009870288,"about_ca_system_score_gemma":0.012185859,"threshold_uncertainty_score":0.13525021},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17058325,0.022755098,0.73790467,0.017392391,0.0023989826,0.010639778,0.0049623647,0.0017478131,0.031615674],"genre_scores_gemma":[0.91401255,0.0016135077,0.06756008,0.0054851547,0.0008788169,0.007855357,0.00096568087,0.00017405786,0.0014548317],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.48810384,0.42975998,0.028944561,0.022787504,0.02709073,0.0033133794],"domain_scores_gemma":[0.13112123,0.6942205,0.098939605,0.06667997,0.0075005447,0.0015382532],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50684327,0.0016902327,0.0035355908,0.0050600967,0.0016928713,0.004651148,0.0037319383,0.004244976,0.0073901233],"category_scores_gemma":[0.6904743,0.0009439947,0.007524766,0.004293603,0.010127997,0.0065596984,0.0052848393,0.006826447,0.00064021477],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018045813,0.0003823693,0.19230546,0.010470745,0.030386409,0.0019326522,0.00617643,0.0478296,0.0021725546,0.34313256,0.0125269545,0.33463854],"study_design_scores_gemma":[0.0031668274,0.00736896,0.12888327,0.007980225,0.019396288,0.0026961474,0.00081695203,0.13156949,0.009891679,0.6506429,0.036899015,0.0006881689],"about_ca_topic_score_codex":0.0008264848,"about_ca_topic_score_gemma":0.0006811234,"teacher_disagreement_score":0.49315673,"about_ca_system_score_codex":0.0041617635,"about_ca_system_score_gemma":0.0033721656,"threshold_uncertainty_score":0.6081501},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51777637,0.07431808,0.10275515,0.010081473,0.0031230624,0.013831621,0.11047566,0.001015132,0.16662347],"genre_scores_gemma":[0.865712,0.01569574,0.054963864,0.0020708134,0.00025753287,0.018520894,0.03145326,0.0006033072,0.010722716],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9707822,0.012544978,0.010755272,0.0015531386,0.0037976764,0.000566687],"domain_scores_gemma":[0.9237132,0.040846094,0.008632526,0.0057102772,0.020571312,0.0005267233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033034343,0.0007044211,0.0012771762,0.008218348,0.0018926599,0.003026088,0.00095411245,0.00077717897,0.027270228],"category_scores_gemma":[0.11724982,0.00045516968,0.0022016817,0.008550606,0.0015732829,0.002295791,0.004223965,0.0009665834,0.0041927965],"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":[0.005661003,0.00029472256,0.105190985,0.0991037,0.0030276102,0.00096430373,0.04618203,0.00088672177,0.0064986055,0.058085624,0.08162176,0.592483],"study_design_scores_gemma":[0.0010287969,0.0006434683,0.3369718,0.04582036,0.0076631815,0.0017001599,0.030822188,0.0022436182,0.007235237,0.0247221,0.540773,0.00037616168],"about_ca_topic_score_codex":0.01995921,"about_ca_topic_score_gemma":0.029129166,"teacher_disagreement_score":0.033034343,"about_ca_system_score_codex":0.004398262,"about_ca_system_score_gemma":0.009692302,"threshold_uncertainty_score":0.17470437},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85486174,0.0026225245,0.13578248,0.00081822294,0.000090699934,0.0016370298,0.00085443654,0.0001833063,0.0031495392],"genre_scores_gemma":[0.9788552,0.0003703561,0.019088794,0.00014883412,0.000017450968,0.0009662122,0.00029775614,0.000017636208,0.00023768909],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95401746,0.041895438,0.00117493,0.0010842526,0.0013228789,0.00050496904],"domain_scores_gemma":[0.48221338,0.4918546,0.01079963,0.008550831,0.00555242,0.0010291225],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.083738305,0.0010505939,0.0015037068,0.0009740846,0.0005049035,0.0014095394,0.001597088,0.001993275,0.0020418025],"category_scores_gemma":[0.22619705,0.00054844207,0.0036009774,0.0010662011,0.0010454964,0.0016154313,0.0017058168,0.0021471423,0.00019028717],"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":[0.00975537,0.000934955,0.057096735,0.0010113952,0.0022800511,0.000571722,0.00048304762,0.898114,0.0007913656,0.005663569,0.00068586203,0.022611862],"study_design_scores_gemma":[0.001269295,0.0052262438,0.01177727,0.0004699577,0.0013583559,0.00033876265,0.00015663441,0.9690242,0.0019218908,0.0075367223,0.00082103995,0.00009967472],"about_ca_topic_score_codex":0.004487111,"about_ca_topic_score_gemma":0.0020755413,"teacher_disagreement_score":0.9162617,"about_ca_system_score_codex":0.0018202108,"about_ca_system_score_gemma":0.0020655605,"threshold_uncertainty_score":0.44285578},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008563484,0.00983436,0.6324461,0.2141023,0.00555554,0.07698729,0.0056428383,0.02119874,0.025669454],"genre_scores_gemma":[0.00503472,0.001443275,0.97293144,0.003513779,0.00030006943,0.015252247,0.0004961097,0.00040530492,0.0006231628],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.24783538,0.53573555,0.16505513,0.007930549,0.03893705,0.0045063784],"domain_scores_gemma":[0.0599373,0.6759165,0.05788846,0.05044214,0.14697476,0.008840869],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6417096,0.004883707,0.0062335893,0.047667097,0.006711561,0.0298678,0.01397307,0.011893507,0.015742097],"category_scores_gemma":[0.8469676,0.0063034385,0.011611669,0.028984735,0.008926971,0.030424422,0.018365106,0.015720507,0.019892512],"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":[0.00093425135,0.0008304555,0.007333614,0.034222342,0.00095490087,0.0011929036,0.043625854,0.00469891,0.003205142,0.02125118,0.2921165,0.589634],"study_design_scores_gemma":[0.0040978887,0.0011095686,0.011888223,0.1570235,0.0018881899,0.002446801,0.022728162,0.031598177,0.0068801194,0.16758284,0.59035045,0.0024060302],"about_ca_topic_score_codex":0.013469405,"about_ca_topic_score_gemma":0.038338013,"teacher_disagreement_score":0.35829037,"about_ca_system_score_codex":0.016640497,"about_ca_system_score_gemma":0.11167694,"threshold_uncertainty_score":0.44183588},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010860516,0.9958366,0.001010259,0.00050314795,0.00014444329,0.00052921294,0.00072710146,0.000011203522,0.00015196788],"genre_scores_gemma":[0.025540356,0.96728146,0.0032009373,0.0010963717,0.00016957836,0.0019366577,0.00067752827,0.000013537828,0.00008361093],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9239011,0.03289337,0.03012055,0.004339541,0.007940744,0.0008047989],"domain_scores_gemma":[0.68928677,0.26040098,0.03473957,0.005185913,0.009749907,0.00063693867],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07799754,0.0019894398,0.010416868,0.017252605,0.0009738183,0.004358747,0.0033689125,0.0026227853,0.0035064095],"category_scores_gemma":[0.24343292,0.0020426481,0.017012425,0.019650176,0.0021772305,0.005116855,0.002606928,0.0019578852,0.00034282493],"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":[0.00016350394,0.000012263111,0.0027126924,0.93724513,0.03025261,0.00009505519,0.00034560976,0.00015277963,0.000073005656,0.00052584737,0.0008558835,0.02756575],"study_design_scores_gemma":[0.00019628376,0.00014300458,0.0069640186,0.8542201,0.12574318,0.00026723245,0.00048768116,0.00017942884,0.00015174679,0.0010163616,0.0105759585,0.000054952496],"about_ca_topic_score_codex":0.009493108,"about_ca_topic_score_gemma":0.023048755,"teacher_disagreement_score":0.92200243,"about_ca_system_score_codex":0.0051743197,"about_ca_system_score_gemma":0.021155667,"threshold_uncertainty_score":0.41249537},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7690875,0.0025735614,0.0024457504,0.008366632,0.00036592525,0.00023916652,0.1995672,0.0001705078,0.017183727],"genre_scores_gemma":[0.9358749,0.0013825595,0.0017361477,0.0010174055,0.00021384703,0.00025332652,0.057664253,0.000026183314,0.0018313555],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983669,0.0006447622,0.00016742248,0.00024724356,0.0002996776,0.00027393922],"domain_scores_gemma":[0.9920845,0.0023584324,0.002955908,0.0005759372,0.0012055779,0.0008196319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018163224,0.0003310472,0.00030524968,0.0011547232,0.0004938547,0.0010934153,0.0005382446,0.00036307276,0.008338822],"category_scores_gemma":[0.011126435,0.00013273983,0.0010093792,0.0019387484,0.00034913275,0.00078308984,0.0019855003,0.00096554426,0.0011242229],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013538582,0.00007317099,0.958096,0.00028209135,0.00021492619,0.000072356124,0.00030939098,0.0010837495,0.00008082168,0.00065760664,0.017549755,0.02144466],"study_design_scores_gemma":[0.000013231126,0.00006416819,0.9848875,0.0002938463,0.000098068274,0.000082753715,0.00094069174,0.0022910151,0.00019652271,0.00075732416,0.010356366,0.000018479805],"about_ca_topic_score_codex":0.043985523,"about_ca_topic_score_gemma":0.04804283,"teacher_disagreement_score":0.043985523,"about_ca_system_score_codex":0.0013813351,"about_ca_system_score_gemma":0.0014503533,"threshold_uncertainty_score":0.08745897},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009297072,0.0004123635,0.9881975,0.00025464286,0.00007085156,0.00008705164,0.0006150318,0.00043448477,0.00063096336],"genre_scores_gemma":[0.51478344,0.002622541,0.4499465,0.0007059211,0.0006561773,0.0019673146,0.0066607688,0.00054597703,0.022111295],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956567,0.0024569298,0.00023713292,0.000683688,0.00055493717,0.000410622],"domain_scores_gemma":[0.9820256,0.012354275,0.0021335843,0.0015705245,0.0014742981,0.00044167234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016649537,0.0021513158,0.002352991,0.0023246417,0.0006314005,0.002231321,0.0045733084,0.0025757942,0.0068651107],"category_scores_gemma":[0.03148148,0.0010968043,0.0029071688,0.0024562108,0.0016693098,0.0032102298,0.0030149394,0.003761577,0.002083965],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022103207,0.000087812725,0.0045432276,0.00029171506,0.0003086401,0.00028382108,0.0004171146,0.6846237,0.0010421701,0.24015848,0.0032631706,0.06475914],"study_design_scores_gemma":[0.000017328251,0.00007163124,0.0006932831,0.000045555174,0.000056371442,0.000056929202,0.00003312415,0.917941,0.00023397022,0.07865795,0.002156728,0.000036213332],"about_ca_topic_score_codex":0.007055412,"about_ca_topic_score_gemma":0.006266107,"teacher_disagreement_score":0.016649537,"about_ca_system_score_codex":0.0014526816,"about_ca_system_score_gemma":0.0019057039,"threshold_uncertainty_score":0.08805215},"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":"reporting","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4282219,0.24786063,0.05617823,0.019753749,0.0026893893,0.06400366,0.16481116,0.00084455847,0.015636694],"genre_scores_gemma":[0.66948307,0.07191557,0.06406779,0.013122763,0.0013012757,0.1282808,0.0497164,0.0004844266,0.0016279231],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.3651349,0.14394279,0.4323977,0.014557297,0.041468248,0.0024990684],"domain_scores_gemma":[0.12646505,0.44597417,0.31104934,0.035853267,0.077846356,0.002811868],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3676085,0.001743192,0.005637251,0.036349494,0.0025773395,0.006587016,0.003329772,0.0029224271,0.004853754],"category_scores_gemma":[0.65320915,0.002542309,0.0065201577,0.031983525,0.003743597,0.010991192,0.009288657,0.0024918478,0.0013438719],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031130142,0.00029624766,0.54704505,0.27747867,0.0090143625,0.0011059225,0.03636749,0.00053670566,0.0030015039,0.0048714713,0.031457253,0.08571231],"study_design_scores_gemma":[0.0017008279,0.0024287049,0.5543141,0.2259517,0.013737424,0.004544841,0.039530262,0.0017488428,0.0057073645,0.007837728,0.14154996,0.00094831764],"about_ca_topic_score_codex":0.0039197598,"about_ca_topic_score_gemma":0.003860238,"teacher_disagreement_score":0.6323915,"about_ca_system_score_codex":0.00651477,"about_ca_system_score_gemma":0.013523502,"threshold_uncertainty_score":0.7798513},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9742318,0.005000549,0.0022185359,0.0053083585,0.00004958763,0.00018472299,0.010098753,0.000054081203,0.0028536636],"genre_scores_gemma":[0.9949945,0.0008228675,0.0017799229,0.00036598474,0.00001536454,0.000038862632,0.0017563096,0.000018273706,0.00020784585],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9813597,0.007907089,0.001265572,0.0016469582,0.005410664,0.0024099955],"domain_scores_gemma":[0.92645717,0.03807924,0.012634433,0.0039766585,0.015711587,0.0031408977],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0200234,0.0004405712,0.0006103552,0.0023247655,0.0027695415,0.0030975991,0.0026751605,0.0005897021,0.0011212854],"category_scores_gemma":[0.08495908,0.00042245092,0.0017654409,0.008593188,0.0018423051,0.0012327889,0.0026881157,0.0014394781,0.00009107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015649479,0.000020792175,0.9856958,0.00014184773,0.0003403568,0.000076042365,0.0013525521,0.0011624461,0.00007379007,0.00061719766,0.0012493333,0.009113435],"study_design_scores_gemma":[0.000012869691,0.000035749956,0.99052167,0.0002486758,0.00024050089,0.00006470216,0.0019200963,0.0045573423,0.00016115267,0.00026861098,0.0019314941,0.000037089052],"about_ca_topic_score_codex":0.989744,"about_ca_topic_score_gemma":0.9909843,"teacher_disagreement_score":0.9799766,"about_ca_system_score_codex":0.046413794,"about_ca_system_score_gemma":0.05949474,"threshold_uncertainty_score":0.33675724},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5662743,0.0040170536,0.40130785,0.011125063,0.00021727648,0.00062056433,0.006341635,0.002536943,0.007559282],"genre_scores_gemma":[0.77867967,0.0012320112,0.21803908,0.00015005376,0.000068858346,0.00017526322,0.001291612,0.0000812415,0.00028220064],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99836344,0.0009709182,0.00013967001,0.000174641,0.0002930714,0.000058220514],"domain_scores_gemma":[0.9887918,0.0072163492,0.0015671597,0.0010712672,0.0010401561,0.00031340952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043983418,0.0006366349,0.0004956061,0.006358152,0.00051681313,0.0030958254,0.000882648,0.00035950865,0.001689249],"category_scores_gemma":[0.01884282,0.00022105969,0.00094768364,0.0043774233,0.00069659436,0.001434473,0.0013362349,0.000599507,0.00017486434],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026875388,0.00025688537,0.57471794,0.00071010255,0.0007545678,0.0003170647,0.0033879213,0.034508582,0.0028414507,0.01838724,0.005605488,0.358244],"study_design_scores_gemma":[0.00006749745,0.00037164215,0.42018846,0.0007789779,0.00038234497,0.0007961905,0.010609224,0.42821184,0.0065884506,0.10678397,0.025024652,0.00019683318],"about_ca_topic_score_codex":0.008121681,"about_ca_topic_score_gemma":0.011919957,"teacher_disagreement_score":0.008121681,"about_ca_system_score_codex":0.0011426978,"about_ca_system_score_gemma":0.002172727,"threshold_uncertainty_score":0.023260951},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008834689,0.0045610904,0.048049394,0.14098431,0.76148826,0.0006618129,0.013310519,0.0019259237,0.020184044],"genre_scores_gemma":[0.15098254,0.010512606,0.23231335,0.1443064,0.07347047,0.0038735785,0.017293375,0.0072564655,0.35999125],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928255,0.002873012,0.0013038667,0.0005870454,0.0022422464,0.00016829617],"domain_scores_gemma":[0.8719243,0.09477785,0.0036008814,0.003746935,0.02483998,0.0011102252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01132793,0.0013071956,0.0015926878,0.0020996819,0.002135537,0.0020380197,0.0020251165,0.003727394,0.051895767],"category_scores_gemma":[0.23681268,0.0009162072,0.0015852262,0.0025589557,0.0015591995,0.0016567111,0.0009732929,0.0041627917,0.011696939],"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":[0.0005466961,0.00010549099,0.0010938781,0.00056382257,0.00008254994,0.00043827645,0.00014844925,0.0021052363,0.000121543235,0.008386124,0.9579114,0.028496528],"study_design_scores_gemma":[0.0017699507,0.0008310288,0.008188022,0.0036033923,0.0009590604,0.0024151162,0.0008035104,0.019361435,0.0023842026,0.039176393,0.9201113,0.00039653067],"about_ca_topic_score_codex":0.01458939,"about_ca_topic_score_gemma":0.022683414,"teacher_disagreement_score":0.051895767,"about_ca_system_score_codex":0.0031401375,"about_ca_system_score_gemma":0.0051982943,"threshold_uncertainty_score":0.17360866},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34100202,0.013310981,0.6161165,0.0051764087,0.00044192976,0.008579624,0.002300876,0.00049919495,0.012572482],"genre_scores_gemma":[0.8314221,0.0024627019,0.15487298,0.0010553075,0.000114255665,0.008136734,0.0007110525,0.000066773384,0.0011580811],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9578887,0.03876205,0.0009672846,0.0008230839,0.00093580695,0.0006230672],"domain_scores_gemma":[0.70612997,0.2752034,0.008180126,0.0043900143,0.0048442674,0.0012522779],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.053206068,0.001786937,0.003324462,0.0015685591,0.0007132486,0.0015098994,0.0025817808,0.0030685996,0.006499332],"category_scores_gemma":[0.13349918,0.000999776,0.0049649724,0.001845496,0.0012276687,0.0018774424,0.002160917,0.0039031673,0.0003737787],"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":[0.0033636575,0.0010840255,0.00893608,0.0029023488,0.0028808475,0.000438191,0.00039402719,0.9257491,0.00033302515,0.029743442,0.002203864,0.02197142],"study_design_scores_gemma":[0.0028201302,0.0016480223,0.0013736073,0.00065826846,0.0011638631,0.00016940932,0.00014631095,0.96510524,0.00034408024,0.024552604,0.0019439682,0.00007449607],"about_ca_topic_score_codex":0.008042852,"about_ca_topic_score_gemma":0.0044915327,"teacher_disagreement_score":0.9467939,"about_ca_system_score_codex":0.0031387184,"about_ca_system_score_gemma":0.004135305,"threshold_uncertainty_score":0.281384},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41672814,0.014914117,0.21878189,0.19672114,0.0037917586,0.12344548,0.002448293,0.00047450012,0.022694763],"genre_scores_gemma":[0.6804293,0.003717615,0.15160938,0.037617985,0.00047763926,0.1231011,0.00027301186,0.00021744888,0.00255647],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.29040927,0.6779531,0.01410636,0.00478687,0.007572159,0.005172298],"domain_scores_gemma":[0.25776243,0.70406026,0.010306544,0.008490323,0.012780332,0.0066000926],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.51958776,0.0010952944,0.0024168037,0.0040490967,0.01120172,0.011385461,0.006086983,0.008344182,0.0072189854],"category_scores_gemma":[0.57185876,0.0020001298,0.0024343913,0.004039211,0.018241601,0.013505859,0.0099079,0.010473325,0.0008082353],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013373634,0.0004941577,0.0024708782,0.008493389,0.00021826051,0.0015905577,0.8879775,0.0013001678,0.0018980921,0.030790217,0.0064711515,0.056958254],"study_design_scores_gemma":[0.0021726855,0.0016515402,0.0015170682,0.013881119,0.00026453787,0.0009335028,0.8088744,0.004740574,0.0029698124,0.048494626,0.114188224,0.00031179574],"about_ca_topic_score_codex":0.0026718164,"about_ca_topic_score_gemma":0.0036592411,"teacher_disagreement_score":0.48041224,"about_ca_system_score_codex":0.024047049,"about_ca_system_score_gemma":0.043997437,"threshold_uncertainty_score":0.59243387},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021831572,0.010248756,0.8395193,0.06469408,0.0034742537,0.011256014,0.00046510829,0.0005681681,0.04794275],"genre_scores_gemma":[0.23733222,0.0049998425,0.7077986,0.009300017,0.00074527244,0.03750871,0.00021691663,0.0004640269,0.0016344677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.19362745,0.7519554,0.022550555,0.0110282935,0.018851979,0.0019863038],"domain_scores_gemma":[0.10394158,0.7933576,0.022354139,0.032737765,0.044617116,0.002991849],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5809739,0.0016294034,0.0029648733,0.011089696,0.014476942,0.031632237,0.0059079933,0.005089167,0.0069976132],"category_scores_gemma":[0.6230712,0.002767596,0.0018150121,0.015632616,0.08698508,0.030289749,0.023132551,0.011990335,0.0018583102],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000155568,0.000067441586,0.0023246256,0.0062565524,0.00009492149,0.00026917056,0.4128637,0.00047475912,0.0005693058,0.4905971,0.007187865,0.07913894],"study_design_scores_gemma":[0.00026070746,0.00021747802,0.0012243334,0.024594754,0.000109401866,0.000941345,0.1637783,0.0031918231,0.0014151208,0.61111456,0.19290598,0.00024625118],"about_ca_topic_score_codex":0.0031967303,"about_ca_topic_score_gemma":0.0026970727,"teacher_disagreement_score":0.41902608,"about_ca_system_score_codex":0.020737888,"about_ca_system_score_gemma":0.047309455,"threshold_uncertainty_score":0.51673377},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00707591,0.0013045215,0.98784524,0.0010476019,0.00022339141,0.00018350004,0.0009119847,0.0003800346,0.0010278675],"genre_scores_gemma":[0.14334634,0.0036580332,0.8430036,0.00062771083,0.0003182809,0.002476357,0.002610081,0.000572073,0.0033875497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9688431,0.025960546,0.0013210014,0.001937117,0.0015526905,0.0003854357],"domain_scores_gemma":[0.92442197,0.061629836,0.0044945693,0.005697963,0.003241246,0.00051447743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.050851036,0.0017181237,0.0013164405,0.0043770387,0.001048812,0.0036630733,0.0031716514,0.0022968932,0.005819772],"category_scores_gemma":[0.116393626,0.0010012196,0.0065973992,0.0072140624,0.0025342035,0.003737678,0.0037965684,0.005915102,0.0015457004],"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":[0.0005098833,0.00018584785,0.059389252,0.0025396491,0.002327621,0.0006490181,0.006253596,0.23361374,0.000983984,0.38320878,0.018805167,0.29153356],"study_design_scores_gemma":[0.00009071075,0.00048516455,0.014721648,0.0018357931,0.0005578637,0.00051761203,0.0016683044,0.5293399,0.0008445522,0.4074963,0.04216519,0.000276965],"about_ca_topic_score_codex":0.016290423,"about_ca_topic_score_gemma":0.020406203,"teacher_disagreement_score":0.050851036,"about_ca_system_score_codex":0.0018175831,"about_ca_system_score_gemma":0.004214561,"threshold_uncertainty_score":0.26892918},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39777318,0.01111471,0.36142236,0.020280026,0.0021230516,0.05220618,0.02203748,0.005925892,0.12711719],"genre_scores_gemma":[0.2711711,0.0056069996,0.68489987,0.001979761,0.00016291493,0.025571767,0.0075217327,0.00017571196,0.0029101213],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96227175,0.018160153,0.010201987,0.0010901454,0.007093269,0.0011825999],"domain_scores_gemma":[0.7583904,0.1855602,0.016709726,0.0055395877,0.03066587,0.0031343207],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.058953032,0.0011019234,0.0015873255,0.01966697,0.0013395101,0.0048943595,0.0023217008,0.0016806097,0.0070621665],"category_scores_gemma":[0.19587757,0.00068151497,0.0026604014,0.011076688,0.0013032249,0.007747098,0.004756534,0.0021316519,0.002839881],"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":[0.00026240197,0.0006684174,0.085894145,0.012897863,0.00026398202,0.0005732916,0.013990855,0.0011763041,0.0019165295,0.004291879,0.031002097,0.84706223],"study_design_scores_gemma":[0.0009890512,0.004436904,0.36819056,0.04999664,0.001304723,0.005089432,0.07468013,0.018070288,0.016480545,0.0314312,0.42838588,0.0009447002],"about_ca_topic_score_codex":0.0023020664,"about_ca_topic_score_gemma":0.0037879958,"teacher_disagreement_score":0.94104695,"about_ca_system_score_codex":0.0032209437,"about_ca_system_score_gemma":0.015759386,"threshold_uncertainty_score":0.31177717},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5777429,0.0032434515,0.2128907,0.0059228227,0.0025545135,0.15673168,0.011657399,0.0028798128,0.026376626],"genre_scores_gemma":[0.5849165,0.000933605,0.23723705,0.0041882675,0.0005365741,0.16365965,0.0051684454,0.00046445255,0.0028955434],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6474433,0.22638825,0.0787897,0.008871224,0.034937244,0.0035702565],"domain_scores_gemma":[0.41394636,0.2716135,0.1016957,0.07799104,0.13134977,0.0034035845],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31245047,0.0011355182,0.0017498919,0.0062545226,0.0033430338,0.0024401173,0.0026802232,0.0018056701,0.0033357113],"category_scores_gemma":[0.3709274,0.0012958446,0.0029141468,0.005708123,0.0021965902,0.0020592501,0.0036094391,0.0026581949,0.0013940976],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033327756,0.0034798086,0.5975871,0.0081702275,0.0013427435,0.00055097754,0.038128596,0.0016757688,0.00886693,0.0057392213,0.043922056,0.28720376],"study_design_scores_gemma":[0.0011626427,0.00558242,0.8394052,0.006208592,0.0009462527,0.00076555373,0.013168832,0.013555084,0.015914952,0.0041566524,0.098699026,0.00043482296],"about_ca_topic_score_codex":0.0041218107,"about_ca_topic_score_gemma":0.0076131723,"teacher_disagreement_score":0.68754953,"about_ca_system_score_codex":0.0037976077,"about_ca_system_score_gemma":0.009645392,"threshold_uncertainty_score":0.847871},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.827259,0.0063572084,0.13444307,0.0050105737,0.0010292728,0.0054226993,0.009934536,0.00030003206,0.010243682],"genre_scores_gemma":[0.9507768,0.0005438158,0.039561123,0.00089296204,0.0001806733,0.004167157,0.003452972,0.00010686984,0.00031760056],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.68515354,0.26724684,0.018551722,0.009400533,0.017734392,0.0019129812],"domain_scores_gemma":[0.5111009,0.33445704,0.056660406,0.05385139,0.042232785,0.0016975049],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2323473,0.0009297118,0.002200577,0.0051948754,0.0010232384,0.0039737304,0.001969638,0.0014008952,0.0038482682],"category_scores_gemma":[0.43887025,0.001081487,0.0061536306,0.009948913,0.003263141,0.003098387,0.002665182,0.002097129,0.0009317124],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006600639,0.0002706077,0.9367441,0.0020117234,0.0063826954,0.000084337866,0.0027138134,0.0010714998,0.00039768335,0.003208634,0.00294382,0.04351105],"study_design_scores_gemma":[0.00027673622,0.0018299845,0.9608289,0.004280225,0.0034478877,0.0002596933,0.0056235753,0.008863167,0.00066958385,0.0051455414,0.00867059,0.00010413656],"about_ca_topic_score_codex":0.0028956214,"about_ca_topic_score_gemma":0.0026082152,"teacher_disagreement_score":0.7676527,"about_ca_system_score_codex":0.0014093434,"about_ca_system_score_gemma":0.0025609818,"threshold_uncertainty_score":0.9466525},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27331394,0.10781585,0.27392668,0.006009112,0.0024728065,0.24173401,0.06679402,0.0055818525,0.02235175],"genre_scores_gemma":[0.23242846,0.017863197,0.49557003,0.00212706,0.00076116965,0.21676871,0.031877093,0.0005193259,0.0020849286],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.7526219,0.06476472,0.13014874,0.01343507,0.036135495,0.002893988],"domain_scores_gemma":[0.36755913,0.44584644,0.07526875,0.02222823,0.0870232,0.0020742512],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26643607,0.0042680744,0.009874123,0.08229834,0.0026675048,0.00575203,0.0055252234,0.004357944,0.005044665],"category_scores_gemma":[0.5106139,0.0023328764,0.011745082,0.03392993,0.0023012792,0.007951283,0.0052823285,0.0015512081,0.0021220532],"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":[0.0071648606,0.00084814074,0.13787739,0.274743,0.0132840425,0.0022175887,0.009772542,0.0043686074,0.014933976,0.0076419306,0.027951635,0.49919626],"study_design_scores_gemma":[0.007475414,0.0065767835,0.46736917,0.16940686,0.058276057,0.004894468,0.005521215,0.023214832,0.03238739,0.014777089,0.20826776,0.0018330184],"about_ca_topic_score_codex":0.006520741,"about_ca_topic_score_gemma":0.012006484,"teacher_disagreement_score":0.7335639,"about_ca_system_score_codex":0.006312665,"about_ca_system_score_gemma":0.020225497,"threshold_uncertainty_score":0.9046149},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43156955,0.011115721,0.29766327,0.11786241,0.0045897374,0.058132026,0.002602743,0.002328337,0.07413618],"genre_scores_gemma":[0.38336918,0.004059535,0.5571621,0.014731687,0.0006286307,0.028211644,0.0010162503,0.0007758979,0.010045017],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.6081868,0.3449311,0.01610959,0.008663561,0.0146660665,0.0074429233],"domain_scores_gemma":[0.64494467,0.22806147,0.024465283,0.030329315,0.0484415,0.02375776],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33264077,0.0016976198,0.0015671611,0.0039938428,0.006965438,0.010490735,0.006297238,0.0063655577,0.009274439],"category_scores_gemma":[0.33024147,0.0020934201,0.0023472793,0.003641875,0.006214807,0.007496252,0.02299601,0.006752658,0.0033098245],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086525315,0.001777152,0.0116835255,0.008745842,0.00027713247,0.004942584,0.62273526,0.002111021,0.0048613227,0.009069047,0.03374615,0.29918575],"study_design_scores_gemma":[0.0013331355,0.003421456,0.011808262,0.014850064,0.00045612257,0.0036355052,0.42615876,0.0044129323,0.007646903,0.019693669,0.5059074,0.0006758802],"about_ca_topic_score_codex":0.0038059726,"about_ca_topic_score_gemma":0.0068613407,"teacher_disagreement_score":0.66735923,"about_ca_system_score_codex":0.010018951,"about_ca_system_score_gemma":0.03088951,"threshold_uncertainty_score":0.8229728},"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":"reporting","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042310603,0.84527576,0.02450821,0.066298515,0.0051294845,0.0061212736,0.005023981,0.00023827875,0.0050939755],"genre_scores_gemma":[0.34445888,0.49464872,0.10295843,0.029814402,0.0030495555,0.01814527,0.005745105,0.00048467272,0.00069490744],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.30668244,0.30878747,0.31430495,0.013007452,0.054734416,0.002483258],"domain_scores_gemma":[0.084507085,0.59828526,0.1622074,0.035438824,0.11689345,0.0026679686],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6050041,0.0010341962,0.0052660727,0.028674064,0.002933112,0.012689837,0.0056355214,0.004073479,0.002563531],"category_scores_gemma":[0.80405957,0.0027583567,0.007317456,0.034265578,0.007961313,0.0126529755,0.00890201,0.0030660918,0.00065358164],"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":[0.0009642287,0.00010439708,0.09500838,0.5752153,0.008323107,0.0003477418,0.030595941,0.00040948993,0.0011486384,0.006306914,0.018537346,0.2630385],"study_design_scores_gemma":[0.0003993058,0.0004995328,0.06779142,0.790798,0.012965968,0.0012814138,0.01740429,0.0007954022,0.0010532133,0.007124309,0.09954258,0.0003446309],"about_ca_topic_score_codex":0.0070137084,"about_ca_topic_score_gemma":0.010868053,"teacher_disagreement_score":0.39499593,"about_ca_system_score_codex":0.009217963,"about_ca_system_score_gemma":0.033664007,"threshold_uncertainty_score":0.48710036},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958774,0.0006764335,0.001731441,0.00007344959,0.00002061848,0.00006582258,0.00043982844,0.000017666001,0.0010973371],"genre_scores_gemma":[0.99800736,0.00006465679,0.0013942223,0.00002111334,0.00001010769,0.00007090279,0.000278132,0.0000027061592,0.00015076704],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99670297,0.0012664682,0.00062061066,0.0002990449,0.00091002026,0.00020088915],"domain_scores_gemma":[0.9876658,0.005770716,0.004246532,0.0003465553,0.0012652577,0.0007052402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00364603,0.0004589925,0.0007122254,0.0008520238,0.00021516246,0.0007362272,0.0003625659,0.00053879875,0.0015808173],"category_scores_gemma":[0.016938027,0.00016334053,0.00080601947,0.00059166073,0.00037718745,0.0006530489,0.00062225154,0.00073593395,0.0004378452],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025504837,0.00016879055,0.97815186,0.00012283381,0.00019857135,0.00011715631,0.00020897246,0.0005123712,0.0013835513,0.00006309288,0.0003282407,0.01619413],"study_design_scores_gemma":[0.000096744916,0.0024168005,0.99294335,0.00002971013,0.00006318065,0.0005050804,0.00026688396,0.002558903,0.000719498,0.000119805045,0.00025422082,0.000025685753],"about_ca_topic_score_codex":0.0005835993,"about_ca_topic_score_gemma":0.0009851599,"teacher_disagreement_score":0.00364603,"about_ca_system_score_codex":0.00029065477,"about_ca_system_score_gemma":0.00026577327,"threshold_uncertainty_score":0.019282281},"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":"editorial","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007596753,0.3500746,0.0017599842,0.115978174,0.5198261,0.002362467,0.0074527822,0.00021951692,0.0015666041],"genre_scores_gemma":[0.026639316,0.5067244,0.01627365,0.30508766,0.10648147,0.009301546,0.0065891827,0.0006550762,0.022247775],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9388888,0.0132124815,0.033332728,0.0026224996,0.0110107735,0.00093267823],"domain_scores_gemma":[0.8122575,0.10030923,0.03421922,0.0038526927,0.047168374,0.0021929946],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.046556503,0.0030967293,0.007899488,0.015351871,0.001879275,0.0038618606,0.0034901777,0.008021448,0.016735042],"category_scores_gemma":[0.2828413,0.003228586,0.0068751834,0.012024338,0.0031365976,0.0047730836,0.0035314218,0.0071791383,0.0043048766],"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":[0.0004999264,0.00004214307,0.0011601769,0.31537828,0.004090418,0.00062309235,0.00055385195,0.000089562134,0.00022605229,0.0008927314,0.64093435,0.035509463],"study_design_scores_gemma":[0.0024253707,0.00025336072,0.008022244,0.47511643,0.03061841,0.0010693916,0.0012391285,0.0003118052,0.0006303692,0.002238163,0.47774902,0.00032639498],"about_ca_topic_score_codex":0.020555725,"about_ca_topic_score_gemma":0.050816316,"teacher_disagreement_score":0.9534435,"about_ca_system_score_codex":0.008652003,"about_ca_system_score_gemma":0.022661632,"threshold_uncertainty_score":0.24621725},"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":"editorial","genre_gemma":"protocol","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000286885,0.0017192289,0.009659934,0.14138325,0.79634684,0.0026169925,0.03680811,0.0023948855,0.0087838685],"genre_scores_gemma":[0.014505186,0.012603665,0.1527047,0.22612204,0.20147976,0.03783736,0.043062013,0.013920835,0.2977644],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93307143,0.022512812,0.02282958,0.0036658812,0.016230833,0.0016895456],"domain_scores_gemma":[0.5760886,0.1857712,0.022802006,0.029351912,0.18055817,0.005428133],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.055457402,0.0030243176,0.0032391024,0.011297273,0.0035550657,0.008055172,0.0048720017,0.009496476,0.26953292],"category_scores_gemma":[0.5724476,0.0028742084,0.003925071,0.009043325,0.0029444937,0.005220141,0.006995907,0.014552513,0.11419125],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010893527,0.0000101516325,0.000058220114,0.0015074753,0.000046028585,0.000051814644,0.00010326097,0.000038123355,0.00003544397,0.001022565,0.98932403,0.007693958],"study_design_scores_gemma":[0.0005693985,0.0000373821,0.0005519137,0.007533643,0.00021845175,0.00013072009,0.00015152605,0.00025949973,0.00024036317,0.0037551376,0.9864543,0.00009763926],"about_ca_topic_score_codex":0.009887896,"about_ca_topic_score_gemma":0.014306557,"teacher_disagreement_score":0.9445426,"about_ca_system_score_codex":0.0063464646,"about_ca_system_score_gemma":0.02357825,"threshold_uncertainty_score":0.9016774},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18768343,0.011189688,0.7398893,0.037593804,0.0007111852,0.00024456184,0.0015613806,0.00025595637,0.020870693],"genre_scores_gemma":[0.91473585,0.005770792,0.07358942,0.0028482943,0.0003449797,0.0002307061,0.00034779482,0.00012153322,0.0020105848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9869212,0.011568057,0.00015976011,0.0007173655,0.0004401642,0.00019351189],"domain_scores_gemma":[0.8945157,0.098159105,0.0033466464,0.0022822078,0.0012514655,0.0004448774],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021978498,0.0007367104,0.0009394291,0.0008062003,0.000425651,0.0015685107,0.0027591204,0.001968923,0.0039100815],"category_scores_gemma":[0.06274113,0.00039529902,0.0016707758,0.00086612254,0.0020986013,0.0019220383,0.001429171,0.0025281876,0.00028289636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052173116,0.0002108646,0.06359361,0.00095042714,0.0010994362,0.0013664307,0.001512133,0.39109984,0.0014144573,0.4774828,0.0047122887,0.0560359],"study_design_scores_gemma":[0.00019769622,0.0004819823,0.012372447,0.0011843733,0.0010347054,0.00045629707,0.00070065475,0.50720817,0.0017792941,0.45186514,0.022594232,0.00012503291],"about_ca_topic_score_codex":0.01497376,"about_ca_topic_score_gemma":0.010230542,"teacher_disagreement_score":0.9780215,"about_ca_system_score_codex":0.0015307167,"about_ca_system_score_gemma":0.0021946963,"threshold_uncertainty_score":0.11623478},"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":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016995094,0.010569505,0.10487823,0.066692606,0.6488231,0.0040823575,0.14033453,0.012542444,0.010377717],"genre_scores_gemma":[0.120175086,0.012585972,0.3455416,0.0687492,0.11871694,0.051307525,0.046821766,0.034145955,0.20195603],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87842435,0.06651134,0.02519918,0.010968654,0.013755138,0.0051413532],"domain_scores_gemma":[0.55437315,0.32769907,0.03048296,0.040364243,0.043126483,0.0039541195],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.109158896,0.007049889,0.0077560428,0.010248346,0.0023923102,0.010951217,0.008828884,0.010010394,0.34270728],"category_scores_gemma":[0.66213125,0.0050201514,0.014120416,0.01764291,0.003102318,0.008118094,0.0049858475,0.018303102,0.06588403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011258917,0.00003126147,0.0009341851,0.012847803,0.0024896346,0.00028528937,0.00032768378,0.000740225,0.00014217605,0.0059626303,0.95092803,0.024185034],"study_design_scores_gemma":[0.00919104,0.00035909278,0.00987074,0.0217382,0.008074555,0.0014547338,0.00046627296,0.011957809,0.0011145207,0.07199461,0.86310107,0.00067733263],"about_ca_topic_score_codex":0.011962451,"about_ca_topic_score_gemma":0.013545687,"teacher_disagreement_score":0.8908411,"about_ca_system_score_codex":0.0064481115,"about_ca_system_score_gemma":0.017401328,"threshold_uncertainty_score":0.9375483},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04603071,0.0015030737,0.74118924,0.0021209074,0.00035781864,0.0033366748,0.05135918,0.14986975,0.004232698],"genre_scores_gemma":[0.07702602,0.0005272246,0.872169,0.00052787235,0.00022544697,0.0019863385,0.044630434,0.00078788935,0.0021196909],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949051,0.0010444224,0.0011290212,0.0015267157,0.0012419239,0.00015291061],"domain_scores_gemma":[0.9858915,0.0070032547,0.0018812227,0.0013621392,0.0034548454,0.00040692906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004661462,0.0014182572,0.001090727,0.0056707067,0.00074494135,0.0022515506,0.0019175502,0.0010155835,0.004556406],"category_scores_gemma":[0.017195893,0.00062980637,0.00125461,0.0033262179,0.00040069607,0.002518205,0.002192393,0.0010569637,0.0042078146],"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":[0.0007800992,0.00065756874,0.014021879,0.0025367339,0.00025904409,0.001851643,0.0011327937,0.005209648,0.039726347,0.0024932874,0.09545905,0.8358719],"study_design_scores_gemma":[0.00123828,0.0010202808,0.054583527,0.0010970292,0.00072661415,0.005084754,0.0013485315,0.5814076,0.1336571,0.02303428,0.19620219,0.00059979386],"about_ca_topic_score_codex":0.0050846157,"about_ca_topic_score_gemma":0.00606077,"teacher_disagreement_score":0.0056707067,"about_ca_system_score_codex":0.0013401022,"about_ca_system_score_gemma":0.004365469,"threshold_uncertainty_score":0.024652421},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1322432,0.27832007,0.17297061,0.045123186,0.0064105233,0.2543646,0.058730397,0.003340581,0.048496865],"genre_scores_gemma":[0.23788042,0.060774755,0.28422803,0.0040074266,0.000559282,0.3888275,0.021297064,0.00064667605,0.001778881],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.32010445,0.3304684,0.2869058,0.007588488,0.05131107,0.0036218553],"domain_scores_gemma":[0.0754437,0.7211486,0.08501005,0.028668638,0.08758931,0.002139646],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50285614,0.0031187478,0.007357473,0.061142784,0.0043700766,0.011414583,0.0068015703,0.0043051136,0.006164576],"category_scores_gemma":[0.8201222,0.0030355006,0.009192057,0.059658095,0.0064609335,0.01361896,0.015395056,0.004222359,0.0013032729],"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":[0.0013261916,0.00022453816,0.028051872,0.484515,0.0037418674,0.00059985666,0.041841347,0.0021034589,0.0010262792,0.012476268,0.03330991,0.3907834],"study_design_scores_gemma":[0.0015080203,0.0007734212,0.046071142,0.7386082,0.005778055,0.0009771544,0.021808418,0.0023725983,0.0016327981,0.015244346,0.16451892,0.00070698396],"about_ca_topic_score_codex":0.005753833,"about_ca_topic_score_gemma":0.0105554685,"teacher_disagreement_score":0.49714386,"about_ca_system_score_codex":0.01607561,"about_ca_system_score_gemma":0.06594737,"threshold_uncertainty_score":0.6130669},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9261495,0.0017302326,0.061956342,0.00014351652,0.00012615153,0.00027249198,0.0071386807,0.0004615377,0.0020215528],"genre_scores_gemma":[0.95750886,0.0005183662,0.035160657,0.000054836895,0.00008116535,0.0003041662,0.005604529,0.000041453342,0.0007259289],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986217,0.0003393212,0.00022238409,0.00038471405,0.00035536435,0.00007648741],"domain_scores_gemma":[0.9944036,0.0020687894,0.0018185469,0.00038604706,0.0012133565,0.00010963837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019438011,0.0008042005,0.00079417625,0.0018443658,0.00022071112,0.0008872895,0.00052088505,0.0005360331,0.0010220434],"category_scores_gemma":[0.006672764,0.00017764501,0.00081012055,0.0016868149,0.00019447778,0.00035860398,0.00043089193,0.000360048,0.0005729732],"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":[0.0013605573,0.00025971196,0.8320154,0.0010404363,0.00049276307,0.00022610695,0.0004164494,0.005823736,0.012687601,0.0001771798,0.0024260846,0.14307399],"study_design_scores_gemma":[0.000039727416,0.0005886893,0.9453524,0.00015552102,0.00021105823,0.0007688713,0.00024362694,0.04300411,0.006733669,0.00042225877,0.002435547,0.00004451589],"about_ca_topic_score_codex":0.0024546003,"about_ca_topic_score_gemma":0.0052733715,"teacher_disagreement_score":0.0024546003,"about_ca_system_score_codex":0.00026039564,"about_ca_system_score_gemma":0.00032058268,"threshold_uncertainty_score":0.010279894},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13732418,0.059160214,0.74711907,0.022073152,0.0032428787,0.019539537,0.0011486958,0.00039261312,0.009999783],"genre_scores_gemma":[0.7200816,0.0035836343,0.2518316,0.006075222,0.000744526,0.016489245,0.00039377008,0.00022600435,0.00057431945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.06147397,0.8648139,0.0459518,0.007135177,0.020102073,0.00052300957],"domain_scores_gemma":[0.044779245,0.8928648,0.031452287,0.025121437,0.0051880786,0.0005941205],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7821333,0.0019868673,0.003959531,0.0036779218,0.0023723904,0.00684881,0.004250579,0.0061139893,0.003116537],"category_scores_gemma":[0.8790835,0.0017043184,0.010456837,0.0072834934,0.0069358237,0.0052789696,0.0063243927,0.00522998,0.00021269298],"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":[0.038902454,0.0015616202,0.16428319,0.047176987,0.11496767,0.0025154368,0.01900475,0.034954015,0.003471401,0.13097411,0.007970278,0.43421805],"study_design_scores_gemma":[0.0210771,0.01879683,0.17582175,0.052249603,0.09421946,0.005307138,0.004738022,0.1784701,0.01686356,0.38155192,0.04939149,0.0015130615],"about_ca_topic_score_codex":0.0010572402,"about_ca_topic_score_gemma":0.0010025764,"teacher_disagreement_score":0.21786672,"about_ca_system_score_codex":0.0044694026,"about_ca_system_score_gemma":0.007906435,"threshold_uncertainty_score":0.26866853},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012493461,0.00025602005,0.9951133,0.00078320655,0.000040061484,0.00006158355,0.000410801,0.00017952995,0.0019061046],"genre_scores_gemma":[0.11082701,0.0012056914,0.88115567,0.0003455141,0.00018545857,0.001085867,0.0016515986,0.00021345766,0.003329797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944537,0.003730332,0.0003148622,0.0006717358,0.0006126858,0.00021671038],"domain_scores_gemma":[0.9897077,0.0071495282,0.00093618996,0.00063025474,0.0012769143,0.00029935726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012291509,0.0013957043,0.0010869411,0.003268482,0.001157633,0.0039571156,0.0039659413,0.0019457306,0.0043543433],"category_scores_gemma":[0.026853627,0.0010179592,0.003234799,0.0031684677,0.0016133139,0.0038217905,0.0036136843,0.0027102847,0.0011001208],"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":[0.00001979635,0.000040747942,0.00302878,0.00011419936,0.00017009278,0.00014646257,0.00039410676,0.38622892,0.00016969115,0.58142513,0.0034671773,0.024794992],"study_design_scores_gemma":[0.000018419087,0.000040939038,0.00063333765,0.00008793005,0.0000570089,0.000085767504,0.00013701114,0.65356797,0.00007230949,0.33078846,0.014478812,0.000031987696],"about_ca_topic_score_codex":0.046266824,"about_ca_topic_score_gemma":0.03285992,"teacher_disagreement_score":0.046266824,"about_ca_system_score_codex":0.0030129505,"about_ca_system_score_gemma":0.006928214,"threshold_uncertainty_score":0.09199506},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979917,0.00025969703,0.00045195594,0.00009599091,0.000012264429,0.000036016783,0.0007230271,0.0000067158803,0.00042270555],"genre_scores_gemma":[0.99920136,0.00007785283,0.00027023547,0.000028636057,0.000010185195,0.00003900436,0.0003030667,0.000002975991,0.00006675637],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99440634,0.0026152069,0.00036858334,0.0011851517,0.0008209749,0.0006036721],"domain_scores_gemma":[0.9871159,0.003778331,0.0047294493,0.0017293312,0.0013649265,0.0012821454],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006134294,0.00046328446,0.00045773594,0.0024245428,0.0012882455,0.0015279927,0.001143869,0.00088293274,0.0013615264],"category_scores_gemma":[0.020296594,0.00059542834,0.001228442,0.0037937688,0.00073523785,0.0015862521,0.0017782638,0.0013030365,0.0002902184],"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":[0.000047622056,0.000028953487,0.99891794,0.000008553666,0.0001289434,0.00001492271,0.00016653574,0.000035657376,0.000019848057,0.000031929063,0.00007617955,0.00052294467],"study_design_scores_gemma":[0.00000712405,0.00010619426,0.9982368,0.000013407739,0.00009518629,0.00009331745,0.0005013715,0.0006354955,0.000024154584,0.00008230054,0.0001961578,0.000008577819],"about_ca_topic_score_codex":0.049971484,"about_ca_topic_score_gemma":0.04887668,"teacher_disagreement_score":0.9938657,"about_ca_system_score_codex":0.0016928028,"about_ca_system_score_gemma":0.0014781527,"threshold_uncertainty_score":0.09936124},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9882637,0.00008597728,0.0050202166,0.0003767357,0.000037731257,0.0033117037,0.00008953729,0.0000757595,0.00273859],"genre_scores_gemma":[0.9679684,0.00017125499,0.026789082,0.00012061077,0.000021542439,0.0039041701,0.00014903543,0.00001969437,0.0008562292],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9655758,0.023505818,0.0022116827,0.0014777153,0.00570169,0.0015273504],"domain_scores_gemma":[0.93521875,0.031293888,0.006247233,0.0064037307,0.018129118,0.0027072986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06541259,0.00057939626,0.0006075609,0.00087434606,0.0021744054,0.0018355708,0.0018529086,0.00066183676,0.0008785521],"category_scores_gemma":[0.10963292,0.0005521739,0.00067206845,0.0007858284,0.0022938717,0.0013139885,0.0037719482,0.00126913,0.00022090568],"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":[0.0011599802,0.005165687,0.34889144,0.0011389835,0.000076882665,0.0003651387,0.14069483,0.001233703,0.004731245,0.0007381113,0.0021680037,0.49363592],"study_design_scores_gemma":[0.00036919487,0.010603234,0.91352624,0.0007072585,0.0001220795,0.00031711385,0.050541177,0.0043085483,0.005668346,0.00055011973,0.013168721,0.00011789942],"about_ca_topic_score_codex":0.023163782,"about_ca_topic_score_gemma":0.04823456,"teacher_disagreement_score":0.06541259,"about_ca_system_score_codex":0.008183272,"about_ca_system_score_gemma":0.013919511,"threshold_uncertainty_score":0.34593898},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15180504,0.0014065005,0.83975506,0.0036560947,0.00022968256,0.00039490545,0.0005891733,0.00045348384,0.0017100882],"genre_scores_gemma":[0.8588686,0.00042357427,0.13860227,0.0005884826,0.000086441505,0.00050355966,0.0005552418,0.00012339865,0.0002484699],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9485843,0.043310508,0.0014981953,0.004185739,0.0019174878,0.00050379976],"domain_scores_gemma":[0.5745705,0.37775323,0.020533217,0.021346644,0.004923861,0.0008725809],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08805387,0.001323333,0.0020177432,0.002820725,0.0013890179,0.003076114,0.0027695363,0.002751088,0.0029532278],"category_scores_gemma":[0.37414634,0.0006792558,0.002798266,0.0026080045,0.0032736203,0.004476645,0.0024596925,0.0022868381,0.00058831094],"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":[0.0016709315,0.00024645816,0.4717043,0.0020541481,0.0051309573,0.0006792369,0.005028108,0.239607,0.0008508704,0.07224217,0.0057338174,0.19505195],"study_design_scores_gemma":[0.00023342247,0.00040523708,0.036916338,0.0011135772,0.0010394282,0.00074106234,0.0010156143,0.59376377,0.0012488003,0.3576053,0.0057834242,0.0001340109],"about_ca_topic_score_codex":0.007834692,"about_ca_topic_score_gemma":0.004920836,"teacher_disagreement_score":0.9119461,"about_ca_system_score_codex":0.001943322,"about_ca_system_score_gemma":0.003010793,"threshold_uncertainty_score":0.46567893},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15988968,0.009952899,0.81043863,0.009389939,0.0011779104,0.00091488153,0.001283691,0.0012791957,0.0056731896],"genre_scores_gemma":[0.7413529,0.0016315938,0.2508091,0.002894072,0.00030838617,0.0013132009,0.0007342694,0.0004434108,0.00051306136],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.3884761,0.55563307,0.021925826,0.014502731,0.01750671,0.0019556163],"domain_scores_gemma":[0.080098726,0.8691796,0.023744352,0.018551657,0.0077419193,0.00068373035],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38852847,0.0018197907,0.0029137614,0.0028247624,0.0023387244,0.005103214,0.0042545386,0.004778779,0.0031516398],"category_scores_gemma":[0.75840646,0.0019460734,0.004839166,0.0050600944,0.0040075346,0.0057807565,0.004320573,0.007028648,0.00063507835],"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":[0.0048552635,0.00050020986,0.4295463,0.006948073,0.012528361,0.003549772,0.009052018,0.18014587,0.0025059283,0.03237899,0.016760502,0.30122867],"study_design_scores_gemma":[0.00096979475,0.003035173,0.15077697,0.012003935,0.006983947,0.0070301397,0.0030634624,0.6581132,0.012381442,0.12143966,0.023183051,0.0010191805],"about_ca_topic_score_codex":0.0063801934,"about_ca_topic_score_gemma":0.0061074765,"teacher_disagreement_score":0.38852847,"about_ca_system_score_codex":0.003253286,"about_ca_system_score_gemma":0.0041114986,"threshold_uncertainty_score":0.7540533},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065422095,0.0055581713,0.7701047,0.06506625,0.00077555224,0.008588992,0.0005104968,0.00067436567,0.08329928],"genre_scores_gemma":[0.28549185,0.0021646952,0.69923425,0.0026635146,0.00007450637,0.00797104,0.00053748826,0.00022255929,0.0016400144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8115161,0.14716281,0.010334369,0.0065233633,0.018582288,0.0058810837],"domain_scores_gemma":[0.792116,0.13481179,0.012893865,0.019012887,0.034912813,0.006252625],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.19090587,0.0020694702,0.0022757754,0.02326742,0.010471976,0.023924025,0.0064937025,0.0059882947,0.00808202],"category_scores_gemma":[0.19640404,0.0018870312,0.0041356254,0.015168029,0.016643822,0.037729096,0.023091588,0.010955479,0.0013428765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011107508,0.00041795074,0.0086959135,0.004165856,0.00018339576,0.0004801545,0.07747554,0.004054228,0.00086341467,0.7430637,0.00864591,0.1518429],"study_design_scores_gemma":[0.00017445348,0.0003071935,0.004414711,0.020939594,0.00036103054,0.00052465376,0.19011994,0.019385803,0.0024492748,0.6400214,0.12103959,0.00026239117],"about_ca_topic_score_codex":0.009218825,"about_ca_topic_score_gemma":0.014579764,"teacher_disagreement_score":0.19090587,"about_ca_system_score_codex":0.037002116,"about_ca_system_score_gemma":0.07224013,"threshold_uncertainty_score":0.9977571},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99595624,0.00027084333,0.0013928663,0.00024599847,0.000007005237,0.00005317792,0.0015285963,0.000041336127,0.0005038255],"genre_scores_gemma":[0.99509984,0.0001480247,0.0026481687,0.000038892253,0.0000038328176,0.000017255961,0.0017570241,0.0000034614438,0.00028362733],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969673,0.00006839016,0.000021068834,0.00006793694,0.00006312197,0.000082694816],"domain_scores_gemma":[0.9987984,0.00028299022,0.00014142045,0.00003946315,0.0005787332,0.00015891613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008772547,0.0003605887,0.00032301,0.00093391066,0.0007487019,0.00060879614,0.0006167508,0.0002951639,0.0007175899],"category_scores_gemma":[0.0030502698,0.00017187494,0.00038707056,0.0008936198,0.00026142102,0.0001645569,0.000311466,0.00041489734,0.00013668647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022990062,0.00009720977,0.9690027,0.000038000206,0.000088172244,0.000085766536,0.000112427915,0.008907455,0.00036758045,0.00007314275,0.001237471,0.019760158],"study_design_scores_gemma":[0.00005412485,0.000097559445,0.84639645,0.000050843744,0.00008406574,0.00010176709,0.00047178738,0.15121941,0.00053268066,0.00028608213,0.0006823526,0.000022875322],"about_ca_topic_score_codex":0.9386492,"about_ca_topic_score_gemma":0.9517569,"teacher_disagreement_score":0.061350822,"about_ca_system_score_codex":0.007154099,"about_ca_system_score_gemma":0.009611264,"threshold_uncertainty_score":0.12342423},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79852945,0.0010128985,0.19320533,0.00087499944,0.00014639278,0.0016979503,0.0010804653,0.00019813782,0.0032543552],"genre_scores_gemma":[0.9517862,0.00053496956,0.044397987,0.00015896212,0.000057756108,0.0019567253,0.00059634715,0.00002326933,0.00048772962],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9749655,0.022027075,0.0007432323,0.0009811434,0.00069984735,0.0005832773],"domain_scores_gemma":[0.71702707,0.26375565,0.008462507,0.0056668515,0.004036842,0.001051087],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.047514807,0.0013491053,0.0017205022,0.0016839476,0.000548186,0.0013448597,0.0026028412,0.0021121367,0.0031860208],"category_scores_gemma":[0.10284571,0.0007340162,0.0042494447,0.0017276313,0.0010947692,0.0015943713,0.0013443967,0.0024482661,0.00021870909],"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":[0.0046610683,0.0029985257,0.059488945,0.0009290568,0.0037860642,0.00051752594,0.0005785266,0.88621265,0.0007275253,0.016871568,0.0010464462,0.022182142],"study_design_scores_gemma":[0.00068359385,0.0029269254,0.0063668936,0.00016382847,0.0010361045,0.000107567954,0.00023327685,0.9806045,0.00097165006,0.0060461927,0.0007979091,0.00006157194],"about_ca_topic_score_codex":0.009100724,"about_ca_topic_score_gemma":0.003912472,"teacher_disagreement_score":0.9524852,"about_ca_system_score_codex":0.0022665123,"about_ca_system_score_gemma":0.0021888658,"threshold_uncertainty_score":0.2512853},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13338858,0.0137649,0.049506746,0.7426787,0.0049876156,0.0012422281,0.0000490611,0.0001903639,0.05419174],"genre_scores_gemma":[0.88319886,0.005524898,0.023285916,0.081705436,0.0009633071,0.0015954563,0.00004562031,0.00018257435,0.0034979342],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.4328462,0.529884,0.004673322,0.006890778,0.016160285,0.00954549],"domain_scores_gemma":[0.49493343,0.36529085,0.02521145,0.026735906,0.034584507,0.053243812],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28937107,0.00093304255,0.0014510632,0.0029526213,0.050198648,0.031405043,0.005846933,0.014997853,0.0034622948],"category_scores_gemma":[0.2740494,0.0014166961,0.0011576959,0.003159046,0.1434323,0.035994984,0.028403433,0.032890774,0.0010663926],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022412187,0.000107624364,0.0017797516,0.00040760197,0.000024008197,0.0007027259,0.9113768,0.00014029945,0.00034651667,0.060491856,0.01222561,0.012374749],"study_design_scores_gemma":[0.00001965609,0.00007348374,0.0006713016,0.0020281042,0.000010241332,0.0009661872,0.842534,0.00031437693,0.0002860786,0.054152045,0.098887764,0.000056834815],"about_ca_topic_score_codex":0.0037448457,"about_ca_topic_score_gemma":0.0043902164,"teacher_disagreement_score":0.7106289,"about_ca_system_score_codex":0.012533855,"about_ca_system_score_gemma":0.06698619,"threshold_uncertainty_score":0.876332},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54723334,0.013999991,0.16101407,0.011456138,0.0039305673,0.21942858,0.0015656874,0.00053417054,0.04083755],"genre_scores_gemma":[0.8085032,0.0021320374,0.09101324,0.0069117057,0.0006398406,0.088237226,0.00053280045,0.00010603538,0.0019238964],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.15954258,0.7854063,0.017684752,0.008854347,0.02651381,0.0019982487],"domain_scores_gemma":[0.11747097,0.75109684,0.066883504,0.049603835,0.013143996,0.0018009035],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5919026,0.0019796933,0.0022589131,0.0022826642,0.00362869,0.00448251,0.0059484015,0.005905633,0.012509741],"category_scores_gemma":[0.70566636,0.0023570275,0.0031937638,0.0030497336,0.012619214,0.006189311,0.004407131,0.0038316443,0.00182911],"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":[0.16088597,0.03794977,0.17244111,0.037035093,0.012256556,0.0005400988,0.06145205,0.0037641507,0.0017064669,0.060863875,0.0144739775,0.43663087],"study_design_scores_gemma":[0.15649872,0.31811735,0.21350501,0.055208195,0.015890013,0.0016122592,0.022650806,0.042971436,0.015041523,0.070571214,0.08677648,0.001157061],"about_ca_topic_score_codex":0.005433397,"about_ca_topic_score_gemma":0.004602185,"teacher_disagreement_score":0.4080974,"about_ca_system_score_codex":0.0059598875,"about_ca_system_score_gemma":0.012081254,"threshold_uncertainty_score":0.5032568},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98832303,0.00022033596,0.007710224,0.00015102337,0.000026014997,0.0002765657,0.001122297,0.00005277458,0.0021177635],"genre_scores_gemma":[0.99361163,0.000059901835,0.0044686007,0.000018446022,0.0000043763494,0.00031153092,0.0014196023,0.00001582451,0.00009010565],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97924817,0.014791507,0.0014787149,0.0016167065,0.0022835652,0.0005814096],"domain_scores_gemma":[0.96587956,0.022285292,0.004134832,0.003536416,0.0037506772,0.00041328234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026832761,0.00092649163,0.0008655549,0.0062814048,0.00061526016,0.0016973402,0.00097537594,0.0007223237,0.0020108693],"category_scores_gemma":[0.04516897,0.00042467727,0.003751304,0.005713585,0.0013434611,0.0010381809,0.0022954743,0.0009386386,0.00038903786],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019752934,0.00009237677,0.9651901,0.00013744409,0.0009487881,0.00010694688,0.0021474832,0.005509437,0.00031940377,0.0015728526,0.00081052864,0.022967111],"study_design_scores_gemma":[0.00006779376,0.00046149024,0.96929306,0.0001707566,0.00019115608,0.00020009272,0.003073811,0.022453947,0.00033286682,0.0023343512,0.0013799414,0.000040639126],"about_ca_topic_score_codex":0.0031300131,"about_ca_topic_score_gemma":0.0018376075,"teacher_disagreement_score":0.026832761,"about_ca_system_score_codex":0.0015711602,"about_ca_system_score_gemma":0.0010276013,"threshold_uncertainty_score":0.14190692},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07827919,0.00073965476,0.9172135,0.00045348384,0.000077295175,0.00045933196,0.00023286848,0.00071605924,0.0018285998],"genre_scores_gemma":[0.60245746,0.0002625457,0.39516172,0.00027181854,0.00006043794,0.00072844943,0.0005691375,0.00022768725,0.00026063537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8915454,0.090630606,0.0033619446,0.004025786,0.009394175,0.0010420446],"domain_scores_gemma":[0.40703827,0.5301006,0.016181212,0.031141136,0.014315984,0.0012228136],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.120044544,0.0015266364,0.0018266384,0.0035879554,0.0012505869,0.0021668319,0.003970091,0.0031434158,0.002299676],"category_scores_gemma":[0.49260175,0.0009699081,0.0024766452,0.002309997,0.0033856186,0.0032047338,0.0035223172,0.0037845098,0.00056038593],"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":[0.0036194657,0.00051404873,0.07861428,0.0010815291,0.0024443723,0.0009234581,0.0023890652,0.4486287,0.0034195355,0.13414398,0.005656926,0.31856468],"study_design_scores_gemma":[0.00035403515,0.0008100785,0.016927928,0.00051991775,0.00031449643,0.0008419259,0.00047546544,0.87439615,0.0061405236,0.09566,0.0033343337,0.0002250127],"about_ca_topic_score_codex":0.0036409374,"about_ca_topic_score_gemma":0.0020644355,"teacher_disagreement_score":0.8799555,"about_ca_system_score_codex":0.001613095,"about_ca_system_score_gemma":0.001983438,"threshold_uncertainty_score":0.63486385},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6769299,0.0004901849,0.30315614,0.0070672543,0.00003438269,0.00084754126,0.0005950121,0.00016812832,0.010711463],"genre_scores_gemma":[0.9263568,0.00018786051,0.07190772,0.0004175924,0.000023532815,0.00029762016,0.00018556387,0.00003548134,0.0005878044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.94566184,0.04924624,0.0011816365,0.0011641931,0.0018973049,0.00084875384],"domain_scores_gemma":[0.742464,0.2437544,0.0050159586,0.0037464255,0.0041624345,0.0008566821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048747987,0.0008916185,0.00057295815,0.0011289158,0.0014068894,0.001765425,0.0016601296,0.0034461287,0.0033471833],"category_scores_gemma":[0.09145939,0.0004251593,0.0011215808,0.0010367294,0.0015641616,0.0020128933,0.0028966668,0.002322243,0.00042636413],"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":[0.005096677,0.0033623814,0.0818232,0.0033765463,0.00062247505,0.032412313,0.116025835,0.39201623,0.015842285,0.04841272,0.010289418,0.29071996],"study_design_scores_gemma":[0.000832891,0.0019786744,0.015032772,0.0009423761,0.00026526087,0.0073271585,0.044687487,0.8061452,0.012160291,0.0792846,0.031070158,0.00027322245],"about_ca_topic_score_codex":0.0039436608,"about_ca_topic_score_gemma":0.0054616258,"teacher_disagreement_score":0.048747987,"about_ca_system_score_codex":0.0033022498,"about_ca_system_score_gemma":0.0020738728,"threshold_uncertainty_score":0.25780708},"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":"methods","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09561404,0.26227573,0.41139585,0.09665759,0.015043254,0.0971649,0.004285222,0.0016595662,0.01590391],"genre_scores_gemma":[0.34953982,0.009885826,0.5667381,0.015534073,0.0013708196,0.05506942,0.0010711607,0.00034128662,0.000449504],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.054751553,0.7070496,0.16889411,0.020280378,0.04780091,0.0012234155],"domain_scores_gemma":[0.02350759,0.76116,0.072629035,0.06954981,0.07182716,0.001326371],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8395872,0.0036332961,0.010907131,0.023531634,0.007687437,0.019235447,0.011811557,0.013832906,0.0037057067],"category_scores_gemma":[0.96014374,0.0063708653,0.019648591,0.019588973,0.013540293,0.025490815,0.017323377,0.008421957,0.0010666598],"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":[0.011818379,0.0007695835,0.11389237,0.24087095,0.13673796,0.0015448964,0.0652461,0.006998052,0.002280604,0.050977644,0.025948092,0.34291542],"study_design_scores_gemma":[0.02276072,0.0065919207,0.04686452,0.37748736,0.12789458,0.004626591,0.019738492,0.040587705,0.007324793,0.21357366,0.12932996,0.0032196522],"about_ca_topic_score_codex":0.004293307,"about_ca_topic_score_gemma":0.007601422,"teacher_disagreement_score":0.16041279,"about_ca_system_score_codex":0.012889008,"about_ca_system_score_gemma":0.032604557,"threshold_uncertainty_score":0.19781756},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7900816,0.01278409,0.19070143,0.0026807375,0.00027003398,0.00033565605,0.0006790048,0.0003253861,0.0021420096],"genre_scores_gemma":[0.9742556,0.0021491188,0.022636218,0.00016153452,0.00011206822,0.00010704961,0.00032334443,0.00002912685,0.0002259171],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892091,0.008553977,0.00039661294,0.00075517927,0.00087704393,0.00020815276],"domain_scores_gemma":[0.88169885,0.10962539,0.0035262783,0.0020550287,0.002414187,0.00068026595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043433703,0.0008180462,0.0013197548,0.00257657,0.0003258655,0.0013100703,0.0011220616,0.00086396706,0.0006649706],"category_scores_gemma":[0.07420229,0.0003667855,0.0023048916,0.0015605778,0.0005162125,0.0014041228,0.0006931462,0.0015951473,0.0001299069],"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":[0.0040918714,0.0004986598,0.32303083,0.000676752,0.005086642,0.00024876875,0.00047405667,0.5364561,0.00031849736,0.0095064165,0.0020517984,0.11755955],"study_design_scores_gemma":[0.00010656261,0.0007655322,0.023066524,0.00015006699,0.00044786712,0.00010704133,0.00010392784,0.96904784,0.00020012166,0.005382646,0.0005759089,0.000045971872],"about_ca_topic_score_codex":0.007836787,"about_ca_topic_score_gemma":0.004845437,"teacher_disagreement_score":0.043433703,"about_ca_system_score_codex":0.0011833699,"about_ca_system_score_gemma":0.001851766,"threshold_uncertainty_score":0.22970217},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94548565,0.028865064,0.008909174,0.0015980133,0.00091059355,0.010003385,0.0019127065,0.00016854923,0.002146811],"genre_scores_gemma":[0.9822282,0.0013549299,0.004698547,0.0005678081,0.00020913548,0.009375395,0.0008241689,0.000032783253,0.000709086],"study_design_codex":"randomized_trial","study_design_gemma":"meta_analysis","domain_scores_codex":[0.84043723,0.14073521,0.006978294,0.004658363,0.005501937,0.0016890678],"domain_scores_gemma":[0.7940887,0.17313066,0.020049712,0.007560103,0.0031719028,0.001999018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11217903,0.002169919,0.009829299,0.0020297146,0.00048188274,0.0023361738,0.0018428654,0.0036130939,0.0055014626],"category_scores_gemma":[0.13749121,0.0008434549,0.015277992,0.0013651593,0.0035791306,0.0033069898,0.0022574414,0.0040269606,0.00030541793],"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":[0.9450425,0.0005388066,0.011403583,0.0036026535,0.024707207,0.00007318212,0.00015962296,0.0014391216,0.0004739455,0.0005878829,0.00045086327,0.011520699],"study_design_scores_gemma":[0.71729726,0.15701887,0.052759875,0.001484313,0.047464885,0.00022149071,0.00034335745,0.014885303,0.0011280165,0.0045368634,0.0026036273,0.00025611153],"about_ca_topic_score_codex":0.00081620016,"about_ca_topic_score_gemma":0.0010295676,"teacher_disagreement_score":0.11217903,"about_ca_system_score_codex":0.0022057362,"about_ca_system_score_gemma":0.0019196915,"threshold_uncertainty_score":0.5932665},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022550642,0.9940394,0.00045318523,0.00039049648,0.00017704348,0.0015880998,0.0005796983,0.000013835704,0.00050317164],"genre_scores_gemma":[0.020296788,0.97311306,0.0022120737,0.00058342854,0.000084629886,0.0031093867,0.0004346872,0.00000931399,0.0001566733],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.973152,0.009765047,0.010955259,0.0011886628,0.0044636093,0.0004754939],"domain_scores_gemma":[0.9229476,0.05448237,0.012845705,0.0014519315,0.0077486765,0.00052367675],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021985676,0.001967138,0.009379626,0.022334248,0.001276288,0.0039159525,0.0027904676,0.0020787348,0.003953026],"category_scores_gemma":[0.110060595,0.0013805125,0.009121926,0.020351443,0.0014447675,0.0038518035,0.0025324782,0.0015283703,0.00039824613],"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":[0.000099910714,0.000015808471,0.00088144455,0.9596636,0.004561371,0.00009747257,0.00041023907,0.000068172834,0.000103855135,0.0002455293,0.00092952186,0.03292308],"study_design_scores_gemma":[0.00010160865,0.00013454247,0.0036923978,0.95467633,0.029791057,0.00026775472,0.00042297435,0.000060219223,0.00010887978,0.00021355698,0.010500987,0.000029821513],"about_ca_topic_score_codex":0.011240856,"about_ca_topic_score_gemma":0.038455416,"teacher_disagreement_score":0.97801435,"about_ca_system_score_codex":0.0073694033,"about_ca_system_score_gemma":0.026232807,"threshold_uncertainty_score":0.11627281},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97924554,0.0011138937,0.0168707,0.0005684456,0.00003237268,0.000031590644,0.0010351699,0.00022517219,0.0008772003],"genre_scores_gemma":[0.99609214,0.00015121959,0.0029870807,0.00004220692,0.000019805997,0.000006284775,0.00058263,0.000004661655,0.000114051974],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911886,0.00036799593,0.000047027443,0.00016823034,0.00021655948,0.00008129209],"domain_scores_gemma":[0.9960276,0.0021712114,0.00085931615,0.00035751698,0.00042294242,0.00016148952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027513443,0.0005305454,0.00041168774,0.0010109156,0.0002227591,0.0007664381,0.00043189968,0.00043206068,0.00050045294],"category_scores_gemma":[0.0078048846,0.00012673184,0.0006328627,0.0007887239,0.0002614609,0.00034778318,0.00037687042,0.0006630761,0.00016958061],"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":[0.00021339646,0.000110140485,0.9315102,0.000056369554,0.0005099806,0.000057888657,0.00008118965,0.036824603,0.0003867034,0.00014924692,0.0006767395,0.0294236],"study_design_scores_gemma":[0.00003742608,0.00022421623,0.7591873,0.00006158729,0.0003078434,0.00017840907,0.00013112875,0.23667416,0.0009324181,0.0015353123,0.00069367397,0.00003645977],"about_ca_topic_score_codex":0.03287916,"about_ca_topic_score_gemma":0.053087946,"teacher_disagreement_score":0.03287916,"about_ca_system_score_codex":0.0009842212,"about_ca_system_score_gemma":0.0015775559,"threshold_uncertainty_score":0.06537557},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025599573,0.00012127571,0.9732668,0.00024732316,0.000025543442,0.00010985726,0.00012745416,0.00012155036,0.0003806214],"genre_scores_gemma":[0.56820375,0.0007229902,0.42591378,0.00023564664,0.00013710323,0.00093348336,0.00076941215,0.00012024684,0.0029636323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922009,0.005522247,0.0002434742,0.0011176186,0.0005848351,0.00033091087],"domain_scores_gemma":[0.9502163,0.041638143,0.003222288,0.0031802615,0.0013102238,0.00043276907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021073407,0.0011734036,0.0019736325,0.0015962641,0.000557169,0.0017015395,0.0031557055,0.0018430934,0.003946681],"category_scores_gemma":[0.08568963,0.0009845059,0.0024031638,0.0019814586,0.0022123526,0.0030510023,0.002225081,0.0034439005,0.0003995152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027728986,0.00017416965,0.008621587,0.0001700077,0.00043352004,0.00023198988,0.00040314515,0.7335675,0.0004653642,0.1982689,0.0011890003,0.056197487],"study_design_scores_gemma":[0.00006613564,0.00006654853,0.0011429454,0.000036563615,0.00009235252,0.000047332444,0.000051966428,0.8979064,0.0002786016,0.099601924,0.0006836414,0.0000255477],"about_ca_topic_score_codex":0.009949985,"about_ca_topic_score_gemma":0.0063325814,"teacher_disagreement_score":0.021073407,"about_ca_system_score_codex":0.0018706929,"about_ca_system_score_gemma":0.0028876308,"threshold_uncertainty_score":0.11144811},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38124686,0.5751117,0.008294815,0.007927663,0.00066904613,0.0008907196,0.02127495,0.0001769179,0.004407276],"genre_scores_gemma":[0.8767706,0.10491138,0.006087929,0.002239546,0.00031500089,0.0013978281,0.007897631,0.00008212088,0.0002979125],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.82034624,0.057596706,0.09345035,0.007625639,0.019719942,0.0012610673],"domain_scores_gemma":[0.2696631,0.5088326,0.16271493,0.022678655,0.034149967,0.0019607916],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16078798,0.00056216447,0.0025103039,0.016581355,0.0006977505,0.0039911615,0.0021774948,0.0012821802,0.001711085],"category_scores_gemma":[0.42680672,0.0010023577,0.0037793487,0.019360717,0.0015092151,0.0054446794,0.0032556248,0.0011633802,0.00029365154],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080438034,0.00007660295,0.78177476,0.10700394,0.010882592,0.0004671973,0.00593629,0.00041610448,0.0005592483,0.0009791008,0.005075402,0.086024314],"study_design_scores_gemma":[0.00021933539,0.00074108876,0.82086545,0.12065099,0.014894779,0.0031051394,0.0075805243,0.0011445907,0.0009776519,0.0013299044,0.028294202,0.00019635147],"about_ca_topic_score_codex":0.003013174,"about_ca_topic_score_gemma":0.0033214223,"teacher_disagreement_score":0.839212,"about_ca_system_score_codex":0.0017381618,"about_ca_system_score_gemma":0.0043803,"threshold_uncertainty_score":0.8503383},"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":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98658746,0.0068342914,0.00065673795,0.00070233253,0.0000492826,0.0005086021,0.00334112,0.000027254646,0.0012930477],"genre_scores_gemma":[0.9944845,0.0017153831,0.0010084251,0.00020320744,0.00006210339,0.00052880344,0.0018539792,0.00001050787,0.00013306655],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9298807,0.014486728,0.036879115,0.0051796334,0.012391557,0.0011822657],"domain_scores_gemma":[0.7134134,0.114282124,0.12858662,0.010825359,0.029780816,0.0031116842],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.052958116,0.00049741636,0.0019845937,0.016928097,0.0014610897,0.002752127,0.0013511414,0.001246676,0.0025742338],"category_scores_gemma":[0.16796108,0.0007948519,0.0025014612,0.027169244,0.0012697744,0.0041374736,0.0022273096,0.00086197426,0.0003850174],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012562648,0.00005158883,0.9912555,0.0012947582,0.0006838631,0.00005911987,0.0012724573,0.000037268517,0.00009312213,0.000089256,0.00036080313,0.004676745],"study_design_scores_gemma":[0.00004779655,0.00016211718,0.99373215,0.0004589187,0.0007222232,0.00038351462,0.002467784,0.00040724923,0.00014493159,0.00013702297,0.0012975797,0.000038612],"about_ca_topic_score_codex":0.0031775332,"about_ca_topic_score_gemma":0.0030171,"teacher_disagreement_score":0.94704187,"about_ca_system_score_codex":0.002037848,"about_ca_system_score_gemma":0.0030198896,"threshold_uncertainty_score":0.28007263},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85290766,0.0034869665,0.13541326,0.0011297157,0.00026839244,0.00022891344,0.0035398148,0.00072327734,0.0023018743],"genre_scores_gemma":[0.96650195,0.00073078735,0.027105644,0.00022525866,0.00007454649,0.0002123703,0.0039582625,0.00006839512,0.0011227565],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981669,0.0010593301,0.00013053633,0.00035835768,0.00017100763,0.000113868395],"domain_scores_gemma":[0.9870784,0.009513769,0.0006831435,0.00074175675,0.0016835831,0.00029922018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014186597,0.0014144212,0.0013833249,0.0013163796,0.00035581528,0.00090250897,0.0019888529,0.0010158791,0.0016956507],"category_scores_gemma":[0.019653795,0.0005056074,0.0019540882,0.0008093597,0.0003803993,0.0011826019,0.0012909534,0.0018033878,0.00036285547],"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":[0.002319626,0.00030904924,0.07691109,0.0002256163,0.0016282776,0.00011465341,0.0001412105,0.85353667,0.00033346852,0.0019418723,0.0022694983,0.060268983],"study_design_scores_gemma":[0.000051041236,0.00016198115,0.0059755226,0.00003256626,0.0001388734,0.000020695301,0.00001981513,0.9922792,0.00016111102,0.0008832876,0.00025640006,0.000019427405],"about_ca_topic_score_codex":0.030396482,"about_ca_topic_score_gemma":0.019064106,"teacher_disagreement_score":0.030396482,"about_ca_system_score_codex":0.0013988694,"about_ca_system_score_gemma":0.0018274105,"threshold_uncertainty_score":0.07502675},"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":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8030317,0.17063263,0.008127021,0.005710863,0.0003848542,0.001760512,0.0071862903,0.00025556504,0.0029105572],"genre_scores_gemma":[0.989131,0.0034953041,0.0022863904,0.0009515113,0.00013838724,0.0013675588,0.0023009717,0.000057216588,0.00027171607],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.81701773,0.13925564,0.018157193,0.01175756,0.010386584,0.0034252235],"domain_scores_gemma":[0.71479315,0.14805773,0.09587036,0.024481734,0.013615154,0.003181858],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13507013,0.0008783278,0.0029957087,0.0035135413,0.0015950894,0.0047879815,0.0017007622,0.0018660671,0.0043488233],"category_scores_gemma":[0.16422288,0.0009269812,0.0055113905,0.0077511347,0.0015896396,0.0042331833,0.0029118957,0.0017213253,0.0004577416],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014231044,0.00030651718,0.8842062,0.018506829,0.047989827,0.000546915,0.0028621773,0.001362194,0.00043963545,0.0013727344,0.006383187,0.02179288],"study_design_scores_gemma":[0.003243184,0.0016657711,0.9357922,0.010730705,0.035293225,0.0006156075,0.0011289512,0.0029701556,0.0003362972,0.0015943632,0.0064737946,0.00015575138],"about_ca_topic_score_codex":0.011068715,"about_ca_topic_score_gemma":0.017175106,"teacher_disagreement_score":0.86492985,"about_ca_system_score_codex":0.00303801,"about_ca_system_score_gemma":0.0068314145,"threshold_uncertainty_score":0.7143277},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018721681,0.0010971384,0.9778195,0.00036306356,0.00013761061,0.00044684528,0.0002729504,0.00012092515,0.0010202543],"genre_scores_gemma":[0.49176136,0.0015442002,0.49972585,0.0006216119,0.0003787912,0.003824047,0.00091935636,0.00015460193,0.0010701495],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9577682,0.03215823,0.0018412361,0.0028775572,0.0050949454,0.00025986857],"domain_scores_gemma":[0.7468288,0.2247678,0.011253625,0.011487156,0.005268731,0.0003938546],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0698209,0.000989322,0.0014999299,0.002399003,0.0002597262,0.0017391755,0.0014998534,0.0014152161,0.0022672843],"category_scores_gemma":[0.23453829,0.0003338413,0.001854765,0.0016726061,0.0018790781,0.0020775995,0.0015691709,0.0023737836,0.00037663593],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019259498,0.0004936564,0.06568654,0.004198247,0.005549913,0.00040310738,0.0010176324,0.13948059,0.0061101494,0.22211449,0.008042482,0.54497725],"study_design_scores_gemma":[0.0006615634,0.0026239934,0.042392816,0.0018503221,0.002224178,0.0013443856,0.00033308595,0.5546266,0.008724281,0.3659447,0.018960511,0.00031358743],"about_ca_topic_score_codex":0.00042197536,"about_ca_topic_score_gemma":0.00023926559,"teacher_disagreement_score":0.9301791,"about_ca_system_score_codex":0.0007800667,"about_ca_system_score_gemma":0.0012543047,"threshold_uncertainty_score":0.36925262},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005351924,0.0000442575,0.9981377,0.000052979045,0.000016087628,0.00010688149,0.000050379265,0.0006757695,0.00038073095],"genre_scores_gemma":[0.02000935,0.00010507449,0.97758526,0.000089970075,0.000027585678,0.0010482208,0.00015281324,0.0006291496,0.00035259765],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9754508,0.019910743,0.0011287236,0.00094997714,0.0023289341,0.0002307145],"domain_scores_gemma":[0.83556765,0.14503612,0.0047177095,0.007395404,0.006600362,0.00068270596],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03359545,0.0023281777,0.0017568276,0.0054830434,0.0013385932,0.0023227083,0.002745787,0.0024936479,0.010204381],"category_scores_gemma":[0.20391905,0.0016602831,0.0019155563,0.0033507245,0.002218392,0.0029238488,0.003444426,0.0060915714,0.002579975],"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":[0.00064017955,0.000322011,0.0050376067,0.0011202995,0.0007049225,0.0005321435,0.0016242196,0.3707792,0.0043905023,0.30015576,0.012370552,0.3023226],"study_design_scores_gemma":[0.00021596819,0.00020773358,0.0006876764,0.00033877653,0.00011266138,0.00028483436,0.000100972145,0.76560044,0.006825069,0.2072081,0.01828577,0.00013201013],"about_ca_topic_score_codex":0.0024230718,"about_ca_topic_score_gemma":0.0022521194,"teacher_disagreement_score":0.96640456,"about_ca_system_score_codex":0.0013511196,"about_ca_system_score_gemma":0.0037128842,"threshold_uncertainty_score":0.17767191},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045668125,0.0010999786,0.9465116,0.00197174,0.00012920435,0.001813231,0.0004549984,0.0007030204,0.0016481796],"genre_scores_gemma":[0.11266218,0.00036336225,0.883716,0.00032636413,0.00006719712,0.0019417596,0.00044992694,0.00009698465,0.0003761303],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9610984,0.027887765,0.0021821903,0.0016905974,0.0066587427,0.00048238304],"domain_scores_gemma":[0.8506607,0.11794084,0.0066559496,0.010730977,0.0132426005,0.00076896115],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.046145212,0.0018488351,0.0013027616,0.0041226544,0.0010791534,0.0042442265,0.0025854227,0.0013729793,0.0021290276],"category_scores_gemma":[0.12713903,0.0008708855,0.0025742415,0.003804335,0.0018793815,0.0021611885,0.0026128613,0.0023362236,0.0007683724],"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":[0.002189371,0.0018664029,0.038632054,0.004087246,0.0017086876,0.00086203014,0.005675231,0.07152439,0.03735362,0.038681842,0.006549557,0.7908696],"study_design_scores_gemma":[0.0012189059,0.007500161,0.05596648,0.0017721882,0.001338901,0.00143639,0.0060877968,0.6866437,0.06873862,0.112435244,0.0563031,0.00055853394],"about_ca_topic_score_codex":0.003578449,"about_ca_topic_score_gemma":0.0044534146,"teacher_disagreement_score":0.9538548,"about_ca_system_score_codex":0.0015657605,"about_ca_system_score_gemma":0.004484839,"threshold_uncertainty_score":0.24404216},"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":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022738483,0.09195025,0.84064734,0.011541001,0.003348417,0.012377017,0.0037450246,0.0010942989,0.012558133],"genre_scores_gemma":[0.31908625,0.010102637,0.6444007,0.004693809,0.00097563246,0.018452661,0.0012274779,0.00031557854,0.00074515323],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.2696467,0.5238322,0.1075704,0.02106002,0.076501265,0.0013894951],"domain_scores_gemma":[0.1068801,0.8103819,0.039799236,0.027404169,0.014399183,0.0011355333],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.54826325,0.004675088,0.009609334,0.020815503,0.0026208428,0.0121052945,0.0058298954,0.006282292,0.005910189],"category_scores_gemma":[0.7991052,0.0029561892,0.02079011,0.014489199,0.008581221,0.010357302,0.011593149,0.007958482,0.0008644216],"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":[0.005401044,0.0005493797,0.09211109,0.17512427,0.13787472,0.0009633633,0.006101009,0.022293277,0.0032224974,0.07545985,0.013375438,0.46752402],"study_design_scores_gemma":[0.0061163013,0.004779582,0.062522955,0.08396894,0.17177346,0.0025689108,0.0029797368,0.07540751,0.014808674,0.50686365,0.06663414,0.001576071],"about_ca_topic_score_codex":0.002008336,"about_ca_topic_score_gemma":0.0023924515,"teacher_disagreement_score":0.45173675,"about_ca_system_score_codex":0.0061081015,"about_ca_system_score_gemma":0.010960368,"threshold_uncertainty_score":0.55707186},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003564197,0.00072357454,0.0011220727,0.11455231,0.87873757,0.00008344462,0.0010549994,0.00037371367,0.0033166506],"genre_scores_gemma":[0.0038239772,0.0057565845,0.012683119,0.30596238,0.369005,0.0014212874,0.0020997124,0.0044288873,0.2948191],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9773877,0.0067572943,0.004302142,0.0017610762,0.008735604,0.0010561933],"domain_scores_gemma":[0.8241247,0.057880677,0.0060258973,0.00925828,0.09794117,0.0047693825],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019753898,0.0029464904,0.002852179,0.0056115,0.0061420696,0.008012611,0.0047877613,0.01269525,0.10174775],"category_scores_gemma":[0.26140788,0.0018820022,0.0017914941,0.0047744405,0.005725934,0.006529489,0.004782736,0.024341077,0.07192768],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064521723,0.0000022031354,0.000010309755,0.0000670062,0.000002103857,0.00003380916,0.000032500622,0.000009173168,0.0000059793497,0.00041223143,0.9977501,0.001668182],"study_design_scores_gemma":[0.000029802217,0.000007439457,0.00016034469,0.0005982776,0.000015435213,0.00010706205,0.00013260123,0.00008371361,0.00009744448,0.0017622558,0.996976,0.0000295209],"about_ca_topic_score_codex":0.048244882,"about_ca_topic_score_gemma":0.06439884,"teacher_disagreement_score":0.9802461,"about_ca_system_score_codex":0.010373751,"about_ca_system_score_gemma":0.02307132,"threshold_uncertainty_score":0.34038013},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06321032,0.008159186,0.9092254,0.0074130357,0.0007688049,0.007310521,0.00043415197,0.00053617236,0.0029423716],"genre_scores_gemma":[0.5437874,0.001649865,0.43926817,0.0027046534,0.00031670803,0.01110938,0.00022527196,0.00012144608,0.0008170353],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.25760522,0.7120797,0.010869889,0.009500295,0.008244759,0.0017000869],"domain_scores_gemma":[0.0801775,0.8651375,0.024931965,0.022833137,0.006336335,0.0005835271],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5755979,0.002250152,0.0054236986,0.002024473,0.0022793578,0.0040663085,0.005129809,0.007704789,0.0040061413],"category_scores_gemma":[0.67172664,0.0018747501,0.012889052,0.0033044068,0.006923953,0.0050907196,0.0038757701,0.00790819,0.00045051673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0170316,0.0021773998,0.10447402,0.016086765,0.030569851,0.0042327866,0.0077952226,0.27292737,0.0016936248,0.25694844,0.013095134,0.27296785],"study_design_scores_gemma":[0.0062755244,0.009897121,0.019254662,0.0054929107,0.0100241145,0.0015873117,0.00091792725,0.68440264,0.002624385,0.24553815,0.013454992,0.0005303788],"about_ca_topic_score_codex":0.004947498,"about_ca_topic_score_gemma":0.005023754,"teacher_disagreement_score":0.42440212,"about_ca_system_score_codex":0.0059234328,"about_ca_system_score_gemma":0.011323178,"threshold_uncertainty_score":0.5233634},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038321435,0.000055801665,0.95797986,0.00044967158,0.000077947545,0.0002639387,0.00136185,0.0007688775,0.0007206753],"genre_scores_gemma":[0.40279087,0.00008968653,0.58887076,0.00024035214,0.00006606521,0.000943891,0.005086901,0.00011856869,0.0017929011],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976979,0.0012582005,0.00015643028,0.00041172578,0.00038072618,0.00009512039],"domain_scores_gemma":[0.98804104,0.0074095577,0.00085259165,0.0021085574,0.001330784,0.0002573994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008332094,0.00041657095,0.00036513736,0.001226761,0.00046514632,0.0008929745,0.001469818,0.00082522095,0.0027792475],"category_scores_gemma":[0.024755206,0.00047154078,0.0010207769,0.0010638132,0.0006126071,0.0009741589,0.0016514496,0.0011104551,0.00046607395],"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":[0.00053935155,0.00025589735,0.028758166,0.00017031228,0.00026514666,0.00041492947,0.0006703082,0.68485975,0.0033652137,0.07082135,0.0093228,0.2005568],"study_design_scores_gemma":[0.00004048528,0.000056258123,0.001026128,0.000018442975,0.000011697428,0.00008787951,0.00004840604,0.97598255,0.0012882623,0.019154485,0.0022672748,0.000018260436],"about_ca_topic_score_codex":0.003741942,"about_ca_topic_score_gemma":0.0035745609,"teacher_disagreement_score":0.008332094,"about_ca_system_score_codex":0.0009386972,"about_ca_system_score_gemma":0.0012365156,"threshold_uncertainty_score":0.04406482},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012148282,0.0008476561,0.88078195,0.006859745,0.00051281415,0.0068844394,0.0025793712,0.08308634,0.0062994557],"genre_scores_gemma":[0.026506957,0.00043121463,0.96346205,0.0007680791,0.000120405966,0.0031558282,0.0018125655,0.001898972,0.0018438125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9123959,0.045328666,0.01690477,0.0067676743,0.016890515,0.0017124992],"domain_scores_gemma":[0.76027906,0.1359379,0.024223013,0.03619024,0.03647801,0.006891831],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09928418,0.004051345,0.0018724655,0.010892136,0.0018316756,0.012286079,0.0062102997,0.0035268036,0.008886663],"category_scores_gemma":[0.22782005,0.002822488,0.0036895229,0.0043293247,0.0017578664,0.010691472,0.009757293,0.0064854417,0.0048735305],"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":[0.0013513413,0.0015575419,0.013725324,0.007465881,0.0008191451,0.0010074609,0.014895457,0.015857575,0.012498175,0.016633166,0.053539716,0.8606492],"study_design_scores_gemma":[0.0022015842,0.002234585,0.023558024,0.01719381,0.001858267,0.0022636869,0.0052504656,0.21415031,0.052582256,0.10184266,0.5750715,0.0017928956],"about_ca_topic_score_codex":0.002426853,"about_ca_topic_score_gemma":0.0034725184,"teacher_disagreement_score":0.9007158,"about_ca_system_score_codex":0.0035336206,"about_ca_system_score_gemma":0.0098856175,"threshold_uncertainty_score":0.5250712},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008845191,0.975471,0.009681535,0.0019233125,0.00092828716,0.0013910596,0.0009682028,0.00009177684,0.00069958944],"genre_scores_gemma":[0.47737923,0.45912054,0.03539002,0.0074257446,0.0021443346,0.01559032,0.0019803627,0.00029207818,0.000677386],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.6623029,0.20356151,0.09061236,0.016966127,0.024232764,0.002324274],"domain_scores_gemma":[0.41552398,0.5085065,0.047533423,0.014667705,0.01269835,0.0010700341],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22482188,0.0039749215,0.019817222,0.01909907,0.0016414305,0.010312066,0.0045032464,0.00560571,0.003628216],"category_scores_gemma":[0.45495206,0.0034821453,0.05760169,0.023661215,0.003383084,0.00785435,0.0047621713,0.005171471,0.0004454814],"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":[0.001875749,0.000041155447,0.032346576,0.2105405,0.7344244,0.00027556662,0.0005499692,0.00077385164,0.00018945032,0.0010696719,0.001091248,0.016821813],"study_design_scores_gemma":[0.001184095,0.00027080782,0.012523932,0.046513386,0.931395,0.00037099185,0.00023142599,0.0009626248,0.00026312907,0.0037595327,0.0024319142,0.00009323146],"about_ca_topic_score_codex":0.0045820433,"about_ca_topic_score_gemma":0.007277042,"teacher_disagreement_score":0.9960251,"about_ca_system_score_codex":0.005145466,"about_ca_system_score_gemma":0.009225504,"threshold_uncertainty_score":0.9559326},"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":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079642594,0.62792665,0.061660994,0.019254817,0.003928389,0.026842995,0.16537683,0.0005864124,0.014780352],"genre_scores_gemma":[0.48946753,0.2116138,0.11874638,0.014850605,0.0018515881,0.09093846,0.07016995,0.0006071786,0.0017545035],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.36595067,0.20573708,0.36133736,0.016974213,0.047924142,0.0020766172],"domain_scores_gemma":[0.10818095,0.57813627,0.22659247,0.045079257,0.04087601,0.0011351425],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27054715,0.002122953,0.0061469325,0.033360887,0.001985609,0.0075310827,0.0045657563,0.0037352373,0.0056025293],"category_scores_gemma":[0.69570434,0.0023031402,0.009897105,0.043807443,0.0034532675,0.008855103,0.007093778,0.0029181687,0.0010990896],"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":[0.0019611944,0.00010650456,0.15345035,0.6780802,0.038509227,0.0005361434,0.0072220294,0.0009710774,0.0012295305,0.006965267,0.018602079,0.09236642],"study_design_scores_gemma":[0.0013390398,0.0006791766,0.10835756,0.6692608,0.065486446,0.002129436,0.0071216114,0.0015740945,0.0053879535,0.015386009,0.122463934,0.00081390166],"about_ca_topic_score_codex":0.0073655886,"about_ca_topic_score_gemma":0.007381975,"teacher_disagreement_score":0.72945285,"about_ca_system_score_codex":0.005096899,"about_ca_system_score_gemma":0.015916852,"threshold_uncertainty_score":0.89954525},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23700221,0.004252747,0.55537003,0.05746516,0.0030035845,0.03397626,0.006029237,0.003612693,0.09928805],"genre_scores_gemma":[0.45874298,0.0015413986,0.5000261,0.0032150117,0.00038924668,0.030904125,0.0014258054,0.00045961852,0.003295723],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.74972486,0.2235435,0.010403459,0.0060635805,0.0074133445,0.0028513023],"domain_scores_gemma":[0.44532073,0.44243446,0.032722473,0.047250118,0.022649016,0.009623311],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18245304,0.0017970187,0.0015638943,0.0077069867,0.0068800366,0.017349802,0.004603616,0.0029341662,0.022941664],"category_scores_gemma":[0.4023133,0.0016251333,0.0031155266,0.00702561,0.008601259,0.020762281,0.029803308,0.0036198448,0.0032726682],"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":[0.0018036503,0.001124544,0.020625155,0.011060405,0.0004338253,0.00069518544,0.28845564,0.006632447,0.001868406,0.07942869,0.029009672,0.5588624],"study_design_scores_gemma":[0.0016623775,0.0023414243,0.01679116,0.014626533,0.0005490349,0.00049237756,0.26693085,0.013796822,0.0038444463,0.44618082,0.23207186,0.0007122815],"about_ca_topic_score_codex":0.0028646023,"about_ca_topic_score_gemma":0.0049621062,"teacher_disagreement_score":0.81754696,"about_ca_system_score_codex":0.01070461,"about_ca_system_score_gemma":0.02018524,"threshold_uncertainty_score":0.9649154},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8318561,0.0011955426,0.16374402,0.0012491132,0.000035084067,0.00030137555,0.00037721734,0.000295194,0.00094644417],"genre_scores_gemma":[0.9778707,0.0001966042,0.02065075,0.00012129207,0.00003039592,0.00017059552,0.00045803553,0.00001816918,0.00048339067],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99371743,0.0051152473,0.00023351166,0.00041004972,0.00033207153,0.00019168307],"domain_scores_gemma":[0.9605444,0.03542434,0.0021565151,0.0007404909,0.0007948264,0.00033956405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017894838,0.00074241834,0.0013465381,0.001205403,0.00045865684,0.0010938486,0.0009788596,0.0010464465,0.0011216224],"category_scores_gemma":[0.046145912,0.00056309433,0.0021095301,0.0005558862,0.00083769916,0.0006681682,0.000987583,0.0017078163,0.00017237915],"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":[0.0021357352,0.0006158591,0.39983794,0.00019504037,0.0018371585,0.00029287796,0.00046427763,0.48892835,0.0012999307,0.0048843916,0.0018286449,0.097679906],"study_design_scores_gemma":[0.00007424127,0.00029877573,0.037467245,0.00006268033,0.0001476623,0.00010422406,0.000047329304,0.9552709,0.00022688121,0.0058345767,0.00043068596,0.0000347789],"about_ca_topic_score_codex":0.01149711,"about_ca_topic_score_gemma":0.00795785,"teacher_disagreement_score":0.017894838,"about_ca_system_score_codex":0.0011191069,"about_ca_system_score_gemma":0.0017231511,"threshold_uncertainty_score":0.09463805},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019735852,0.002943751,0.99054736,0.0011279047,0.000268651,0.0003669799,0.0011828527,0.00063119864,0.0009576503],"genre_scores_gemma":[0.08989141,0.004549121,0.89491326,0.0010436092,0.0007240388,0.003869704,0.0031449732,0.00060656393,0.0012573523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9186892,0.068310544,0.003602829,0.003564557,0.0052142986,0.00061856996],"domain_scores_gemma":[0.8452634,0.11865722,0.013379475,0.013780082,0.008187617,0.0007322469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06602593,0.0017088368,0.003519351,0.0037339565,0.0013952266,0.002442347,0.006772028,0.0026052226,0.010254557],"category_scores_gemma":[0.18035512,0.0011404668,0.0057087946,0.0061134356,0.0012738385,0.0024106107,0.0030649593,0.004978182,0.002304894],"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":[0.0006037558,0.0002941671,0.040961005,0.008421742,0.00893088,0.0007557092,0.0019129383,0.096633315,0.0010621239,0.15006612,0.05361537,0.6367429],"study_design_scores_gemma":[0.0006038604,0.00055628957,0.016285146,0.0047116037,0.0023873216,0.0010266327,0.00042545152,0.43981108,0.0024349366,0.4500194,0.08133539,0.00040293543],"about_ca_topic_score_codex":0.0035931652,"about_ca_topic_score_gemma":0.0037128064,"teacher_disagreement_score":0.06602593,"about_ca_system_score_codex":0.0014795173,"about_ca_system_score_gemma":0.0048077353,"threshold_uncertainty_score":0.34918267},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1987561,0.00041604633,0.79545695,0.0008305019,0.00010591611,0.0002736985,0.00093479553,0.00092068344,0.0023053058],"genre_scores_gemma":[0.82012546,0.0001858675,0.1776617,0.000118930795,0.000049466744,0.00033650477,0.00065752835,0.00016304571,0.00070153753],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9851983,0.011134517,0.00056098,0.0018274161,0.0008883851,0.00039037014],"domain_scores_gemma":[0.9378882,0.046445016,0.0065099383,0.006365525,0.0022765372,0.0005147131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018147001,0.0011119769,0.0006823149,0.0025037823,0.0006163659,0.0018287235,0.0015903611,0.0008994769,0.004426758],"category_scores_gemma":[0.09491633,0.00054575474,0.0017510043,0.0037743482,0.00091622904,0.002069228,0.0028112798,0.0019024478,0.0008080447],"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":[0.0011297569,0.0005202643,0.3225183,0.00087016943,0.0018268946,0.000521847,0.004578097,0.17492339,0.004345842,0.02300042,0.004162139,0.4616029],"study_design_scores_gemma":[0.00013462576,0.0011465288,0.1347993,0.00040940105,0.00029503365,0.00044820848,0.002188584,0.8009411,0.0035740926,0.047233872,0.008619664,0.00020960423],"about_ca_topic_score_codex":0.011136891,"about_ca_topic_score_gemma":0.011479204,"teacher_disagreement_score":0.018147001,"about_ca_system_score_codex":0.0010535402,"about_ca_system_score_gemma":0.001770984,"threshold_uncertainty_score":0.0959717},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9331712,0.0027088267,0.011186712,0.040083226,0.00040317813,0.0021798266,0.0003510353,0.0001014152,0.009814641],"genre_scores_gemma":[0.9797448,0.0019000436,0.0051894393,0.007966824,0.000090860085,0.0021653308,0.00009933471,0.000076121316,0.0027672085],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.88623434,0.10235975,0.002232737,0.002089801,0.0028312567,0.004252048],"domain_scores_gemma":[0.85628605,0.11750434,0.0056745154,0.002857241,0.0073189125,0.010358917],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08072814,0.00075636,0.0012904961,0.001862704,0.018607467,0.0063981926,0.0032064938,0.0040937075,0.0048758783],"category_scores_gemma":[0.084647544,0.0012426759,0.0006949807,0.0021278881,0.022019077,0.008223145,0.00898387,0.008622287,0.0007471855],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021755492,0.00002474569,0.0005464526,0.00012459545,0.0000020728028,0.00040574066,0.99507314,0.00002014018,0.00027784845,0.00073927164,0.0006059608,0.0021582558],"study_design_scores_gemma":[0.000009123924,0.000043890966,0.00034052384,0.00027630848,0.000002687122,0.0002180238,0.98868155,0.000065978435,0.0001344967,0.00042718634,0.009782688,0.000017570548],"about_ca_topic_score_codex":0.013803158,"about_ca_topic_score_gemma":0.018735658,"teacher_disagreement_score":0.9192718,"about_ca_system_score_codex":0.0132253235,"about_ca_system_score_gemma":0.018557882,"threshold_uncertainty_score":0.42693633},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17878357,0.11558381,0.3829474,0.06742314,0.023563577,0.029157154,0.11181638,0.008688519,0.08203649],"genre_scores_gemma":[0.19846551,0.023066992,0.68229884,0.008529336,0.006618788,0.030692123,0.044594653,0.00128424,0.004449522],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8710003,0.08843048,0.017174019,0.005244149,0.0162364,0.0019147062],"domain_scores_gemma":[0.49376795,0.2002646,0.07472327,0.07620505,0.11599947,0.03903966],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20964417,0.0012010759,0.0021903692,0.016455745,0.0017613306,0.010051624,0.0033030706,0.0022754082,0.005107004],"category_scores_gemma":[0.25998607,0.0012993563,0.0030501352,0.019533768,0.0022796828,0.005879976,0.019197952,0.0033916237,0.0011782527],"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":[0.0009192192,0.00032833067,0.33950928,0.010072791,0.0024496738,0.00047289135,0.009166972,0.0017620132,0.0025760822,0.03629511,0.104605876,0.49184182],"study_design_scores_gemma":[0.000491096,0.0009318343,0.25639927,0.013218827,0.0010135919,0.0010610527,0.0033642289,0.0015718894,0.0013474606,0.015763842,0.70459366,0.00024323304],"about_ca_topic_score_codex":0.004495272,"about_ca_topic_score_gemma":0.0071572424,"teacher_disagreement_score":0.7903558,"about_ca_system_score_codex":0.0029063884,"about_ca_system_score_gemma":0.017480172,"threshold_uncertainty_score":0.9746494},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891361,0.0002875094,0.0052929237,0.00090488355,0.000049649723,0.0018189732,0.0006513456,0.000027924028,0.0018306801],"genre_scores_gemma":[0.99103177,0.0001125806,0.0051662107,0.0006719121,0.000029694449,0.0020064996,0.0004036818,0.000022709559,0.00055506756],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9335765,0.051668458,0.0021648942,0.0041281004,0.005485889,0.0029761393],"domain_scores_gemma":[0.9348284,0.029860163,0.012746856,0.00838767,0.010151526,0.0040253173],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.087787315,0.000566752,0.0004635747,0.0011271446,0.0028942905,0.0017835423,0.0023797906,0.0010396007,0.0025164234],"category_scores_gemma":[0.11050063,0.00074697763,0.00094343,0.0015291622,0.002169863,0.0014616568,0.0032880064,0.0012070645,0.0005164965],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028642814,0.00026568884,0.9701202,0.00014123134,0.00022678956,0.00016608917,0.013867784,0.00020802172,0.00033039154,0.0006216005,0.001373052,0.012392709],"study_design_scores_gemma":[0.00017276418,0.0012851013,0.9695197,0.00036068528,0.00022204843,0.0003482123,0.018627742,0.003622909,0.00079496537,0.0006329825,0.00435255,0.000060380866],"about_ca_topic_score_codex":0.10693972,"about_ca_topic_score_gemma":0.23548083,"teacher_disagreement_score":0.91221267,"about_ca_system_score_codex":0.0033474935,"about_ca_system_score_gemma":0.007041366,"threshold_uncertainty_score":0.46426922},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025062703,0.80361134,0.1638117,0.016300244,0.002429222,0.008775865,0.0007151506,0.00022209482,0.0016280608],"genre_scores_gemma":[0.08666684,0.38169315,0.4390473,0.014634412,0.003584587,0.07201368,0.0009396204,0.00058696663,0.0008334605],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.2531428,0.6295008,0.081922464,0.00892087,0.025437756,0.001075383],"domain_scores_gemma":[0.20170328,0.7392054,0.032609668,0.014361571,0.011268229,0.00085185235],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5084678,0.0024483115,0.009495059,0.010753758,0.0010626899,0.010433333,0.006079268,0.0065297405,0.0036446583],"category_scores_gemma":[0.66313744,0.0021171898,0.021588234,0.012729843,0.0049331514,0.0057500037,0.0058642067,0.00759893,0.00061014295],"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":[0.0054957084,0.00016703256,0.005308701,0.37614432,0.059629574,0.00019581625,0.0026129968,0.0072443974,0.000607076,0.08242716,0.009730461,0.4504367],"study_design_scores_gemma":[0.008533205,0.0023311672,0.006853583,0.58913916,0.05836513,0.0009312355,0.00097424234,0.016266162,0.0020147162,0.21689822,0.09696246,0.0007306557],"about_ca_topic_score_codex":0.0019730944,"about_ca_topic_score_gemma":0.0026101985,"teacher_disagreement_score":0.4915322,"about_ca_system_score_codex":0.008493504,"about_ca_system_score_gemma":0.011379071,"threshold_uncertainty_score":0.60614675},"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":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93639505,0.011533375,0.025478764,0.0028221353,0.00011760759,0.0015505323,0.013974489,0.0003475993,0.007780419],"genre_scores_gemma":[0.9594157,0.0021862043,0.030270448,0.00046019058,0.00007957734,0.00042178668,0.0069959406,0.000012706426,0.00015735155],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9844284,0.0066540004,0.004084229,0.0018276796,0.002652942,0.0003525961],"domain_scores_gemma":[0.87189835,0.08833817,0.025548343,0.0033077716,0.010093504,0.0008139271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018590648,0.0005243504,0.0008514391,0.01116131,0.00034359502,0.0020160943,0.0011220616,0.0009478005,0.0009736912],"category_scores_gemma":[0.08147037,0.00027553985,0.001082091,0.006434111,0.00034221823,0.0012343975,0.0010054867,0.0005384625,0.00030430677],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030400974,0.00015576805,0.9314049,0.00096109346,0.00038854821,0.00018358146,0.0002475958,0.0018680815,0.00028990256,0.000412102,0.0012527608,0.06253172],"study_design_scores_gemma":[0.0003967045,0.00067470677,0.8962519,0.0035329456,0.0012552926,0.0015534958,0.0013454403,0.07947755,0.003975078,0.0027888247,0.008640633,0.00010750786],"about_ca_topic_score_codex":0.0034471818,"about_ca_topic_score_gemma":0.00581994,"teacher_disagreement_score":0.018590648,"about_ca_system_score_codex":0.0009859393,"about_ca_system_score_gemma":0.0022860072,"threshold_uncertainty_score":0.09831792},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25068748,0.018246349,0.7249223,0.0011324906,0.0003507252,0.0016831043,0.0010836957,0.0003859484,0.0015079662],"genre_scores_gemma":[0.9007941,0.0014668026,0.09529757,0.00030295603,0.00013344866,0.0010085274,0.0004640303,0.0000586103,0.00047400035],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.86527735,0.10995338,0.006252426,0.0081314575,0.0092574395,0.0011279328],"domain_scores_gemma":[0.76742256,0.1806621,0.025815776,0.02011387,0.0054638106,0.00052194524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10714992,0.0012637253,0.0021388228,0.0030624617,0.0008185371,0.0016060928,0.0024217903,0.0017986934,0.0020428405],"category_scores_gemma":[0.23003295,0.0009805743,0.009686391,0.0029560796,0.0013097704,0.0018786776,0.0026215517,0.0014510681,0.0001684223],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050858934,0.00022307233,0.735936,0.0038663757,0.050088506,0.0002747065,0.0008808717,0.031133393,0.00097431394,0.013387231,0.0011060551,0.15704368],"study_design_scores_gemma":[0.0018033326,0.003413737,0.55607516,0.0025761395,0.076492675,0.0031798808,0.00038464542,0.27503777,0.00624712,0.06396837,0.010399469,0.00042174995],"about_ca_topic_score_codex":0.0040843636,"about_ca_topic_score_gemma":0.0025220276,"teacher_disagreement_score":0.10714992,"about_ca_system_score_codex":0.0013460566,"about_ca_system_score_gemma":0.0029801102,"threshold_uncertainty_score":0.5666697},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069845435,0.018246954,0.9008905,0.0070352238,0.0021993357,0.046600185,0.00208602,0.00077261723,0.015184608],"genre_scores_gemma":[0.15681443,0.0031524203,0.73160046,0.0026294584,0.00066872634,0.1025109,0.0010613365,0.00042192533,0.0011403534],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.35144296,0.56315297,0.033225577,0.012101461,0.03795052,0.0021265068],"domain_scores_gemma":[0.21602124,0.7070646,0.020387504,0.022837631,0.032461397,0.0012276216],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.51955336,0.0028535107,0.0071275574,0.012224335,0.0016489485,0.006399451,0.007237707,0.0056584617,0.009109892],"category_scores_gemma":[0.8217269,0.0016225784,0.010422237,0.01129925,0.0057350704,0.004008781,0.0052574296,0.007474664,0.0010320599],"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":[0.008458428,0.00023251631,0.023572799,0.03877146,0.019146439,0.0008407176,0.003750022,0.05586114,0.0009713149,0.20086892,0.038516384,0.60900986],"study_design_scores_gemma":[0.013554111,0.003811198,0.05226647,0.042512823,0.024045963,0.0023299695,0.0011328708,0.27986968,0.0050790533,0.4060915,0.16822444,0.0010819004],"about_ca_topic_score_codex":0.024608353,"about_ca_topic_score_gemma":0.016509129,"teacher_disagreement_score":0.9867953,"about_ca_system_score_codex":0.013204717,"about_ca_system_score_gemma":0.021437047,"threshold_uncertainty_score":0.59247625},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8072731,0.0011237409,0.1845871,0.0018692176,0.00009740579,0.0009458512,0.0011609917,0.00023493552,0.0027076784],"genre_scores_gemma":[0.9219372,0.00046422146,0.07435466,0.00041062036,0.00006865893,0.000945534,0.0010867192,0.000038973696,0.00069333136],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9869665,0.011150411,0.0002782222,0.0008804448,0.00039412404,0.00033026913],"domain_scores_gemma":[0.8495591,0.13157988,0.006373938,0.007456908,0.0037242535,0.0013058725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045602284,0.00078849576,0.0009579841,0.0012918138,0.0008304054,0.0010801799,0.002052415,0.0016484971,0.0029832586],"category_scores_gemma":[0.092862606,0.0005135603,0.0025087353,0.0016321136,0.0012316409,0.0014169957,0.0015937187,0.0026792078,0.00025409245],"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":[0.0019679726,0.0016184428,0.084587835,0.00026765664,0.0013110712,0.0006203087,0.0004580524,0.8527909,0.00046404602,0.022383945,0.003197459,0.030332293],"study_design_scores_gemma":[0.00065919623,0.00062324246,0.0059148544,0.00008432747,0.00026450318,0.00013882581,0.000104887,0.9788422,0.0003278055,0.0119644925,0.0010343223,0.000041392424],"about_ca_topic_score_codex":0.01809083,"about_ca_topic_score_gemma":0.012442866,"teacher_disagreement_score":0.045602284,"about_ca_system_score_codex":0.0023952082,"about_ca_system_score_gemma":0.002584572,"threshold_uncertainty_score":0.24117076},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90741855,0.04106393,0.041529216,0.001540885,0.0004860459,0.0010117284,0.0032654665,0.00008574926,0.0035984747],"genre_scores_gemma":[0.9856948,0.0025616041,0.009599766,0.00023962719,0.00014106126,0.00034987912,0.0013111323,0.00001782915,0.00008424486],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.7054496,0.22926283,0.024843143,0.011115008,0.028118733,0.0012107402],"domain_scores_gemma":[0.5868097,0.30835795,0.065384544,0.020882076,0.017046008,0.0015196867],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20213307,0.0005651259,0.0015447057,0.008668717,0.0007065335,0.0041105635,0.002078901,0.0015438999,0.00058713485],"category_scores_gemma":[0.29382455,0.00063647475,0.002380632,0.011380025,0.0021263822,0.0021914179,0.0028468124,0.0009806915,0.00013641916],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047217056,0.00005059731,0.97747713,0.0009577653,0.0055868123,0.000042411073,0.00083455717,0.00058820244,0.000113112925,0.0005726304,0.0002926897,0.013011932],"study_design_scores_gemma":[0.00014047095,0.00048766122,0.9870237,0.0013047835,0.0019423037,0.0003535837,0.0011092299,0.0035973012,0.0003203408,0.001272286,0.0023901786,0.00005809566],"about_ca_topic_score_codex":0.0047112266,"about_ca_topic_score_gemma":0.004395265,"teacher_disagreement_score":0.79786694,"about_ca_system_score_codex":0.0013989441,"about_ca_system_score_gemma":0.001228964,"threshold_uncertainty_score":0.983912},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21250427,0.0023591141,0.7671859,0.001087799,0.00019232277,0.011810401,0.0005453816,0.00043343724,0.0038813883],"genre_scores_gemma":[0.68855304,0.00068204815,0.30016848,0.0004425098,0.000030070209,0.0091276225,0.00025880407,0.00006173137,0.00067571376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8747458,0.116061114,0.0023425967,0.0025968514,0.003266646,0.000987108],"domain_scores_gemma":[0.4980271,0.4664312,0.014929776,0.010708507,0.008230572,0.0016728925],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15439086,0.0018046132,0.0031549735,0.0022460523,0.0005534624,0.0018998962,0.0033130716,0.0026239392,0.004317204],"category_scores_gemma":[0.3132645,0.0013290485,0.0038979556,0.0021270278,0.0017766629,0.0030856365,0.0027172961,0.0029600791,0.00041978073],"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":[0.009453441,0.001021902,0.008500546,0.0018734458,0.0018912993,0.00023523274,0.00053375814,0.890665,0.0005001726,0.03399105,0.0011380092,0.050196245],"study_design_scores_gemma":[0.0030400006,0.002871329,0.0012234786,0.00037650875,0.00057436357,0.00009239547,0.00013888191,0.96940607,0.0005180976,0.020814562,0.00087918655,0.00006506663],"about_ca_topic_score_codex":0.0038438728,"about_ca_topic_score_gemma":0.0018255997,"teacher_disagreement_score":0.8456091,"about_ca_system_score_codex":0.0038073903,"about_ca_system_score_gemma":0.0059949597,"threshold_uncertainty_score":0.8165066},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97393256,0.00078293605,0.012866132,0.001958454,0.00014992656,0.0038857555,0.00030640134,0.00021658531,0.005901267],"genre_scores_gemma":[0.94905126,0.001040223,0.03285714,0.0009745485,0.0002953556,0.013188263,0.00021018863,0.00007169978,0.0023113089],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95534813,0.038985,0.0012446974,0.0014251805,0.0018659898,0.001131002],"domain_scores_gemma":[0.80182225,0.1753803,0.0066075264,0.004585555,0.008127129,0.0034774186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.070266515,0.0012216315,0.00063462,0.0021312046,0.0037707568,0.0027162214,0.0023425682,0.0017738104,0.0080074705],"category_scores_gemma":[0.097457215,0.00064817246,0.00069100823,0.000943903,0.002502987,0.0054749968,0.005237808,0.0011259286,0.0009791888],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019614615,0.0022787002,0.034232665,0.002858363,0.00009164128,0.0011479494,0.69525075,0.00024638808,0.010758218,0.0011392045,0.0036905897,0.24634406],"study_design_scores_gemma":[0.0014996065,0.022445654,0.13298525,0.00643455,0.00034872984,0.0028322916,0.7290196,0.0022063253,0.01720355,0.0079825055,0.076613404,0.00042862588],"about_ca_topic_score_codex":0.0006590632,"about_ca_topic_score_gemma":0.0014090979,"teacher_disagreement_score":0.070266515,"about_ca_system_score_codex":0.0013531981,"about_ca_system_score_gemma":0.0015945657,"threshold_uncertainty_score":0.37160927},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07819199,0.001758419,0.91678673,0.0010183026,0.00037946328,0.00019669314,0.00027098827,0.00045602216,0.000941304],"genre_scores_gemma":[0.6926055,0.00094155484,0.3023098,0.00043461943,0.00027582064,0.00056186033,0.00055042445,0.00021039884,0.0021099353],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9045437,0.07829255,0.003233113,0.0077445745,0.0048381095,0.0013479632],"domain_scores_gemma":[0.7845892,0.17072006,0.016772777,0.019087473,0.0079688905,0.0008616396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09266628,0.001327722,0.0015798031,0.0019418984,0.0010856584,0.0019758465,0.0036970943,0.0020956835,0.0011710263],"category_scores_gemma":[0.28167954,0.0007669206,0.003231899,0.0029179594,0.0023010788,0.0032003468,0.0029976477,0.002869945,0.00030041696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002053865,0.0002446404,0.32201234,0.0013288334,0.0053371144,0.0013608558,0.0028759672,0.3268714,0.0016746429,0.110907875,0.004986408,0.22034599],"study_design_scores_gemma":[0.00017207536,0.0005924178,0.08462873,0.00072120863,0.0011263877,0.0007744268,0.0005921935,0.791308,0.0029065444,0.10731891,0.009570238,0.00028890176],"about_ca_topic_score_codex":0.015342518,"about_ca_topic_score_gemma":0.014550717,"teacher_disagreement_score":0.09266628,"about_ca_system_score_codex":0.0022294587,"about_ca_system_score_gemma":0.0029909515,"threshold_uncertainty_score":0.490072},"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":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027899807,0.0065524783,0.7559575,0.009495077,0.001338682,0.14658985,0.025596773,0.004515291,0.022054473],"genre_scores_gemma":[0.0139923245,0.00054877537,0.95842916,0.00032918534,0.00005171983,0.023608942,0.0022126597,0.00011490886,0.0007123373],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8018526,0.12244869,0.04588364,0.0076135956,0.020780051,0.001421518],"domain_scores_gemma":[0.51909167,0.2774407,0.048055355,0.029277172,0.12365353,0.0024815316],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22251205,0.0025483111,0.0020396167,0.024412856,0.0030539422,0.007877739,0.0039600106,0.0021037522,0.014357571],"category_scores_gemma":[0.4376271,0.001990907,0.0074086543,0.015414033,0.0017904335,0.003931045,0.0076723373,0.004628277,0.0033095982],"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":[0.0009027959,0.00056124234,0.0137774,0.035400894,0.0016794427,0.00079203123,0.025500476,0.006103408,0.0047915014,0.022526257,0.06622095,0.8217437],"study_design_scores_gemma":[0.0020657345,0.001245849,0.03407764,0.046716236,0.004815484,0.0013854429,0.017475732,0.047681447,0.017852746,0.102275364,0.72323394,0.0011744428],"about_ca_topic_score_codex":0.008113795,"about_ca_topic_score_gemma":0.01794434,"teacher_disagreement_score":0.22251205,"about_ca_system_score_codex":0.008545373,"about_ca_system_score_gemma":0.034762662,"threshold_uncertainty_score":0.95878106},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020312289,0.0029561156,0.9707088,0.0032726163,0.00040591328,0.0003096935,0.00051668484,0.0008164303,0.00070140144],"genre_scores_gemma":[0.11063108,0.0013076874,0.8847476,0.00069376413,0.00035143906,0.000832197,0.0006971093,0.00022717891,0.0005118646],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93736315,0.044313762,0.0049498454,0.0050737457,0.007625054,0.00067446026],"domain_scores_gemma":[0.80287385,0.13626058,0.01390301,0.022728333,0.022861004,0.001373204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0839921,0.0016947049,0.0018630091,0.003710664,0.0011717516,0.0049581006,0.003985443,0.0022722161,0.0014074268],"category_scores_gemma":[0.17956206,0.0011230716,0.0025116415,0.0039358838,0.0022707009,0.0032385713,0.0033659951,0.004471516,0.00072558253],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010904778,0.00034680293,0.31502524,0.0027077629,0.0025491111,0.0008750331,0.003803344,0.050021045,0.014880849,0.021558221,0.011064416,0.57607776],"study_design_scores_gemma":[0.00029381248,0.0016122505,0.2180688,0.0029528625,0.0014186262,0.0040633003,0.0046155774,0.5557037,0.03214927,0.110305116,0.067937285,0.00087943027],"about_ca_topic_score_codex":0.007085041,"about_ca_topic_score_gemma":0.010499925,"teacher_disagreement_score":0.0839921,"about_ca_system_score_codex":0.001402336,"about_ca_system_score_gemma":0.0032106189,"threshold_uncertainty_score":0.444198},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015292698,0.00039209795,0.9798432,0.00078640186,0.00006657974,0.00028321941,0.000320762,0.00093712367,0.0020779727],"genre_scores_gemma":[0.12084237,0.00037724536,0.87581336,0.00028451707,0.000044421613,0.0012979788,0.00043318557,0.0002300504,0.0006768373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98754245,0.0106055075,0.00039826013,0.00046920066,0.0008311535,0.00015344121],"domain_scores_gemma":[0.82071084,0.16659632,0.0025691395,0.0048916056,0.0047358107,0.00049628405],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028190834,0.0010144714,0.0010252515,0.0018666454,0.00075306103,0.0016705594,0.0021415367,0.002479698,0.0060638557],"category_scores_gemma":[0.13109773,0.000732769,0.00096266874,0.0016184895,0.0012865737,0.0019382411,0.0030682685,0.0025409637,0.00073651486],"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":[0.00030525704,0.0002902722,0.0076095546,0.00040921438,0.00016719464,0.00022179748,0.00037217772,0.7827025,0.000817897,0.099671,0.0057848436,0.1016483],"study_design_scores_gemma":[0.00008161072,0.0000953331,0.00046001154,0.000070381764,0.000013374637,0.000074726115,0.000043316555,0.968574,0.0005984007,0.027268711,0.0027020902,0.0000180639],"about_ca_topic_score_codex":0.004808922,"about_ca_topic_score_gemma":0.0032247058,"teacher_disagreement_score":0.97180915,"about_ca_system_score_codex":0.0014410671,"about_ca_system_score_gemma":0.0019281298,"threshold_uncertainty_score":0.14908916},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047300404,0.0163647,0.002657767,0.052897926,0.9269312,0.000032251457,0.00012430827,0.00010893726,0.0008355915],"genre_scores_gemma":[0.0004801025,0.012598074,0.0010273261,0.011472438,0.9719649,0.000047364356,0.000047313297,0.00008723285,0.0022752448],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9887477,0.003912223,0.001450614,0.0012290379,0.0043802285,0.000280165],"domain_scores_gemma":[0.83710414,0.12899004,0.003966629,0.0027922366,0.022397365,0.0047494895],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024535833,0.0029193328,0.003934454,0.0040348917,0.0019484245,0.00784654,0.004098533,0.011321821,0.011540181],"category_scores_gemma":[0.110314816,0.0012392681,0.0033545834,0.0024261626,0.0038526615,0.005192441,0.002206495,0.024721108,0.007789247],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006629147,0.00001823405,0.00006682395,0.000835864,0.000098791425,0.00007468086,0.000030427971,0.00014477469,0.00006112364,0.0026527755,0.9765688,0.019381499],"study_design_scores_gemma":[0.00016218073,0.00007101278,0.00046542552,0.0018386662,0.00025589933,0.00046761602,0.00007047911,0.0015599141,0.00023874195,0.024880387,0.9699192,0.00007045156],"about_ca_topic_score_codex":0.0010516254,"about_ca_topic_score_gemma":0.0025546728,"teacher_disagreement_score":0.97546417,"about_ca_system_score_codex":0.002329914,"about_ca_system_score_gemma":0.004817222,"threshold_uncertainty_score":0.12975943},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9699167,0.0011478517,0.016839039,0.0031943484,0.00008146559,0.00017874848,0.0017132588,0.00007691558,0.006851575],"genre_scores_gemma":[0.9978713,0.00017565086,0.0010974767,0.00006309479,0.000050428633,0.000036121026,0.00024402527,0.000008326666,0.00045356585],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996838,0.0019400845,0.00012731183,0.0005919907,0.00024465923,0.00025801567],"domain_scores_gemma":[0.9785131,0.016560664,0.0024154983,0.0010094948,0.0007867695,0.0007143707],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038736204,0.0005946922,0.0007890411,0.0025807752,0.0010586597,0.0015374785,0.00095561077,0.0010971596,0.0087240385],"category_scores_gemma":[0.025892537,0.00029613095,0.0019071201,0.0024436251,0.0011756249,0.0020293177,0.0013156609,0.0008702841,0.00064945157],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027314737,0.00013656763,0.9426948,0.00017124617,0.0014967861,0.00078511785,0.002021633,0.014513501,0.00033397943,0.01037808,0.0025910335,0.02460407],"study_design_scores_gemma":[0.00009752814,0.00024539142,0.65147185,0.00018287536,0.0014815723,0.0009019031,0.0030182106,0.2956568,0.0002703433,0.040651135,0.0059512183,0.00007121239],"about_ca_topic_score_codex":0.026314521,"about_ca_topic_score_gemma":0.013125663,"teacher_disagreement_score":0.99612635,"about_ca_system_score_codex":0.0011267822,"about_ca_system_score_gemma":0.00082030444,"threshold_uncertainty_score":0.052322745},"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":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006989318,0.0018863638,0.9455426,0.013964393,0.0007725845,0.01066934,0.00041040225,0.0006373139,0.019127788],"genre_scores_gemma":[0.039331328,0.0003117602,0.9472961,0.0008201905,0.00003703796,0.011453037,0.00023728414,0.00007531176,0.0004380306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4502251,0.4756645,0.0322978,0.014760643,0.022585485,0.0044664554],"domain_scores_gemma":[0.38996246,0.46456873,0.018192997,0.045065496,0.076218285,0.005992069],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.46387058,0.003011746,0.003993173,0.020766798,0.010560339,0.021668924,0.010689551,0.008739376,0.0073163793],"category_scores_gemma":[0.46853596,0.002678186,0.00773046,0.015615265,0.025230162,0.029476762,0.027442042,0.015398272,0.0014132634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010592674,0.00021486846,0.0022563173,0.0060254075,0.00021633983,0.00027589023,0.088849075,0.0031116,0.0005446745,0.71725667,0.008165444,0.17297778],"study_design_scores_gemma":[0.00025636793,0.00040399015,0.001709832,0.023714073,0.00044614996,0.00055459293,0.05383593,0.018730894,0.0020836426,0.7225615,0.17529516,0.00040784595],"about_ca_topic_score_codex":0.008530865,"about_ca_topic_score_gemma":0.0098603815,"teacher_disagreement_score":0.46387058,"about_ca_system_score_codex":0.028515803,"about_ca_system_score_gemma":0.0753092,"threshold_uncertainty_score":0.66114306},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015331781,0.8238019,0.054859105,0.038819354,0.0035781723,0.038017556,0.007538356,0.0004050013,0.017648822],"genre_scores_gemma":[0.15902099,0.57959056,0.1772696,0.008108537,0.0011269097,0.06639007,0.0071780058,0.00022355349,0.0010917317],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.61120546,0.20150241,0.12378158,0.009691798,0.050716974,0.0031017745],"domain_scores_gemma":[0.39410818,0.373344,0.073588304,0.020589119,0.13540646,0.00296397],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38409713,0.0017574272,0.0071320366,0.04748215,0.0035073147,0.013266701,0.00545254,0.004391655,0.0045379275],"category_scores_gemma":[0.5835828,0.002298076,0.009384258,0.045565616,0.0037316564,0.015375155,0.011763594,0.004088959,0.0009496336],"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":[0.00032596648,0.000095557894,0.012549938,0.5509148,0.0044274144,0.0002052765,0.008731367,0.0010508477,0.0004493833,0.011363397,0.020090392,0.38979563],"study_design_scores_gemma":[0.0001938121,0.00015415825,0.009186328,0.9198647,0.006797705,0.00021185886,0.005535394,0.00093367643,0.00051317766,0.005057345,0.051430997,0.00012071758],"about_ca_topic_score_codex":0.014490472,"about_ca_topic_score_gemma":0.026872106,"teacher_disagreement_score":0.6159029,"about_ca_system_score_codex":0.017935561,"about_ca_system_score_gemma":0.09093427,"threshold_uncertainty_score":0.7595179},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09426227,0.00053543516,0.9005172,0.00065847463,0.0002707379,0.0011862088,0.0009111386,0.0006176312,0.0010407872],"genre_scores_gemma":[0.50850004,0.0003967257,0.48356438,0.00043126187,0.000105440435,0.0040354184,0.0012642221,0.00029357104,0.0014090132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9615827,0.031709015,0.0019768628,0.0020760281,0.0021387055,0.0005165762],"domain_scores_gemma":[0.8695334,0.09225624,0.012839379,0.017432544,0.007304197,0.0006342275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11107612,0.0012346073,0.0011751591,0.0021937066,0.00071117474,0.0015177549,0.002428711,0.0012358662,0.0030662783],"category_scores_gemma":[0.22228172,0.0006829779,0.0027105722,0.0020672204,0.00088272826,0.0013491933,0.0018197577,0.0024722784,0.00057049457],"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":[0.001501134,0.00053783617,0.3942041,0.0010361817,0.004227437,0.00025790706,0.0023286277,0.08265078,0.0028203242,0.02618033,0.010239487,0.47401577],"study_design_scores_gemma":[0.0006601537,0.002506563,0.18833421,0.0013843592,0.002128045,0.00058648124,0.0009360983,0.68562466,0.008570842,0.08077651,0.028210226,0.00028181224],"about_ca_topic_score_codex":0.0038033053,"about_ca_topic_score_gemma":0.003765437,"teacher_disagreement_score":0.8889239,"about_ca_system_score_codex":0.0009311186,"about_ca_system_score_gemma":0.002391219,"threshold_uncertainty_score":0.5874337},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0873877,0.029648397,0.8082591,0.06341757,0.001663473,0.0012242249,0.0039282194,0.0005914446,0.0038798521],"genre_scores_gemma":[0.6680304,0.011046445,0.30412665,0.0091348365,0.0014822984,0.0018302598,0.0031865034,0.00031324956,0.0008493911],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6458813,0.3201354,0.011109383,0.010496321,0.010753631,0.0016239006],"domain_scores_gemma":[0.17734076,0.77644026,0.019967554,0.015355287,0.0094327135,0.0014634752],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28754658,0.0014228033,0.004448407,0.0031516668,0.0019822083,0.0050237207,0.0050871614,0.004318354,0.003043186],"category_scores_gemma":[0.6060191,0.0012473875,0.0050229966,0.006792608,0.0046119117,0.0070087016,0.0042303377,0.007119285,0.000557329],"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":[0.0017326105,0.00053562195,0.29176053,0.010578762,0.009319581,0.0020794203,0.0069595915,0.21947187,0.0006698545,0.07802784,0.024580862,0.35428345],"study_design_scores_gemma":[0.00056721386,0.0012747113,0.06617335,0.012086079,0.002711443,0.0027263954,0.004740416,0.39941552,0.0017629737,0.47718972,0.030905964,0.00044617782],"about_ca_topic_score_codex":0.009100388,"about_ca_topic_score_gemma":0.0075847637,"teacher_disagreement_score":0.7124534,"about_ca_system_score_codex":0.003083223,"about_ca_system_score_gemma":0.007946082,"threshold_uncertainty_score":0.87858194},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047440045,0.16711432,0.7546293,0.0072312565,0.0028678628,0.007599384,0.0060975687,0.004190406,0.0028298786],"genre_scores_gemma":[0.6793387,0.011517925,0.2780138,0.004067508,0.00086772384,0.020555848,0.0030109638,0.0016340084,0.0009935026],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.32509884,0.60166943,0.029461268,0.026484279,0.01593138,0.0013547898],"domain_scores_gemma":[0.1510554,0.77845454,0.023277193,0.03936426,0.006997953,0.00085066777],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5018169,0.0066793067,0.017330416,0.014922316,0.0016094667,0.008536114,0.010994988,0.007926965,0.004834743],"category_scores_gemma":[0.7469904,0.0035982614,0.06812615,0.01725817,0.00642475,0.008602395,0.0068320227,0.008901627,0.0010623959],"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":[0.008296285,0.000113123795,0.033788696,0.023924349,0.8399613,0.00059697934,0.00092850544,0.019741744,0.0005915391,0.008567632,0.00425279,0.059237055],"study_design_scores_gemma":[0.013231929,0.0032258653,0.031532586,0.012824387,0.7101106,0.0020288904,0.0008417146,0.10559339,0.0025465225,0.10161368,0.015540533,0.00090994145],"about_ca_topic_score_codex":0.0037255152,"about_ca_topic_score_gemma":0.0023329607,"teacher_disagreement_score":0.49818307,"about_ca_system_score_codex":0.004027674,"about_ca_system_score_gemma":0.003506393,"threshold_uncertainty_score":0.6143485},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018978375,0.00018761563,0.9966978,0.00012083481,0.000029179959,0.000090422414,0.0001644369,0.00035629378,0.00045559308],"genre_scores_gemma":[0.1561756,0.00067592063,0.8389982,0.00024672342,0.00015467308,0.00095214794,0.0016286178,0.0004401298,0.00072797236],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96748996,0.023833767,0.0014785212,0.0030043223,0.0037035896,0.0004898464],"domain_scores_gemma":[0.9290455,0.04598196,0.0057076183,0.013809975,0.0050480072,0.00040690016],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04170361,0.0016051786,0.0030082988,0.003066577,0.00087842945,0.0027302022,0.004259877,0.0017742772,0.003297551],"category_scores_gemma":[0.09748232,0.0011670025,0.00397441,0.0051289843,0.0016523123,0.002739257,0.0037575336,0.003299103,0.001119133],"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":[0.0003945308,0.00026258646,0.02084658,0.0013318552,0.0023689463,0.0005129018,0.0007666169,0.45832402,0.0018686039,0.14871928,0.013798475,0.35080564],"study_design_scores_gemma":[0.00015465962,0.00012050258,0.003283331,0.00026949332,0.00029993447,0.0003239757,0.000060890477,0.7866465,0.0025344698,0.19561043,0.010599965,0.0000958479],"about_ca_topic_score_codex":0.0029898512,"about_ca_topic_score_gemma":0.0021743092,"teacher_disagreement_score":0.9582964,"about_ca_system_score_codex":0.0014518539,"about_ca_system_score_gemma":0.0042248657,"threshold_uncertainty_score":0.22055238},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019009577,0.39206764,0.5577851,0.0036558025,0.0030249383,0.016049836,0.0050701126,0.0013567522,0.0019802854],"genre_scores_gemma":[0.36241215,0.09668333,0.46684042,0.0029731002,0.0012486988,0.06370222,0.0043185623,0.0010159859,0.00080550654],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.4083475,0.507256,0.048794936,0.013539849,0.020982677,0.0010790506],"domain_scores_gemma":[0.18559222,0.7504656,0.026797691,0.024663124,0.011873844,0.0006075012],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3845185,0.0046494463,0.015405989,0.016601,0.0011925107,0.007446706,0.00691,0.0050009624,0.00573179],"category_scores_gemma":[0.7111118,0.0027056143,0.06268821,0.01947567,0.002950449,0.006345214,0.0037713822,0.006313736,0.0007342524],"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":[0.0058898265,0.00018352168,0.014662474,0.11884267,0.7521151,0.00043246153,0.00096844626,0.012894822,0.00037355753,0.006100861,0.003812998,0.08372325],"study_design_scores_gemma":[0.0077792704,0.0029538483,0.018420393,0.06443749,0.7984578,0.0009780749,0.0009485768,0.03545837,0.001774347,0.046708334,0.02151933,0.00056418777],"about_ca_topic_score_codex":0.0025109118,"about_ca_topic_score_gemma":0.0020718449,"teacher_disagreement_score":0.6154815,"about_ca_system_score_codex":0.0045927432,"about_ca_system_score_gemma":0.005250101,"threshold_uncertainty_score":0.7589983},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91963047,0.0021348181,0.06777778,0.0041670846,0.000117531126,0.00016110718,0.004004867,0.00027393625,0.0017323793],"genre_scores_gemma":[0.9511397,0.0005678092,0.0445113,0.00022655656,0.00005512874,0.00008951521,0.0032127162,0.000028172424,0.00016909016],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99126303,0.0061826413,0.0005133022,0.0007805453,0.000976872,0.0002835514],"domain_scores_gemma":[0.9551497,0.033489484,0.0035626786,0.004109211,0.0031448267,0.00054411986],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018217305,0.0006265165,0.00061848114,0.0013495756,0.0011053944,0.0013232392,0.0009075432,0.0010051999,0.00049906486],"category_scores_gemma":[0.04138081,0.00024399749,0.001402887,0.0029324372,0.0010348418,0.00092703773,0.001440403,0.0010441919,0.000095798096],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003179217,0.00015094246,0.8968259,0.0003621657,0.0003974264,0.0009822233,0.0016589846,0.03317786,0.0012048577,0.0045526307,0.0030113559,0.05735775],"study_design_scores_gemma":[0.00012888946,0.00034305223,0.6289616,0.0003814115,0.00039109145,0.000994105,0.0043027303,0.32771334,0.0032713865,0.021140622,0.012254232,0.00011755872],"about_ca_topic_score_codex":0.04468881,"about_ca_topic_score_gemma":0.03472231,"teacher_disagreement_score":0.9817827,"about_ca_system_score_codex":0.0013186346,"about_ca_system_score_gemma":0.001885664,"threshold_uncertainty_score":0.09634352},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002819725,0.99339044,0.0007150207,0.00045607763,0.0002169294,0.0013065774,0.00077792536,0.000018772287,0.0002985224],"genre_scores_gemma":[0.1353051,0.84596485,0.00666683,0.00140303,0.00033588416,0.008989828,0.0011007863,0.000026973188,0.0002067395],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.93131125,0.03041479,0.023928402,0.0031853556,0.010479184,0.0006810181],"domain_scores_gemma":[0.78383845,0.17913736,0.026792822,0.0021869713,0.007322332,0.00072203134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041045632,0.001641361,0.012857735,0.014893534,0.0008193962,0.004042341,0.002986936,0.0025011124,0.0030187846],"category_scores_gemma":[0.20720215,0.0013244691,0.012391257,0.013020006,0.001866743,0.004000861,0.0024483919,0.0021863761,0.00019261554],"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":[0.00034160897,0.000014560894,0.0011676009,0.9611531,0.02017084,0.00004974028,0.00017510247,0.00010954352,0.00008210066,0.00024324232,0.0007111355,0.01578146],"study_design_scores_gemma":[0.00089716085,0.0003705924,0.008006223,0.8137335,0.16736977,0.0003178193,0.00040200423,0.0003300338,0.00030469362,0.0010959418,0.007085774,0.000086441236],"about_ca_topic_score_codex":0.0036764578,"about_ca_topic_score_gemma":0.009474054,"teacher_disagreement_score":0.041045632,"about_ca_system_score_codex":0.0063228915,"about_ca_system_score_gemma":0.01285045,"threshold_uncertainty_score":0.21707267},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027047008,0.0017895901,0.9085647,0.0026889923,0.0002198853,0.0024930425,0.03506503,0.018085422,0.004046368],"genre_scores_gemma":[0.11969534,0.0007308894,0.81957793,0.000576472,0.00017578606,0.001216059,0.05560492,0.00025064423,0.0021719385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759537,0.0004057424,0.0004965479,0.00074980396,0.0006220591,0.00013050972],"domain_scores_gemma":[0.9949267,0.002838059,0.0005623327,0.00023398943,0.0012013192,0.00023755187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002996126,0.0014365729,0.0009026892,0.010292404,0.0010285925,0.0024039962,0.0019101204,0.0010757609,0.0030067721],"category_scores_gemma":[0.009619177,0.00029498243,0.002209325,0.0039527086,0.0005843586,0.002430291,0.0013971686,0.0011535612,0.0016926884],"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":[0.0007287283,0.00070580264,0.028977968,0.0033769386,0.0005045165,0.0053781327,0.0021458096,0.038053043,0.026949286,0.02967497,0.059405573,0.80409926],"study_design_scores_gemma":[0.00016910005,0.00035934066,0.01799064,0.0007717803,0.0006555614,0.002618612,0.0016869099,0.7923891,0.023264872,0.073348746,0.08656633,0.00017901245],"about_ca_topic_score_codex":0.01103615,"about_ca_topic_score_gemma":0.015811868,"teacher_disagreement_score":0.01103615,"about_ca_system_score_codex":0.0013935169,"about_ca_system_score_gemma":0.0029674175,"threshold_uncertainty_score":0.021943867},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105086476,0.01298224,0.8729899,0.001034285,0.00026774494,0.002081519,0.0007065012,0.00036245273,0.0044888104],"genre_scores_gemma":[0.56360143,0.0019876538,0.42875308,0.00048076943,0.00012648443,0.0036794192,0.00060471793,0.000115948154,0.000650454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.7013312,0.26901785,0.0063744537,0.008019082,0.014346031,0.0009112945],"domain_scores_gemma":[0.22866336,0.72727776,0.012644581,0.021259135,0.009118452,0.0010367536],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.26648054,0.0016539351,0.0025647935,0.0028691825,0.0009901776,0.0030137943,0.0048672925,0.003459785,0.006983192],"category_scores_gemma":[0.5594991,0.0009143976,0.0039674034,0.0036703565,0.0036399586,0.006349235,0.0046384763,0.0030316978,0.00050345314],"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":[0.010840649,0.0008463654,0.07781701,0.010416817,0.011313251,0.00076247344,0.005603368,0.2894058,0.0012685042,0.17223866,0.003885506,0.41560164],"study_design_scores_gemma":[0.0022556612,0.0074964846,0.041727927,0.004020878,0.0053643775,0.0014969718,0.0022362045,0.7300729,0.0022097228,0.18777907,0.014900031,0.0004397833],"about_ca_topic_score_codex":0.0022116157,"about_ca_topic_score_gemma":0.0015258183,"teacher_disagreement_score":0.26648054,"about_ca_system_score_codex":0.0028745981,"about_ca_system_score_gemma":0.003130306,"threshold_uncertainty_score":0.9045601},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38175586,0.0008023669,0.6063655,0.004159559,0.00024455434,0.00088327046,0.0026676175,0.00082887313,0.0022923264],"genre_scores_gemma":[0.8790423,0.00022838704,0.11688535,0.00044697698,0.000106670894,0.0006711672,0.0013890002,0.00010066655,0.0011294232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98362607,0.012428861,0.0007314509,0.001678438,0.0010989053,0.00043620067],"domain_scores_gemma":[0.8742631,0.10405861,0.0070919446,0.006278856,0.007337629,0.00096978614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.058459524,0.0010024474,0.0013199747,0.0010970446,0.0009854509,0.0027239644,0.0032718156,0.0011699086,0.0021584292],"category_scores_gemma":[0.11699439,0.0007971268,0.0022917204,0.0012835499,0.00086496293,0.0012238782,0.0020157048,0.0029977716,0.00037835573],"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":[0.0009902262,0.0002533334,0.3498953,0.0002124484,0.001145517,0.0004633744,0.00059373147,0.5616266,0.00037192737,0.020649254,0.004760139,0.05903816],"study_design_scores_gemma":[0.000055519948,0.000084260144,0.00877628,0.000059413127,0.000105055035,0.00009895264,0.000048196787,0.9829915,0.00022483843,0.006588421,0.00094329414,0.00002421777],"about_ca_topic_score_codex":0.026881224,"about_ca_topic_score_gemma":0.011393262,"teacher_disagreement_score":0.058459524,"about_ca_system_score_codex":0.0027170766,"about_ca_system_score_gemma":0.004995392,"threshold_uncertainty_score":0.3091672},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9383012,0.0025390135,0.055155087,0.0003045063,0.00012120489,0.0006195746,0.002293873,0.0001760889,0.0004894116],"genre_scores_gemma":[0.9728563,0.0006153658,0.023828045,0.00008818442,0.00006137692,0.00043948088,0.0018087116,0.00004993817,0.00025260018],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9850676,0.009617746,0.0010352527,0.0019520198,0.0020435601,0.00028390766],"domain_scores_gemma":[0.9179928,0.054853927,0.01145195,0.00658381,0.008099353,0.001018085],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06289218,0.0012922309,0.0009718293,0.0026194532,0.000552396,0.0013418947,0.0013700834,0.0010456932,0.00065234106],"category_scores_gemma":[0.07502078,0.00041916073,0.002478836,0.0013517226,0.00056914444,0.00076258567,0.00088521215,0.0012391673,0.00025361322],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014813051,0.00022614838,0.9635252,0.00011085209,0.001787834,0.00007053751,0.00015144965,0.009384346,0.00028875485,0.00015748663,0.0006819952,0.022133933],"study_design_scores_gemma":[0.00036487082,0.003502412,0.65807354,0.00027476373,0.0016745756,0.00075825606,0.0005133321,0.33018842,0.0016457305,0.0010021955,0.0018819907,0.000119924734],"about_ca_topic_score_codex":0.0093811555,"about_ca_topic_score_gemma":0.00699537,"teacher_disagreement_score":0.9371078,"about_ca_system_score_codex":0.0012002845,"about_ca_system_score_gemma":0.0014847444,"threshold_uncertainty_score":0.33260965},"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":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52156633,0.001651383,0.47212034,0.0006515902,0.00014073294,0.00046526807,0.0008446199,0.0014646413,0.0010950988],"genre_scores_gemma":[0.9214786,0.0001434878,0.07504027,0.00024424048,0.000059510556,0.00023442638,0.002024211,0.00008984137,0.00068533083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965835,0.0015746283,0.0003922933,0.0008097314,0.0003347336,0.0003051177],"domain_scores_gemma":[0.9941199,0.003472217,0.0005661237,0.0005959788,0.0009753088,0.00027046565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010552744,0.0010380183,0.0015896321,0.002124483,0.0005545092,0.001145898,0.0010581783,0.0016047943,0.0008290968],"category_scores_gemma":[0.009480522,0.00037080082,0.001981122,0.000713091,0.00046757693,0.00047070684,0.00077263097,0.0013605225,0.0003893616],"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":[0.0035702635,0.0011340637,0.23379391,0.00038500104,0.0013494712,0.0012794514,0.0010893595,0.2968754,0.02507376,0.0016833245,0.008816123,0.42494982],"study_design_scores_gemma":[0.00007521535,0.0003202625,0.020872356,0.000034605113,0.00012603855,0.00027293686,0.000093922754,0.97242945,0.0036741768,0.0011606549,0.0009103406,0.000029918112],"about_ca_topic_score_codex":0.0044552945,"about_ca_topic_score_gemma":0.003369705,"teacher_disagreement_score":0.010552744,"about_ca_system_score_codex":0.00059391133,"about_ca_system_score_gemma":0.0011866608,"threshold_uncertainty_score":0.05580896},"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":"protocol","genre_gemma":"review","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042542745,0.058550138,0.2073416,0.0124460105,0.004039318,0.6993642,0.009140114,0.0017522362,0.0031121215],"genre_scores_gemma":[0.008374892,0.013580873,0.24026859,0.0020732633,0.0002993896,0.7329096,0.0019073194,0.00015227162,0.00043370077],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.18420485,0.4727781,0.2977669,0.0073252223,0.03613365,0.0017913332],"domain_scores_gemma":[0.20211917,0.44750905,0.14652804,0.05274275,0.14769815,0.0034029074],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.66104937,0.005107927,0.011439717,0.02906727,0.004936807,0.010133707,0.0100240605,0.007021999,0.0071747215],"category_scores_gemma":[0.76754576,0.00609428,0.017932689,0.027148709,0.00798083,0.012400849,0.0097812805,0.008305482,0.003651116],"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":[0.00097318663,0.0002394369,0.003788263,0.6764197,0.0056101703,0.00024529538,0.012902528,0.0017164445,0.0014429782,0.009000334,0.050126776,0.23753496],"study_design_scores_gemma":[0.0039347047,0.0011648777,0.006585449,0.8016307,0.007746781,0.00041758196,0.004547633,0.0042743413,0.00274784,0.015467799,0.15066883,0.0008135027],"about_ca_topic_score_codex":0.0049105594,"about_ca_topic_score_gemma":0.008352796,"teacher_disagreement_score":0.33895063,"about_ca_system_score_codex":0.01615135,"about_ca_system_score_gemma":0.07986802,"threshold_uncertainty_score":0.4179865},"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":"methods","genre_gemma":"review","domain_codex":"methods","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018607252,0.08607854,0.8361682,0.04401964,0.0063399374,0.016418021,0.004858431,0.0014430014,0.0028135017],"genre_scores_gemma":[0.020370582,0.02500501,0.8952783,0.009956661,0.0017839107,0.045401964,0.0015679165,0.0002846002,0.00035113384],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.13767654,0.6342635,0.18312706,0.009991429,0.034102093,0.00083932583],"domain_scores_gemma":[0.05123325,0.7739837,0.05951535,0.059658494,0.054739162,0.00087005174],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.74468166,0.0036086608,0.008783156,0.019672642,0.0032659944,0.016480785,0.011651149,0.011333607,0.0036333292],"category_scores_gemma":[0.900713,0.0054139355,0.017078944,0.021988405,0.009231944,0.012245865,0.0092027765,0.01572349,0.0013505245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013173047,0.00018388985,0.009184701,0.28094617,0.033845723,0.0004753397,0.006955949,0.007968505,0.0011631872,0.13583657,0.07530703,0.44681558],"study_design_scores_gemma":[0.0041877357,0.00084755407,0.008029499,0.29491583,0.041123267,0.0010370129,0.0013834931,0.030994436,0.0067333453,0.36334932,0.24632059,0.001077934],"about_ca_topic_score_codex":0.0066786734,"about_ca_topic_score_gemma":0.0054719904,"teacher_disagreement_score":0.25531834,"about_ca_system_score_codex":0.009527448,"about_ca_system_score_gemma":0.03417158,"threshold_uncertainty_score":0.314853},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859715,0.0007073833,0.0015845413,0.00085154333,0.000029207305,0.00049354386,0.005951637,0.000018831055,0.0043917256],"genre_scores_gemma":[0.994787,0.0002660241,0.0020849977,0.0001964873,0.000009698959,0.00021906788,0.0020261034,0.0000062568897,0.0004044146],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99018717,0.0031269975,0.00091382384,0.0011913072,0.0033087088,0.0012718994],"domain_scores_gemma":[0.9677055,0.005374121,0.00709317,0.0023858824,0.016157018,0.001284328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016132697,0.0004269168,0.0003928493,0.0019258537,0.0025484508,0.0020956316,0.0015333702,0.0005506914,0.00081740686],"category_scores_gemma":[0.034483623,0.00033814542,0.0004848574,0.0034939095,0.0014778818,0.0007048801,0.0018554518,0.0005299129,0.00020632094],"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":[0.000035910318,0.000013215732,0.9884644,0.00008936215,0.000034662935,0.000054941444,0.0039530294,0.0001009295,0.00021939346,0.000104869636,0.0009907525,0.0059385393],"study_design_scores_gemma":[0.000006250525,0.00002014562,0.99320096,0.00015608559,0.000023386852,0.000034587134,0.0034640515,0.0005291002,0.00018586071,0.000046546516,0.0023196272,0.000013398125],"about_ca_topic_score_codex":0.9738669,"about_ca_topic_score_gemma":0.98033935,"teacher_disagreement_score":0.02613312,"about_ca_system_score_codex":0.020155903,"about_ca_system_score_gemma":0.030434376,"threshold_uncertainty_score":0.14624202},"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":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33604926,0.0055666845,0.045007754,0.050645705,0.00620803,0.53308314,0.0056101675,0.000933747,0.01689551],"genre_scores_gemma":[0.29619914,0.0010883516,0.055555128,0.015374484,0.0014027224,0.6256954,0.0021165435,0.00016966269,0.002398581],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.49667782,0.46495837,0.019826038,0.0051438245,0.009197982,0.0041959113],"domain_scores_gemma":[0.67102647,0.18939528,0.054125335,0.0507269,0.021938967,0.012787138],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38205308,0.0011829287,0.0020249092,0.00079406315,0.0024801404,0.0033839874,0.0032529365,0.0057402393,0.0068968195],"category_scores_gemma":[0.3547627,0.0012850601,0.0029622626,0.0017700335,0.0033890118,0.0029437307,0.003440449,0.0063813087,0.0016286193],"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":[0.61154675,0.017279316,0.0132945,0.007014697,0.0044191787,0.00062051724,0.0054967,0.0044183144,0.0026810935,0.008601036,0.056394402,0.2682335],"study_design_scores_gemma":[0.7590701,0.13365124,0.015611564,0.004938609,0.0018546667,0.0003561486,0.0011251417,0.0050186487,0.002722054,0.008190634,0.06712573,0.00033553725],"about_ca_topic_score_codex":0.0012936125,"about_ca_topic_score_gemma":0.0017576899,"teacher_disagreement_score":0.6179469,"about_ca_system_score_codex":0.0039922213,"about_ca_system_score_gemma":0.01891799,"threshold_uncertainty_score":0.7620386},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020626271,0.0073648705,0.96490777,0.0023711089,0.00027965693,0.00086041226,0.0008006986,0.000708573,0.0020806466],"genre_scores_gemma":[0.16990721,0.002989044,0.8214642,0.0009354687,0.00017136527,0.0031691047,0.00061444513,0.0002528078,0.0004963878],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9484687,0.0465441,0.001502352,0.001103022,0.0021745712,0.00020724678],"domain_scores_gemma":[0.57653457,0.39778203,0.0075477627,0.009422135,0.008000313,0.00071330153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.087047055,0.001766844,0.0028108093,0.0029911164,0.00083933875,0.0021687762,0.0034488824,0.0019158645,0.0034800954],"category_scores_gemma":[0.27788505,0.0010691258,0.004602006,0.003323358,0.0010365567,0.0021645846,0.0025484131,0.0026175452,0.0003654346],"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":[0.0011531892,0.0001483429,0.008001778,0.0038436656,0.005422518,0.00030074824,0.00044069352,0.79115766,0.00056879036,0.0452433,0.004608285,0.1391111],"study_design_scores_gemma":[0.000606044,0.00022216751,0.0011923573,0.0007051983,0.0012364847,0.00016147377,0.000090327296,0.95770574,0.00041599126,0.03386573,0.0037424206,0.000056011995],"about_ca_topic_score_codex":0.008651863,"about_ca_topic_score_gemma":0.01030241,"teacher_disagreement_score":0.91295296,"about_ca_system_score_codex":0.002368168,"about_ca_system_score_gemma":0.0059666117,"threshold_uncertainty_score":0.46035433},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.989856,0.0010047014,0.0048136157,0.00065711833,0.000036099555,0.00018093846,0.0025352275,0.000059819864,0.0008563964],"genre_scores_gemma":[0.99480927,0.00007895424,0.0033140166,0.00010964304,0.00003167697,0.00009212068,0.0014690392,0.000012285218,0.00008289301],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9694239,0.0205015,0.0019430252,0.0028192056,0.004232422,0.0010799743],"domain_scores_gemma":[0.8322843,0.12414874,0.025168706,0.007596622,0.0073356833,0.0034660008],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04988147,0.0008315968,0.0009055867,0.0025570772,0.0013520708,0.0022405055,0.0018016393,0.0010340057,0.0007910523],"category_scores_gemma":[0.10164462,0.0004881281,0.002742994,0.0029843324,0.0012277155,0.0017200256,0.0020176894,0.0017590014,0.00015345702],"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":[0.00014638629,0.000040910963,0.99647504,0.00002034619,0.00029822218,0.000009415572,0.00006744106,0.0006042995,0.000025793708,0.00003320717,0.00013585637,0.0021429386],"study_design_scores_gemma":[0.000018606583,0.0003168918,0.9869081,0.000042875352,0.0002287066,0.000052798376,0.00015942102,0.01170578,0.00013190303,0.00013521362,0.00027879534,0.000020944419],"about_ca_topic_score_codex":0.08519352,"about_ca_topic_score_gemma":0.081990965,"teacher_disagreement_score":0.95011854,"about_ca_system_score_codex":0.0028928376,"about_ca_system_score_gemma":0.0040499177,"threshold_uncertainty_score":0.26380157},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17464727,0.2559947,0.200954,0.1602512,0.00419071,0.068882704,0.06338582,0.010316684,0.06137682],"genre_scores_gemma":[0.27766636,0.05048078,0.61398536,0.0068807765,0.0005461635,0.035875298,0.011985475,0.00093837664,0.0016414957],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.5825261,0.24848342,0.13257805,0.008486606,0.024991324,0.0029345124],"domain_scores_gemma":[0.116142705,0.70223695,0.06925481,0.054778997,0.053801794,0.0037847806],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3823213,0.0012859048,0.0037992334,0.04141178,0.002786943,0.023440948,0.004909476,0.00388377,0.008616493],"category_scores_gemma":[0.7737766,0.0023484386,0.006930455,0.049717523,0.002573399,0.019130781,0.012116442,0.002702334,0.002048664],"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":[0.0019623218,0.00023950961,0.0350045,0.2257609,0.0051238183,0.00064236595,0.017991947,0.0015263621,0.0021653217,0.015545413,0.023820912,0.67021674],"study_design_scores_gemma":[0.002450782,0.0012992732,0.050491933,0.578559,0.028113257,0.0016921018,0.023638826,0.004216639,0.006567317,0.03780719,0.26410264,0.0010610049],"about_ca_topic_score_codex":0.006201448,"about_ca_topic_score_gemma":0.016953819,"teacher_disagreement_score":0.6176787,"about_ca_system_score_codex":0.012634017,"about_ca_system_score_gemma":0.049382206,"threshold_uncertainty_score":0.7617078},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004684112,0.00080751895,0.9345315,0.00036758147,0.00013468253,0.0004927697,0.00572042,0.052431587,0.000829871],"genre_scores_gemma":[0.030754836,0.00045708756,0.95515734,0.00021118196,0.00007795668,0.0021742107,0.0058923163,0.004201634,0.0010735614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995656,0.0018729251,0.0006899611,0.0008618976,0.000791331,0.00012790912],"domain_scores_gemma":[0.9722271,0.022174416,0.0018554913,0.0015447055,0.0019904522,0.00020782043],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016119275,0.0027654357,0.0022264258,0.008761003,0.0008066465,0.0028480375,0.0033336354,0.0017708213,0.015788103],"category_scores_gemma":[0.049403306,0.0019944876,0.0035097934,0.0049824943,0.00070665334,0.0018953778,0.002768554,0.0035777707,0.005145456],"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":[0.001371769,0.00020671386,0.017438402,0.0022376392,0.0022182777,0.0003511452,0.00093303464,0.10959386,0.003124583,0.012000236,0.10650403,0.7440203],"study_design_scores_gemma":[0.00080281915,0.00022361918,0.00448425,0.00031747555,0.0005351764,0.0005611191,0.0001412684,0.8863416,0.008014188,0.027203536,0.07115019,0.00022479842],"about_ca_topic_score_codex":0.0059318845,"about_ca_topic_score_gemma":0.007142184,"teacher_disagreement_score":0.9838807,"about_ca_system_score_codex":0.0017635268,"about_ca_system_score_gemma":0.004437806,"threshold_uncertainty_score":0.085247874},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16772415,0.0011115745,0.8248403,0.0026827566,0.00012383971,0.00015426188,0.00035106172,0.0005645289,0.0024475337],"genre_scores_gemma":[0.8447811,0.00061880244,0.15187772,0.0006821989,0.000093751776,0.00023284568,0.00034393705,0.000055722077,0.0013138916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639565,0.0026423729,0.00013213673,0.00041130194,0.0002609706,0.00015760673],"domain_scores_gemma":[0.97575265,0.018987402,0.001728382,0.0017171066,0.0014974163,0.000317137],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014726511,0.0007714075,0.0007755495,0.0006725644,0.00032057625,0.0012678052,0.0011237732,0.0010301557,0.002348051],"category_scores_gemma":[0.062313724,0.00043998993,0.0008981592,0.0006215755,0.0010817627,0.0021897887,0.0012118765,0.0017353459,0.00045261733],"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":[0.00065203884,0.00029575208,0.040319677,0.0003468449,0.0006232161,0.000106943946,0.00028420004,0.67243576,0.0011984163,0.036310367,0.0034750095,0.24395174],"study_design_scores_gemma":[0.000054750788,0.00009739415,0.002226555,0.00008507119,0.00006164726,0.000023850216,0.000025648871,0.96287686,0.00074646354,0.033055514,0.0007316079,0.000014683788],"about_ca_topic_score_codex":0.0048421593,"about_ca_topic_score_gemma":0.006034849,"teacher_disagreement_score":0.9852735,"about_ca_system_score_codex":0.0011915449,"about_ca_system_score_gemma":0.0021307475,"threshold_uncertainty_score":0.07788211},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9981493,0.00007174624,0.00019123536,0.00009643404,0.000010721609,0.00019932477,0.00017585467,0.000004754243,0.0011006579],"genre_scores_gemma":[0.9946648,0.0002539989,0.0034242081,0.000059844275,0.000005793221,0.00058897457,0.00041315847,0.000005045103,0.00058404653],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99937683,0.00023025165,0.00011389655,0.000047135458,0.00016910858,0.000062883635],"domain_scores_gemma":[0.9983809,0.00048462916,0.00036700664,0.00008548762,0.000455122,0.00022684682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023117594,0.00032242114,0.0003042441,0.0007261324,0.0005670262,0.00062650157,0.0003700887,0.00027752854,0.0019510782],"category_scores_gemma":[0.0050212024,0.00017812484,0.00050384126,0.00050544355,0.00040248563,0.00038118687,0.0007348806,0.0006395049,0.0002696385],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027438247,0.00077033974,0.87967396,0.0003128458,0.00007232495,0.0006564954,0.018170208,0.00030237477,0.0050792266,0.00043729812,0.0010500125,0.09320052],"study_design_scores_gemma":[0.000052773925,0.0007335447,0.97002274,0.00020730888,0.000035224246,0.000626873,0.02171393,0.0006957278,0.0013724194,0.00020417487,0.0043069334,0.000028407101],"about_ca_topic_score_codex":0.0013993557,"about_ca_topic_score_gemma":0.0035101438,"teacher_disagreement_score":0.0023117594,"about_ca_system_score_codex":0.0004918545,"about_ca_system_score_gemma":0.00085033104,"threshold_uncertainty_score":0.012225926},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063477107,0.7000272,0.1582199,0.037303433,0.0037191992,0.08073839,0.004954852,0.0012101199,0.007479225],"genre_scores_gemma":[0.039810803,0.31535533,0.480508,0.008605999,0.0009021634,0.15166737,0.0020583621,0.00038382222,0.0007080503],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.27322227,0.44258362,0.2193628,0.009533975,0.052985415,0.002311971],"domain_scores_gemma":[0.094040304,0.75636476,0.056098774,0.024030983,0.0676378,0.0018274164],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.624938,0.0057806517,0.016895814,0.10805767,0.006215546,0.026929136,0.009233449,0.008056102,0.008957825],"category_scores_gemma":[0.82212377,0.0073201517,0.020612232,0.07815244,0.008197584,0.027997753,0.017255848,0.007401392,0.0018527517],"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":[0.00037073813,0.00009010224,0.0029026743,0.69940084,0.006475954,0.00045453984,0.008703863,0.0009657093,0.00072807743,0.009348388,0.008879684,0.26167944],"study_design_scores_gemma":[0.00020830921,0.00012783159,0.0010872842,0.9532355,0.006791643,0.00021449267,0.002241657,0.0008841089,0.00042392386,0.005645969,0.029003913,0.00013529432],"about_ca_topic_score_codex":0.0050961883,"about_ca_topic_score_gemma":0.014162929,"teacher_disagreement_score":0.375062,"about_ca_system_score_codex":0.023476241,"about_ca_system_score_gemma":0.100499526,"threshold_uncertainty_score":0.46251827},"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":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000699801,0.9843709,0.0031388055,0.0009131531,0.00066550955,0.008834178,0.0006094359,0.000042536125,0.00072570314],"genre_scores_gemma":[0.022532249,0.9050694,0.027039587,0.0022278952,0.0007914779,0.041146528,0.00080568873,0.000047362057,0.0003397901],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8084589,0.11672425,0.052995127,0.004911776,0.015962673,0.0009472229],"domain_scores_gemma":[0.62521243,0.30543667,0.04759391,0.008138255,0.0128386365,0.0007800761],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11893111,0.002741552,0.009918188,0.013251903,0.0010679308,0.0059948633,0.0030740541,0.0039371382,0.009212782],"category_scores_gemma":[0.3156198,0.0021194497,0.011220824,0.01777501,0.0035776992,0.0067046853,0.0025524888,0.002980534,0.0012676085],"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":[0.00024717135,0.000028057842,0.00042402637,0.94801325,0.0050581293,0.000029669574,0.0001896913,0.00022480155,0.00011491697,0.0008375614,0.0020854906,0.042747192],"study_design_scores_gemma":[0.0009775191,0.00033742358,0.0018462258,0.9469469,0.02389198,0.00018711694,0.00017273815,0.00034732907,0.00020836177,0.0019800651,0.023051077,0.000053312968],"about_ca_topic_score_codex":0.002394486,"about_ca_topic_score_gemma":0.0053149853,"teacher_disagreement_score":0.8810689,"about_ca_system_score_codex":0.009302886,"about_ca_system_score_gemma":0.01882094,"threshold_uncertainty_score":0.62897533},"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":"review","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05042362,0.69589806,0.15438686,0.053531997,0.007822266,0.021652723,0.0044617513,0.00048515177,0.011337553],"genre_scores_gemma":[0.5399781,0.18453501,0.19530676,0.018286807,0.0029776637,0.055356324,0.002262914,0.000545695,0.0007508106],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.054499056,0.63221705,0.23335561,0.01526795,0.06290336,0.0017570058],"domain_scores_gemma":[0.012876393,0.7844272,0.12507166,0.027446736,0.049473733,0.0007043072],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8127444,0.0029004647,0.01315857,0.042572785,0.004313899,0.02618293,0.009315635,0.009082534,0.0034802428],"category_scores_gemma":[0.9648657,0.007986185,0.012328986,0.056286074,0.016010184,0.038624544,0.0148645565,0.007793799,0.0013309029],"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":[0.002531438,0.00018132481,0.08512305,0.49874467,0.058880188,0.0003513079,0.080174215,0.0018534665,0.00070479425,0.029813625,0.010014597,0.23162732],"study_design_scores_gemma":[0.0027947032,0.0011316659,0.04167699,0.7844532,0.034666564,0.0012297732,0.0247509,0.0040800977,0.0018990862,0.05755826,0.04494645,0.00081226975],"about_ca_topic_score_codex":0.004304952,"about_ca_topic_score_gemma":0.0049054823,"teacher_disagreement_score":0.18725562,"about_ca_system_score_codex":0.023085048,"about_ca_system_score_gemma":0.032992404,"threshold_uncertainty_score":0.2309196},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9060898,0.0006402964,0.05335076,0.01318994,0.00019651078,0.0147975385,0.00010060382,0.00020419549,0.011430553],"genre_scores_gemma":[0.8679887,0.00023786005,0.11931358,0.0014113622,0.000041980267,0.010522452,0.00004009802,0.00005277777,0.00039124896],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.43588576,0.51212305,0.018659685,0.0060197352,0.020732585,0.006579154],"domain_scores_gemma":[0.17518829,0.7466714,0.03303233,0.019264694,0.017486136,0.008357143],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.48493066,0.0009380633,0.0009533577,0.003117125,0.007987005,0.015892753,0.0036247598,0.0029858253,0.0034335828],"category_scores_gemma":[0.57640105,0.0013270507,0.0021477544,0.002977134,0.014982688,0.012627696,0.009057006,0.0063351025,0.0002763494],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010715437,0.0062866025,0.10680294,0.007510274,0.00068325334,0.0005340402,0.5522459,0.0016639103,0.0027768454,0.034640577,0.0023254887,0.2834585],"study_design_scores_gemma":[0.0021196273,0.018588312,0.18521146,0.008989111,0.0011537524,0.0009911142,0.6932029,0.013390793,0.0053579183,0.024110511,0.046396606,0.0004879533],"about_ca_topic_score_codex":0.0020167574,"about_ca_topic_score_gemma":0.0029498236,"teacher_disagreement_score":0.51506937,"about_ca_system_score_codex":0.021377694,"about_ca_system_score_gemma":0.05199188,"threshold_uncertainty_score":0.6351722},"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":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6309942,0.010790822,0.22386602,0.089161396,0.0017376117,0.029947948,0.0012137307,0.0007993948,0.011488966],"genre_scores_gemma":[0.8071799,0.0056668324,0.13904434,0.01482293,0.00042084098,0.030504072,0.0006001515,0.0004551904,0.00130564],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.3610824,0.5517806,0.052147534,0.0072004534,0.021881852,0.0059071225],"domain_scores_gemma":[0.22447096,0.6205271,0.061204452,0.021279842,0.06304421,0.00947346],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.53364617,0.0010593765,0.0024271726,0.010248612,0.0073277545,0.008522066,0.0046238746,0.004161232,0.0026793466],"category_scores_gemma":[0.64250994,0.0018116971,0.0027054998,0.009923915,0.016030628,0.014386812,0.020868946,0.0068620713,0.0007503901],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003453302,0.000104406325,0.012014184,0.0053436337,0.00011321641,0.0004774527,0.91722363,0.00049467565,0.0018868411,0.0041938843,0.00501382,0.052788936],"study_design_scores_gemma":[0.00024087395,0.0005943839,0.008695346,0.0075854408,0.0001164536,0.0010831377,0.9046595,0.003137614,0.0010815486,0.018707024,0.05384904,0.00024968942],"about_ca_topic_score_codex":0.002645846,"about_ca_topic_score_gemma":0.0019055116,"teacher_disagreement_score":0.46635383,"about_ca_system_score_codex":0.014935857,"about_ca_system_score_gemma":0.03520673,"threshold_uncertainty_score":0.5750973},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.920215,0.0036408706,0.06554171,0.0010569858,0.00017283096,0.0003143114,0.0077705286,0.00028092295,0.00100685],"genre_scores_gemma":[0.9619219,0.0008320012,0.03210643,0.000102674516,0.00008785886,0.0002773439,0.004211181,0.000036905938,0.00042383408],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99521834,0.0035318611,0.00020709987,0.00034898997,0.00049722055,0.00019642334],"domain_scores_gemma":[0.9840942,0.011428267,0.0019863734,0.00081817113,0.0011686244,0.0005043152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014432766,0.00080963667,0.0011346973,0.002031214,0.00037123446,0.00074137584,0.0010583245,0.00080298295,0.0012415448],"category_scores_gemma":[0.029215723,0.00036988253,0.0016729198,0.001569404,0.0002002684,0.00047687278,0.00060820434,0.001993758,0.00037532623],"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":[0.001502961,0.00022097953,0.93666136,0.0001138141,0.0012319431,0.00024054358,0.0001560476,0.024385883,0.0002688909,0.0007722063,0.0031204477,0.031324904],"study_design_scores_gemma":[0.00021803625,0.00079144794,0.46967915,0.00021427489,0.0010718849,0.00052189326,0.00025153422,0.51943326,0.00039312418,0.0041186493,0.0032306348,0.000076135635],"about_ca_topic_score_codex":0.017073527,"about_ca_topic_score_gemma":0.011978015,"teacher_disagreement_score":0.017073527,"about_ca_system_score_codex":0.00046437213,"about_ca_system_score_gemma":0.0009465219,"threshold_uncertainty_score":0.076328695},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9888592,0.00081134774,0.0023558878,0.0041105263,0.00009058406,0.0005618573,0.00017600482,0.000023400064,0.0030112974],"genre_scores_gemma":[0.994101,0.00078463694,0.0015123624,0.0013392514,0.000047501373,0.00072380196,0.00009570262,0.000025341751,0.0013704487],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9658015,0.028660115,0.0008209303,0.0009313384,0.0015804527,0.0022057837],"domain_scores_gemma":[0.9406531,0.048767228,0.0032372638,0.00072431815,0.0024482042,0.0041698646],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0403524,0.00052215514,0.0009576975,0.0012970305,0.0066959206,0.004607527,0.0024518322,0.0023634904,0.0025845817],"category_scores_gemma":[0.064608,0.00077231484,0.0006250201,0.0008749882,0.006431947,0.0044819717,0.0065775467,0.0041832807,0.00038668662],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000966299,0.00007569141,0.0048939656,0.00015889078,0.000007868644,0.00057444954,0.9888418,0.000025285737,0.00051445124,0.00041604537,0.00044623812,0.0039486894],"study_design_scores_gemma":[0.000013962635,0.00015373855,0.0026263543,0.00021996863,0.0000068433847,0.0002158548,0.9922152,0.00010994703,0.00021887317,0.0002619314,0.003933469,0.00002383054],"about_ca_topic_score_codex":0.0054599815,"about_ca_topic_score_gemma":0.0074472125,"teacher_disagreement_score":0.9596476,"about_ca_system_score_codex":0.003445611,"about_ca_system_score_gemma":0.005450528,"threshold_uncertainty_score":0.21340644},"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":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34111175,0.10082947,0.3464896,0.007116647,0.0010535979,0.17701079,0.011208022,0.0020558655,0.013124297],"genre_scores_gemma":[0.40441868,0.0087147225,0.4901831,0.0012148255,0.00023424829,0.09213103,0.0026038424,0.00027390997,0.00022560699],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.2126892,0.3615338,0.33668348,0.028938495,0.05722524,0.0029298689],"domain_scores_gemma":[0.12614597,0.64894176,0.09197517,0.054165613,0.0772243,0.0015471985],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.57672846,0.0033636412,0.011171081,0.041725177,0.004668545,0.012005784,0.005379996,0.0051731835,0.0031217427],"category_scores_gemma":[0.8342275,0.0045735515,0.023461968,0.03228971,0.0050971094,0.0139810145,0.009629958,0.0028289037,0.0011183923],"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":[0.012463129,0.0012961209,0.1832397,0.28445542,0.05631287,0.0014218416,0.029555582,0.005942561,0.008325336,0.008085914,0.005285572,0.403616],"study_design_scores_gemma":[0.021624135,0.014392841,0.23250891,0.298623,0.22941908,0.0055432366,0.014543773,0.05325356,0.033984773,0.036606025,0.055968095,0.0035325885],"about_ca_topic_score_codex":0.0028516704,"about_ca_topic_score_gemma":0.0058025266,"teacher_disagreement_score":0.42327154,"about_ca_system_score_codex":0.010400512,"about_ca_system_score_gemma":0.029994747,"threshold_uncertainty_score":0.5219692},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81219774,0.0186564,0.06039247,0.047000386,0.0020027142,0.000977189,0.0031030271,0.00015309874,0.055516943],"genre_scores_gemma":[0.9850093,0.0015650225,0.009360103,0.0024635552,0.00030846792,0.00020175602,0.0007308223,0.000048802427,0.0003122451],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8414604,0.067209296,0.025480928,0.01004239,0.05259266,0.003214274],"domain_scores_gemma":[0.32402468,0.48980814,0.06779934,0.033286918,0.083113536,0.001967403],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17123449,0.0007512251,0.00061346195,0.007491915,0.0027681,0.0027861826,0.003469538,0.0017961276,0.004195455],"category_scores_gemma":[0.40401757,0.0007622387,0.0028719297,0.0066994512,0.012785149,0.0033183803,0.0049612867,0.004277114,0.0005135885],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007094569,0.0001534336,0.8773329,0.0023806237,0.0010963696,0.00060740614,0.012215493,0.00053652097,0.0010990935,0.019272048,0.004965906,0.07963084],"study_design_scores_gemma":[0.00019650815,0.0006420834,0.8891688,0.008368427,0.0013052052,0.0031372563,0.0219984,0.0053132344,0.0052974415,0.027050246,0.03731961,0.00020271294],"about_ca_topic_score_codex":0.01474672,"about_ca_topic_score_gemma":0.013270697,"teacher_disagreement_score":0.8287655,"about_ca_system_score_codex":0.0051356237,"about_ca_system_score_gemma":0.0061210287,"threshold_uncertainty_score":0.90558535},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38394845,0.0031932811,0.56443334,0.031234588,0.00016816908,0.001281007,0.000979376,0.0001474868,0.014614351],"genre_scores_gemma":[0.86784196,0.00049089023,0.12831429,0.0018584726,0.0001682859,0.00045511726,0.00022673805,0.000024257828,0.0006199391],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91930544,0.0650882,0.0030319924,0.00503787,0.006253759,0.0012827531],"domain_scores_gemma":[0.6631385,0.30752274,0.015513535,0.0057869973,0.006577093,0.0014610891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.092661195,0.00105881,0.0020455916,0.0063931956,0.0023477403,0.0048151948,0.0027227274,0.005015988,0.003942702],"category_scores_gemma":[0.28236532,0.0010463663,0.0035253947,0.0045201033,0.005294557,0.0045061484,0.0035501586,0.0043826215,0.0002431714],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023731766,0.00050591514,0.2958635,0.0018193718,0.0042878683,0.008166446,0.024283811,0.17232497,0.0020410754,0.25317338,0.01063562,0.22452481],"study_design_scores_gemma":[0.00035272012,0.000425314,0.039831065,0.0012239672,0.0015917891,0.0027220317,0.0043216953,0.5113452,0.000746376,0.42762095,0.009563864,0.00025500872],"about_ca_topic_score_codex":0.015432549,"about_ca_topic_score_gemma":0.013369463,"teacher_disagreement_score":0.092661195,"about_ca_system_score_codex":0.005057922,"about_ca_system_score_gemma":0.003359743,"threshold_uncertainty_score":0.49004507},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01098034,0.008371864,0.9530161,0.019032618,0.00035576453,0.00091191614,0.00024379807,0.00019601874,0.006891511],"genre_scores_gemma":[0.28882688,0.003967336,0.6936627,0.006954762,0.00077385054,0.004140585,0.00021742807,0.00032429775,0.0011322197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.32699898,0.65012455,0.0066366405,0.0052144644,0.009786711,0.0012385562],"domain_scores_gemma":[0.11062209,0.86372447,0.0083896695,0.013036681,0.0036376552,0.0005893482],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45918927,0.002349148,0.0052234796,0.0028919163,0.0016175722,0.008422594,0.0037303679,0.009140089,0.0035951738],"category_scores_gemma":[0.63686585,0.0015353542,0.007660446,0.0035094682,0.010863999,0.008650133,0.0057550794,0.016896645,0.0006344984],"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":[0.002874753,0.00043902628,0.015708333,0.004037642,0.0034539304,0.0022701884,0.0030489666,0.08660293,0.0007447136,0.71380687,0.0066297404,0.16038294],"study_design_scores_gemma":[0.0009948835,0.0016489071,0.0027926038,0.0035802303,0.0011988535,0.0013729183,0.0007003385,0.24260838,0.0019307686,0.72232556,0.020577556,0.00026899963],"about_ca_topic_score_codex":0.0030897153,"about_ca_topic_score_gemma":0.0021217796,"teacher_disagreement_score":0.5408107,"about_ca_system_score_codex":0.004920269,"about_ca_system_score_gemma":0.0085031185,"threshold_uncertainty_score":0.6669159},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011474855,0.010038208,0.97022086,0.0035625703,0.0006135797,0.0013079774,0.00032309027,0.00026351734,0.0021954274],"genre_scores_gemma":[0.53336203,0.0064156577,0.44657522,0.003601608,0.0014858454,0.0063479138,0.00043561278,0.00024402338,0.0015321117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5725814,0.3731241,0.01728533,0.016491719,0.01864545,0.0018720448],"domain_scores_gemma":[0.20674142,0.71092945,0.040060587,0.03536956,0.00624532,0.0006536908],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.38585386,0.0015922603,0.0039361757,0.0029645113,0.0009341625,0.0045676376,0.003949813,0.0038172982,0.004730726],"category_scores_gemma":[0.6184887,0.0012961995,0.0067934413,0.003662645,0.008474258,0.0054485514,0.004272456,0.0045657908,0.00044872303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025286172,0.00017484286,0.041118205,0.011496959,0.0117896125,0.001042121,0.0025379898,0.047345944,0.0009439772,0.63868535,0.006211947,0.23612452],"study_design_scores_gemma":[0.0014516352,0.0008899958,0.009424811,0.0031847148,0.004731941,0.0011917724,0.00020070818,0.132942,0.0028054586,0.8326113,0.010353508,0.00021218728],"about_ca_topic_score_codex":0.0013777615,"about_ca_topic_score_gemma":0.0008505166,"teacher_disagreement_score":0.6141461,"about_ca_system_score_codex":0.0036408354,"about_ca_system_score_gemma":0.006091147,"threshold_uncertainty_score":0.7573515},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14969075,0.10025898,0.34352267,0.019194541,0.0027526675,0.24907151,0.08452786,0.017769795,0.033211213],"genre_scores_gemma":[0.09606155,0.014425238,0.7312913,0.0032729108,0.00067858567,0.12939951,0.021553662,0.000820353,0.00249687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8690527,0.04824689,0.06568103,0.005073477,0.010543016,0.0014028539],"domain_scores_gemma":[0.5544299,0.33927423,0.03991353,0.017041238,0.046326533,0.003014575],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15288655,0.0034520451,0.0077207806,0.060184155,0.0031707801,0.0053709783,0.0042823628,0.0039622267,0.015185383],"category_scores_gemma":[0.39088115,0.002326256,0.0059226663,0.031564567,0.001429757,0.007118132,0.0066159004,0.0015149047,0.0040513314],"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":[0.0043479186,0.00036870493,0.023209913,0.35259685,0.0043896683,0.0034680208,0.009657747,0.0018281477,0.01730292,0.005950503,0.06120539,0.51567423],"study_design_scores_gemma":[0.0089281965,0.005517998,0.11599885,0.29949403,0.04091691,0.00807331,0.009111592,0.014532961,0.022576664,0.022219442,0.450861,0.0017689357],"about_ca_topic_score_codex":0.0050587766,"about_ca_topic_score_gemma":0.012468332,"teacher_disagreement_score":0.84711343,"about_ca_system_score_codex":0.00405112,"about_ca_system_score_gemma":0.023810001,"threshold_uncertainty_score":0.8085511},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051133785,0.91465807,0.01146549,0.0018499679,0.0010041557,0.01628857,0.0014613816,0.00015247737,0.0019862053],"genre_scores_gemma":[0.5372032,0.35544255,0.0413905,0.005436376,0.00072088616,0.05727394,0.0017283524,0.00016813561,0.0006361034],"study_design_codex":"systematic_review","study_design_gemma":"qualitative","domain_scores_codex":[0.8208421,0.11980061,0.03885721,0.0077136527,0.011129661,0.0016567133],"domain_scores_gemma":[0.52854383,0.4123178,0.026951758,0.012495742,0.018085102,0.0016056966],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18872948,0.0028734049,0.012015142,0.020182297,0.0022775582,0.0072272434,0.004180866,0.0038230326,0.004982428],"category_scores_gemma":[0.35125187,0.002436911,0.022472357,0.017036667,0.0027152605,0.011863468,0.0047649764,0.0025832816,0.0005962387],"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":[0.0025141018,0.00036540406,0.0143314,0.762271,0.14793345,0.00030917727,0.010880658,0.00029366993,0.00031314083,0.0011069224,0.0013329176,0.0583481],"study_design_scores_gemma":[0.0026801378,0.0019454238,0.010403885,0.52822256,0.4358525,0.00051482057,0.008326916,0.00047215924,0.00070156483,0.0021117365,0.008593088,0.00017518812],"about_ca_topic_score_codex":0.004202374,"about_ca_topic_score_gemma":0.009496287,"teacher_disagreement_score":0.81127053,"about_ca_system_score_codex":0.008827065,"about_ca_system_score_gemma":0.013207009,"threshold_uncertainty_score":0.9981088},"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":"methods","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013974201,0.0116262315,0.9511411,0.008274088,0.0013407457,0.010103372,0.0010647464,0.00056842656,0.01448383],"genre_scores_gemma":[0.042684667,0.004035339,0.90540713,0.003305973,0.00076958636,0.042082947,0.00060832745,0.00022683763,0.0008791668],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.16024981,0.70199966,0.06938549,0.026647631,0.039415143,0.0023022597],"domain_scores_gemma":[0.10345693,0.78963727,0.036455162,0.04897482,0.020257253,0.0012184939],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.65584695,0.0077965884,0.009311064,0.04021898,0.0075857867,0.033064056,0.019796647,0.014785539,0.018841075],"category_scores_gemma":[0.75903374,0.005942582,0.027795635,0.029167352,0.035603937,0.037083607,0.02374105,0.016131176,0.0034362567],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042863868,0.00006344619,0.003127655,0.02058082,0.00497996,0.00045836344,0.012464758,0.002865541,0.00018885311,0.8562587,0.00407407,0.09450909],"study_design_scores_gemma":[0.0003268318,0.00016785269,0.0007278534,0.015698038,0.0026386345,0.00057213614,0.0015578414,0.0077222846,0.00087502814,0.93982625,0.029726436,0.00016080406],"about_ca_topic_score_codex":0.002764844,"about_ca_topic_score_gemma":0.0023887577,"teacher_disagreement_score":0.34415305,"about_ca_system_score_codex":0.02514802,"about_ca_system_score_gemma":0.020586554,"threshold_uncertainty_score":0.424402},"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":"commentary","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023787073,0.020594638,0.34892887,0.6109636,0.009922664,0.0019043557,0.00010172848,0.00041562217,0.004789822],"genre_scores_gemma":[0.10619108,0.024775,0.7398289,0.107904196,0.004230596,0.014416131,0.00017601799,0.0006099467,0.0018681735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.09329837,0.8442373,0.026393361,0.008354167,0.024861205,0.0028555845],"domain_scores_gemma":[0.0462864,0.79612845,0.021032305,0.06803535,0.062026214,0.0064912825],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8484514,0.004616949,0.0074270507,0.013167835,0.020999234,0.051618405,0.01863801,0.033627775,0.0069809537],"category_scores_gemma":[0.782825,0.0072589316,0.005502358,0.016572352,0.19934148,0.10085225,0.04594616,0.07138117,0.0047486555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026412847,0.00017784146,0.0015154212,0.013376427,0.00026836514,0.0006095766,0.24665248,0.00089663325,0.0012112852,0.6212072,0.025724486,0.088096045],"study_design_scores_gemma":[0.00023860022,0.00016573585,0.00043812866,0.047200724,0.00016380342,0.0007801176,0.081996895,0.0025523668,0.0009513811,0.69958615,0.16555125,0.00037497803],"about_ca_topic_score_codex":0.014598072,"about_ca_topic_score_gemma":0.013582585,"teacher_disagreement_score":0.15154862,"about_ca_system_score_codex":0.034987397,"about_ca_system_score_gemma":0.10469043,"threshold_uncertainty_score":0.25385255},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025874456,0.004192125,0.95637393,0.008105052,0.0006122371,0.000630146,0.0023579071,0.0004897196,0.0013644471],"genre_scores_gemma":[0.6250592,0.005023794,0.35537168,0.0035302301,0.0015306647,0.0034459177,0.0044598617,0.0002718121,0.0013068656],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8482005,0.12748128,0.008285582,0.008144525,0.006635144,0.0012530121],"domain_scores_gemma":[0.6246089,0.30562857,0.035368413,0.025561549,0.0076715513,0.0011611907],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13917913,0.001279196,0.0028210043,0.0021087234,0.0009674338,0.0031451464,0.0059079207,0.0034629465,0.003721956],"category_scores_gemma":[0.30562136,0.0011167704,0.0039001114,0.0036734426,0.0031586827,0.0033695018,0.003194283,0.0042197774,0.000753668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024872033,0.0004926321,0.14817412,0.012518897,0.0069213226,0.0031129355,0.0061444677,0.14309289,0.0017260885,0.19708656,0.026123926,0.45211902],"study_design_scores_gemma":[0.0006120082,0.0010379927,0.03782992,0.007719863,0.0021969578,0.002706245,0.0009306623,0.28335828,0.0031552098,0.6305786,0.029501755,0.00037261704],"about_ca_topic_score_codex":0.002558801,"about_ca_topic_score_gemma":0.001801654,"teacher_disagreement_score":0.8608209,"about_ca_system_score_codex":0.0019220363,"about_ca_system_score_gemma":0.00552829,"threshold_uncertainty_score":0.73605835},"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":"review","genre_gemma":"empirical","domain_codex":"reporting","domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":"reporting","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04285325,0.8010651,0.0897712,0.02208726,0.003551421,0.016067142,0.018946543,0.00037813673,0.0052799624],"genre_scores_gemma":[0.616712,0.18080956,0.09986146,0.0125901755,0.002227371,0.07449841,0.011735273,0.0003879619,0.0011778708],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.2733802,0.3256975,0.3355214,0.016299304,0.047394563,0.0017070081],"domain_scores_gemma":[0.0673331,0.7466578,0.12184866,0.030070124,0.032995142,0.0010951381],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5818158,0.0017955193,0.0064967643,0.01793252,0.0020739844,0.008417637,0.005582582,0.0037812858,0.0037758886],"category_scores_gemma":[0.8373703,0.0022609744,0.0101220235,0.016927803,0.004674194,0.006736721,0.0057894695,0.0027491588,0.00041693065],"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":[0.0028015273,0.00011501464,0.06924634,0.7001232,0.038979493,0.00038677818,0.0073058065,0.0019279688,0.0009253512,0.00842217,0.011067641,0.15869872],"study_design_scores_gemma":[0.0028817742,0.0012404573,0.0691704,0.70648915,0.091875106,0.0017171539,0.004330092,0.00620121,0.0047367737,0.032665342,0.07808925,0.0006032761],"about_ca_topic_score_codex":0.007797256,"about_ca_topic_score_gemma":0.0053123385,"teacher_disagreement_score":0.41818422,"about_ca_system_score_codex":0.009280956,"about_ca_system_score_gemma":0.018148178,"threshold_uncertainty_score":0.51569563},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014256134,0.023958387,0.95139706,0.002947994,0.0005992605,0.002071783,0.0018452854,0.0008922341,0.0020317817],"genre_scores_gemma":[0.2795454,0.0043412386,0.7095044,0.00090216857,0.00035683962,0.003558232,0.0010126043,0.00030398605,0.00047502603],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7167028,0.25881606,0.0091267545,0.007024383,0.0077610533,0.00056885084],"domain_scores_gemma":[0.5765047,0.39897984,0.0099931,0.009022411,0.0045933155,0.00090673816],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.13941805,0.0028697075,0.005617764,0.011752656,0.0010791298,0.0056507518,0.003522091,0.002183109,0.0033157207],"category_scores_gemma":[0.32749695,0.0011127389,0.010704726,0.007961411,0.0015241366,0.0035585184,0.0026618012,0.004293332,0.0003206481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050335904,0.00022493613,0.02325478,0.024783036,0.0733308,0.00049425603,0.0007849321,0.36277828,0.0011271837,0.050593514,0.015333024,0.44226167],"study_design_scores_gemma":[0.0014997872,0.0013539625,0.0062065283,0.0031726963,0.02783127,0.00051359774,0.0001690332,0.7129679,0.0018759306,0.229659,0.014356412,0.0003939378],"about_ca_topic_score_codex":0.003548184,"about_ca_topic_score_gemma":0.0062207854,"teacher_disagreement_score":0.86058193,"about_ca_system_score_codex":0.0036865654,"about_ca_system_score_gemma":0.003643024,"threshold_uncertainty_score":0.737322},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9103109,0.014861145,0.040867373,0.0057639955,0.00057281816,0.0021916784,0.016384954,0.00038917916,0.008657859],"genre_scores_gemma":[0.95004505,0.0022170087,0.039978076,0.00056679884,0.000117337266,0.00073098525,0.0051256213,0.00009853311,0.0011205426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.91059273,0.056542568,0.004227035,0.0045867977,0.02126697,0.0027838114],"domain_scores_gemma":[0.7804984,0.1497444,0.02276924,0.012408651,0.032087766,0.0024914683],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09286517,0.0013727628,0.0011457179,0.0040479237,0.0030656252,0.0038206344,0.0044692117,0.0010000055,0.0014403872],"category_scores_gemma":[0.24695003,0.00071533845,0.004242558,0.01092681,0.0020297929,0.0016982113,0.0038873265,0.0017529549,0.00022344684],"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":[0.0013961077,0.00014020779,0.921586,0.0007739337,0.0036332295,0.00009382669,0.0016091983,0.01213516,0.00015575725,0.0028362838,0.004169618,0.051470667],"study_design_scores_gemma":[0.0004279028,0.00065464375,0.9142412,0.0008778597,0.0015383243,0.00014052687,0.0031552478,0.06474358,0.00070896157,0.0020440593,0.011207864,0.00025986816],"about_ca_topic_score_codex":0.9564648,"about_ca_topic_score_gemma":0.95592904,"teacher_disagreement_score":0.9651975,"about_ca_system_score_codex":0.034802493,"about_ca_system_score_gemma":0.047857054,"threshold_uncertainty_score":0.4911238},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015574351,0.2513642,0.5911885,0.07176077,0.00455598,0.039809514,0.0019372744,0.0015833589,0.02222601],"genre_scores_gemma":[0.08055851,0.028842114,0.85191536,0.0074038263,0.0008334645,0.029419413,0.00037144817,0.00018433125,0.00047146695],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.04281973,0.89466774,0.038183987,0.0037850759,0.020014789,0.00052866596],"domain_scores_gemma":[0.022242334,0.9050408,0.023367096,0.033817224,0.015006236,0.00052628294],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.76225686,0.004605281,0.012748506,0.04837372,0.005601249,0.021088272,0.0056633553,0.008606726,0.00447141],"category_scores_gemma":[0.86377394,0.0031377578,0.0105704535,0.040894352,0.020371474,0.023090178,0.018132435,0.007600347,0.0013770787],"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":[0.0023309866,0.00027131903,0.006267857,0.34286085,0.014947251,0.0013564845,0.041179974,0.0052156127,0.0021914274,0.12440555,0.019750003,0.4392226],"study_design_scores_gemma":[0.0030765662,0.0022637588,0.0065611564,0.4548228,0.011481793,0.0038794717,0.009790061,0.022589823,0.0050085303,0.312744,0.16635562,0.0014263806],"about_ca_topic_score_codex":0.0033503454,"about_ca_topic_score_gemma":0.0070453505,"teacher_disagreement_score":0.23774314,"about_ca_system_score_codex":0.019063504,"about_ca_system_score_gemma":0.03546216,"threshold_uncertainty_score":0.2931797},"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":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060778703,0.004074607,0.005402564,0.9689938,0.0037624221,0.0006784655,0.00011559472,0.00004675618,0.010847966],"genre_scores_gemma":[0.2562425,0.011261429,0.06791703,0.64273113,0.007144688,0.0072574182,0.00020665166,0.0001677172,0.007071333],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.56112665,0.34690166,0.036393315,0.0040081604,0.04774238,0.0038278082],"domain_scores_gemma":[0.25743097,0.6394535,0.02119868,0.008899483,0.0656229,0.007394467],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36603498,0.00042617458,0.0007678351,0.003689805,0.0064856266,0.010249307,0.0029832756,0.013215513,0.003102601],"category_scores_gemma":[0.5760242,0.0007099745,0.0009630269,0.004500864,0.00901802,0.008482307,0.010449814,0.012997593,0.0009065886],"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":[0.00031189134,0.00017643049,0.022607652,0.005069884,0.00012738153,0.0031487504,0.097712934,0.0005218739,0.0014350306,0.057780854,0.5009395,0.31016794],"study_design_scores_gemma":[0.00033551935,0.0009652632,0.033916127,0.034488887,0.00018708082,0.00453733,0.09003187,0.005278126,0.0016097052,0.071583435,0.7564195,0.0006472053],"about_ca_topic_score_codex":0.016747946,"about_ca_topic_score_gemma":0.046111472,"teacher_disagreement_score":0.633965,"about_ca_system_score_codex":0.0194442,"about_ca_system_score_gemma":0.043263946,"threshold_uncertainty_score":0.78179175},"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":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"reporting","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"reporting","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037715577,0.92955536,0.019304913,0.0022791943,0.0017358554,0.006273131,0.0016693557,0.00013920435,0.0013274342],"genre_scores_gemma":[0.7958039,0.13658066,0.04074135,0.0049773846,0.0014884021,0.017803574,0.0017457382,0.00013532443,0.00072368945],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.61816,0.2664571,0.0809598,0.012307185,0.020616503,0.0014993871],"domain_scores_gemma":[0.4578795,0.44520614,0.0676542,0.016181441,0.012116796,0.0009619465],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22499448,0.0032327056,0.0154812755,0.009855834,0.001216943,0.0065175393,0.0027001014,0.0046836627,0.0038056676],"category_scores_gemma":[0.38071033,0.0020870515,0.047773864,0.00788235,0.0020274548,0.004731076,0.0030793033,0.0027656711,0.00035233697],"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":[0.005902831,0.00009764787,0.023963254,0.16079207,0.7917638,0.00014164187,0.00028310993,0.00062149647,0.00028537857,0.0006493421,0.0005014438,0.014998051],"study_design_scores_gemma":[0.0034311253,0.0011823066,0.014708136,0.04533553,0.9280094,0.00026173468,0.00026132737,0.0012766877,0.0005151785,0.0021724005,0.0027522345,0.000093958064],"about_ca_topic_score_codex":0.0013424559,"about_ca_topic_score_gemma":0.002088492,"teacher_disagreement_score":0.9967673,"about_ca_system_score_codex":0.0034066443,"about_ca_system_score_gemma":0.0042937594,"threshold_uncertainty_score":0.95571977},"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":"protocol","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035789113,0.23186919,0.17730004,0.16078138,0.060013432,0.29096,0.021266075,0.0024992467,0.01952158],"genre_scores_gemma":[0.2183206,0.04761308,0.25505266,0.031635623,0.0055054394,0.4338203,0.0036642824,0.0011331176,0.0032549943],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.078578316,0.46149182,0.35210052,0.015085934,0.089537725,0.0032057425],"domain_scores_gemma":[0.01913867,0.7277472,0.09338307,0.04490346,0.11328305,0.0015445766],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.76488703,0.006281074,0.014365832,0.046054095,0.008495753,0.022825444,0.011218412,0.017655501,0.0076280977],"category_scores_gemma":[0.9477123,0.008809644,0.013982442,0.032448344,0.02313821,0.013651044,0.0146319205,0.011321634,0.0024616285],"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":[0.0030909278,0.00014174185,0.0097153615,0.6910465,0.017741269,0.0021793412,0.059870765,0.0023392974,0.0018438363,0.0332655,0.06935832,0.109407164],"study_design_scores_gemma":[0.0017657831,0.00053529174,0.0042947587,0.77004397,0.015309408,0.0008081554,0.009604715,0.004209378,0.003984941,0.048093308,0.14066587,0.000684298],"about_ca_topic_score_codex":0.0062324107,"about_ca_topic_score_gemma":0.009030362,"teacher_disagreement_score":0.23511297,"about_ca_system_score_codex":0.0311451,"about_ca_system_score_gemma":0.098773524,"threshold_uncertainty_score":0.28993618},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36900684,0.004353611,0.62020296,0.0010479077,0.00014393973,0.0006149736,0.00039423263,0.0014049285,0.002830653],"genre_scores_gemma":[0.79682165,0.0008101901,0.20027745,0.0003448474,0.000057320693,0.00044600872,0.0005262551,0.00020223718,0.00051403063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996402,0.0022819515,0.00021840264,0.0005462863,0.0004104026,0.00014085663],"domain_scores_gemma":[0.9859504,0.010777599,0.0008235763,0.00090559653,0.0013062254,0.00023656452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013664384,0.0013135863,0.0011012711,0.0013208934,0.00046815467,0.0010058581,0.0015187452,0.001599775,0.0007454448],"category_scores_gemma":[0.02723085,0.0005851276,0.0013139498,0.0008658766,0.00056583737,0.0011907252,0.0012762187,0.0020873684,0.00028983405],"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":[0.0009905886,0.00042652854,0.017330756,0.00027686512,0.00066419464,0.000059545207,0.00017560259,0.86145425,0.0015284528,0.0015085252,0.0013189621,0.11426571],"study_design_scores_gemma":[0.000110633126,0.0002095767,0.0039839516,0.00006717601,0.00008304486,0.00004186492,0.000036361358,0.9913668,0.0017444675,0.0018715708,0.0004555218,0.000029069397],"about_ca_topic_score_codex":0.005448135,"about_ca_topic_score_gemma":0.0037274999,"teacher_disagreement_score":0.013664384,"about_ca_system_score_codex":0.0011564284,"about_ca_system_score_gemma":0.0016168685,"threshold_uncertainty_score":0.07226503},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4859695,0.007046556,0.49664804,0.0017583644,0.00029716152,0.0027556787,0.001062376,0.00057069084,0.003891723],"genre_scores_gemma":[0.8248186,0.00130059,0.16935502,0.00038816707,0.00011079495,0.0027926783,0.00074774196,0.00009093204,0.0003954717],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9439428,0.050953086,0.0014750194,0.00143702,0.0016456961,0.0005463748],"domain_scores_gemma":[0.40690872,0.56535715,0.008363576,0.009452133,0.00849014,0.0014282869],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09983845,0.0013182542,0.0019977754,0.003082852,0.00071347604,0.0016421049,0.002960096,0.0028601314,0.0026284445],"category_scores_gemma":[0.23561038,0.0009817128,0.0045840987,0.0021392687,0.0012187405,0.0020795974,0.0017884618,0.002687409,0.00025932977],"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":[0.008290622,0.0010779346,0.06996684,0.0017958864,0.0042279596,0.0004243614,0.0008736577,0.8241999,0.00062249735,0.01334753,0.0022268712,0.07294586],"study_design_scores_gemma":[0.0011957476,0.0013903291,0.0068410966,0.00042983107,0.00072942954,0.00027529502,0.00013258879,0.97963834,0.00063622463,0.007641908,0.0009994044,0.00008989167],"about_ca_topic_score_codex":0.007539819,"about_ca_topic_score_gemma":0.0036702189,"teacher_disagreement_score":0.90016156,"about_ca_system_score_codex":0.0025786073,"about_ca_system_score_gemma":0.002652802,"threshold_uncertainty_score":0.5280025},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.143572,0.1683511,0.6332348,0.007917442,0.0056326296,0.023595158,0.0050443183,0.0014843682,0.011168238],"genre_scores_gemma":[0.8358261,0.0078032617,0.12649874,0.0026880011,0.0008546703,0.023084905,0.0014993547,0.00056210655,0.0011828886],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.2188178,0.71657807,0.03044872,0.014200519,0.018298848,0.0016561141],"domain_scores_gemma":[0.13449769,0.81280535,0.019998096,0.026885679,0.0048838267,0.0009294468],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.55365825,0.003102253,0.013725101,0.006430658,0.0011436613,0.0062864604,0.004776174,0.0063819224,0.0055435207],"category_scores_gemma":[0.72441286,0.0016562254,0.05327442,0.0066043683,0.0055286437,0.007913653,0.0048738862,0.008083879,0.00042231803],"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":[0.070314735,0.00038648603,0.045497924,0.040795162,0.6263843,0.0012176073,0.0031381203,0.041887812,0.0013538669,0.039661825,0.006799058,0.12256304],"study_design_scores_gemma":[0.050990004,0.027002383,0.07214353,0.017897531,0.33740014,0.002847628,0.0012149173,0.1715285,0.005777106,0.2856105,0.026092922,0.0014948896],"about_ca_topic_score_codex":0.001263655,"about_ca_topic_score_gemma":0.0013434322,"teacher_disagreement_score":0.44634175,"about_ca_system_score_codex":0.003876171,"about_ca_system_score_gemma":0.0039397646,"threshold_uncertainty_score":0.55041885},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9688709,0.0021966638,0.0005064848,0.0008513395,0.000035052875,0.0003052124,0.022081299,0.00003287011,0.0051202886],"genre_scores_gemma":[0.98991895,0.0012379184,0.00090216286,0.00031707803,0.000008320324,0.0001334431,0.0061059175,0.000011256143,0.0013648983],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99787843,0.00018285199,0.00021986605,0.00033786998,0.00072776136,0.00065329246],"domain_scores_gemma":[0.99512404,0.00031800475,0.00062176975,0.00014573931,0.0029228728,0.0008676475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012558379,0.0004546623,0.0005164059,0.002976099,0.0036728336,0.0018050814,0.002243993,0.00051677646,0.0017553094],"category_scores_gemma":[0.006058311,0.00045079555,0.00049529725,0.0078158295,0.0007795451,0.0004886236,0.0018111478,0.00087335025,0.00024528458],"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":[0.00008328749,0.000033333825,0.98202765,0.00014493921,0.00006873037,0.000104504375,0.0017269902,0.00029458114,0.00014317236,0.0001918855,0.0037855098,0.011395462],"study_design_scores_gemma":[0.000009320012,0.000016904536,0.9936846,0.00015104224,0.000036701305,0.00005143096,0.0036530932,0.00053739134,0.000085048494,0.000048266193,0.0017098101,0.000016518155],"about_ca_topic_score_codex":0.99883157,"about_ca_topic_score_gemma":0.99940276,"teacher_disagreement_score":0.054683857,"about_ca_system_score_codex":0.054683857,"about_ca_system_score_gemma":0.058263972,"threshold_uncertainty_score":0.396761},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020819368,0.028004028,0.4805031,0.360852,0.0028363015,0.005678949,0.00033434923,0.0004010203,0.10057093],"genre_scores_gemma":[0.27614763,0.010227677,0.68750274,0.015420954,0.00048683007,0.0046588304,0.0003037923,0.00013364688,0.0051178834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.809898,0.16412288,0.007955957,0.0043993006,0.008587687,0.005036108],"domain_scores_gemma":[0.80779636,0.15225123,0.0065130363,0.0050312667,0.020897198,0.0075109573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12035807,0.0017694168,0.0013454702,0.008868274,0.013620017,0.017915213,0.005067792,0.011764636,0.003965985],"category_scores_gemma":[0.12849797,0.0010918025,0.004002049,0.0072552664,0.02501954,0.015058597,0.015518612,0.011404358,0.0007691159],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008663827,0.00012754484,0.0016705012,0.0035063848,0.00007436114,0.0016236684,0.0662694,0.0047779307,0.0004331926,0.84957606,0.015225776,0.056628633],"study_design_scores_gemma":[0.00025407356,0.00035512433,0.0015023231,0.009654395,0.00015015424,0.0017950032,0.045348253,0.008928847,0.0006516297,0.53142166,0.3997032,0.0002353093],"about_ca_topic_score_codex":0.026708037,"about_ca_topic_score_gemma":0.038502954,"teacher_disagreement_score":0.12035807,"about_ca_system_score_codex":0.035036266,"about_ca_system_score_gemma":0.07087275,"threshold_uncertainty_score":0.63652194},"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":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40908584,0.0072436626,0.5646355,0.0025289366,0.0008701016,0.011160908,0.0009209898,0.000506112,0.003047892],"genre_scores_gemma":[0.82729363,0.0013607459,0.15588558,0.000736023,0.0001311313,0.013133373,0.00046028054,0.00007252623,0.00092664006],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8438443,0.14765753,0.0030717608,0.0028182284,0.0016503109,0.00095790427],"domain_scores_gemma":[0.45648244,0.5127249,0.013539092,0.011911475,0.004149189,0.00119288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15987003,0.0019633465,0.004426467,0.0013489736,0.00048228275,0.0019024299,0.001925259,0.0031308567,0.0036295815],"category_scores_gemma":[0.262288,0.0010626581,0.007723897,0.0011456269,0.0021657322,0.0021839358,0.0021695318,0.0039782985,0.0003020459],"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":[0.12505065,0.0050361017,0.018367002,0.0071740355,0.021813564,0.00081762514,0.0010937601,0.70920527,0.0023914261,0.04571518,0.0020894944,0.061245997],"study_design_scores_gemma":[0.04468298,0.032928396,0.0043000476,0.00095912867,0.008885362,0.0003258014,0.00019032776,0.8503272,0.0026277283,0.051091056,0.003431542,0.00025041268],"about_ca_topic_score_codex":0.0019112126,"about_ca_topic_score_gemma":0.0008782169,"teacher_disagreement_score":0.84013,"about_ca_system_score_codex":0.0020995233,"about_ca_system_score_gemma":0.0034151978,"threshold_uncertainty_score":0.84548366},"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":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000688322,0.00010671814,0.0070743267,0.00021282965,0.00018204717,0.99002844,0.0010518592,0.0002678305,0.00038757143],"genre_scores_gemma":[0.00033197642,0.00001952308,0.0057641976,0.00003234706,0.0000067768988,0.99370474,0.00007267214,0.000009549443,0.000058172594],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6840594,0.22391938,0.058564633,0.012697773,0.01578455,0.0049742223],"domain_scores_gemma":[0.5142837,0.25597507,0.06330341,0.07851917,0.08067188,0.0072468063],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31058222,0.0071088574,0.0073711025,0.008176475,0.005104705,0.004843885,0.0052601937,0.008471794,0.053301986],"category_scores_gemma":[0.42442533,0.0059811524,0.012055909,0.008252203,0.00697935,0.007306986,0.0064735194,0.011704097,0.016260892],"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":[0.18427007,0.009862248,0.0071929563,0.23245437,0.008198351,0.0020396567,0.020258764,0.018430227,0.011720743,0.030010602,0.17663677,0.29892528],"study_design_scores_gemma":[0.33150268,0.03187759,0.020833837,0.091709815,0.005974621,0.0011256469,0.0053950674,0.0389812,0.016141295,0.066914685,0.38703883,0.002504758],"about_ca_topic_score_codex":0.002830311,"about_ca_topic_score_gemma":0.0064918697,"teacher_disagreement_score":0.6894178,"about_ca_system_score_codex":0.01250082,"about_ca_system_score_gemma":0.03694225,"threshold_uncertainty_score":0.8501749},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010753075,0.00026359863,0.96695495,0.0022508255,0.00020178202,0.024068423,0.00061827083,0.003087677,0.0014791507],"genre_scores_gemma":[0.0025617387,0.00009466969,0.9768267,0.00025145005,0.000041534327,0.019502383,0.00031753513,0.0001851426,0.00021884707],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.64131767,0.28262943,0.044927254,0.0085558565,0.019961746,0.0026080431],"domain_scores_gemma":[0.4194497,0.4393694,0.033496164,0.042352438,0.055560533,0.00977177],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45018792,0.0055283993,0.0033463372,0.016919663,0.0041639106,0.01262719,0.009492059,0.007537861,0.009534758],"category_scores_gemma":[0.42375225,0.005090529,0.0070433463,0.008578697,0.008024521,0.01155779,0.014847571,0.011170845,0.0058184206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010855007,0.0015087482,0.0057144486,0.024369152,0.0011921825,0.0012480116,0.0385716,0.024366304,0.009597599,0.16195816,0.0681804,0.66220784],"study_design_scores_gemma":[0.002872818,0.002361897,0.004655974,0.032946203,0.0011731804,0.0014678895,0.006951229,0.09760936,0.012148168,0.24548417,0.5912454,0.001083709],"about_ca_topic_score_codex":0.003637146,"about_ca_topic_score_gemma":0.0046578352,"teacher_disagreement_score":0.5498121,"about_ca_system_score_codex":0.012030904,"about_ca_system_score_gemma":0.051047087,"threshold_uncertainty_score":0.6780162},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9816989,0.0017223065,0.0058511333,0.0019867902,0.00007658204,0.0006523151,0.0003878066,0.00004073312,0.0075835637],"genre_scores_gemma":[0.9947025,0.00049607834,0.0038955607,0.00012583633,0.000015202755,0.0003164101,0.00015992275,0.00001576227,0.0002727095],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.6891568,0.20429648,0.028994163,0.011396919,0.057421595,0.008734072],"domain_scores_gemma":[0.48578662,0.30811453,0.065956965,0.026335921,0.102246046,0.011559935],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24087365,0.00032973752,0.0010260908,0.007958177,0.007117795,0.006963067,0.0027273449,0.00094078964,0.0007700561],"category_scores_gemma":[0.42111284,0.0008251199,0.0009983768,0.01228262,0.0069529945,0.0033538295,0.012949495,0.0016386096,0.00011520056],"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":[0.00034505696,0.000060729388,0.49995297,0.0014381708,0.00028171163,0.00035678776,0.438286,0.00029745375,0.0011850983,0.0025008041,0.0011501428,0.05414507],"study_design_scores_gemma":[0.00004425651,0.00025891038,0.6168128,0.0015751638,0.00021660041,0.0005571692,0.36032575,0.0022581972,0.001199602,0.0021278446,0.014440217,0.00018352247],"about_ca_topic_score_codex":0.1953116,"about_ca_topic_score_gemma":0.2573332,"teacher_disagreement_score":0.97952676,"about_ca_system_score_codex":0.020473212,"about_ca_system_score_gemma":0.04258757,"threshold_uncertainty_score":0.9361379},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.094060645,0.0016924232,0.89650565,0.0025492029,0.00034156325,0.0012334188,0.0010331545,0.00090808375,0.0016759017],"genre_scores_gemma":[0.70273197,0.0007650167,0.28724656,0.002589272,0.00018376972,0.0027703093,0.001555469,0.000381429,0.0017761932],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.92297137,0.065361194,0.0035898623,0.0044473256,0.002412978,0.001217221],"domain_scores_gemma":[0.66082454,0.29337627,0.019333009,0.01958727,0.0056976434,0.0011812515],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15385564,0.001965736,0.003696228,0.0011692139,0.0008887644,0.0025600598,0.0032165973,0.0023240987,0.002908745],"category_scores_gemma":[0.31102088,0.0011333427,0.0056773704,0.0016163898,0.0024604907,0.002777897,0.0026042317,0.0042675333,0.00052052597],"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":[0.008328205,0.00063737936,0.14907174,0.0019270018,0.009610847,0.0020953126,0.0022749987,0.5334234,0.0023470337,0.052895647,0.01101048,0.22637792],"study_design_scores_gemma":[0.0020739266,0.0012982788,0.019648083,0.0006735256,0.002721745,0.0009829345,0.00028746616,0.8437225,0.0024734265,0.11655482,0.00931728,0.00024601055],"about_ca_topic_score_codex":0.008316691,"about_ca_topic_score_gemma":0.0063769836,"teacher_disagreement_score":0.8461444,"about_ca_system_score_codex":0.0013988015,"about_ca_system_score_gemma":0.003370746,"threshold_uncertainty_score":0.8136761},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097221404,0.9864936,0.0037976876,0.0017620478,0.00060954154,0.0039097415,0.00035007915,0.000026431131,0.0020787178],"genre_scores_gemma":[0.01005941,0.9698211,0.008773237,0.00067645614,0.00016771199,0.009875066,0.00030881216,0.00002022444,0.0002980139],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9140283,0.056318004,0.01778165,0.002343864,0.008391381,0.0011368643],"domain_scores_gemma":[0.7043819,0.2461179,0.01805939,0.0058782706,0.024320744,0.0012418821],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10522182,0.0020358912,0.008067145,0.044136837,0.0039704684,0.010410273,0.0047287215,0.005102662,0.0069678826],"category_scores_gemma":[0.23972268,0.0022719589,0.0061920276,0.049852982,0.004342763,0.011015263,0.008608761,0.0030860868,0.001219601],"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":[0.00013161138,0.00006668054,0.0010157354,0.722878,0.0012023603,0.00032600496,0.009823486,0.00044643626,0.00020607802,0.0057320464,0.0074506416,0.25072098],"study_design_scores_gemma":[0.000021657666,0.000050050417,0.0005215836,0.96331394,0.0011325966,0.00017634405,0.0039583626,0.00012092898,0.0000847708,0.0014587744,0.029135471,0.000025477264],"about_ca_topic_score_codex":0.00856426,"about_ca_topic_score_gemma":0.016840879,"teacher_disagreement_score":0.8947782,"about_ca_system_score_codex":0.013220421,"about_ca_system_score_gemma":0.036911167,"threshold_uncertainty_score":0.55647284},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021073548,0.0013329985,0.9419158,0.020084543,0.0000942062,0.00019618012,0.00027790488,0.00015781596,0.014866995],"genre_scores_gemma":[0.750447,0.0008740662,0.24497469,0.0010880493,0.0002681115,0.000449016,0.00030208548,0.00006374629,0.0015332521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9768563,0.018071953,0.0010151009,0.0017103883,0.0017542959,0.0005919642],"domain_scores_gemma":[0.8300922,0.1499892,0.008091643,0.0075326543,0.0030492987,0.0012450437],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025076319,0.0011031281,0.0009812148,0.0058351234,0.00180785,0.00623311,0.0038932539,0.004099049,0.0061107716],"category_scores_gemma":[0.08162474,0.0007958285,0.0020176233,0.003032766,0.018927367,0.0126006715,0.006075005,0.00426957,0.00036960235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015226656,0.000023229773,0.0007430965,0.00011817726,0.00004441887,0.00012537757,0.0009770395,0.01021386,0.000083147854,0.9825508,0.00037807686,0.004727578],"study_design_scores_gemma":[0.000012990602,0.000010536939,0.00014703031,0.00008509283,0.000016890363,0.000051490864,0.0001788007,0.029544355,0.00008463758,0.96843064,0.0014256024,0.00001199519],"about_ca_topic_score_codex":0.003098723,"about_ca_topic_score_gemma":0.0024345384,"teacher_disagreement_score":0.9749237,"about_ca_system_score_codex":0.004671479,"about_ca_system_score_gemma":0.002965666,"threshold_uncertainty_score":0.13261783},"labels":[],"label_agreement":null}]}