{"id":"W4387440449","doi":"10.1136/fmch-2023-002437","title":"Trustworthy evidence-based versus untrustworthy guidelines: detecting the difference","year":2023,"lang":"en","type":"article","venue":"Family Medicine and Community Health","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"Einstein Stiftung Berlin","keywords":"Trustworthiness; Health professionals; Psychology; Certainty; Evidence-based medicine; Health care; Scientific evidence; Computer science; Medicine; Social psychology; Alternative medicine; Political science; Epistemology; Mathematics; Law; Pathology; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4780678,0.0006659733,0.002538676,0.01019831,0.003114628,0.01210852,0.002756998,0.005261029,0.001998964],"category_scores_gemma":[0.8625109,0.00126348,0.001951291,0.008748039,0.01509756,0.01837341,0.01328455,0.008617152,0.0003231684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008589075,"about_ca_system_score_gemma":0.01842229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003814923,"about_ca_topic_score_gemma":0.004685399,"domain_scores_codex":[0.3262363,0.4786649,0.09437046,0.01420526,0.08126983,0.005253346],"domain_scores_gemma":[0.06954838,0.7965463,0.08823208,0.02040755,0.02137545,0.003890228],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003093548,0.0006787754,0.3986947,0.01205503,0.006159065,0.0005211678,0.06202132,0.001784224,0.0009771868,0.1086766,0.01366479,0.3916736],"study_design_scores_gemma":[0.001863085,0.002718149,0.2689887,0.05049608,0.004809487,0.002335063,0.04436602,0.02360826,0.003035866,0.5534155,0.04348169,0.0008820782],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"commentary","genre_scores_codex":[0.5010915,0.06248844,0.1142171,0.2773416,0.003286172,0.004707327,0.001486359,0.0002718501,0.03510949],"genre_scores_gemma":[0.9440114,0.003006438,0.04421157,0.006814083,0.000435819,0.00114234,0.0001692394,0.00004503039,0.0001639373],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.5219322,"threshold_uncertainty_score":0.6436353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7560419374799492,"score_gpt":0.5769581508986422,"score_spread":0.179083786581307,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}