{"id":"W4407006035","doi":"10.1177/23743735241309468","title":"Developing and Validating a User-Friendly Quality Benchmark: Enhancing the Integrity of Online Health Information for Patients and Clinicians","year":2025,"lang":"en","type":"article","venue":"Journal of Patient Experience","topic":"Health Literacy and Information Accessibility","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Social Sciences and Humanities Research Council of Canada","keywords":"Benchmark (surveying); Misinformation; Quality (philosophy); Computer science; Health care; Reliability (semiconductor); Dissemination; Set (abstract data type); Knowledge management; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":[0.4391533,0.001017781,0.002592753,0.01056773,0.004643732,0.01248668,0.003219257,0.002488746,0.00225062],"category_scores_gemma":[0.550212,0.0009605373,0.003584776,0.007033346,0.003833778,0.008799373,0.008481982,0.003438446,0.0008562665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01426379,"about_ca_system_score_gemma":0.041892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003707415,"about_ca_topic_score_gemma":0.005410401,"domain_scores_codex":[0.5662675,0.242064,0.1073591,0.007273639,0.07253814,0.004497561],"domain_scores_gemma":[0.3483984,0.3370004,0.04948346,0.03961603,0.2181644,0.007337376],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009713707,0.001911726,0.09912061,0.01033921,0.0007706117,0.0002332103,0.02081303,0.003785672,0.002647473,0.0202335,0.02509981,0.8140739],"study_design_scores_gemma":[0.002405715,0.01481496,0.3251585,0.0641818,0.003256658,0.001739616,0.05800187,0.05508728,0.06268748,0.08753592,0.3225004,0.002629829],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3198181,0.008078526,0.5177984,0.03071425,0.002551087,0.06485528,0.00498727,0.003104603,0.04809251],"genre_scores_gemma":[0.3493754,0.001787408,0.6034207,0.002508003,0.0001704042,0.03890491,0.002556755,0.0002759376,0.001000533],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5608467,"threshold_uncertainty_score":0.6916238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07289979831256437,"score_gpt":0.5120626335239368,"score_spread":0.4391628352113724,"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."}}