{"id":"W7117158505","doi":"10.1093/jamia/ocaf223","title":"AutoReporter: development of an artificial intelligence tool for automated assessment of research reporting guideline adherence","year":2025,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Princess Margaret Cancer Centre; BC Cancer Agency; McMaster University; University of Toronto","funders":"","keywords":"Guideline; Quality (philosophy); Control (management); MEDLINE; Scalability","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":[],"category_scores_codex":[0.02617086,0.002880474,0.001537625,0.004885814,0.000709425,0.004329004,0.003967432,0.002052031,0.01516895],"category_scores_gemma":[0.1251578,0.001578754,0.002798921,0.002106176,0.0006284598,0.004028573,0.004656336,0.00293267,0.01160289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00217127,"about_ca_system_score_gemma":0.007400162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004954872,"about_ca_topic_score_gemma":0.01098392,"domain_scores_codex":[0.9779466,0.01154511,0.003703649,0.003224604,0.00327265,0.0003073481],"domain_scores_gemma":[0.9234172,0.05109124,0.007494987,0.00875274,0.00829955,0.0009442093],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00170339,0.0005312749,0.0112779,0.01148714,0.001143897,0.0005998574,0.002297209,0.01904839,0.01736929,0.008739847,0.3718795,0.5539224],"study_design_scores_gemma":[0.001807039,0.001089449,0.009883233,0.004138631,0.0009077439,0.001032172,0.001175753,0.5062572,0.06134928,0.04175878,0.3699294,0.0006713271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.01339352,0.002090019,0.4119081,0.002868095,0.0005815955,0.002863779,0.05672915,0.5048717,0.004694122],"genre_scores_gemma":[0.05812256,0.0007621625,0.8485936,0.002065717,0.0001453995,0.003803915,0.07498492,0.008201079,0.003320631],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9738292,"threshold_uncertainty_score":0.1384064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.642779943123821,"score_gpt":0.6432471026700052,"score_spread":0.0004671595461841482,"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."}}