{"id":"W4386766759","doi":"10.1109/access.2023.3316019","title":"Check It Before You Wreck It: A Guide to STAR-ML for Screening Machine Learning Reporting in Research","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; McMaster University; Toronto Rehabilitation Institute; University Health Network","funders":"Ministère de la Défense Nationale; McMaster University","keywords":"Checklist; Computer science; Inclusion (mineral); Field (mathematics); Quality (philosophy); Systematic review; Data science; Artificial intelligence; Machine learning; MEDLINE; Psychology","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":[],"category_scores_codex":[0.1562278,0.002939619,0.00488211,0.02320706,0.002970445,0.01259913,0.00521523,0.007096704,0.0773634],"category_scores_gemma":[0.4379911,0.003968318,0.007125064,0.02078331,0.004547184,0.01411363,0.00986488,0.008567674,0.06928212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004487128,"about_ca_system_score_gemma":0.03299549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004035221,"about_ca_topic_score_gemma":0.01043,"domain_scores_codex":[0.8015652,0.1206055,0.05666806,0.00290627,0.01667206,0.001582968],"domain_scores_gemma":[0.379052,0.4536677,0.04042369,0.02678723,0.09416381,0.005905497],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000354369,0.0002382295,0.001131351,0.0192644,0.0002146518,0.0003652518,0.006109371,0.0006515597,0.00158251,0.01130189,0.6745011,0.2842853],"study_design_scores_gemma":[0.0005221366,0.0002688079,0.002053795,0.02158454,0.0001166464,0.0006416381,0.003188043,0.001185111,0.001168338,0.02591526,0.9429452,0.0004106421],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005296172,0.02823927,0.5233527,0.1262307,0.01791229,0.1194078,0.07221224,0.04506191,0.06228686],"genre_scores_gemma":[0.004476483,0.01041451,0.887245,0.01300471,0.0014404,0.05570121,0.007785794,0.004541069,0.01539084],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8437722,"threshold_uncertainty_score":0.8262216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6916805745804292,"score_gpt":0.6363962134281208,"score_spread":0.05528436115230839,"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."}}