{"id":"W4308091336","doi":"10.1109/ccece49351.2022.9918312","title":"STAR-ML: A Rapid Screening Tool for Assessing Reporting of Machine Learning in Research","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Toronto Rehabilitation Institute; McMaster University","funders":"McMaster University","keywords":"Computer science; Systematic review; Correctness; Reliability (semiconductor); Transparency (behavior); Machine learning; Field (mathematics); Quality (philosophy); Artificial intelligence; MEDLINE; Algorithm","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":[0.5821046,0.005273121,0.009226376,0.08488642,0.004233336,0.01384616,0.006136315,0.004655519,0.02162337],"category_scores_gemma":[0.8399302,0.004749516,0.01634417,0.04797583,0.004067034,0.01903996,0.02336059,0.004907382,0.007648295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01025226,"about_ca_system_score_gemma":0.05276715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003223106,"about_ca_topic_score_gemma":0.007816137,"domain_scores_codex":[0.2905941,0.3744388,0.2707729,0.0101015,0.05158988,0.002502804],"domain_scores_gemma":[0.05701663,0.6948283,0.09871492,0.03918423,0.1080911,0.002164873],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002618279,0.0003057217,0.0272942,0.2104425,0.007040289,0.0006700225,0.0172444,0.002693278,0.003541716,0.01485777,0.1664202,0.5468717],"study_design_scores_gemma":[0.006625932,0.002890431,0.06917683,0.1854784,0.01420911,0.002629157,0.01526615,0.02321354,0.01937522,0.06516372,0.5921663,0.003805274],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03140184,0.02773115,0.5875433,0.02061039,0.005595712,0.1771599,0.08365958,0.04385779,0.02244035],"genre_scores_gemma":[0.03440084,0.004923332,0.7748256,0.001692608,0.0005391371,0.1695877,0.01046695,0.001798087,0.001765772],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4178954,"threshold_uncertainty_score":0.5153395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6367094351459659,"score_gpt":0.5806251038723957,"score_spread":0.05608433127357015,"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."}}