{"id":"W4410056551","doi":"10.1038/s41597-025-05054-0","title":"A Dataset for Understanding Radiologist-Artificial Intelligence Collaboration","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Alfred P. Sloan Foundation","keywords":"Computer science; Data science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.002997046,0.001171661,0.0007406239,0.003402258,0.0009062556,0.001731639,0.002282356,0.002604141,0.005561134],"category_scores_gemma":[0.01596862,0.0003512733,0.001186507,0.003194219,0.0006391177,0.001017064,0.002275335,0.00159082,0.004180846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001749082,"about_ca_system_score_gemma":0.001880715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009683679,"about_ca_topic_score_gemma":0.02341768,"domain_scores_codex":[0.9962291,0.001165781,0.0005564245,0.0008645145,0.0009523619,0.000231833],"domain_scores_gemma":[0.9872934,0.007051568,0.001072042,0.002103021,0.001799367,0.000680654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001331192,0.001847605,0.08725273,0.004336619,0.0005688401,0.001554078,0.001327705,0.02192057,0.006173397,0.007274043,0.7279204,0.1384928],"study_design_scores_gemma":[0.0007581091,0.0006624655,0.1451409,0.001074814,0.0002825979,0.002572873,0.002041023,0.07075663,0.00987768,0.01433494,0.7522434,0.0002545563],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.08467761,0.002872422,0.02066332,0.002429855,0.0005113962,0.001332335,0.8720954,0.004457358,0.01096028],"genre_scores_gemma":[0.08440293,0.0004587673,0.0370732,0.0005035548,0.000114728,0.001500149,0.8739629,0.0002099307,0.001773729],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.009683679,"threshold_uncertainty_score":0.01925462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6273723659303506,"score_gpt":0.545717655039745,"score_spread":0.08165471089060561,"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."}}