{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001781052,0.00009765381,0.0001636357,0.0002500344,0.0005734228,0.0002933355,0.0004801262,0.00008509748,0.00008878729],"category_scores_gemma":[0.001999852,0.00009045503,0.00002459389,0.001045579,0.0003278599,0.0003489495,0.0001572453,0.0001045423,0.00007518232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002398179,"about_ca_system_score_gemma":0.0009612624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008840577,"about_ca_topic_score_gemma":0.0005056274,"domain_scores_codex":[0.9983575,0.00003981009,0.0004480843,0.0006913667,0.0001853403,0.000277858],"domain_scores_gemma":[0.9978175,0.000291728,0.00008321618,0.00149412,0.0002244467,0.00008898009],"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":[0.0002381594,0.0001618125,0.0003180721,0.0001919418,0.00003062781,0.000002201451,0.0004491904,0.00003647276,0.001837417,0.05809096,0.8526469,0.08599624],"study_design_scores_gemma":[0.00006843653,0.0002245904,0.00008395338,0.0002725256,0.0002102203,0.00001007831,0.02392266,0.08091519,0.02354499,0.3359782,0.534471,0.0002982141],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005125703,0.0004572986,0.9287846,0.02682387,0.009419929,0.001989005,0.02666156,0.00008229029,0.0006557436],"genre_scores_gemma":[0.8346319,0.0000320363,0.008767652,0.0009754822,0.0004133298,0.00007917138,0.1533419,0.00001277735,0.00174575],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9200169,"threshold_uncertainty_score":0.4410362,"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."}}