{"id":"W4404543514","doi":"10.5334/pme.1270","title":"Digital Evidence: Revisiting Assumptions at the Intersection of Technology and Assessment","year":2024,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Radiology practices and education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Queen's University","funders":"","keywords":"Intersection (aeronautics); Computer science; Data science; Management science; Engineering","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":[0.0004482458,0.00006946413,0.0001105844,0.0002001755,0.00009995087,0.00003526876,0.00004871678,0.00009846187,0.0004534742],"category_scores_gemma":[0.003036643,0.00004575593,0.00004076345,0.0003445027,0.0002726059,0.000195917,0.00002781037,0.0003889804,0.00002360813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003989741,"about_ca_system_score_gemma":0.0007856394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001352093,"about_ca_topic_score_gemma":0.000002151281,"domain_scores_codex":[0.9992356,0.00004374226,0.0001683644,0.0002370701,0.0002276691,0.00008751265],"domain_scores_gemma":[0.9992029,0.0003927217,0.00006392087,0.0001602648,0.0001066087,0.00007356199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00007496902,0.0003645609,0.01973968,0.0002267782,0.0001294608,0.000003134571,0.007993584,0.000001124318,0.0009331605,0.05431153,0.004317631,0.9119044],"study_design_scores_gemma":[0.0006958751,0.00206746,0.4939797,0.009176051,0.0007404357,0.00266698,0.3533439,0.007112688,0.0005015,0.006198061,0.1231144,0.0004029892],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8419201,0.008942336,0.0003991963,0.1377127,0.0005950168,0.000204781,0.000001111474,0.00004825569,0.01017653],"genre_scores_gemma":[0.9959788,0.001518581,0.000280833,0.0001966843,0.0004774618,0.00004409743,0.00001042338,0.000007548512,0.001485606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9115014,"threshold_uncertainty_score":0.4965224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02742320241281658,"score_gpt":0.4256833106578201,"score_spread":0.3982601082450035,"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."}}