{"id":"W2988571156","doi":"10.1145/3359178","title":"Understanding Expert Disagreement in Medical Data Analysis through Structured Adjudication","year":2019,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; University of Waterloo","funders":"Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Adjudication; CLARITY; Context (archaeology); Psychology; Presentation (obstetrics); Computer science; Data science; Medicine; Political science; Law","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006957551,0.0001840868,0.0003064656,0.0003299042,0.000125477,0.0001560083,0.005661675,0.0001080403,0.0001125169],"category_scores_gemma":[0.0003050287,0.0001403047,0.0001062023,0.0009722004,0.00003852648,0.001214483,0.002877218,0.0005385685,0.00001292362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004002328,"about_ca_system_score_gemma":0.00003316117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003407197,"about_ca_topic_score_gemma":0.0000930947,"domain_scores_codex":[0.9974424,0.00005279636,0.0005451204,0.0007563077,0.0009568459,0.0002465777],"domain_scores_gemma":[0.9974822,0.0001866408,0.0005223372,0.00164652,0.0001055361,0.00005675535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000253526,0.0009303716,0.5280918,0.0008057216,0.001354318,0.000006159778,0.03268433,0.007871145,0.005980769,0.3471622,0.02120595,0.05365368],"study_design_scores_gemma":[0.0008427519,0.0002825463,0.1171817,0.0006711676,0.00005459456,0.00001643986,0.0005136278,0.8501691,0.001689493,0.02713105,0.001066323,0.0003812448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8534861,0.00004770902,0.1166135,0.02372942,0.002552116,0.000926999,0.000005192772,0.0002157676,0.002423226],"genre_scores_gemma":[0.9843459,0.00001115834,0.01465163,0.000749965,0.0001748621,0.00001002705,0.00001626288,0.00001165829,0.00002854281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8422979,"threshold_uncertainty_score":0.9997182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2065316819450487,"score_gpt":0.4112688192082902,"score_spread":0.2047371372632415,"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."}}