{"id":"W3196522557","doi":"10.1609/aaai.v36i11.21459","title":"Fair Conformal Predictors for Applications in Medical Imaging","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"AI in cancer detection","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Interpretability; Deep learning; Transparency (behavior); Artificial intelligence; Machine learning; Computer science; Data science; Field (mathematics); Mathematics; Computer security","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":[0.0008425867,0.0001446105,0.0001747538,0.0001792791,0.000358842,0.00009833176,0.002395978,0.00004332085,0.0001043618],"category_scores_gemma":[0.0002148873,0.0001243617,0.0000923739,0.0008257541,0.0001825759,0.0003651059,0.0006826195,0.0003866796,0.000006503887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001603427,"about_ca_system_score_gemma":0.0002435693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004608409,"about_ca_topic_score_gemma":0.0000153826,"domain_scores_codex":[0.9980137,0.00001555542,0.000509928,0.0004118081,0.0007392053,0.0003098446],"domain_scores_gemma":[0.9989833,0.000138023,0.0002876774,0.0002390803,0.0002742512,0.00007766683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004618282,0.0001156987,0.00124128,0.00002954465,0.000006179307,2.17821e-7,0.001223207,0.0002384928,0.001953548,0.8788127,0.0002170738,0.1161158],"study_design_scores_gemma":[0.00009920992,0.0002499757,0.0006413641,0.0000857117,0.000009951834,0.00001596478,0.002798021,0.6234949,0.1385499,0.2295161,0.004214745,0.000324198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09118279,0.00006706037,0.8743668,0.0161395,0.001798749,0.002935598,0.00003901334,0.0003355521,0.01313495],"genre_scores_gemma":[0.997638,0.000009114529,0.001194188,0.0002875016,0.00006552823,0.0007256949,9.927369e-7,0.00001004278,0.00006889565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9064553,"threshold_uncertainty_score":0.5071324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0394845294127556,"score_gpt":0.2989227623119308,"score_spread":0.2594382328991752,"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."}}