{"id":"W4403090795","doi":"10.1101/2024.10.02.24314783","title":"Inconsistency detection in cancer data classification using explainable-AI","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Computer science; Artificial intelligence; Cancer detection; Cancer; Machine learning; Pattern recognition (psychology); Medicine; Internal medicine","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":[0.000789181,0.0001998378,0.0002250955,0.0003425352,0.00006300501,0.0002886642,0.001887079,0.0002225781,0.000007412636],"category_scores_gemma":[0.00008516981,0.0002065574,0.00004273525,0.0004116884,0.00002297303,0.0003394501,0.004745092,0.0008641955,0.0000188362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003925304,"about_ca_system_score_gemma":0.0004821251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002067715,"about_ca_topic_score_gemma":0.001429328,"domain_scores_codex":[0.9977033,0.0001224985,0.000431701,0.001200055,0.000287215,0.0002552255],"domain_scores_gemma":[0.9973163,0.00003817633,0.0001436929,0.002374682,0.00007429555,0.00005282634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001710499,0.000205694,0.03456174,0.002887601,0.000156996,0.0002887547,0.004699122,0.07022718,0.024069,0.02063797,0.0002874509,0.8419614],"study_design_scores_gemma":[0.00005852437,0.000003511078,0.002273007,0.0003322641,0.00001641131,0.000006787784,0.00002443438,0.9816331,0.000565968,0.01421828,0.0006627766,0.0002049671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3415034,0.001379285,0.6513479,0.00150884,0.003421298,0.0002927496,0.00001272205,0.000210236,0.0003236459],"genre_scores_gemma":[0.982448,0.00008567541,0.01691211,0.0001021346,0.0002596114,0.00007369357,0.00001369355,0.0000199903,0.00008512952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9114059,"threshold_uncertainty_score":0.8423167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1801339199482145,"score_gpt":0.3615955237455872,"score_spread":0.1814616037973727,"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."}}