{"id":"W4390537026","doi":"10.1007/s43681-023-00397-z","title":"AITA: AI trustworthiness assessment","year":2024,"lang":"en","type":"article","venue":"AI and Ethics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Trustworthiness; Computer science; Psychology; 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":[0.0005692827,0.00006648048,0.0001000971,0.00005350355,0.0001201496,0.00006106147,0.00002301287,0.0001882391,0.000125331],"category_scores_gemma":[0.0001462795,0.00005270732,0.00002923941,0.0001446172,0.00006330342,0.00009438131,0.00001328032,0.0009810223,0.00005972053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000389484,"about_ca_system_score_gemma":0.0005777603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003797174,"about_ca_topic_score_gemma":0.00007707025,"domain_scores_codex":[0.9993374,0.00003196012,0.0001663309,0.0001640268,0.0001661958,0.0001341369],"domain_scores_gemma":[0.9993805,0.0002577535,0.00001065793,0.000113386,0.0001388489,0.00009882834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004728512,0.0001488601,0.04864779,0.002546618,0.00009195956,0.0001176461,0.02671134,0.00001741006,0.000563667,0.1633365,0.04368226,0.7140886],"study_design_scores_gemma":[0.0001172921,0.0009214679,0.05371974,0.002060072,0.0003416436,0.0003219162,0.007085206,0.04048259,0.003707114,0.1534336,0.7372506,0.0005587134],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.4053624,0.004624888,0.01159809,0.5667151,0.003918522,0.000352792,0.000005101071,0.0002340696,0.007189129],"genre_scores_gemma":[0.98138,0.0009354139,0.0002335778,0.01584697,0.0006104977,0.00001305701,0.00001681743,0.00001070475,0.0009529304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7135299,"threshold_uncertainty_score":0.4262108,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2466775578676759,"score_gpt":0.5558212560243472,"score_spread":0.3091436981566713,"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."}}