{"id":"W4309344674","doi":"10.1109/smc53654.2022.9945351","title":"A Formal Theory of AI Trustworthiness for Evaluating Autonomous AI Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","topic":"Cognitive Computing and Networks","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Novelty; Computer science; Trustworthiness; Artificial intelligence; Context (archaeology); Robot; Human–computer interaction; Cognition; Intelligent decision support system; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01562354,0.001561911,0.001256382,0.004213256,0.001693887,0.005947573,0.00231879,0.002029294,0.003680841],"category_scores_gemma":[0.06381933,0.0006736497,0.002077146,0.002075608,0.009181701,0.009676054,0.003178683,0.00377318,0.0007111744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00432313,"about_ca_system_score_gemma":0.003159913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003167617,"about_ca_topic_score_gemma":0.001797027,"domain_scores_codex":[0.9846214,0.006447655,0.001472073,0.001600061,0.005106015,0.0007527674],"domain_scores_gemma":[0.9521315,0.03017074,0.005172695,0.004841064,0.00668214,0.00100184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003135922,0.00003730822,0.001131894,0.0001440784,0.000076965,0.0001095122,0.0005149511,0.04712457,0.0009144194,0.9334518,0.0009880355,0.01547514],"study_design_scores_gemma":[0.00002254985,0.00008627884,0.0005675839,0.0001068931,0.0000440628,0.0001260236,0.0002111308,0.2224699,0.0006314588,0.7721237,0.003564067,0.00004647958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007195393,0.0004440317,0.9833269,0.0008963804,0.000108792,0.0001216832,0.00009706164,0.0001273801,0.007682417],"genre_scores_gemma":[0.6745324,0.000773191,0.3194456,0.0003475178,0.0004723912,0.0008153878,0.0002863307,0.0001083021,0.003218739],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01562354,"threshold_uncertainty_score":0.08262616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07171883577656224,"score_gpt":0.3280246335687882,"score_spread":0.256305797792226,"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."}}