{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002120809,0.0002510085,0.0003890035,0.0002322302,0.0003623893,0.0003662888,0.001035306,0.00007200663,0.00004872496],"category_scores_gemma":[0.00007261983,0.0002518909,0.0001111657,0.0002020285,0.0000711977,0.0002141718,0.0004622784,0.0004074071,0.000005449236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001231804,"about_ca_system_score_gemma":0.0002299811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000104916,"about_ca_topic_score_gemma":0.000009457729,"domain_scores_codex":[0.9971425,0.0004000919,0.0006769209,0.00057341,0.0008467038,0.0003604092],"domain_scores_gemma":[0.9978385,0.0005133009,0.0004505356,0.0003565665,0.0007504344,0.00009066694],"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":[0.0001648666,0.0001257569,0.0004675813,0.0001290745,0.0001536777,0.00001154046,0.000996116,0.02322708,0.0002032098,0.9484311,0.001436429,0.02465353],"study_design_scores_gemma":[0.0009172896,0.0005990454,0.0003316402,0.0001972847,0.00002899175,0.00008165936,0.0007592052,0.9858079,0.00006254323,0.005950527,0.004959468,0.0003044546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1298612,0.001175814,0.8411027,0.0009257648,0.01137982,0.001535387,0.0002708684,0.000215841,0.01353263],"genre_scores_gemma":[0.9950658,0.00002816827,0.0002475157,0.0003720664,0.0003233621,0.0003081298,0.00003945886,0.00002154245,0.003593958],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9625808,"threshold_uncertainty_score":0.9999933,"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."}}