{"id":"W4379933269","doi":"10.48550/arxiv.2306.04025","title":"Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Introspection; Inference; Computer science; Artificial intelligence; Covert; Machine learning; Cognitive science; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005447944,0.0004903569,0.000513461,0.0005567686,0.0006505678,0.000536363,0.001417185,0.0004351226,0.00001629012],"category_scores_gemma":[0.0004924323,0.000530587,0.0001565477,0.001330047,0.0002291945,0.0009022712,0.000930489,0.000870324,0.00003699711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004498819,"about_ca_system_score_gemma":0.0003254991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001421465,"about_ca_topic_score_gemma":0.0003689642,"domain_scores_codex":[0.9967223,0.0001030867,0.0004200691,0.001830438,0.0002114234,0.0007127105],"domain_scores_gemma":[0.9957799,0.002234591,0.0003890817,0.0009843417,0.0004145103,0.0001975837],"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":[0.000328954,0.00007171558,0.0002773875,0.00009655177,0.00007754674,0.0001511122,0.002277304,0.4082517,0.00003462601,0.5574005,0.000007245467,0.0310253],"study_design_scores_gemma":[0.00003995852,0.0001911673,0.00010652,0.000709029,0.00004730341,0.000003276536,0.001995508,0.399613,0.00256374,0.5943283,0.000007058425,0.0003950745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07285365,0.00003268686,0.9248998,0.00009649676,0.000644493,0.0009510657,0.00001625749,0.000444027,0.00006149684],"genre_scores_gemma":[0.8352069,0.0001442292,0.164397,0.00003056159,0.0001129818,0.0000282342,0.000005605054,0.00004010172,0.00003433015],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7623533,"threshold_uncertainty_score":0.9997146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1760215851321559,"score_gpt":0.2816004834873103,"score_spread":0.1055788983551544,"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."}}