{"id":"W4388694426","doi":"10.1007/978-3-031-47958-8_9","title":"Designing Explainable Artificial Intelligence with Active Inference: A Framework for Transparent Introspection and Decision-Making","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; HEC Montréal","funders":"","keywords":"Introspection; Computer science; Inference; Artificial intelligence; Covert; Machine learning; Cognitive science; Psychology","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":[0.00258875,0.0008772697,0.0004796441,0.0005929205,0.0007676054,0.00382764,0.002600987,0.00168573,0.007635624],"category_scores_gemma":[0.005913131,0.0009972388,0.001521853,0.0005814415,0.003802624,0.005773072,0.002951047,0.003766587,0.001197669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001145137,"about_ca_system_score_gemma":0.001447584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001249853,"about_ca_topic_score_gemma":0.00168914,"domain_scores_codex":[0.9985209,0.0006599545,0.00009564348,0.0002258009,0.0003845184,0.0001131485],"domain_scores_gemma":[0.9973133,0.00179727,0.0001388665,0.000549829,0.0001256099,0.00007504058],"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":[0.00001583442,0.00002348559,0.000112409,0.0001070438,0.00002658894,0.00005227937,0.0004755624,0.01150658,0.001168772,0.9535672,0.002273734,0.03067035],"study_design_scores_gemma":[0.00001474561,0.00001357124,0.00005508589,0.00005371811,0.0000295939,0.00004415344,0.0000534028,0.08007409,0.003063606,0.8883995,0.02818178,0.00001678099],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001750717,0.0003444704,0.9868755,0.0006968738,0.00004171634,0.00004431775,0.00004170114,0.0005976284,0.009607054],"genre_scores_gemma":[0.1071216,0.0007114506,0.8821231,0.0002803007,0.00009222765,0.0002172007,0.0001844835,0.0003568763,0.008912776],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007635624,"threshold_uncertainty_score":0.02554369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1064324970603927,"score_gpt":0.364949812949029,"score_spread":0.2585173158886362,"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."}}