{"id":"W4213331418","doi":"10.5220/0010899100003116","title":"BRL: A Toolkit for Learning How an Agent Performs Belief Revision","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"British Columbia Institute of Technology","funders":"","keywords":"Computer science; Belief revision; Artificial intelligence; Programming language; Human–computer interaction","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":[0.001003274,0.0002362325,0.0002277968,0.0001980126,0.0009266098,0.000647606,0.002364025,0.0000531152,0.0001959726],"category_scores_gemma":[0.0004075353,0.000190503,0.0001355461,0.0003753267,0.0001440573,0.0009297712,0.001006852,0.0004036579,0.00000963764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001203254,"about_ca_system_score_gemma":0.00007080193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003868926,"about_ca_topic_score_gemma":0.000005875224,"domain_scores_codex":[0.9976016,0.00003666747,0.0004873715,0.0006657276,0.0008423594,0.0003663157],"domain_scores_gemma":[0.9984152,0.00008458261,0.0004480698,0.0002319459,0.0006969947,0.0001232614],"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":[0.0001034041,0.0002197856,0.0003497584,0.00002799856,0.00002492817,0.000001065952,0.002381176,0.0009392307,0.006919485,0.853264,0.0003280889,0.135441],"study_design_scores_gemma":[0.00007818228,0.001412934,0.0002659083,0.0001375814,0.00001779442,0.00002019694,0.008050781,0.7398458,0.09411331,0.136099,0.01949371,0.0004647945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8299279,0.00006840428,0.1260767,0.03081864,0.003366626,0.001955496,0.00005791427,0.0002490428,0.007479339],"genre_scores_gemma":[0.9947497,0.00008058386,0.003117119,0.0004964995,0.0001416612,0.0001062417,0.000005555912,0.00001797864,0.001284702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7389066,"threshold_uncertainty_score":0.7768485,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1163914368832862,"score_gpt":0.3271015344080956,"score_spread":0.2107100975248095,"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."}}