{"id":"W3042234123","doi":"10.48550/arxiv.2007.09028","title":"Sequential Explanations with Mental Model-Based Policies","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Computer science; Reinforcement learning; Proxy (statistics); Representation (politics); Selection (genetic algorithm); Mental representation; Baseline (sea); Machine learning; Artificial intelligence; Mental model; Cognitive psychology; Data science; Psychology; Cognitive science; Cognition","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":[0.0001086713,0.0003256736,0.0002715405,0.0002847937,0.0002899538,0.000240455,0.001967831,0.0001705166,0.00002920371],"category_scores_gemma":[0.00001827182,0.0003607061,0.0001529449,0.0007337222,0.0001807666,0.0005373317,0.001170757,0.0004572569,0.000134239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003243422,"about_ca_system_score_gemma":0.0006278576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004903715,"about_ca_topic_score_gemma":0.0002951625,"domain_scores_codex":[0.9981014,0.00009269375,0.000193091,0.001037868,0.0001705083,0.0004044296],"domain_scores_gemma":[0.9983643,0.00005442706,0.0001931356,0.0009671346,0.0001840652,0.0002368897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002846609,0.0000613558,0.0001904493,0.00002432314,0.00004508139,0.0001804971,0.001050262,0.7275623,0.0001707579,0.270207,0.0004091178,0.00007038725],"study_design_scores_gemma":[0.0001696719,0.00007127098,0.000024622,0.00004362644,0.00003903887,0.000002519408,0.0002108045,0.959847,0.004613407,0.03433225,0.0002419625,0.0004037821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08714627,0.00001134926,0.907462,0.001444137,0.0002375081,0.0003240952,0.00004120053,0.0003852407,0.002948203],"genre_scores_gemma":[0.9924408,0.00001813988,0.006421891,0.0004654867,0.00006035351,0.000002945747,0.00004148145,0.00002213616,0.0005268203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9052945,"threshold_uncertainty_score":0.9998845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1489738218570813,"score_gpt":0.2217217124871226,"score_spread":0.07274789063004128,"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."}}