{"id":"W4312465291","doi":"10.1609/icaps.v32i1.19862","title":"Resolving Misconceptions about the Plans of Agents via Theory of Mind","year":2022,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Schwartz/Reisman Emergency Medicine Institute; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Plan (archaeology); Set (abstract data type); Appeal; Computer science; Epistemology; Psychology; Management science; Political science; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01752023,0.001520621,0.0009355431,0.003360399,0.00276705,0.01062128,0.004292131,0.003303085,0.003486735],"category_scores_gemma":[0.05836134,0.001612563,0.002594177,0.001920463,0.009990457,0.01731761,0.006611655,0.007158833,0.0006042456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005012096,"about_ca_system_score_gemma":0.006618462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01024523,"about_ca_topic_score_gemma":0.01014965,"domain_scores_codex":[0.986667,0.007578482,0.0007382967,0.001413236,0.003028389,0.0005746108],"domain_scores_gemma":[0.944313,0.04316473,0.003753456,0.005301006,0.002728791,0.0007389535],"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":[0.0005193709,0.0002473567,0.006699043,0.001087102,0.0005141608,0.001583691,0.02189883,0.1011346,0.005576297,0.6710749,0.006125025,0.1835395],"study_design_scores_gemma":[0.00008191403,0.00008041559,0.0006132699,0.0002832261,0.0001625537,0.0003085133,0.002636799,0.2086345,0.003450881,0.7685893,0.01505395,0.0001047465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02912167,0.0007900838,0.9539829,0.005510661,0.0001201487,0.000139751,0.0001113975,0.001216267,0.009007095],"genre_scores_gemma":[0.5565706,0.000913972,0.4386599,0.0009643061,0.00009715365,0.0002592603,0.000379035,0.0001931295,0.001962657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01752023,"threshold_uncertainty_score":0.09265697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05234666380518317,"score_gpt":0.2905745783898468,"score_spread":0.2382279145846637,"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."}}