{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001105964,0.000127252,0.0001785631,0.0001464448,0.0003597574,0.00007797205,0.001434888,0.00004174826,0.00004795187],"category_scores_gemma":[0.0001850975,0.0000904869,0.00007065966,0.0002448063,0.0001251293,0.0001530736,0.0004528819,0.0003403432,6.57787e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000213227,"about_ca_system_score_gemma":0.0000789681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002333055,"about_ca_topic_score_gemma":2.951201e-7,"domain_scores_codex":[0.9986231,0.00004579795,0.000398808,0.0002378931,0.0005347083,0.0001596855],"domain_scores_gemma":[0.9987029,0.0002835419,0.0005998088,0.0001349718,0.000245995,0.00003277025],"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":[0.0004405245,0.0003040427,0.0769818,0.0003114428,0.0007293759,0.000006150368,0.05797108,0.1258013,0.191569,0.5345268,0.001621722,0.009736767],"study_design_scores_gemma":[0.0002986926,0.0001243258,0.005760026,0.0007263178,0.00002868433,0.00003340194,0.003077887,0.9696516,0.01464194,0.005351629,0.0001637996,0.000141646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988151,0.0002396983,0.004320481,0.00135574,0.0003701691,0.0001551649,0.00005780361,0.00009182652,0.005258163],"genre_scores_gemma":[0.9944149,0.0000060148,0.005279497,0.00009724782,0.00001904546,0.0000115955,0.000004334831,0.00000699521,0.0001603146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8438503,"threshold_uncertainty_score":0.3689949,"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."}}