{"id":"W6910465000","doi":"10.48448/r1ds-3r08","title":"Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Inference; Theory of mind; Perception; Key (lock); Causal inference; Mental model","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002520146,0.0003763674,0.0004960989,0.003161521,0.00008530886,0.0001095662,0.001092452,0.0001789983,0.001021868],"category_scores_gemma":[0.0003831133,0.0003391628,0.0001036737,0.001971296,0.0006712727,0.0004761682,0.000389003,0.0003151943,0.001532492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002459155,"about_ca_system_score_gemma":0.0006588889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002154796,"about_ca_topic_score_gemma":0.005759244,"domain_scores_codex":[0.9969131,0.00007791282,0.0004835008,0.0009736527,0.0007859167,0.0007659137],"domain_scores_gemma":[0.9986739,0.0001492548,0.0001870677,0.0006643678,0.0001356948,0.0001897054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002145682,0.002468343,0.0005996171,0.002604491,0.0003146693,0.00005100047,0.2901298,0.008566825,0.05453546,0.4444973,0.1090569,0.08696102],"study_design_scores_gemma":[0.005579099,0.002609854,0.0009845701,0.02656813,0.0008877525,0.00003736016,0.3260432,0.1362832,0.008589272,0.2885061,0.1953455,0.008565992],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0724911,0.005915761,0.06223451,0.000334302,0.002699624,0.006638612,0.009356877,0.001075921,0.8392533],"genre_scores_gemma":[0.65882,0.00009733057,0.04295648,0.0001214926,0.0006546,0.001008837,0.000163069,0.001264474,0.2949137],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.5863289,"threshold_uncertainty_score":0.9999061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09940177417123831,"score_gpt":0.3586536911618868,"score_spread":0.2592519169906485,"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."}}