{"paper":{"title":"Jev-ToM: Evaluating Theory of Mind in Typed Decision Models","arxiv_id":"2610.18610","primary_cat":"cs.CL","submitted_at":"2026-10-13T15:59:00+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Dialogue and collaborative assistants repeatedly judge what a partner knows, believes, or intends.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.96,"id":"s1","own":false,"role":"background","text":"Typed decision models offer a potential alternative to generative large language models for bounded Theory of Mind (ToM) selection.","hedge":{"p":1.0,"label":"hedged_possibility"},"own_p":0.06,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.23,"role_probabilities":{"gap":0.02,"method":0.01,"result":0.0,"background":0.96,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":2,"p":0.8,"id":"s2","own":true,"role":"contribution","text":"We present Jev-ToM, comparing five typed decision models and seven generative baselines on 11,117 English text questions from nine ToM benchmarks across six capability groups.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.2,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.8,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"result","text":"TypeSafe Jev reaches 73.2% source-balanced accuracy including native controls and ranks first or second across all six capabilities, leading beliefs, goals/desires/intentions, and emotions.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.59,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"result","text":"Other typed models show distinct strengths across tasks.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.8,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.99,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":5,"p":0.86,"id":"s5","own":true,"role":"result","text":"Separate resource comparisons suggest that Jev could reduce the cost and waiting time of repeated ToM selection.","hedge":{"p":0.99,"label":"hedged_possibility"},"own_p":0.84,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.16,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.86,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.14}},{"i":6,"p":0.94,"id":"s6","own":true,"role":"result","text":"Confidence-based selection remains benchmark-dependent, and supplied reasons can repair errors or overturn correct answers depending on their attachment.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.84,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.94,"background":0.0,"limitation":0.03,"future_work":0.0,"contribution":0.0,"interpretation":0.03}},{"i":7,"p":0.96,"id":"s7","own":true,"role":"result","text":"Candidate expansion reveals distinct selection and output-validity problems.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.85,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.96,"background":0.0,"limitation":0.02,"future_work":0.0,"contribution":0.01,"interpretation":0.01}},{"i":8,"p":0.86,"id":"s8","own":true,"role":"result","text":"Related-question cues account for most of Jev's downstream gains, with task-dependent effects from predicted states.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.91,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.25,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.86,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.14}},{"i":9,"p":1.0,"id":"s9","own":false,"role":"future_work","text":"The findings motivate testing Jev as a ToM selection component in assistants, with task-specific confidence calibration, candidate design, and output validation as integration priorities.","hedge":{"p":0.72,"label":"hedged_possibility"},"own_p":0.28,"main_claim_p":0.5,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":1.0,"contribution":0.0,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.73,"text":"TypeSafe the classifier reaches 73.2% source-balanced accuracy including native controls and ranks first or second across all six capabilities, leading beliefs, goals/desires/intentions, and emotions.","location":"abstract s3","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7395,"cost_usd_reported":0.0},"compiled_at":"2026-10-14","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.05,"states_limitation":0.9,"human_participants":0.12,"controlled_comparison":0.95,"randomized_assignment":0.03,"states_quantitative_result":0.99,"compares_with_prior_results":0.96,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.86,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.03,"observation_or_experiment":0.86,"simulation_or_computation":0.11}},"contribution_type":{"p":0.64,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.36,"empirical_study":0.64,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We present the classifier-ToM, comparing five typed decision models and seven generative baselines on 11,117 English text questions from nine ToM benchmarks across six capability groups.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}