{"paper":{"title":"Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops","arxiv_id":"2610.18579","primary_cat":"cs.AI","submitted_at":"2026-10-13T15:43:30+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":0.99,"id":"s0","own":false,"role":"background","text":"System One models choose an agent's next action by scoring a supplied set of options in a single pass.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.99,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.7,"id":"s1","own":false,"role":"gap","text":"This makes them fast and cheap, but when they choose wrongly there is nothing to inspect: did the model misread what the agent has seen, or read it correctly and still act wrongly? We answer behaviorally.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.25,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.12,"role_probabilities":{"gap":0.7,"method":0.0,"result":0.0,"background":0.22,"limitation":0.0,"future_work":0.0,"contribution":0.08,"interpretation":0.0}},{"i":2,"p":0.99,"id":"s2","own":true,"role":"method","text":"On a frozen benchmark of agent decision states from simulated environments, customer-service policies, tool use, web navigation and coding, we pair every next-action question with factual probes about the same state, each answered independently.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.94,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"result","text":"Across seventeen fast systems and a reasoning model, the answer is consistent: most wrong actions follow correct reading, and the more accurate a system, the more of its errors take this form.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.94,"main_claim_p":0.86,"quantitative":true,"quantitative_p":0.9,"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":0.81,"id":"s4","own":true,"role":"result","text":"These errors are not noise; they gather on the same states across systems of every kind.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.91,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.81,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.19}},{"i":5,"p":0.8,"id":"s5","own":true,"role":"result","text":"Where the probed facts provably determine the action, models that read every fact still fail to combine them, and their own answers, composed by code, repair the failure.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.86,"main_claim_p":0.18,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.8,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.2}},{"i":6,"p":0.63,"id":"s6","own":true,"role":"result","text":"On real states, what is missing is often not a fact but the next sub-goal.","hedge":{"p":0.85,"label":"asserted"},"own_p":0.8,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.63,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.36}}]},"compiled":{"main_claim":{"p":1.0,"text":"Across seventeen fast systems and a reasoning model, the answer is consistent: most wrong actions follow correct reading, and the more accurate a system, the more of its errors take this form.","location":"abstract s3","hedge_strength":{"p":0.96,"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":5608,"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":0.53,"human_participants":0.04,"controlled_comparison":0.21,"randomized_assignment":0.02,"states_quantitative_result":0.4,"compares_with_prior_results":0.34,"mentions_code_or_data_availability":0.07},"evidential_basis":{"p":0.76,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.08,"observation_or_experiment":0.76,"simulation_or_computation":0.16}},"contribution_type":{"p":0.99,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.01,"empirical_study":0.99,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.98,"text":"On a frozen benchmark of agent decision states from simulated environments, customer-service policies, tool use, web navigation and coding, we pair every next-action question with factual probes about the same state, each answered independently.","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":7,"sentences_in_abstract":7},"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"}}}