{"paper":{"title":"After the Fix: How Corrected Agent Histories Transfer to Related Tasks","arxiv_id":"2609.34603","primary_cat":"cs.AI","submitted_at":"2026-09-28T08:35:23+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":0.56,"id":"s0","own":false,"role":"background","text":"Does repairing an episode make its experience a better memory for the next task?","hedge":{"p":0.92,"label":"unclear"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.44,"method":0.0,"result":0.0,"background":0.56,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.91,"id":"s1","own":true,"role":"method","text":"We transfer the same failed source before and after accepted repair to a fixed target, alongside independent execution.","hedge":{"p":0.77,"label":"asserted"},"own_p":0.94,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.27,"role_probabilities":{"gap":0.0,"method":0.91,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.09,"interpretation":0.0}},{"i":2,"p":0.99,"id":"s2","own":true,"role":"method","text":"Our 3,300 runs cover 100 ThinkingBox pairs and the same 100 APEX pairs with and without source-state inheritance, under eleven conditions.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.95,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.98,"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":"ThinkingBox's Full/Skill/Hybrid correction gains are 44/29/32 percentage points, with corrected performance 25/22/18 points above independence; inference weakens at the task-family level.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.16,"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":0.74,"id":"s4","own":true,"role":"result","text":"Yet 12 of Full's 15-point larger correction gap over Skill come from worse uncorrected performance, not better corrected memory.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.09,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.74,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.26}},{"i":5,"p":0.97,"id":"s5","own":true,"role":"result","text":"Moreover, 22 of Full's 46 upward transitions restore observed baseline success.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.97,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.03}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"Neither APEX regime establishes comparable aggregate correction benefits.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.29,"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":7,"p":0.91,"id":"s7","own":true,"role":"interpretation","text":"Action evidence connects workflow gains with reusable obligations and convention conflicts with source-local choices.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.77,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.09,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.91}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Text APEX's accepted execution reaches 52% versus its summary's 40%, without robust global/group-level superiority or an estab- lished advantage over independence.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.92,"main_claim_p":0.06,"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":9,"p":0.93,"id":"s9","own":true,"role":"result","text":"Smaller handoffs reduce input but increase calls.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.72,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.72,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.93,"background":0.0,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.06}},{"i":10,"p":1.0,"id":"s10","own":true,"role":"interpretation","text":"The value of repairing experience is therefore distinct from the value of reusing it: memory updates require both a previous-version reference and a fresh-start reference.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.77,"main_claim_p":0.83,"quantitative":false,"quantitative_p":0.21,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":1.0}}]},"compiled":{"main_claim":{"p":1.0,"text":"The value of repairing experience is therefore distinct from the value of reusing it: memory updates require both a previous-version reference and a fresh-start reference.","location":"abstract s10","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":8081,"cost_usd_reported":0.0},"compiled_at":"2026-09-29","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.03,"states_limitation":0.91,"human_participants":0.06,"controlled_comparison":0.97,"randomized_assignment":0.04,"states_quantitative_result":0.99,"compares_with_prior_results":0.91,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.72,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.72,"simulation_or_computation":0.28}},"contribution_type":{"p":0.93,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":0.93,"simulation_study":0.07,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.99,"text":"We transfer the same failed source before and after accepted repair to a fixed target, alongside independent execution.","location":"abstract s1"}},"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":11,"sentences_in_abstract":11},"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"}}}