{"paper":{"title":"Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate","arxiv_id":"2610.15710","primary_cat":"cs.AI","submitted_at":"2026-10-11T15:48:16+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":"Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.04,"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":0.89,"id":"s1","own":false,"role":"gap","text":"Benchmark labels for this step mark a pair as changed or not, so they cannot tell a gate that acts on established change from one that acts on a hint.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.11,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.89,"method":0.0,"result":0.0,"background":0.11,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.77,"id":"s2","own":true,"role":"method","text":"We write a task contract that separates the two (SUPERSEDED vs. NEEDS-CONFIRMATION vs. COMPATIBLE), label 500 test pairs built from STALE (change pairs plus same-user controls) with three LLM annotators and two human adjudicators (one author and a second annotator; provenance reported), and evaluate Jev, a typed \"System One\" decision model, under pre-registered hypotheses.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.96,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.95,"role_probabilities":{"gap":0.0,"method":0.77,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.23,"interpretation":0.0}},{"i":3,"p":0.99,"id":"s3","own":true,"role":"result","text":"Of the 179 test pairs STALE marks as changed, 72 meet the contract's bar for an established change.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.99,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":1.0,"id":"s4","own":true,"role":"result","text":"Jev never retired a claim on 141 same-conversation non-changes.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.88,"main_claim_p":0.07,"quantitative":true,"quantitative_p":0.98,"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":5,"p":0.98,"id":"s5","own":true,"role":"result","text":"Its failure is premature retirement: the binary gate retires 39.2% of claims whose change is only suggested.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.9,"main_claim_p":0.19,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.98,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.02}},{"i":6,"p":0.98,"id":"s6","own":true,"role":"result","text":"A three-way decision cuts this to 15.5% at a 15.3-point detection cost, which misses our pre-registered 10-point budget, and it lands on the binary gate's own threshold frontier; these verdicts hold under three readings of the gold labels.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.23,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.98,"background":0.0,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"On a held-out vault scored against a second annotator's labels, a cascade that escalated uncertain cases to a reasoning model and looked best on development data was indistinguishable from simply raising the threshold (premature retirement 26.8% vs. 6.5% on dev).","hedge":{"p":0.99,"label":"asserted"},"own_p":0.92,"main_claim_p":0.08,"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":8,"p":0.51,"id":"s8","own":true,"role":"interpretation","text":"Part of the gap comes from the gold labels: relative to that annotator's reading, LLM-majority gold shares most of its errors with a same-family escalation model, and an identity for binary labels says how much such shared errors hide.","hedge":{"p":0.82,"label":"asserted"},"own_p":0.86,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.29,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.27,"background":0.0,"limitation":0.21,"future_work":0.0,"contribution":0.0,"interpretation":0.51}},{"i":9,"p":0.48,"id":"s9","own":true,"role":"interpretation","text":"The rest is small-sample selection on development data.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.73,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.09,"background":0.0,"limitation":0.43,"future_work":0.0,"contribution":0.0,"interpretation":0.48}},{"i":10,"p":0.9,"id":"s10","own":true,"role":"interpretation","text":"For builders this means a binary score should not be wired to delete: route suggested changes to pending evidence, and do not trust a cascade selected on development data of this size.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.58,"main_claim_p":0.82,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.1,"contribution":0.0,"interpretation":0.9}}]},"compiled":{"main_claim":{"p":0.99,"text":"For builders this means a binary score should not be wired to delete: route suggested changes to pending evidence, and do not trust a cascade selected on development data of this size.","location":"abstract s10","hedge_strength":{"p":0.97,"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":8569,"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":0.07,"states_limitation":0.95,"human_participants":0.65,"controlled_comparison":0.86,"randomized_assignment":0.04,"states_quantitative_result":0.99,"compares_with_prior_results":0.91,"mentions_code_or_data_availability":0.06},"evidential_basis":{"p":0.99,"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":0.99,"simulation_or_computation":0.01}},"contribution_type":{"p":0.99,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":0.99,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.01,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We write a task contract that separates the two (SUPERSEDED vs. NEEDS-CONFIRMATION vs. COMPATIBLE), label 500 test pairs built from STALE (change pairs plus same-user controls) with three LLM annotators and two human adjudicators (one author and a second annotator; provenance reported), and evaluate the classifier, a typed \"System One\" decision model, under pre-registered hypotheses.","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":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"}}}