{"paper":{"title":"Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback","arxiv_id":"2610.19380","primary_cat":"cs.CL","submitted_at":"2026-10-14T01:27:19+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":0.96,"id":"s0","own":false,"role":"background","text":"User feedback enables LLMs to refine reusable personalized skills, but often mixes persistent preferences with request-specific corrections.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.11,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.04,"method":0.0,"result":0.0,"background":0.96,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.73,"id":"s1","own":false,"role":"background","text":"Indiscriminately retaining both risks negative transfer, motivating selective retention at the level of individual requirements.","hedge":{"p":0.69,"label":"asserted"},"own_p":0.07,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.26,"method":0.0,"result":0.0,"background":0.73,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":2,"p":0.98,"id":"s2","own":true,"role":"contribution","text":"We frame this challenge as selective transfer over atomic rules and propose SkillGrain, a framework for learning reusable personalized skills from user feedback.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.82,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.98,"interpretation":0.0}},{"i":3,"p":0.94,"id":"s3","own":true,"role":"method","text":"SkillGrain decomposes feedback into independently actionable rules, predicts their transferability, and retains only those suitable for future requests.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.83,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.94,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.06,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"To learn these decisions, we combine rubric-guided skill rewards with fine-grained credit assignment that separately evaluates rule content and retention decisions.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.93,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.05,"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":5,"p":0.99,"id":"s5","own":true,"role":"method","text":"We further jointly optimize skill induction and skill-conditioned generation through reinforcement learning, ensuring that learned skills support downstream personalization.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.94,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.04,"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":6,"p":0.87,"id":"s6","own":true,"role":"method","text":"We construct a benchmark spanning five personalized writing tasks to evaluate cross-request generalization.","hedge":{"p":0.95,"label":"asserted"},"own_p":0.95,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.91,"role_probabilities":{"gap":0.0,"method":0.87,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.13,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"Experiments across three base models in both in-domain and out-of-domain settings show that SkillGrain achieves the best overall average performance among competing methods.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.75,"quantitative":true,"quantitative_p":0.97,"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}}]},"compiled":{"main_claim":{"p":1.0,"text":"Experiments across three base models in both in-domain and out-of-domain settings show that SkillGrain achieves the best overall average performance among competing methods.","location":"abstract s7","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":6140,"cost_usd_reported":0.0},"compiled_at":"2026-10-15","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.06,"states_limitation":0.11,"human_participants":0.3,"controlled_comparison":0.69,"randomized_assignment":0.02,"states_quantitative_result":0.36,"compares_with_prior_results":0.94,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":1.0,"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":1.0,"simulation_or_computation":0.0}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.93,"text":"We frame this challenge as selective transfer over atomic rules and propose SkillGrain, a framework for learning reusable personalized skills from user feedback.","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":8,"sentences_in_abstract":8},"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"}}}