{"paper":{"title":"FedSkillGit: Federated Skill Evolution via Version Control","arxiv_id":"2610.21348","primary_cat":"cs.AI","submitted_at":"2026-10-15T06:29:57+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":"Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience.","hedge":{"p":0.56,"label":"hedged_possibility"},"own_p":0.09,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.06,"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":0.94,"id":"s1","own":false,"role":"background","text":"In real-world deployments, this experience is distributed across data owners who cannot pool their raw data, which motivates federated skill evolution.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.08,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.06,"method":0.0,"result":0.0,"background":0.94,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.95,"id":"s2","own":false,"role":"background","text":"The natural first design lets each client evolve the whole skill document and upload the result for server-side aggregation.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.08,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.02,"method":0.03,"result":0.0,"background":0.95,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.55,"id":"s3","own":false,"role":"gap","text":"That design is poorly matched to skill evolution for three reasons.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.21,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.48,"role_probabilities":{"gap":0.55,"method":0.0,"result":0.0,"background":0.4,"limitation":0.03,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":4,"p":0.61,"id":"s4","own":false,"role":"background","text":"An evolved document can still carry client-specific content distilled from private traces, repeated transmission of a nearly unchanged document spends communication on knowledge that the population already holds and the contribution of a single client is buried in a document that the server cannot meaningfully attribute.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.2,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.35,"method":0.0,"result":0.0,"background":0.61,"limitation":0.03,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":5,"p":0.95,"id":"s5","own":true,"role":"contribution","text":"We propose FedSkillGit, a federated skill evolution framework that replaces full-document updates with commits.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.79,"main_claim_p":0.13,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.95,"interpretation":0.0}},{"i":6,"p":0.97,"id":"s6","own":true,"role":"method","text":"Each participating client submits a bounded set of patches over named rules together with its local experience, which summarizes what the round taught it, and the pair passes a two-stage privacy filter before it leaves the client.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.72,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.65,"role_probabilities":{"gap":0.0,"method":0.97,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.03,"interpretation":0.0}},{"i":7,"p":0.99,"id":"s7","own":true,"role":"method","text":"The server deduplicates the submitted patches and the local experience of all participants, updates a global experience document that only the optimizers read, and merges the surviving patches into a candidate skill.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.74,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.06,"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":8,"p":1.0,"id":"s8","own":true,"role":"method","text":"The candidate is distributed to the clients, which score it on their own validation sets and report the results, and it is published only when the reported scores improve on the current version.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.8,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.52,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":9,"p":1.0,"id":"s9","own":true,"role":"result","text":"Experiments on three datasets and three language model families show that FedSkillGit outperforms state-of-the-art baselines by up to 22% and approaches centralized evolution without sharing raw client data.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.84,"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}}]},"compiled":{"main_claim":{"p":1.0,"text":"Experiments on three datasets and three language model families show that FedSkillGit outperforms state-of-the-art baselines by up to 22% and approaches centralized evolution without sharing raw client data.","location":"abstract s9","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":7599,"cost_usd_reported":0.0},"compiled_at":"2026-10-16","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.1,"states_limitation":0.24,"human_participants":0.09,"controlled_comparison":0.91,"randomized_assignment":0.02,"states_quantitative_result":0.98,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.04},"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":1.0,"text":"We propose FedSkillGit, a federated skill evolution framework that replaces full-document updates with commits.","location":"abstract s5"}},"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"}}}