{"paper":{"title":"SkillRep: Characterizing and Understanding the Representation Design Space of Agent Skill Retrieval","arxiv_id":"2610.32336","primary_cat":"cs.IR","submitted_at":"2026-10-23T08:30:15+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":"Retrieving the right skill from a large library is essential for LLM agents, yet requests and skills are written for different purposes and in different words.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.14,"role_probabilities":{"gap":0.01,"method":0.0,"result":0.0,"background":0.99,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.8,"id":"s1","own":false,"role":"gap","text":"Existing retrievers narrow this request-skill gap with one or two representation choices each, so it is unknown whether their gains hold in combination.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"quantitative":true,"quantitative_p":0.52,"role_probabilities":{"gap":0.8,"method":0.0,"result":0.0,"background":0.2,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.99,"id":"s2","own":false,"role":"gap","text":"No prior work measures the gap itself, so it is also unclear which part of it each choice narrows.","hedge":{"p":0.94,"label":"asserted"},"own_p":0.07,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.99,"method":0.0,"result":0.0,"background":0.01,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.78,"id":"s3","own":true,"role":"contribution","text":"We define a representation design space by five choices -- encoder fine-tuning, query-side and document-side expansion, background projection and a lexical channel -- and evaluate them together for the first time, as modules of one retriever, SkillRep.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.83,"role_probabilities":{"gap":0.0,"method":0.22,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.78,"interpretation":0.0}},{"i":4,"p":1.0,"id":"s4","own":true,"role":"result","text":"With a 0.6B encoder and LLM expansion, SkillRep improves MRR@10 on SRA-Bench over the strongest same-size retriever by 7.02 points with the official skill pool and 8.79 with UniPool, a 111,247-skill pool we build from public registries, and is best on SkillsBench.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.25,"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":5,"p":0.78,"id":"s5","own":true,"role":"result","text":"The value of each choice depends on the others.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.86,"main_claim_p":0.28,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.78,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.21}},{"i":6,"p":0.86,"id":"s6","own":true,"role":"result","text":"Fine-tuning, for instance, reverses the ranking of the four training-free modules and turns them from complementary into overlapping.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.41,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.86,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.14}},{"i":7,"p":0.8,"id":"s7","own":true,"role":"method","text":"To understand why, we measure the gap with three quantities: background, the embedding component that does not separate skills; unsaid vocabulary, the gold skill's content a request leaves unsaid; and dilution, the information lost when a skill is encoded into a single vector.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.93,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.66,"role_probabilities":{"gap":0.0,"method":0.8,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.19,"interpretation":0.01}},{"i":8,"p":0.37,"id":"s8","own":true,"role":"result","text":"They show which part each module narrows and by what mechanism.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.2,"result":0.37,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.32,"interpretation":0.11}},{"i":9,"p":0.97,"id":"s9","own":true,"role":"interpretation","text":"This reveals that modules narrowing the same part compete for it, while those narrowing different parts complement each other.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.48,"quantitative":false,"quantitative_p":0.12,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.03,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.97}}]},"compiled":{"main_claim":{"p":0.7,"text":"This reveals that modules narrowing the same part compete for it, while those narrowing different parts complement each other.","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":7699,"cost_usd_reported":0.0},"compiled_at":"2026-10-26","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.89,"states_limitation":0.34,"human_participants":0.04,"controlled_comparison":0.84,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.96,"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":0.63,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":0.63,"empirical_study":0.37,"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 define a representation design space by five choices -- encoder fine-tuning, query-side and document-side expansion, background projection and a lexical channel -- and evaluate them together for the first time, as modules of one retriever, SkillRep.","location":"abstract s3"}},"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"}}}