{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5PA2QLZ63DDMVGB43Z4OTHZCJR","short_pith_number":"pith:5PA2QLZ6","schema_version":"1.0","canonical_sha256":"ebc1a82f3ed8c6ca983cde78e99f224c746516ad564478e1c370eaad94558b34","source":{"kind":"arxiv","id":"2606.10546","version":1},"attestation_state":"computed","paper":{"title":"SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Arjun Radhakrishna, Srishti Gautam, Sumit Gulwani","submitted_at":"2026-06-09T08:14:39Z","abstract_excerpt":"Skill documents, structured natural-language instructions that guide Large Language Model (LLM) agents, are critical to modern agent frameworks, yet LLMs struggle to write skills that actually work. On SkillsBench, human-authored skills improve pass rates by 16.2 percentage points, while LLM-authored skills provide no measurable gain. We introduce SkillAxe, a fully unsupervised framework that enables LLMs to iteratively diagnose and refine their own skills. SkillAxe decomposes skill quality into four interpretable dimensions (quality impact, trigger precision, instruction compliance with fault"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.10546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-06-09T08:14:39Z","cross_cats_sorted":[],"title_canon_sha256":"b54a53b060bf367f58876879c3c2dd1affc1163a6a4364f605e73f9cb5fbefa9","abstract_canon_sha256":"311b5fba67866aa0a3fbe3a9cd9d69d32d44cce9e3342010851aa3724e3b4e14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:25.473486Z","signature_b64":"sr2YA76bEsVVVd9V7h0Pc4SGnFuF3PO43pjWgZbsCvrJspYACFbeexYWNqmWRLNtI0ovEbAzhdw760pnAFzLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebc1a82f3ed8c6ca983cde78e99f224c746516ad564478e1c370eaad94558b34","last_reissued_at":"2026-06-10T01:10:25.472578Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:25.472578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Arjun Radhakrishna, Srishti Gautam, Sumit Gulwani","submitted_at":"2026-06-09T08:14:39Z","abstract_excerpt":"Skill documents, structured natural-language instructions that guide Large Language Model (LLM) agents, are critical to modern agent frameworks, yet LLMs struggle to write skills that actually work. On SkillsBench, human-authored skills improve pass rates by 16.2 percentage points, while LLM-authored skills provide no measurable gain. We introduce SkillAxe, a fully unsupervised framework that enables LLMs to iteratively diagnose and refine their own skills. SkillAxe decomposes skill quality into four interpretable dimensions (quality impact, trigger precision, instruction compliance with fault"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10546","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.10546/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.10546","created_at":"2026-06-10T01:10:25.472749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10546v1","created_at":"2026-06-10T01:10:25.472749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10546","created_at":"2026-06-10T01:10:25.472749+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PA2QLZ63DDM","created_at":"2026-06-10T01:10:25.472749+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PA2QLZ63DDMVGB4","created_at":"2026-06-10T01:10:25.472749+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PA2QLZ6","created_at":"2026-06-10T01:10:25.472749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR","json":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR.json","graph_json":"https://pith.science/api/pith-number/5PA2QLZ63DDMVGB43Z4OTHZCJR/graph.json","events_json":"https://pith.science/api/pith-number/5PA2QLZ63DDMVGB43Z4OTHZCJR/events.json","paper":"https://pith.science/paper/5PA2QLZ6"},"agent_actions":{"view_html":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR","download_json":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR.json","view_paper":"https://pith.science/paper/5PA2QLZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10546&json=true","fetch_graph":"https://pith.science/api/pith-number/5PA2QLZ63DDMVGB43Z4OTHZCJR/graph.json","fetch_events":"https://pith.science/api/pith-number/5PA2QLZ63DDMVGB43Z4OTHZCJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR/action/storage_attestation","attest_author":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR/action/author_attestation","sign_citation":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR/action/citation_signature","submit_replication":"https://pith.science/pith/5PA2QLZ63DDMVGB43Z4OTHZCJR/action/replication_record"}},"created_at":"2026-06-10T01:10:25.472749+00:00","updated_at":"2026-06-10T01:10:25.472749+00:00"}