{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KABWFSIMHAOPLPXYZZE7BVVPYF","short_pith_number":"pith:KABWFSIM","schema_version":"1.0","canonical_sha256":"500362c90c381cf5bef8ce49f0d6afc1639af0c674669569fc390c6c8f359eef","source":{"kind":"arxiv","id":"2606.03056","version":1},"attestation_state":"computed","paper":{"title":"SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ivor W. Tsang, Pengfei Zhou, Tong Bai, Wangbo Zhao, Xingrui Yu, Yang You, Zhenglin Wan","submitted_at":"2026-06-02T02:45:21Z","abstract_excerpt":"As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specialize, or duplicate one another, a structure invisible to both full enumeration and embedding similarity. We present SkillDAG, which models inter-skill relationships as a typed directed graph and exposes it to an LLM agent as an inference-time, agent-callable structural retrieval interface, queried and evolved during execution rather than baked into a fixed retrieval pipeline: each search returns vector matches, typed-ed"},"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":"2606.03056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T02:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"e414a40052be53f0177777309b18550f9362cda191e55ed92916c001daa61021","abstract_canon_sha256":"82b34df78abcd0ac50e774c6f226f3a8e55dd3f0dff86464570e22169d64b4e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:30.490892Z","signature_b64":"48e9UYyJ4sbgezL1RLpEhsRyxkx50w9cKRURzotzeFNvp8r0xzt/VwCq0aGz/m0+vJk7vUbRYEIxZ21xToREAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"500362c90c381cf5bef8ce49f0d6afc1639af0c674669569fc390c6c8f359eef","last_reissued_at":"2026-06-03T01:05:30.490464Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:30.490464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ivor W. Tsang, Pengfei Zhou, Tong Bai, Wangbo Zhao, Xingrui Yu, Yang You, Zhenglin Wan","submitted_at":"2026-06-02T02:45:21Z","abstract_excerpt":"As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specialize, or duplicate one another, a structure invisible to both full enumeration and embedding similarity. We present SkillDAG, which models inter-skill relationships as a typed directed graph and exposes it to an LLM agent as an inference-time, agent-callable structural retrieval interface, queried and evolved during execution rather than baked into a fixed retrieval pipeline: each search returns vector matches, typed-ed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03056","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/2606.03056/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":"2606.03056","created_at":"2026-06-03T01:05:30.490541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03056v1","created_at":"2026-06-03T01:05:30.490541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03056","created_at":"2026-06-03T01:05:30.490541+00:00"},{"alias_kind":"pith_short_12","alias_value":"KABWFSIMHAOP","created_at":"2026-06-03T01:05:30.490541+00:00"},{"alias_kind":"pith_short_16","alias_value":"KABWFSIMHAOPLPXY","created_at":"2026-06-03T01:05:30.490541+00:00"},{"alias_kind":"pith_short_8","alias_value":"KABWFSIM","created_at":"2026-06-03T01:05:30.490541+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/KABWFSIMHAOPLPXYZZE7BVVPYF","json":"https://pith.science/pith/KABWFSIMHAOPLPXYZZE7BVVPYF.json","graph_json":"https://pith.science/api/pith-number/KABWFSIMHAOPLPXYZZE7BVVPYF/graph.json","events_json":"https://pith.science/api/pith-number/KABWFSIMHAOPLPXYZZE7BVVPYF/events.json","paper":"https://pith.science/paper/KABWFSIM"},"agent_actions":{"view_html":"https://pith.science/pith/KABWFSIMHAOPLPXYZZE7BVVPYF","download_json":"https://pith.science/pith/KABWFSIMHAOPLPXYZZE7BVVPYF.json","view_paper":"https://pith.science/paper/KABWFSIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03056&json=true","fetch_graph":"https://pith.science/api/pith-number/KABWFSIMHAOPLPXYZZE7BVVPYF/graph.json","fetch_events":"https://pith.science/api/pith-number/KABWFSIMHAOPLPXYZZE7BVVPYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KABWFSIMHAOPLPXYZZE7BVVPYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KABWFSIMHAOPLPXYZZE7BVVPYF/action/storage_attestation","attest_author":"https://pith.science/pith/KABWFSIMHAOPLPXYZZE7BVVPYF/action/author_attestation","sign_citation":"https://pith.science/pith/KABWFSIMHAOPLPXYZZE7BVVPYF/action/citation_signature","submit_replication":"https://pith.science/pith/KABWFSIMHAOPLPXYZZE7BVVPYF/action/replication_record"}},"created_at":"2026-06-03T01:05:30.490541+00:00","updated_at":"2026-06-03T01:05:30.490541+00:00"}