{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KMTY5WOV5Q53PL2N32AEZSZW2B","short_pith_number":"pith:KMTY5WOV","schema_version":"1.0","canonical_sha256":"53278ed9d5ec3bb7af4dde804ccb36d06d378b24d0dd419b3fd8d597a049809e","source":{"kind":"arxiv","id":"2606.11543","version":1},"attestation_state":"computed","paper":{"title":"SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Bingwei Lu, Bo Huang, Jianghao Lin, Weinan Zhang, Yuanjian Zhou, Zhiyu Chen, Zihan Guo","submitted_at":"2026-06-10T01:11:50Z","abstract_excerpt":"Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized. We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand, and compare it with a normalized flat baseline. We present SkillJuror, a framework for evaluating Skill writing paradigms through semantically controlled variants, matched multi-trial evaluations, and trajectory evidence while holding task knowledge fixed. In an 82-task SkillsBenc"},"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":"2606.11543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T01:11:50Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"a627065fc1356b244afed4768fc92feacdf7fcade2d191358461afd603103b60","abstract_canon_sha256":"c2e120b29a7fdfdbefd1f2f76561acbd81dde795cd4d69b5cb8dbf01f35dbf07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:55.249834Z","signature_b64":"6yMx55HMlC9bGOpJSeHyPjHAdmmdpfil7e7GV7BYrHTtuDIXxvxGsFNNymin50qXCnc1pJk+HZdmubERCq/fAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53278ed9d5ec3bb7af4dde804ccb36d06d378b24d0dd419b3fd8d597a049809e","last_reissued_at":"2026-06-11T01:09:55.248976Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:55.248976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Bingwei Lu, Bo Huang, Jianghao Lin, Weinan Zhang, Yuanjian Zhou, Zhiyu Chen, Zihan Guo","submitted_at":"2026-06-10T01:11:50Z","abstract_excerpt":"Agent Skills augment large language model (LLM) agents with procedural knowledge at inference time, but current benchmarks rarely distinguish what a Skill says from how it is organized. We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand, and compare it with a normalized flat baseline. We present SkillJuror, a framework for evaluating Skill writing paradigms through semantically controlled variants, matched multi-trial evaluations, and trajectory evidence while holding task knowledge fixed. In an 82-task SkillsBenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11543","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/2606.11543/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":"2606.11543","created_at":"2026-06-11T01:09:55.249116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11543v1","created_at":"2026-06-11T01:09:55.249116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11543","created_at":"2026-06-11T01:09:55.249116+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMTY5WOV5Q53","created_at":"2026-06-11T01:09:55.249116+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMTY5WOV5Q53PL2N","created_at":"2026-06-11T01:09:55.249116+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMTY5WOV","created_at":"2026-06-11T01:09:55.249116+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/KMTY5WOV5Q53PL2N32AEZSZW2B","json":"https://pith.science/pith/KMTY5WOV5Q53PL2N32AEZSZW2B.json","graph_json":"https://pith.science/api/pith-number/KMTY5WOV5Q53PL2N32AEZSZW2B/graph.json","events_json":"https://pith.science/api/pith-number/KMTY5WOV5Q53PL2N32AEZSZW2B/events.json","paper":"https://pith.science/paper/KMTY5WOV"},"agent_actions":{"view_html":"https://pith.science/pith/KMTY5WOV5Q53PL2N32AEZSZW2B","download_json":"https://pith.science/pith/KMTY5WOV5Q53PL2N32AEZSZW2B.json","view_paper":"https://pith.science/paper/KMTY5WOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11543&json=true","fetch_graph":"https://pith.science/api/pith-number/KMTY5WOV5Q53PL2N32AEZSZW2B/graph.json","fetch_events":"https://pith.science/api/pith-number/KMTY5WOV5Q53PL2N32AEZSZW2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMTY5WOV5Q53PL2N32AEZSZW2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMTY5WOV5Q53PL2N32AEZSZW2B/action/storage_attestation","attest_author":"https://pith.science/pith/KMTY5WOV5Q53PL2N32AEZSZW2B/action/author_attestation","sign_citation":"https://pith.science/pith/KMTY5WOV5Q53PL2N32AEZSZW2B/action/citation_signature","submit_replication":"https://pith.science/pith/KMTY5WOV5Q53PL2N32AEZSZW2B/action/replication_record"}},"created_at":"2026-06-11T01:09:55.249116+00:00","updated_at":"2026-06-11T01:09:55.249116+00:00"}