{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2L5R7JD3LUNPXBAFWSB7SS5W3C","short_pith_number":"pith:2L5R7JD3","schema_version":"1.0","canonical_sha256":"d2fb1fa47b5d1afb8405b483f94bb6d8bdd5dcc8515a279c82ee0a60d1792ffc","source":{"kind":"arxiv","id":"2606.05415","version":1},"attestation_state":"computed","paper":{"title":"Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hilaf Hasson, Kamalika Das, Padmaja Jonnalagedda, Xiang Gao, Yuguang Yao","submitted_at":"2026-06-03T20:28:36Z","abstract_excerpt":"Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically discovers an executable schema from raw multi-source data and uses it as a shared contract for knowledge graph construction and query-time retrieval. A closed-world field catalog constrains LLM-based schema discovery to attested fields; deterministic structural analysis infers identit"},"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":"2606.05415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T20:28:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"28ef9b860c222163fb83a5815d10bc79b0704109c8f3cc6fbbbca35bd67e2771","abstract_canon_sha256":"10e953d48b8f79856d5969dc2de40356648c73a9e290b545e4f04478c236ddc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:57.030156Z","signature_b64":"R6FVFFNSdjrSux4c0yRhwTOfm3GjeAyQivE7JbQiQ5xKbo3/C9Cxt9eCwWGcs05hkIO9W1eiclOpLYY41psGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2fb1fa47b5d1afb8405b483f94bb6d8bdd5dcc8515a279c82ee0a60d1792ffc","last_reissued_at":"2026-06-05T00:13:57.029641Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:57.029641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hilaf Hasson, Kamalika Das, Padmaja Jonnalagedda, Xiang Gao, Yuguang Yao","submitted_at":"2026-06-03T20:28:36Z","abstract_excerpt":"Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically discovers an executable schema from raw multi-source data and uses it as a shared contract for knowledge graph construction and query-time retrieval. A closed-world field catalog constrains LLM-based schema discovery to attested fields; deterministic structural analysis infers identit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05415","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/2606.05415/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":"2606.05415","created_at":"2026-06-05T00:13:57.029711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05415v1","created_at":"2026-06-05T00:13:57.029711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05415","created_at":"2026-06-05T00:13:57.029711+00:00"},{"alias_kind":"pith_short_12","alias_value":"2L5R7JD3LUNP","created_at":"2026-06-05T00:13:57.029711+00:00"},{"alias_kind":"pith_short_16","alias_value":"2L5R7JD3LUNPXBAF","created_at":"2026-06-05T00:13:57.029711+00:00"},{"alias_kind":"pith_short_8","alias_value":"2L5R7JD3","created_at":"2026-06-05T00:13:57.029711+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/2L5R7JD3LUNPXBAFWSB7SS5W3C","json":"https://pith.science/pith/2L5R7JD3LUNPXBAFWSB7SS5W3C.json","graph_json":"https://pith.science/api/pith-number/2L5R7JD3LUNPXBAFWSB7SS5W3C/graph.json","events_json":"https://pith.science/api/pith-number/2L5R7JD3LUNPXBAFWSB7SS5W3C/events.json","paper":"https://pith.science/paper/2L5R7JD3"},"agent_actions":{"view_html":"https://pith.science/pith/2L5R7JD3LUNPXBAFWSB7SS5W3C","download_json":"https://pith.science/pith/2L5R7JD3LUNPXBAFWSB7SS5W3C.json","view_paper":"https://pith.science/paper/2L5R7JD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05415&json=true","fetch_graph":"https://pith.science/api/pith-number/2L5R7JD3LUNPXBAFWSB7SS5W3C/graph.json","fetch_events":"https://pith.science/api/pith-number/2L5R7JD3LUNPXBAFWSB7SS5W3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2L5R7JD3LUNPXBAFWSB7SS5W3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2L5R7JD3LUNPXBAFWSB7SS5W3C/action/storage_attestation","attest_author":"https://pith.science/pith/2L5R7JD3LUNPXBAFWSB7SS5W3C/action/author_attestation","sign_citation":"https://pith.science/pith/2L5R7JD3LUNPXBAFWSB7SS5W3C/action/citation_signature","submit_replication":"https://pith.science/pith/2L5R7JD3LUNPXBAFWSB7SS5W3C/action/replication_record"}},"created_at":"2026-06-05T00:13:57.029711+00:00","updated_at":"2026-06-05T00:13:57.029711+00:00"}