{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RSPQVUGLMBHX54IOHMKA3TLDGY","short_pith_number":"pith:RSPQVUGL","schema_version":"1.0","canonical_sha256":"8c9f0ad0cb604f7ef10e3b140dcd633622b09de56bb633b4b1611b90f5ece2dd","source":{"kind":"arxiv","id":"2608.08459","version":1},"attestation_state":"computed","paper":{"title":"Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Jiayang Wang, Jiazhuo Chen, Nan Tang, Zhengxuan Zhang, Zhuowen Liang","submitted_at":"2026-08-09T03:58:39Z","abstract_excerpt":"Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets. In domains such as finance, healthcare, education, transportation, and enterprise operations, downstream workflows rely on normalized schemas, entity identities, keys, cross-table relationships, and integrity constraints for analytics, compliance, auditing, and SQL-backed decision making. Existing Document-to-Table benchmarks are insufficient for this setting: flattening evidence into single tables can duplicate entities, obscure many-to-many relationship"},"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":"2608.08459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-09T03:58:39Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"9a5b48524b145ee3f5d12b657837231bd25f16ede572eebf9f15fa0fd9a63193","abstract_canon_sha256":"a6040b84d192ba622c1db250ea4013713e6df0b57ab457212147feb1bc7ef54f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:41.188646Z","signature_b64":"yuvjwpujOa5OFh0dZ/4iFKbKlIqPf08ENUYfvq63KmlgowCbfSK0tfv3BLImMaZJKOr2NHEEnfSOYXmeqCEQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c9f0ad0cb604f7ef10e3b140dcd633622b09de56bb633b4b1611b90f5ece2dd","last_reissued_at":"2026-08-11T01:22:41.186347Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:41.186347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Jiayang Wang, Jiazhuo Chen, Nan Tang, Zhengxuan Zhang, Zhuowen Liang","submitted_at":"2026-08-09T03:58:39Z","abstract_excerpt":"Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets. In domains such as finance, healthcare, education, transportation, and enterprise operations, downstream workflows rely on normalized schemas, entity identities, keys, cross-table relationships, and integrity constraints for analytics, compliance, auditing, and SQL-backed decision making. Existing Document-to-Table benchmarks are insufficient for this setting: flattening evidence into single tables can duplicate entities, obscure many-to-many relationship"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08459","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/2608.08459/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":"2608.08459","created_at":"2026-08-11T01:22:41.187060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08459v1","created_at":"2026-08-11T01:22:41.187060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08459","created_at":"2026-08-11T01:22:41.187060+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSPQVUGLMBHX","created_at":"2026-08-11T01:22:41.187060+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSPQVUGLMBHX54IO","created_at":"2026-08-11T01:22:41.187060+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSPQVUGL","created_at":"2026-08-11T01:22:41.187060+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/RSPQVUGLMBHX54IOHMKA3TLDGY","json":"https://pith.science/pith/RSPQVUGLMBHX54IOHMKA3TLDGY.json","graph_json":"https://pith.science/api/pith-number/RSPQVUGLMBHX54IOHMKA3TLDGY/graph.json","events_json":"https://pith.science/api/pith-number/RSPQVUGLMBHX54IOHMKA3TLDGY/events.json","paper":"https://pith.science/paper/RSPQVUGL"},"agent_actions":{"view_html":"https://pith.science/pith/RSPQVUGLMBHX54IOHMKA3TLDGY","download_json":"https://pith.science/pith/RSPQVUGLMBHX54IOHMKA3TLDGY.json","view_paper":"https://pith.science/paper/RSPQVUGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08459&json=true","fetch_graph":"https://pith.science/api/pith-number/RSPQVUGLMBHX54IOHMKA3TLDGY/graph.json","fetch_events":"https://pith.science/api/pith-number/RSPQVUGLMBHX54IOHMKA3TLDGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSPQVUGLMBHX54IOHMKA3TLDGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSPQVUGLMBHX54IOHMKA3TLDGY/action/storage_attestation","attest_author":"https://pith.science/pith/RSPQVUGLMBHX54IOHMKA3TLDGY/action/author_attestation","sign_citation":"https://pith.science/pith/RSPQVUGLMBHX54IOHMKA3TLDGY/action/citation_signature","submit_replication":"https://pith.science/pith/RSPQVUGLMBHX54IOHMKA3TLDGY/action/replication_record"}},"created_at":"2026-08-11T01:22:41.187060+00:00","updated_at":"2026-08-11T01:22:41.187060+00:00"}