{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JOK7SFW6NS2W3QUROMZ2G2CUZW","short_pith_number":"pith:JOK7SFW6","schema_version":"1.0","canonical_sha256":"4b95f916de6cb56dc2917333a36854cd811bf20e4d7c20e5e32120ff960c02b3","source":{"kind":"arxiv","id":"2607.28662","version":1},"attestation_state":"computed","paper":{"title":"An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kevin Lewis, Kundeshwar Pundalik, Vaibhav Dangaich","submitted_at":"2026-07-22T09:45:26Z","abstract_excerpt":"Large language models extract entities and relationships from unstructured documents fluently but inconsistently: type vocabularies fracture across documents, the same person surfaces under several name variants, relationships duplicate, and distinct individuals who share a name risk silent conflation. This paper presents the design, implementation, and empirical refinement of a production extraction layer that converts a live document stream into a validated knowledge graph aligned to a formal ontology. The system consumes document metadata from Kafka, routes PDF, spreadsheet, Office, and ima"},"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":"2607.28662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-22T09:45:26Z","cross_cats_sorted":[],"title_canon_sha256":"badec4d1ad1dd349b8d60b5d713d719c64c5b4823d12c6745dafd09fd2949593","abstract_canon_sha256":"fc06b8b93d6968fe1af045a0ae3a6d5455c287e63378b7e5d501592c11c341a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T00:12:02.281013Z","signature_b64":"NvpPNChzXMaA431gHzdbRGaV+sW27VU/yOiz/6rMFEU+wyB/2o/7jWT9S642Xmeasnt8EC36TLfuIjiVPmRFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b95f916de6cb56dc2917333a36854cd811bf20e4d7c20e5e32120ff960c02b3","last_reissued_at":"2026-08-03T00:12:02.237021Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T00:12:02.237021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kevin Lewis, Kundeshwar Pundalik, Vaibhav Dangaich","submitted_at":"2026-07-22T09:45:26Z","abstract_excerpt":"Large language models extract entities and relationships from unstructured documents fluently but inconsistently: type vocabularies fracture across documents, the same person surfaces under several name variants, relationships duplicate, and distinct individuals who share a name risk silent conflation. This paper presents the design, implementation, and empirical refinement of a production extraction layer that converts a live document stream into a validated knowledge graph aligned to a formal ontology. The system consumes document metadata from Kafka, routes PDF, spreadsheet, Office, and ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28662","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/2607.28662/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":"2607.28662","created_at":"2026-08-03T00:12:02.239213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28662v1","created_at":"2026-08-03T00:12:02.239213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28662","created_at":"2026-08-03T00:12:02.239213+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOK7SFW6NS2W","created_at":"2026-08-03T00:12:02.239213+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOK7SFW6NS2W3QUR","created_at":"2026-08-03T00:12:02.239213+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOK7SFW6","created_at":"2026-08-03T00:12:02.239213+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/JOK7SFW6NS2W3QUROMZ2G2CUZW","json":"https://pith.science/pith/JOK7SFW6NS2W3QUROMZ2G2CUZW.json","graph_json":"https://pith.science/api/pith-number/JOK7SFW6NS2W3QUROMZ2G2CUZW/graph.json","events_json":"https://pith.science/api/pith-number/JOK7SFW6NS2W3QUROMZ2G2CUZW/events.json","paper":"https://pith.science/paper/JOK7SFW6"},"agent_actions":{"view_html":"https://pith.science/pith/JOK7SFW6NS2W3QUROMZ2G2CUZW","download_json":"https://pith.science/pith/JOK7SFW6NS2W3QUROMZ2G2CUZW.json","view_paper":"https://pith.science/paper/JOK7SFW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28662&json=true","fetch_graph":"https://pith.science/api/pith-number/JOK7SFW6NS2W3QUROMZ2G2CUZW/graph.json","fetch_events":"https://pith.science/api/pith-number/JOK7SFW6NS2W3QUROMZ2G2CUZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOK7SFW6NS2W3QUROMZ2G2CUZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOK7SFW6NS2W3QUROMZ2G2CUZW/action/storage_attestation","attest_author":"https://pith.science/pith/JOK7SFW6NS2W3QUROMZ2G2CUZW/action/author_attestation","sign_citation":"https://pith.science/pith/JOK7SFW6NS2W3QUROMZ2G2CUZW/action/citation_signature","submit_replication":"https://pith.science/pith/JOK7SFW6NS2W3QUROMZ2G2CUZW/action/replication_record"}},"created_at":"2026-08-03T00:12:02.239213+00:00","updated_at":"2026-08-03T00:12:02.239213+00:00"}