{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AJECSOH4XBWGJ57XL67STBNEV2","short_pith_number":"pith:AJECSOH4","schema_version":"1.0","canonical_sha256":"02482938fcb86c64f7f75fbf2985a4ae8ebf019cceb38d5321bf1621f677fed7","source":{"kind":"arxiv","id":"2509.04696","version":1},"attestation_state":"computed","paper":{"title":"ODKE+: Ontology-Guided Open-Domain Knowledge Extraction with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Fakhry, Alexis McClimans, Ali Kasgari, Azadeh Nikfarjam, Hyun Jang, Mohamed Soliman, Samira Khorshidi, Suprita Shankar, Vishnu Konda, Xiaoguang Qi, Yash Govind, Yisi Sang","submitted_at":"2025-09-04T23:05:23Z","abstract_excerpt":"Knowledge graphs (KGs) are foundational to many AI applications, but maintaining their freshness and completeness remains costly. We present ODKE+, a production-grade system that automatically extracts and ingests millions of open-domain facts from web sources with high precision. ODKE+ combines modular components into a scalable pipeline: (1) the Extraction Initiator detects missing or stale facts, (2) the Evidence Retriever collects supporting documents, (3) hybrid Knowledge Extractors apply both pattern-based rules and ontology-guided prompting for large language models (LLMs), (4) a lightw"},"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":"2509.04696","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T23:05:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f916b690f8328170e3c612d5f5f6d656536e13c8c6ee8f03e8930f0f7f3acb14","abstract_canon_sha256":"889ea0e52b60cb0c76d4dd2d63b5bddc25c2fb0b65eae6c79d5de2f040f2445c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:27.854104Z","signature_b64":"V/wlnsLV1giLZaQrZlRN3IKoW9kVIuxb/3cXxBV1Of07rvHph4vg7/MXkDX65/BK8TIVLh888mBzBz29CbAECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02482938fcb86c64f7f75fbf2985a4ae8ebf019cceb38d5321bf1621f677fed7","last_reissued_at":"2026-07-05T12:05:27.853679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:27.853679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ODKE+: Ontology-Guided Open-Domain Knowledge Extraction with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Fakhry, Alexis McClimans, Ali Kasgari, Azadeh Nikfarjam, Hyun Jang, Mohamed Soliman, Samira Khorshidi, Suprita Shankar, Vishnu Konda, Xiaoguang Qi, Yash Govind, Yisi Sang","submitted_at":"2025-09-04T23:05:23Z","abstract_excerpt":"Knowledge graphs (KGs) are foundational to many AI applications, but maintaining their freshness and completeness remains costly. We present ODKE+, a production-grade system that automatically extracts and ingests millions of open-domain facts from web sources with high precision. ODKE+ combines modular components into a scalable pipeline: (1) the Extraction Initiator detects missing or stale facts, (2) the Evidence Retriever collects supporting documents, (3) hybrid Knowledge Extractors apply both pattern-based rules and ontology-guided prompting for large language models (LLMs), (4) a lightw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04696","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/2509.04696/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":"2509.04696","created_at":"2026-07-05T12:05:27.853737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04696v1","created_at":"2026-07-05T12:05:27.853737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04696","created_at":"2026-07-05T12:05:27.853737+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJECSOH4XBWG","created_at":"2026-07-05T12:05:27.853737+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJECSOH4XBWGJ57X","created_at":"2026-07-05T12:05:27.853737+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJECSOH4","created_at":"2026-07-05T12:05:27.853737+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/AJECSOH4XBWGJ57XL67STBNEV2","json":"https://pith.science/pith/AJECSOH4XBWGJ57XL67STBNEV2.json","graph_json":"https://pith.science/api/pith-number/AJECSOH4XBWGJ57XL67STBNEV2/graph.json","events_json":"https://pith.science/api/pith-number/AJECSOH4XBWGJ57XL67STBNEV2/events.json","paper":"https://pith.science/paper/AJECSOH4"},"agent_actions":{"view_html":"https://pith.science/pith/AJECSOH4XBWGJ57XL67STBNEV2","download_json":"https://pith.science/pith/AJECSOH4XBWGJ57XL67STBNEV2.json","view_paper":"https://pith.science/paper/AJECSOH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04696&json=true","fetch_graph":"https://pith.science/api/pith-number/AJECSOH4XBWGJ57XL67STBNEV2/graph.json","fetch_events":"https://pith.science/api/pith-number/AJECSOH4XBWGJ57XL67STBNEV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJECSOH4XBWGJ57XL67STBNEV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJECSOH4XBWGJ57XL67STBNEV2/action/storage_attestation","attest_author":"https://pith.science/pith/AJECSOH4XBWGJ57XL67STBNEV2/action/author_attestation","sign_citation":"https://pith.science/pith/AJECSOH4XBWGJ57XL67STBNEV2/action/citation_signature","submit_replication":"https://pith.science/pith/AJECSOH4XBWGJ57XL67STBNEV2/action/replication_record"}},"created_at":"2026-07-05T12:05:27.853737+00:00","updated_at":"2026-07-05T12:05:27.853737+00:00"}