{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BLR2WKCLI27VIVMHYDEDXWXXV4","short_pith_number":"pith:BLR2WKCL","schema_version":"1.0","canonical_sha256":"0ae3ab284b46bf545587c0c83bdaf7af2a1425a6b2c3db1daaee2ce522fd0b98","source":{"kind":"arxiv","id":"2308.14217","version":1},"attestation_state":"computed","paper":{"title":"Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Xin Luna Dong","submitted_at":"2023-08-27T22:35:27Z","abstract_excerpt":"Knowledge Graphs (KGs) have been used to support a wide range of applications, from web search to personal assistant. In this paper, we describe three generations of knowledge graphs: entity-based KGs, which have been supporting general search and question answering (e.g., at Google and Bing); text-rich KGs, which have been supporting search and recommendations for products, bio-informatics, etc. (e.g., at Amazon and Alibaba); and the emerging integration of KGs and LLMs, which we call dual neural KGs. We describe the characteristics of each generation of KGs, the crazy ideas behind the scenes"},"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":"2308.14217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-08-27T22:35:27Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ac9784870c79b2724301254e32f91baaed38e6136a5cd950b5273b8965636f4b","abstract_canon_sha256":"007e7293b12c281fe8908ff6edaced89ab5f38dfba6a04e1d5ca34c03e082697"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:23.434902Z","signature_b64":"rJQdW9L5K7Q36+Vk51vZEAmjsNCXEZc6k+nYRP0nUrXS3GTrTB8AdvV1HsFd8XU2Yi54cmZhzJuOZ6cL26LaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ae3ab284b46bf545587c0c83bdaf7af2a1425a6b2c3db1daaee2ce522fd0b98","last_reissued_at":"2026-07-05T06:45:23.434454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:23.434454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Xin Luna Dong","submitted_at":"2023-08-27T22:35:27Z","abstract_excerpt":"Knowledge Graphs (KGs) have been used to support a wide range of applications, from web search to personal assistant. In this paper, we describe three generations of knowledge graphs: entity-based KGs, which have been supporting general search and question answering (e.g., at Google and Bing); text-rich KGs, which have been supporting search and recommendations for products, bio-informatics, etc. (e.g., at Amazon and Alibaba); and the emerging integration of KGs and LLMs, which we call dual neural KGs. We describe the characteristics of each generation of KGs, the crazy ideas behind the scenes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14217","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/2308.14217/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":"2308.14217","created_at":"2026-07-05T06:45:23.434511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14217v1","created_at":"2026-07-05T06:45:23.434511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14217","created_at":"2026-07-05T06:45:23.434511+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLR2WKCLI27V","created_at":"2026-07-05T06:45:23.434511+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLR2WKCLI27VIVMH","created_at":"2026-07-05T06:45:23.434511+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLR2WKCL","created_at":"2026-07-05T06:45:23.434511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.02851","citing_title":"Leveraging LLMs to Create Content Corpora for Niche Domains","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4","json":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4.json","graph_json":"https://pith.science/api/pith-number/BLR2WKCLI27VIVMHYDEDXWXXV4/graph.json","events_json":"https://pith.science/api/pith-number/BLR2WKCLI27VIVMHYDEDXWXXV4/events.json","paper":"https://pith.science/paper/BLR2WKCL"},"agent_actions":{"view_html":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4","download_json":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4.json","view_paper":"https://pith.science/paper/BLR2WKCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14217&json=true","fetch_graph":"https://pith.science/api/pith-number/BLR2WKCLI27VIVMHYDEDXWXXV4/graph.json","fetch_events":"https://pith.science/api/pith-number/BLR2WKCLI27VIVMHYDEDXWXXV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4/action/storage_attestation","attest_author":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4/action/author_attestation","sign_citation":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4/action/citation_signature","submit_replication":"https://pith.science/pith/BLR2WKCLI27VIVMHYDEDXWXXV4/action/replication_record"}},"created_at":"2026-07-05T06:45:23.434511+00:00","updated_at":"2026-07-05T06:45:23.434511+00:00"}