{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JRVXXQGC7KGY5F6ISMK4BL4D7P","short_pith_number":"pith:JRVXXQGC","schema_version":"1.0","canonical_sha256":"4c6b7bc0c2fa8d8e97c89315c0af83fbf96844ff6fec96fb1f51101c606ea8d5","source":{"kind":"arxiv","id":"2404.03868","version":2},"attestation_state":"computed","paper":{"title":"Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Zhang, Harold Soh","submitted_at":"2024-04-05T02:53:51Z","abstract_excerpt":"In this work, we are interested in automated methods for knowledge graph creation (KGC) from input text. Progress on large language models (LLMs) has prompted a series of recent works applying them to KGC, e.g., via zero/few-shot prompting. Despite successes on small domain-specific datasets, these models face difficulties scaling up to text common in many real-world applications. A principal issue is that, in prior methods, the KG schema has to be included in the LLM prompt to generate valid triplets; larger and more complex schemas easily exceed the LLMs' context window length. Furthermore, "},"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":"2404.03868","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:53:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b53662630a5dfbf1e5d0903bb4b40f324013a1eb8041cc6a0eaf49ef9afe7c90","abstract_canon_sha256":"e6e081e349f012f4467b796afaa66ec2b3e3192f47301180eca742433b6243c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:31.621400Z","signature_b64":"C0AgBUoJbRyiygKniKsUo6ja87KLHeaMbCC9MOXTnlsC1vmxgXHD0RWmY5k1Wu+ienCQb0o0oSzChlVUZqZLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c6b7bc0c2fa8d8e97c89315c0af83fbf96844ff6fec96fb1f51101c606ea8d5","last_reissued_at":"2026-07-05T09:14:31.620891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:31.620891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Zhang, Harold Soh","submitted_at":"2024-04-05T02:53:51Z","abstract_excerpt":"In this work, we are interested in automated methods for knowledge graph creation (KGC) from input text. Progress on large language models (LLMs) has prompted a series of recent works applying them to KGC, e.g., via zero/few-shot prompting. Despite successes on small domain-specific datasets, these models face difficulties scaling up to text common in many real-world applications. A principal issue is that, in prior methods, the KG schema has to be included in the LLM prompt to generate valid triplets; larger and more complex schemas easily exceed the LLMs' context window length. Furthermore, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03868","kind":"arxiv","version":2},"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/2404.03868/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":"2404.03868","created_at":"2026-07-05T09:14:31.620950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03868v2","created_at":"2026-07-05T09:14:31.620950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03868","created_at":"2026-07-05T09:14:31.620950+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRVXXQGC7KGY","created_at":"2026-07-05T09:14:31.620950+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRVXXQGC7KGY5F6I","created_at":"2026-07-05T09:14:31.620950+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRVXXQGC","created_at":"2026-07-05T09:14:31.620950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.21582","citing_title":"VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08694","citing_title":"A Learning Method for Symbolic Systems Using Large Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14930","citing_title":"IE as Cache: Information Extraction Enhanced Agentic Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":269,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P","json":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P.json","graph_json":"https://pith.science/api/pith-number/JRVXXQGC7KGY5F6ISMK4BL4D7P/graph.json","events_json":"https://pith.science/api/pith-number/JRVXXQGC7KGY5F6ISMK4BL4D7P/events.json","paper":"https://pith.science/paper/JRVXXQGC"},"agent_actions":{"view_html":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P","download_json":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P.json","view_paper":"https://pith.science/paper/JRVXXQGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03868&json=true","fetch_graph":"https://pith.science/api/pith-number/JRVXXQGC7KGY5F6ISMK4BL4D7P/graph.json","fetch_events":"https://pith.science/api/pith-number/JRVXXQGC7KGY5F6ISMK4BL4D7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/action/storage_attestation","attest_author":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/action/author_attestation","sign_citation":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/action/citation_signature","submit_replication":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/action/replication_record"}},"created_at":"2026-07-05T09:14:31.620950+00:00","updated_at":"2026-07-05T09:14:31.620950+00:00"}