{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QWCSD2YKVISJOGFS44EHN4ZJ7T","short_pith_number":"pith:QWCSD2YK","schema_version":"1.0","canonical_sha256":"858521eb0aaa249718b2e70876f329fce7bee653d8d96ebf6563a1010483f973","source":{"kind":"arxiv","id":"2401.13598","version":1},"attestation_state":"computed","paper":{"title":"Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kun Huang, Kun Zhang, Qi Sun, Rong Tong, Soujanya Poria, Xiaocui Yang","submitted_at":"2024-01-24T17:04:28Z","abstract_excerpt":"Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of fully labeled data. However, collecting and annotating data for newly emerging relations is time-consuming and labor-intensive. Recent advanced Large Language Models (LLMs), such as ChatGPT and LLaMA, exhibit impressive long-text generation capabilities, inspiring us to explore an alternative approach for obtaining auto-labeled documents with new relations. "},"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":"2401.13598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T17:04:28Z","cross_cats_sorted":[],"title_canon_sha256":"b44923e33fc65dbf1b22855a51b7cda133c49947afb805a1d6d558ae17c4e1a9","abstract_canon_sha256":"a7be835889b58c96106716a66d15819d5f720a6487726638cc2d9c247efd8d46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:07.808120Z","signature_b64":"l42sAvudaefZ/PJO2QoMp9DSwptmSrgb4gn3Kt+g2M+HqqlmPBCjRpPrYgKpx5a6Q2ott3eVAMpX+g9Ln+t9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"858521eb0aaa249718b2e70876f329fce7bee653d8d96ebf6563a1010483f973","last_reissued_at":"2026-07-05T07:37:07.807628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:07.807628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kun Huang, Kun Zhang, Qi Sun, Rong Tong, Soujanya Poria, Xiaocui Yang","submitted_at":"2024-01-24T17:04:28Z","abstract_excerpt":"Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of fully labeled data. However, collecting and annotating data for newly emerging relations is time-consuming and labor-intensive. Recent advanced Large Language Models (LLMs), such as ChatGPT and LLaMA, exhibit impressive long-text generation capabilities, inspiring us to explore an alternative approach for obtaining auto-labeled documents with new relations. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13598","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/2401.13598/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":"2401.13598","created_at":"2026-07-05T07:37:07.807690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13598v1","created_at":"2026-07-05T07:37:07.807690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13598","created_at":"2026-07-05T07:37:07.807690+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWCSD2YKVISJ","created_at":"2026-07-05T07:37:07.807690+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWCSD2YKVISJOGFS","created_at":"2026-07-05T07:37:07.807690+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWCSD2YK","created_at":"2026-07-05T07:37:07.807690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10108","citing_title":"GLiNER-Relex: A Unified Framework for Joint Named Entity Recognition and Relation Extraction","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T","json":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T.json","graph_json":"https://pith.science/api/pith-number/QWCSD2YKVISJOGFS44EHN4ZJ7T/graph.json","events_json":"https://pith.science/api/pith-number/QWCSD2YKVISJOGFS44EHN4ZJ7T/events.json","paper":"https://pith.science/paper/QWCSD2YK"},"agent_actions":{"view_html":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T","download_json":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T.json","view_paper":"https://pith.science/paper/QWCSD2YK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13598&json=true","fetch_graph":"https://pith.science/api/pith-number/QWCSD2YKVISJOGFS44EHN4ZJ7T/graph.json","fetch_events":"https://pith.science/api/pith-number/QWCSD2YKVISJOGFS44EHN4ZJ7T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T/action/storage_attestation","attest_author":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T/action/author_attestation","sign_citation":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T/action/citation_signature","submit_replication":"https://pith.science/pith/QWCSD2YKVISJOGFS44EHN4ZJ7T/action/replication_record"}},"created_at":"2026-07-05T07:37:07.807690+00:00","updated_at":"2026-07-05T07:37:07.807690+00:00"}