{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YBFRNFR53RQNQSJYHJOZTFRWJ5","short_pith_number":"pith:YBFRNFR5","schema_version":"1.0","canonical_sha256":"c04b16963ddc60d849383a5d9996364f4cb93b23ba3a9a869e2b8b9cff758b59","source":{"kind":"arxiv","id":"2310.11085","version":4},"attestation_state":"computed","paper":{"title":"Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ce Zhang, Stefan Feuerriegel, Yilmazcan Ozyurt","submitted_at":"2023-10-17T09:10:27Z","abstract_excerpt":"Document-level relation extraction aims at inferring structured human knowledge from textual documents. State-of-the-art methods for this task use pre-trained language models (LMs) via fine-tuning, yet fine-tuning is computationally expensive and cannot adapt to new relation types or new LMs. As a remedy, we leverage the generalization capabilities of pre-trained LMs and present a novel framework for document-level in-context few-shot relation extraction. Our framework has three strengths: it eliminates the need (1) for named entity recognition and (2) for human annotations of documents, and ("},"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":"2310.11085","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T09:10:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c94c3493f2229daaecb8087872d571d3fe92429c22aed6211f6b9405b347b17b","abstract_canon_sha256":"d732906c4297b4af4b792fe895556ca7c23c33d1e8f3000ec5fce46e5cb02da0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:28.530772Z","signature_b64":"x6Nu1TNv/mnuyaP91rEJwcJkq9Op8TzYXcCbv95Wgwd7xwgP+plEu78ew+ieWeV8dnUi+G38sRmm5fTwjmh4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c04b16963ddc60d849383a5d9996364f4cb93b23ba3a9a869e2b8b9cff758b59","last_reissued_at":"2026-07-05T09:14:28.530236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:28.530236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ce Zhang, Stefan Feuerriegel, Yilmazcan Ozyurt","submitted_at":"2023-10-17T09:10:27Z","abstract_excerpt":"Document-level relation extraction aims at inferring structured human knowledge from textual documents. State-of-the-art methods for this task use pre-trained language models (LMs) via fine-tuning, yet fine-tuning is computationally expensive and cannot adapt to new relation types or new LMs. As a remedy, we leverage the generalization capabilities of pre-trained LMs and present a novel framework for document-level in-context few-shot relation extraction. Our framework has three strengths: it eliminates the need (1) for named entity recognition and (2) for human annotations of documents, and ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11085","kind":"arxiv","version":4},"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/2310.11085/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":"2310.11085","created_at":"2026-07-05T09:14:28.530286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11085v4","created_at":"2026-07-05T09:14:28.530286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11085","created_at":"2026-07-05T09:14:28.530286+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBFRNFR53RQN","created_at":"2026-07-05T09:14:28.530286+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBFRNFR53RQNQSJY","created_at":"2026-07-05T09:14:28.530286+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBFRNFR5","created_at":"2026-07-05T09:14:28.530286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11104","citing_title":"Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial Crowds","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5","json":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5.json","graph_json":"https://pith.science/api/pith-number/YBFRNFR53RQNQSJYHJOZTFRWJ5/graph.json","events_json":"https://pith.science/api/pith-number/YBFRNFR53RQNQSJYHJOZTFRWJ5/events.json","paper":"https://pith.science/paper/YBFRNFR5"},"agent_actions":{"view_html":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5","download_json":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5.json","view_paper":"https://pith.science/paper/YBFRNFR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11085&json=true","fetch_graph":"https://pith.science/api/pith-number/YBFRNFR53RQNQSJYHJOZTFRWJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/YBFRNFR53RQNQSJYHJOZTFRWJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5/action/storage_attestation","attest_author":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5/action/author_attestation","sign_citation":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5/action/citation_signature","submit_replication":"https://pith.science/pith/YBFRNFR53RQNQSJYHJOZTFRWJ5/action/replication_record"}},"created_at":"2026-07-05T09:14:28.530286+00:00","updated_at":"2026-07-05T09:14:28.530286+00:00"}