{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ENFNIGKZHIXF2WYOEU3WYZWQCR","short_pith_number":"pith:ENFNIGKZ","schema_version":"1.0","canonical_sha256":"234ad419593a2e5d5b0e25376c66d0147c7ac5b3d7b2903ef6eafbb45e51f67c","source":{"kind":"arxiv","id":"2106.03618","version":2},"attestation_state":"computed","paper":{"title":"Document-level Relation Extraction as Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chuanqi Tan, Fei Huang, Huajun Chen, Luo Si, Mosha Chen, Ningyu Zhang, Shumin Deng, Xiang Chen, Xin Xie","submitted_at":"2021-06-07T13:44:44Z","abstract_excerpt":"Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among relational triples. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information, parallel to the semantic segmentation task in computer vision. Herein, we propose a Document U-shaped Network for document-level relation extraction. Specifically, we leverage an encoder module to capture the context i"},"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":"2106.03618","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T13:44:44Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG"],"title_canon_sha256":"d6a457b2263cf024e1e9ca7159d591bcef17cc609f5c74a05bad115633998761","abstract_canon_sha256":"aa5ae1e7e518a18d215c2bc2f1123afbcaeed5e99bfbbf7a775921533e639785"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:00.550728Z","signature_b64":"Hw08Im161nSvMpsVHqmoc2hEImvzQmG0v39FAMcVlylkMoAXXrHPs8YxrxvC9kZPnIloqL/vC5QcolxRzufRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"234ad419593a2e5d5b0e25376c66d0147c7ac5b3d7b2903ef6eafbb45e51f67c","last_reissued_at":"2026-07-05T05:36:00.550207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:00.550207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document-level Relation Extraction as Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chuanqi Tan, Fei Huang, Huajun Chen, Luo Si, Mosha Chen, Ningyu Zhang, Shumin Deng, Xiang Chen, Xin Xie","submitted_at":"2021-06-07T13:44:44Z","abstract_excerpt":"Document-level relation extraction aims to extract relations among multiple entity pairs from a document. Previously proposed graph-based or transformer-based models utilize the entities independently, regardless of global information among relational triples. This paper approaches the problem by predicting an entity-level relation matrix to capture local and global information, parallel to the semantic segmentation task in computer vision. Herein, we propose a Document U-shaped Network for document-level relation extraction. Specifically, we leverage an encoder module to capture the context i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03618","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/2106.03618/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":"2106.03618","created_at":"2026-07-05T05:36:00.550270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03618v2","created_at":"2026-07-05T05:36:00.550270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03618","created_at":"2026-07-05T05:36:00.550270+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENFNIGKZHIXF","created_at":"2026-07-05T05:36:00.550270+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENFNIGKZHIXF2WYO","created_at":"2026-07-05T05:36:00.550270+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENFNIGKZ","created_at":"2026-07-05T05:36:00.550270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22926","citing_title":"Multi-Relation Extraction in Entity Pairs using Global Context","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR","json":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR.json","graph_json":"https://pith.science/api/pith-number/ENFNIGKZHIXF2WYOEU3WYZWQCR/graph.json","events_json":"https://pith.science/api/pith-number/ENFNIGKZHIXF2WYOEU3WYZWQCR/events.json","paper":"https://pith.science/paper/ENFNIGKZ"},"agent_actions":{"view_html":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR","download_json":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR.json","view_paper":"https://pith.science/paper/ENFNIGKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03618&json=true","fetch_graph":"https://pith.science/api/pith-number/ENFNIGKZHIXF2WYOEU3WYZWQCR/graph.json","fetch_events":"https://pith.science/api/pith-number/ENFNIGKZHIXF2WYOEU3WYZWQCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR/action/storage_attestation","attest_author":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR/action/author_attestation","sign_citation":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR/action/citation_signature","submit_replication":"https://pith.science/pith/ENFNIGKZHIXF2WYOEU3WYZWQCR/action/replication_record"}},"created_at":"2026-07-05T05:36:00.550270+00:00","updated_at":"2026-07-05T05:36:00.550270+00:00"}