{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NN5TRK5MIXZUJB5W3TNFKFB2XI","short_pith_number":"pith:NN5TRK5M","schema_version":"1.0","canonical_sha256":"6b7b38abac45f34487b6dcda55143aba39e42b0bda4749e07724217bae95de50","source":{"kind":"arxiv","id":"2103.08200","version":1},"attestation_state":"computed","paper":{"title":"Mention-centered Graph Neural Network for Document-level Relation Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaxin Pan, Min Peng, Yiyan Zhang","submitted_at":"2021-03-15T08:19:44Z","abstract_excerpt":"Document-level relation extraction aims to discover relations between entities across a whole document. How to build the dependency of entities from different sentences in a document remains to be a great challenge. Current approaches either leverage syntactic trees to construct document-level graphs or aggregate inference information from different sentences. In this paper, we build cross-sentence dependencies by inferring compositional relations between inter-sentence mentions. Adopting aggressive linking strategy, intermediate relations are reasoned on the document-level graphs by mention c"},"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":"2103.08200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-15T08:19:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94e1e3dbd94bed1667c9040ea189653848f5a8157d3159b7fb083d3dca1a45d0","abstract_canon_sha256":"4d988f00a140db35fcd3a663b078895580be2c2cb8fff5dce9f8ae1915c4dae6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:48.915250Z","signature_b64":"alF1uCuGDiUnO6DdkyUb4ordWBktF3ibdRJIZMtAKnMg1TEjzwwS2DA5HxWPEbSCFQ8+5U3eEoBrk4iyorD8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b7b38abac45f34487b6dcda55143aba39e42b0bda4749e07724217bae95de50","last_reissued_at":"2026-07-05T02:22:48.914810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:48.914810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mention-centered Graph Neural Network for Document-level Relation Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiaxin Pan, Min Peng, Yiyan Zhang","submitted_at":"2021-03-15T08:19:44Z","abstract_excerpt":"Document-level relation extraction aims to discover relations between entities across a whole document. How to build the dependency of entities from different sentences in a document remains to be a great challenge. Current approaches either leverage syntactic trees to construct document-level graphs or aggregate inference information from different sentences. In this paper, we build cross-sentence dependencies by inferring compositional relations between inter-sentence mentions. Adopting aggressive linking strategy, intermediate relations are reasoned on the document-level graphs by mention c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08200","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/2103.08200/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":"2103.08200","created_at":"2026-07-05T02:22:48.914869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.08200v1","created_at":"2026-07-05T02:22:48.914869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08200","created_at":"2026-07-05T02:22:48.914869+00:00"},{"alias_kind":"pith_short_12","alias_value":"NN5TRK5MIXZU","created_at":"2026-07-05T02:22:48.914869+00:00"},{"alias_kind":"pith_short_16","alias_value":"NN5TRK5MIXZUJB5W","created_at":"2026-07-05T02:22:48.914869+00:00"},{"alias_kind":"pith_short_8","alias_value":"NN5TRK5M","created_at":"2026-07-05T02:22:48.914869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI","json":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI.json","graph_json":"https://pith.science/api/pith-number/NN5TRK5MIXZUJB5W3TNFKFB2XI/graph.json","events_json":"https://pith.science/api/pith-number/NN5TRK5MIXZUJB5W3TNFKFB2XI/events.json","paper":"https://pith.science/paper/NN5TRK5M"},"agent_actions":{"view_html":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI","download_json":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI.json","view_paper":"https://pith.science/paper/NN5TRK5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.08200&json=true","fetch_graph":"https://pith.science/api/pith-number/NN5TRK5MIXZUJB5W3TNFKFB2XI/graph.json","fetch_events":"https://pith.science/api/pith-number/NN5TRK5MIXZUJB5W3TNFKFB2XI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI/action/storage_attestation","attest_author":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI/action/author_attestation","sign_citation":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI/action/citation_signature","submit_replication":"https://pith.science/pith/NN5TRK5MIXZUJB5W3TNFKFB2XI/action/replication_record"}},"created_at":"2026-07-05T02:22:48.914869+00:00","updated_at":"2026-07-05T02:22:48.914869+00:00"}