{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LFFWRMJMR7PFDYSQAUXZPBIXIK","short_pith_number":"pith:LFFWRMJM","schema_version":"1.0","canonical_sha256":"594b68b12c8fde51e250052f97851742b5455758d64d8efa8acbe0672b7665ba","source":{"kind":"arxiv","id":"1909.03546","version":2},"attestation_state":"computed","paper":{"title":"Entity, Relation, and Event Extraction with Contextualized Span Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Wadden, Hannaneh Hajishirzi, Ulme Wennberg, Yi Luan","submitted_at":"2019-09-08T21:19:09Z","abstract_excerpt":"We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans designed to capture local (within-sentence) and global (cross-sentence) context. Our framework achieves state-of-the-art results across all tasks, on four datasets from a variety of domains. We perform experiments comparing different techniques to construct span representations. Contextualized embeddings like BERT perform w"},"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":"1909.03546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-08T21:19:09Z","cross_cats_sorted":[],"title_canon_sha256":"24482647fa6056a3994603366a556174e00ba30583fe65f5bbdfd8521a2d4f4e","abstract_canon_sha256":"bd9379d1c7a2f085d07362886acf5041bd2af876e3fc71683fbc1111ad39fcc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:18.116998Z","signature_b64":"+cg58P9ph0zbK9Ixxbj+QWHT1UvWLxffhW3ZbYyD/GcqYFa0uXHbbWnnFCwSEBm0lwc35CU2gmaGM1++0EhAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"594b68b12c8fde51e250052f97851742b5455758d64d8efa8acbe0672b7665ba","last_reissued_at":"2026-07-05T00:03:18.116536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:18.116536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity, Relation, and Event Extraction with Contextualized Span Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Wadden, Hannaneh Hajishirzi, Ulme Wennberg, Yi Luan","submitted_at":"2019-09-08T21:19:09Z","abstract_excerpt":"We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by enumerating, refining, and scoring text spans designed to capture local (within-sentence) and global (cross-sentence) context. Our framework achieves state-of-the-art results across all tasks, on four datasets from a variety of domains. We perform experiments comparing different techniques to construct span representations. Contextualized embeddings like BERT perform w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03546","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/1909.03546/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":"1909.03546","created_at":"2026-07-05T00:03:18.116593+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.03546v2","created_at":"2026-07-05T00:03:18.116593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03546","created_at":"2026-07-05T00:03:18.116593+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFFWRMJMR7PF","created_at":"2026-07-05T00:03:18.116593+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFFWRMJMR7PFDYSQ","created_at":"2026-07-05T00:03:18.116593+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFFWRMJM","created_at":"2026-07-05T00:03:18.116593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.14075","citing_title":"EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20650","citing_title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02271","citing_title":"Medical Report Generation: A Hierarchical Task Structure-Based Cross-Modal Causal Intervention Framework","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK","json":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK.json","graph_json":"https://pith.science/api/pith-number/LFFWRMJMR7PFDYSQAUXZPBIXIK/graph.json","events_json":"https://pith.science/api/pith-number/LFFWRMJMR7PFDYSQAUXZPBIXIK/events.json","paper":"https://pith.science/paper/LFFWRMJM"},"agent_actions":{"view_html":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK","download_json":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK.json","view_paper":"https://pith.science/paper/LFFWRMJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.03546&json=true","fetch_graph":"https://pith.science/api/pith-number/LFFWRMJMR7PFDYSQAUXZPBIXIK/graph.json","fetch_events":"https://pith.science/api/pith-number/LFFWRMJMR7PFDYSQAUXZPBIXIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK/action/storage_attestation","attest_author":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK/action/author_attestation","sign_citation":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK/action/citation_signature","submit_replication":"https://pith.science/pith/LFFWRMJMR7PFDYSQAUXZPBIXIK/action/replication_record"}},"created_at":"2026-07-05T00:03:18.116593+00:00","updated_at":"2026-07-05T00:03:18.116593+00:00"}