{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DXDXVOX66KX2XMKZJKT7M55MQT","short_pith_number":"pith:DXDXVOX6","schema_version":"1.0","canonical_sha256":"1dc77abafef2afabb1594aa7f677ac84eebb11219ae332fa633dfed741bc82b6","source":{"kind":"arxiv","id":"2203.12277","version":1},"attestation_state":"computed","paper":{"title":"Unified Structure Generation for Universal Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dai Dai, Hongyu Lin, Hua Wu, Le Sun, Qing Liu, Xianpei Han, Xinyan Xiao, Yaojie Lu","submitted_at":"2022-03-23T08:49:29Z","abstract_excerpt":"Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas. In this paper, we propose a unified text-to-structure generation framework, namely UIE, which can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources. Specifically, UIE uniformly encodes different extraction structures via a structured extraction language, adaptively generates target extractions via a schema-based prompt mechanism - structural schema instructor, and captures the"},"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":"2203.12277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-23T08:49:29Z","cross_cats_sorted":[],"title_canon_sha256":"6cfad0b2fae8f248a8eb17c19caf036cf2785ec9d46b1520d6b4d3384c17a6f8","abstract_canon_sha256":"13102f2ea920d698ba34e9a17cc27a1dd47fed535d08704144504c3c512608bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:57.732513Z","signature_b64":"96sMxc5oyfc+13T58s9S1KwfW4PWW44UwT7AB2WwBuICREQFceYgpXPhxUsTP9YjO5n+rf9rbq8ZJQuAoJBgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dc77abafef2afabb1594aa7f677ac84eebb11219ae332fa633dfed741bc82b6","last_reissued_at":"2026-07-05T04:07:57.732038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:57.732038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Structure Generation for Universal Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dai Dai, Hongyu Lin, Hua Wu, Le Sun, Qing Liu, Xianpei Han, Xinyan Xiao, Yaojie Lu","submitted_at":"2022-03-23T08:49:29Z","abstract_excerpt":"Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas. In this paper, we propose a unified text-to-structure generation framework, namely UIE, which can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources. Specifically, UIE uniformly encodes different extraction structures via a structured extraction language, adaptively generates target extractions via a schema-based prompt mechanism - structural schema instructor, and captures the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12277","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/2203.12277/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":"2203.12277","created_at":"2026-07-05T04:07:57.732094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.12277v1","created_at":"2026-07-05T04:07:57.732094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12277","created_at":"2026-07-05T04:07:57.732094+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXDXVOX66KX2","created_at":"2026-07-05T04:07:57.732094+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXDXVOX66KX2XMKZ","created_at":"2026-07-05T04:07:57.732094+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXDXVOX6","created_at":"2026-07-05T04:07:57.732094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21890","citing_title":"Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14075","citing_title":"EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT","json":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT.json","graph_json":"https://pith.science/api/pith-number/DXDXVOX66KX2XMKZJKT7M55MQT/graph.json","events_json":"https://pith.science/api/pith-number/DXDXVOX66KX2XMKZJKT7M55MQT/events.json","paper":"https://pith.science/paper/DXDXVOX6"},"agent_actions":{"view_html":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT","download_json":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT.json","view_paper":"https://pith.science/paper/DXDXVOX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.12277&json=true","fetch_graph":"https://pith.science/api/pith-number/DXDXVOX66KX2XMKZJKT7M55MQT/graph.json","fetch_events":"https://pith.science/api/pith-number/DXDXVOX66KX2XMKZJKT7M55MQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT/action/storage_attestation","attest_author":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT/action/author_attestation","sign_citation":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT/action/citation_signature","submit_replication":"https://pith.science/pith/DXDXVOX66KX2XMKZJKT7M55MQT/action/replication_record"}},"created_at":"2026-07-05T04:07:57.732094+00:00","updated_at":"2026-07-05T04:07:57.732094+00:00"}