{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G7XIAONSIARYZMTODLJ74OLHIF","short_pith_number":"pith:G7XIAONS","schema_version":"1.0","canonical_sha256":"37ee8039b240238cb26e1ad3fe3967417c0882ebd176c7fd976acf19f91ce9f8","source":{"kind":"arxiv","id":"2112.08340","version":3},"attestation_state":"computed","paper":{"title":"GenIE: Generative Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Fabio Petroni, Martin Josifoski, Maxime Peyrard, Nicola De Cao, Robert West","submitted_at":"2021-12-15T18:45:14Z","abstract_excerpt":"Structured and grounded representation of text is typically formalized by closed information extraction, the problem of extracting an exhaustive set of (subject, relation, object) triplets that are consistent with a predefined set of entities and relations from a knowledge base schema. Most existing works are pipelines prone to error accumulation, and all approaches are only applicable to unrealistically small numbers of entities and relations. We introduce GenIE (generative information extraction), the first end-to-end autoregressive formulation of closed information extraction. GenIE natural"},"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":"2112.08340","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-15T18:45:14Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0727dbbe53fc090f1863aeef6286e6d1983319904bb8de8f134d76312f9e57a3","abstract_canon_sha256":"b72a83c3bcb4e2983f8d1ad3991d78ca6f80d71dea6d1ac90809844a9257826d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:26.908439Z","signature_b64":"2QkH/x0wIyzGIJVMaUYK0ERq9+7flLyC3nJCgH/yIqNWteEZpUlSBq2FA8DTBSil/siG0QIkTrCL8CMJVUR/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37ee8039b240238cb26e1ad3fe3967417c0882ebd176c7fd976acf19f91ce9f8","last_reissued_at":"2026-07-05T04:14:26.907922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:26.907922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenIE: Generative Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Fabio Petroni, Martin Josifoski, Maxime Peyrard, Nicola De Cao, Robert West","submitted_at":"2021-12-15T18:45:14Z","abstract_excerpt":"Structured and grounded representation of text is typically formalized by closed information extraction, the problem of extracting an exhaustive set of (subject, relation, object) triplets that are consistent with a predefined set of entities and relations from a knowledge base schema. Most existing works are pipelines prone to error accumulation, and all approaches are only applicable to unrealistically small numbers of entities and relations. We introduce GenIE (generative information extraction), the first end-to-end autoregressive formulation of closed information extraction. GenIE natural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08340","kind":"arxiv","version":3},"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/2112.08340/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":"2112.08340","created_at":"2026-07-05T04:14:26.907979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08340v3","created_at":"2026-07-05T04:14:26.907979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08340","created_at":"2026-07-05T04:14:26.907979+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7XIAONSIARY","created_at":"2026-07-05T04:14:26.907979+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7XIAONSIARYZMTO","created_at":"2026-07-05T04:14:26.907979+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7XIAONS","created_at":"2026-07-05T04:14:26.907979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16794","citing_title":"Algorithm for Automatic Legislative Text Consolidation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF","json":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF.json","graph_json":"https://pith.science/api/pith-number/G7XIAONSIARYZMTODLJ74OLHIF/graph.json","events_json":"https://pith.science/api/pith-number/G7XIAONSIARYZMTODLJ74OLHIF/events.json","paper":"https://pith.science/paper/G7XIAONS"},"agent_actions":{"view_html":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF","download_json":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF.json","view_paper":"https://pith.science/paper/G7XIAONS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08340&json=true","fetch_graph":"https://pith.science/api/pith-number/G7XIAONSIARYZMTODLJ74OLHIF/graph.json","fetch_events":"https://pith.science/api/pith-number/G7XIAONSIARYZMTODLJ74OLHIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF/action/storage_attestation","attest_author":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF/action/author_attestation","sign_citation":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF/action/citation_signature","submit_replication":"https://pith.science/pith/G7XIAONSIARYZMTODLJ74OLHIF/action/replication_record"}},"created_at":"2026-07-05T04:14:26.907979+00:00","updated_at":"2026-07-05T04:14:26.907979+00:00"}