{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RZPBW4CTANSDH6SAUPR5QGSVE5","short_pith_number":"pith:RZPBW4CT","schema_version":"1.0","canonical_sha256":"8e5e1b7053036433fa40a3e3d81a552765cb9ac736239b5e3f4af30cd1738cea","source":{"kind":"arxiv","id":"1812.07248","version":3},"attestation_state":"computed","paper":{"title":"Attend, Copy, Parse -- End-to-end information extraction from documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Florian Laws, Ole Winther, Rasmus Berg Palm","submitted_at":"2018-12-18T09:05:53Z","abstract_excerpt":"Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs. This end-to-end data is naturally consumed and produced when performing the task because it is valuable in and of itself. It is naturally available, at no additional cost. Unfortunately, state-of-the-art word classification methods for information extraction cannot use this data, instead requiring word-level labels which are expensive to create and consequently not available for many real life tasks. In this paper we propose the Attend, Copy, Parse ar"},"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":"1812.07248","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-18T09:05:53Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"3d61395c9a4df4712124c66a0f647a0deef499f51d1b10457c7fbe1299ede7eb","abstract_canon_sha256":"16662dc273b05c936d1e03d465fa5e0571554a7eb298bbc56184df7515505e08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:19.542242Z","signature_b64":"zzWb5T4+/G3DKACxh4mVUxsGAc0pAQXTBtsz8t2LRnBvAGy926Vrfmjd1ZKj2B+ErKI7P60pvVkP2goolvfhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e5e1b7053036433fa40a3e3d81a552765cb9ac736239b5e3f4af30cd1738cea","last_reissued_at":"2026-07-05T02:34:19.541767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:19.541767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attend, Copy, Parse -- End-to-end information extraction from documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Florian Laws, Ole Winther, Rasmus Berg Palm","submitted_at":"2018-12-18T09:05:53Z","abstract_excerpt":"Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs. This end-to-end data is naturally consumed and produced when performing the task because it is valuable in and of itself. It is naturally available, at no additional cost. Unfortunately, state-of-the-art word classification methods for information extraction cannot use this data, instead requiring word-level labels which are expensive to create and consequently not available for many real life tasks. In this paper we propose the Attend, Copy, Parse ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07248","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/1812.07248/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":"1812.07248","created_at":"2026-07-05T02:34:19.541825+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07248v3","created_at":"2026-07-05T02:34:19.541825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07248","created_at":"2026-07-05T02:34:19.541825+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZPBW4CTANSD","created_at":"2026-07-05T02:34:19.541825+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZPBW4CTANSDH6SA","created_at":"2026-07-05T02:34:19.541825+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZPBW4CT","created_at":"2026-07-05T02:34:19.541825+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/RZPBW4CTANSDH6SAUPR5QGSVE5","json":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5.json","graph_json":"https://pith.science/api/pith-number/RZPBW4CTANSDH6SAUPR5QGSVE5/graph.json","events_json":"https://pith.science/api/pith-number/RZPBW4CTANSDH6SAUPR5QGSVE5/events.json","paper":"https://pith.science/paper/RZPBW4CT"},"agent_actions":{"view_html":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5","download_json":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5.json","view_paper":"https://pith.science/paper/RZPBW4CT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07248&json=true","fetch_graph":"https://pith.science/api/pith-number/RZPBW4CTANSDH6SAUPR5QGSVE5/graph.json","fetch_events":"https://pith.science/api/pith-number/RZPBW4CTANSDH6SAUPR5QGSVE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/action/storage_attestation","attest_author":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/action/author_attestation","sign_citation":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/action/citation_signature","submit_replication":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/action/replication_record"}},"created_at":"2026-07-05T02:34:19.541825+00:00","updated_at":"2026-07-05T02:34:19.541825+00:00"}