{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RZPBW4CTANSDH6SAUPR5QGSVE5","short_pith_number":"pith:RZPBW4CT","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"},"canonical_sha256":"8e5e1b7053036433fa40a3e3d81a552765cb9ac736239b5e3f4af30cd1738cea","source":{"kind":"arxiv","id":"1812.07248","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07248","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07248v3","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07248","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"RZPBW4CTANSD","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"RZPBW4CTANSDH6SA","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"RZPBW4CT","created_at":"2026-07-05T02:34:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RZPBW4CTANSDH6SAUPR5QGSVE5","target":"record","payload":{"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"},"canonical_sha256":"8e5e1b7053036433fa40a3e3d81a552765cb9ac736239b5e3f4af30cd1738cea","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"},"source_kind":"arxiv","source_id":"1812.07248","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrItfMMl/P2ELIgUIIKb7vlvbBOIXDnnBl/Ao6+HwgEVIilwJqJmo3hukugxLEocSjbjhL7jQ/4PaFdXHwB1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:54:08.260483Z"},"content_sha256":"92e6604efcff640668c26ac74097153c698983ac556a83266823705da0b71fcb","schema_version":"1.0","event_id":"sha256:92e6604efcff640668c26ac74097153c698983ac556a83266823705da0b71fcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RZPBW4CTANSDH6SAUPR5QGSVE5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IdIyQRqrYwI+h8FssDoz37NC++H/uQMHbwPoV8et/4eKHp2m6fFZkWq316GXN1ma2JsD6XjOYx0o4804AzKSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:54:08.260869Z"},"content_sha256":"88496328c7c6f3aa6a3e8179523b175bfab8e8f505a87adb5a69940689a1487c","schema_version":"1.0","event_id":"sha256:88496328c7c6f3aa6a3e8179523b175bfab8e8f505a87adb5a69940689a1487c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/bundle.json","state_url":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-24T23:54:08Z","links":{"resolver":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5","bundle":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/bundle.json","state":"https://pith.science/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZPBW4CTANSDH6SAUPR5QGSVE5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RZPBW4CTANSDH6SAUPR5QGSVE5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"16662dc273b05c936d1e03d465fa5e0571554a7eb298bbc56184df7515505e08","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-18T09:05:53Z","title_canon_sha256":"3d61395c9a4df4712124c66a0f647a0deef499f51d1b10457c7fbe1299ede7eb"},"schema_version":"1.0","source":{"id":"1812.07248","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07248","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07248v3","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07248","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"RZPBW4CTANSD","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"RZPBW4CTANSDH6SA","created_at":"2026-07-05T02:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"RZPBW4CT","created_at":"2026-07-05T02:34:19Z"}],"graph_snapshots":[{"event_id":"sha256:88496328c7c6f3aa6a3e8179523b175bfab8e8f505a87adb5a69940689a1487c","target":"graph","created_at":"2026-07-05T02:34:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1812.07248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Florian Laws, Ole Winther, Rasmus Berg Palm","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-18T09:05:53Z","title":"Attend, Copy, Parse -- End-to-end information extraction from documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07248","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:92e6604efcff640668c26ac74097153c698983ac556a83266823705da0b71fcb","target":"record","created_at":"2026-07-05T02:34:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"16662dc273b05c936d1e03d465fa5e0571554a7eb298bbc56184df7515505e08","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-18T09:05:53Z","title_canon_sha256":"3d61395c9a4df4712124c66a0f647a0deef499f51d1b10457c7fbe1299ede7eb"},"schema_version":"1.0","source":{"id":"1812.07248","kind":"arxiv","version":3}},"canonical_sha256":"8e5e1b7053036433fa40a3e3d81a552765cb9ac736239b5e3f4af30cd1738cea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e5e1b7053036433fa40a3e3d81a552765cb9ac736239b5e3f4af30cd1738cea","first_computed_at":"2026-07-05T02:34:19.541767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:34:19.541767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zzWb5T4+/G3DKACxh4mVUxsGAc0pAQXTBtsz8t2LRnBvAGy926Vrfmjd1ZKj2B+ErKI7P60pvVkP2goolvfhDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:34:19.542242Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.07248","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92e6604efcff640668c26ac74097153c698983ac556a83266823705da0b71fcb","sha256:88496328c7c6f3aa6a3e8179523b175bfab8e8f505a87adb5a69940689a1487c"],"state_sha256":"8ee0975999ebb04cc1682cf1f39cc316412ff37a439522cb1b13878ca303c6e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXlyK6BcFQQcBSwrJLD6CO+lib8swUDPx+f+hSp80M5AZnYHNtJZGI0ccPFt+5OO0PyHi58frqMGGSiWCbZ1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T23:54:08.263539Z","bundle_sha256":"e333ac7632bdc4e3d8013b02c8a393563b052cbe6e6a1c86f5c92857f0b9041a"}}