{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5WDMNXJWY5FY2GER5M4EOUY5DK","short_pith_number":"pith:5WDMNXJW","schema_version":"1.0","canonical_sha256":"ed86c6dd36c74b8d1891eb3847531d1abcb2d0d6d0e65731c074b3b4c1dcc2ee","source":{"kind":"arxiv","id":"1812.04377","version":2},"attestation_state":"computed","paper":{"title":"Deep Reader: Information extraction from Document images via relation extraction and Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Arindam Chowdhury, Ashwin Srinivasan, Gautam Shroff, Gunjan Sehgal, Lovekesh Vig, Monika Sharma, Rohit Rahul, Swati, Vishwanath D","submitted_at":"2018-12-11T13:09:13Z","abstract_excerpt":"Recent advancements in the area of Computer Vision with state-of-art Neural Networks has given a boost to Optical Character Recognition (OCR) accuracies. However, extracting characters/text alone is often insufficient for relevant information extraction as documents also have a visual structure that is not captured by OCR. Extracting information from tables, charts, footnotes, boxes, headings and retrieving the corresponding structured representation for the document remains a challenge and finds application in a large number of real-world use cases. In this paper, we propose a novel enterpris"},"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":"1812.04377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-11T13:09:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a2aa2f1039fb2e6b58dcdcb8edc5363ff4ca9380e9db6276aaae2380004199eb","abstract_canon_sha256":"db13346fc28200d84b44e2d38ac34c04a885eb735ae4793e74b0f7671b983544"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:18.687488Z","signature_b64":"SVBrnnhigLkbnFJqPaqnphazGIqjSLlDFICo/HffQ4FOPqZ3TAnbCGEUK+ly+zw8HT+fGIN6dsXgbkojTUvTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed86c6dd36c74b8d1891eb3847531d1abcb2d0d6d0e65731c074b3b4c1dcc2ee","last_reissued_at":"2026-05-17T23:58:18.686971Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:18.686971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reader: Information extraction from Document images via relation extraction and Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Arindam Chowdhury, Ashwin Srinivasan, Gautam Shroff, Gunjan Sehgal, Lovekesh Vig, Monika Sharma, Rohit Rahul, Swati, Vishwanath D","submitted_at":"2018-12-11T13:09:13Z","abstract_excerpt":"Recent advancements in the area of Computer Vision with state-of-art Neural Networks has given a boost to Optical Character Recognition (OCR) accuracies. However, extracting characters/text alone is often insufficient for relevant information extraction as documents also have a visual structure that is not captured by OCR. Extracting information from tables, charts, footnotes, boxes, headings and retrieving the corresponding structured representation for the document remains a challenge and finds application in a large number of real-world use cases. In this paper, we propose a novel enterpris"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04377","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":""},"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":"1812.04377","created_at":"2026-05-17T23:58:18.687047+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.04377v2","created_at":"2026-05-17T23:58:18.687047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04377","created_at":"2026-05-17T23:58:18.687047+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WDMNXJWY5FY","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WDMNXJWY5FY2GER","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WDMNXJW","created_at":"2026-05-18T12:32:08.215937+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/5WDMNXJWY5FY2GER5M4EOUY5DK","json":"https://pith.science/pith/5WDMNXJWY5FY2GER5M4EOUY5DK.json","graph_json":"https://pith.science/api/pith-number/5WDMNXJWY5FY2GER5M4EOUY5DK/graph.json","events_json":"https://pith.science/api/pith-number/5WDMNXJWY5FY2GER5M4EOUY5DK/events.json","paper":"https://pith.science/paper/5WDMNXJW"},"agent_actions":{"view_html":"https://pith.science/pith/5WDMNXJWY5FY2GER5M4EOUY5DK","download_json":"https://pith.science/pith/5WDMNXJWY5FY2GER5M4EOUY5DK.json","view_paper":"https://pith.science/paper/5WDMNXJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.04377&json=true","fetch_graph":"https://pith.science/api/pith-number/5WDMNXJWY5FY2GER5M4EOUY5DK/graph.json","fetch_events":"https://pith.science/api/pith-number/5WDMNXJWY5FY2GER5M4EOUY5DK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WDMNXJWY5FY2GER5M4EOUY5DK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WDMNXJWY5FY2GER5M4EOUY5DK/action/storage_attestation","attest_author":"https://pith.science/pith/5WDMNXJWY5FY2GER5M4EOUY5DK/action/author_attestation","sign_citation":"https://pith.science/pith/5WDMNXJWY5FY2GER5M4EOUY5DK/action/citation_signature","submit_replication":"https://pith.science/pith/5WDMNXJWY5FY2GER5M4EOUY5DK/action/replication_record"}},"created_at":"2026-05-17T23:58:18.687047+00:00","updated_at":"2026-05-17T23:58:18.687047+00:00"}