{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OXA4RE67AKQWBGVRLFWT55EZJR","short_pith_number":"pith:OXA4RE67","schema_version":"1.0","canonical_sha256":"75c1c893df02a1609ab1596d3ef4994c48076493060100958551d9a4fa09e854","source":{"kind":"arxiv","id":"1809.08799","version":1},"attestation_state":"computed","paper":{"title":"Chargrid: Towards Understanding 2D Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Anoop Raveendra Katti, Christian Reisswig, Cordula Guder, Jean Baptiste Faddoul, Johannes H\\\"ohne, Sebastian Brarda, Steffen Bickel","submitted_at":"2018-09-24T08:37:02Z","abstract_excerpt":"We introduce a novel type of text representation that preserves the 2D layout of a document. This is achieved by encoding each document page as a two-dimensional grid of characters. Based on this representation, we present a generic document understanding pipeline for structured documents. This pipeline makes use of a fully convolutional encoder-decoder network that predicts a segmentation mask and bounding boxes. We demonstrate its capabilities on an information extraction task from invoices and show that it significantly outperforms approaches based on sequential text or document images."},"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":"1809.08799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-24T08:37:02Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"2eb9ab0a2d381b23cb902c64153d68a5a8a085732e752d759f903adad9266a53","abstract_canon_sha256":"c44e36da5fac76142e1cdcb3a8b315517a51999ce6c9f071795efe6df02078c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:03.531239Z","signature_b64":"5qYHGWidDa2KHpkOenESP5aYUwPucsbNZLI/76uw3hTSWZJBidBaec6OyIdbucFpWGj/siV3cK2XklFP7T0uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75c1c893df02a1609ab1596d3ef4994c48076493060100958551d9a4fa09e854","last_reissued_at":"2026-05-18T00:05:03.530670Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:03.530670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chargrid: Towards Understanding 2D Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Anoop Raveendra Katti, Christian Reisswig, Cordula Guder, Jean Baptiste Faddoul, Johannes H\\\"ohne, Sebastian Brarda, Steffen Bickel","submitted_at":"2018-09-24T08:37:02Z","abstract_excerpt":"We introduce a novel type of text representation that preserves the 2D layout of a document. This is achieved by encoding each document page as a two-dimensional grid of characters. Based on this representation, we present a generic document understanding pipeline for structured documents. This pipeline makes use of a fully convolutional encoder-decoder network that predicts a segmentation mask and bounding boxes. We demonstrate its capabilities on an information extraction task from invoices and show that it significantly outperforms approaches based on sequential text or document images."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08799","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":""},"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":"1809.08799","created_at":"2026-05-18T00:05:03.530770+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.08799v1","created_at":"2026-05-18T00:05:03.530770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08799","created_at":"2026-05-18T00:05:03.530770+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXA4RE67AKQW","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXA4RE67AKQWBGVR","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXA4RE67","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2410.21169","citing_title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2602.01785","citing_title":"CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR","json":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR.json","graph_json":"https://pith.science/api/pith-number/OXA4RE67AKQWBGVRLFWT55EZJR/graph.json","events_json":"https://pith.science/api/pith-number/OXA4RE67AKQWBGVRLFWT55EZJR/events.json","paper":"https://pith.science/paper/OXA4RE67"},"agent_actions":{"view_html":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR","download_json":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR.json","view_paper":"https://pith.science/paper/OXA4RE67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.08799&json=true","fetch_graph":"https://pith.science/api/pith-number/OXA4RE67AKQWBGVRLFWT55EZJR/graph.json","fetch_events":"https://pith.science/api/pith-number/OXA4RE67AKQWBGVRLFWT55EZJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR/action/storage_attestation","attest_author":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR/action/author_attestation","sign_citation":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR/action/citation_signature","submit_replication":"https://pith.science/pith/OXA4RE67AKQWBGVRLFWT55EZJR/action/replication_record"}},"created_at":"2026-05-18T00:05:03.530770+00:00","updated_at":"2026-05-18T00:05:03.530770+00:00"}