{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PZMWJBTYISI5T423YPPMUFJB4N","short_pith_number":"pith:PZMWJBTY","schema_version":"1.0","canonical_sha256":"7e596486784491d9f35bc3deca1521e3577b4ce555f576d7f7e74b65299c979e","source":{"kind":"arxiv","id":"1909.04948","version":2},"attestation_state":"computed","paper":{"title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Reisswig, Timo I. Denk","submitted_at":"2019-09-11T09:51:02Z","abstract_excerpt":"For understanding generic documents, information like font sizes, column layout, and generally the positioning of words may carry semantic information that is crucial for solving a downstream document intelligence task. Our novel BERTgrid, which is based on Chargrid by Katti et al. (2018), represents a document as a grid of contextualized word piece embedding vectors, thereby making its spatial structure and semantics accessible to the processing neural network. The contextualized embedding vectors are retrieved from a BERT language model. We use BERTgrid in combination with a fully convolutio"},"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":"1909.04948","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-11T09:51:02Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"13493d29c97364bdf12e36c166e192a43924e9694e02bd1bd88aae88f465d996","abstract_canon_sha256":"ff7a747b4c7f20c3ddc4caab38f6e4cbf2ff08aec5b620b075d0baee1752a316"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:36.363903Z","signature_b64":"jR01YnPeAa3aELjknPT4JobFF/wF/J5V41z0XDnFjZnYPICV9uk4VnDWPazD6vHTiAwoICH+kTWHThS4iWi9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e596486784491d9f35bc3deca1521e3577b4ce555f576d7f7e74b65299c979e","last_reissued_at":"2026-07-05T00:11:36.363455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:36.363455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Reisswig, Timo I. Denk","submitted_at":"2019-09-11T09:51:02Z","abstract_excerpt":"For understanding generic documents, information like font sizes, column layout, and generally the positioning of words may carry semantic information that is crucial for solving a downstream document intelligence task. Our novel BERTgrid, which is based on Chargrid by Katti et al. (2018), represents a document as a grid of contextualized word piece embedding vectors, thereby making its spatial structure and semantics accessible to the processing neural network. The contextualized embedding vectors are retrieved from a BERT language model. We use BERTgrid in combination with a fully convolutio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04948","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.04948/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":"1909.04948","created_at":"2026-07-05T00:11:36.363511+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.04948v2","created_at":"2026-07-05T00:11:36.363511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04948","created_at":"2026-07-05T00:11:36.363511+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZMWJBTYISI5","created_at":"2026-07-05T00:11:36.363511+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZMWJBTYISI5T423","created_at":"2026-07-05T00:11:36.363511+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZMWJBTY","created_at":"2026-07-05T00:11:36.363511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.21169","citing_title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09861","citing_title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N","json":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N.json","graph_json":"https://pith.science/api/pith-number/PZMWJBTYISI5T423YPPMUFJB4N/graph.json","events_json":"https://pith.science/api/pith-number/PZMWJBTYISI5T423YPPMUFJB4N/events.json","paper":"https://pith.science/paper/PZMWJBTY"},"agent_actions":{"view_html":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N","download_json":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N.json","view_paper":"https://pith.science/paper/PZMWJBTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.04948&json=true","fetch_graph":"https://pith.science/api/pith-number/PZMWJBTYISI5T423YPPMUFJB4N/graph.json","fetch_events":"https://pith.science/api/pith-number/PZMWJBTYISI5T423YPPMUFJB4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N/action/storage_attestation","attest_author":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N/action/author_attestation","sign_citation":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N/action/citation_signature","submit_replication":"https://pith.science/pith/PZMWJBTYISI5T423YPPMUFJB4N/action/replication_record"}},"created_at":"2026-07-05T00:11:36.363511+00:00","updated_at":"2026-07-05T00:11:36.363511+00:00"}