{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2H7HS5DCJFSSP7W57HWUB7OMRY","short_pith_number":"pith:2H7HS5DC","schema_version":"1.0","canonical_sha256":"d1fe797462496527feddf9ed40fdcc8e39947abd4015f77a84bc63072d68e32c","source":{"kind":"arxiv","id":"2105.11672","version":1},"attestation_state":"computed","paper":{"title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kai Hu, Lei Sun, Qiang Huo, Qifang Gao, Qin Ren, Weihong Lin, Zhuoyao Zhong","submitted_at":"2021-05-25T05:12:08Z","abstract_excerpt":"Recent grid-based document representations like BERTgrid allow the simultaneous encoding of the textual and layout information of a document in a 2D feature map so that state-of-the-art image segmentation and/or object detection models can be straightforwardly leveraged to extract key information from documents. However, such methods have not achieved comparable performance to state-of-the-art sequence- and graph-based methods such as LayoutLM and PICK yet. In this paper, we propose a new multi-modal backbone network by concatenating a BERTgrid to an intermediate layer of a CNN model, where th"},"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":"2105.11672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-25T05:12:08Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"4e059d96bd9ef0d8e9d310b4a8df8771cfd4e4d6e64bb8dc0cc1c7d833a545de","abstract_canon_sha256":"894982bb97ee85662e04c9690afe8c74033cad03f34efddb8d779f0419405e6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:55.236436Z","signature_b64":"FeYjaDwt9drpygdqXzzvQnxyLkusPEx+L1eZV23nY4BUmUjT11vHZ17iCV77VHRfQYMK5fvU3sGgq7z3NF62BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1fe797462496527feddf9ed40fdcc8e39947abd4015f77a84bc63072d68e32c","last_reissued_at":"2026-07-05T02:42:55.235943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:55.235943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kai Hu, Lei Sun, Qiang Huo, Qifang Gao, Qin Ren, Weihong Lin, Zhuoyao Zhong","submitted_at":"2021-05-25T05:12:08Z","abstract_excerpt":"Recent grid-based document representations like BERTgrid allow the simultaneous encoding of the textual and layout information of a document in a 2D feature map so that state-of-the-art image segmentation and/or object detection models can be straightforwardly leveraged to extract key information from documents. However, such methods have not achieved comparable performance to state-of-the-art sequence- and graph-based methods such as LayoutLM and PICK yet. In this paper, we propose a new multi-modal backbone network by concatenating a BERTgrid to an intermediate layer of a CNN model, where th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11672","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2105.11672/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":"2105.11672","created_at":"2026-07-05T02:42:55.236002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.11672v1","created_at":"2026-07-05T02:42:55.236002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11672","created_at":"2026-07-05T02:42:55.236002+00:00"},{"alias_kind":"pith_short_12","alias_value":"2H7HS5DCJFSS","created_at":"2026-07-05T02:42:55.236002+00:00"},{"alias_kind":"pith_short_16","alias_value":"2H7HS5DCJFSSP7W5","created_at":"2026-07-05T02:42:55.236002+00:00"},{"alias_kind":"pith_short_8","alias_value":"2H7HS5DC","created_at":"2026-07-05T02:42:55.236002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10155","citing_title":"WordVIS: A Color Worth A Thousand Words","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY","json":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY.json","graph_json":"https://pith.science/api/pith-number/2H7HS5DCJFSSP7W57HWUB7OMRY/graph.json","events_json":"https://pith.science/api/pith-number/2H7HS5DCJFSSP7W57HWUB7OMRY/events.json","paper":"https://pith.science/paper/2H7HS5DC"},"agent_actions":{"view_html":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY","download_json":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY.json","view_paper":"https://pith.science/paper/2H7HS5DC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.11672&json=true","fetch_graph":"https://pith.science/api/pith-number/2H7HS5DCJFSSP7W57HWUB7OMRY/graph.json","fetch_events":"https://pith.science/api/pith-number/2H7HS5DCJFSSP7W57HWUB7OMRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY/action/storage_attestation","attest_author":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY/action/author_attestation","sign_citation":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY/action/citation_signature","submit_replication":"https://pith.science/pith/2H7HS5DCJFSSP7W57HWUB7OMRY/action/replication_record"}},"created_at":"2026-07-05T02:42:55.236002+00:00","updated_at":"2026-07-05T02:42:55.236002+00:00"}