{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2H7HS5DCJFSSP7W57HWUB7OMRY","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":"894982bb97ee85662e04c9690afe8c74033cad03f34efddb8d779f0419405e6c","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-25T05:12:08Z","title_canon_sha256":"4e059d96bd9ef0d8e9d310b4a8df8771cfd4e4d6e64bb8dc0cc1c7d833a545de"},"schema_version":"1.0","source":{"id":"2105.11672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11672","created_at":"2026-07-05T02:42:55Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11672v1","created_at":"2026-07-05T02:42:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11672","created_at":"2026-07-05T02:42:55Z"},{"alias_kind":"pith_short_12","alias_value":"2H7HS5DCJFSS","created_at":"2026-07-05T02:42:55Z"},{"alias_kind":"pith_short_16","alias_value":"2H7HS5DCJFSSP7W5","created_at":"2026-07-05T02:42:55Z"},{"alias_kind":"pith_short_8","alias_value":"2H7HS5DC","created_at":"2026-07-05T02:42:55Z"}],"graph_snapshots":[{"event_id":"sha256:a00cc058c467bb2008ca1b84464b075bdd6cd4e5fb71c8b2c9903f9a98789099","target":"graph","created_at":"2026-07-05T02:42:55Z","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/2105.11672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kai Hu, Lei Sun, Qiang Huo, Qifang Gao, Qin Ren, Weihong Lin, Zhuoyao Zhong","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-25T05:12:08Z","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11672","kind":"arxiv","version":1},"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:e43cb9e886917479c2777c4b807ff098755d557718d5968fee80978f49fb00ba","target":"record","created_at":"2026-07-05T02:42:55Z","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":"894982bb97ee85662e04c9690afe8c74033cad03f34efddb8d779f0419405e6c","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-25T05:12:08Z","title_canon_sha256":"4e059d96bd9ef0d8e9d310b4a8df8771cfd4e4d6e64bb8dc0cc1c7d833a545de"},"schema_version":"1.0","source":{"id":"2105.11672","kind":"arxiv","version":1}},"canonical_sha256":"d1fe797462496527feddf9ed40fdcc8e39947abd4015f77a84bc63072d68e32c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1fe797462496527feddf9ed40fdcc8e39947abd4015f77a84bc63072d68e32c","first_computed_at":"2026-07-05T02:42:55.235943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:55.235943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FeYjaDwt9drpygdqXzzvQnxyLkusPEx+L1eZV23nY4BUmUjT11vHZ17iCV77VHRfQYMK5fvU3sGgq7z3NF62BA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:55.236436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e43cb9e886917479c2777c4b807ff098755d557718d5968fee80978f49fb00ba","sha256:a00cc058c467bb2008ca1b84464b075bdd6cd4e5fb71c8b2c9903f9a98789099"],"state_sha256":"e5f6f27baf0bbefb200aad5188aa0017a32cc772c47b490bb624132d24edd9de"}