{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SQBYDZQATSO6235VGNIFPQNP2Q","short_pith_number":"pith:SQBYDZQA","schema_version":"1.0","canonical_sha256":"940381e6009c9ded6fb5335057c1afd40826dafa1c35ed9bf0e96187013ec413","source":{"kind":"arxiv","id":"2103.14470","version":1},"attestation_state":"computed","paper":{"title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhao Lin, Hongbin Sun, Wayne Zhang, Xiaoyu Yue, Zhanghui Kuang","submitted_at":"2021-03-26T13:46:00Z","abstract_excerpt":"Key information extraction from document images is of paramount importance in office automation. Conventional template matching based approaches fail to generalize well to document images of unseen templates, and are not robust against text recognition errors. In this paper, we propose an end-to-end Spatial Dual-Modality Graph Reasoning method (SDMG-R) to extract key information from unstructured document images. We model document images as dual-modality graphs, nodes of which encode both the visual and textual features of detected text regions, and edges of which represent the spatial relatio"},"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":"2103.14470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-26T13:46:00Z","cross_cats_sorted":[],"title_canon_sha256":"52fd1d520e5ed8011a40a62b35215a0f140d4c81f8911c3c4e0db1be66abb194","abstract_canon_sha256":"3315b3092ac08fb423f376e518acb8db121aef9771ec1e542423fd4fabce131e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:41.304208Z","signature_b64":"QASlZBYirEbZzphtE5tXVJ+bym7UvvZof9YxUZfb3jMccTNmsyFb+WLdOtJgiEP3I3RW+Dj2oWoNz6fDz7F0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"940381e6009c9ded6fb5335057c1afd40826dafa1c35ed9bf0e96187013ec413","last_reissued_at":"2026-07-05T02:26:41.303847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:41.303847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial Dual-Modality Graph Reasoning for Key Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenhao Lin, Hongbin Sun, Wayne Zhang, Xiaoyu Yue, Zhanghui Kuang","submitted_at":"2021-03-26T13:46:00Z","abstract_excerpt":"Key information extraction from document images is of paramount importance in office automation. Conventional template matching based approaches fail to generalize well to document images of unseen templates, and are not robust against text recognition errors. In this paper, we propose an end-to-end Spatial Dual-Modality Graph Reasoning method (SDMG-R) to extract key information from unstructured document images. We model document images as dual-modality graphs, nodes of which encode both the visual and textual features of detected text regions, and edges of which represent the spatial relatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14470","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/2103.14470/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":"2103.14470","created_at":"2026-07-05T02:26:41.303902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14470v1","created_at":"2026-07-05T02:26:41.303902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14470","created_at":"2026-07-05T02:26:41.303902+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQBYDZQATSO6","created_at":"2026-07-05T02:26:41.303902+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQBYDZQATSO6235V","created_at":"2026-07-05T02:26:41.303902+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQBYDZQA","created_at":"2026-07-05T02:26:41.303902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06560","citing_title":"Vision as Unified Multimodal Generation","ref_index":160,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25212","citing_title":"Noncrossing Duality and the Geometry of Positive Tropical Linear Spaces","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25213","citing_title":"When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q","json":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q.json","graph_json":"https://pith.science/api/pith-number/SQBYDZQATSO6235VGNIFPQNP2Q/graph.json","events_json":"https://pith.science/api/pith-number/SQBYDZQATSO6235VGNIFPQNP2Q/events.json","paper":"https://pith.science/paper/SQBYDZQA"},"agent_actions":{"view_html":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q","download_json":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q.json","view_paper":"https://pith.science/paper/SQBYDZQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14470&json=true","fetch_graph":"https://pith.science/api/pith-number/SQBYDZQATSO6235VGNIFPQNP2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/SQBYDZQATSO6235VGNIFPQNP2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q/action/storage_attestation","attest_author":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q/action/author_attestation","sign_citation":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q/action/citation_signature","submit_replication":"https://pith.science/pith/SQBYDZQATSO6235VGNIFPQNP2Q/action/replication_record"}},"created_at":"2026-07-05T02:26:41.303902+00:00","updated_at":"2026-07-05T02:26:41.303902+00:00"}