{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:POJ6HK2CA6I2SPXTAC7CL5PK2A","short_pith_number":"pith:POJ6HK2C","schema_version":"1.0","canonical_sha256":"7b93e3ab420791a93ef300be25f5ead015f924793a31d0429385d12b8f985391","source":{"kind":"arxiv","id":"2207.04713","version":1},"attestation_state":"computed","paper":{"title":"GMN: Generative Multi-modal Network for Practical Document Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antai Guo, Bo Ren, Deqiang Jiang, Hao Liu, Haoyu Cao, Jiefeng Ma, Yinsong Liu, Yiqing Hu","submitted_at":"2022-07-11T08:52:36Z","abstract_excerpt":"Document Information Extraction (DIE) has attracted increasing attention due to its various advanced applications in the real world. Although recent literature has already achieved competitive results, these approaches usually fail when dealing with complex documents with noisy OCR results or mutative layouts. This paper proposes Generative Multi-modal Network (GMN) for real-world scenarios to address these problems, which is a robust multi-modal generation method without predefined label categories. With the carefully designed spatial encoder and modal-aware mask module, GMN can deal with com"},"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":"2207.04713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-11T08:52:36Z","cross_cats_sorted":[],"title_canon_sha256":"7ee0a8d82c5fc5900eda8e275054432799bf72064513154212c4f767a8f6063d","abstract_canon_sha256":"12556ea4d70c4317f8b9f884f8b80c2fa227c4884babe4d77d058c514ff081e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:02.639080Z","signature_b64":"uMXTTlLghhAMiBeTIwqbb2hJD0YJbFxWx1aN9aJFGLxpt+bE4LxxMD38myo0As3aTeKIKmK9aC3FEkEQFcynDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b93e3ab420791a93ef300be25f5ead015f924793a31d0429385d12b8f985391","last_reissued_at":"2026-07-05T04:39:02.638681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:02.638681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GMN: Generative Multi-modal Network for Practical Document Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antai Guo, Bo Ren, Deqiang Jiang, Hao Liu, Haoyu Cao, Jiefeng Ma, Yinsong Liu, Yiqing Hu","submitted_at":"2022-07-11T08:52:36Z","abstract_excerpt":"Document Information Extraction (DIE) has attracted increasing attention due to its various advanced applications in the real world. Although recent literature has already achieved competitive results, these approaches usually fail when dealing with complex documents with noisy OCR results or mutative layouts. This paper proposes Generative Multi-modal Network (GMN) for real-world scenarios to address these problems, which is a robust multi-modal generation method without predefined label categories. With the carefully designed spatial encoder and modal-aware mask module, GMN can deal with com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04713","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/2207.04713/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":"2207.04713","created_at":"2026-07-05T04:39:02.638740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04713v1","created_at":"2026-07-05T04:39:02.638740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04713","created_at":"2026-07-05T04:39:02.638740+00:00"},{"alias_kind":"pith_short_12","alias_value":"POJ6HK2CA6I2","created_at":"2026-07-05T04:39:02.638740+00:00"},{"alias_kind":"pith_short_16","alias_value":"POJ6HK2CA6I2SPXT","created_at":"2026-07-05T04:39:02.638740+00:00"},{"alias_kind":"pith_short_8","alias_value":"POJ6HK2C","created_at":"2026-07-05T04:39:02.638740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A","json":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A.json","graph_json":"https://pith.science/api/pith-number/POJ6HK2CA6I2SPXTAC7CL5PK2A/graph.json","events_json":"https://pith.science/api/pith-number/POJ6HK2CA6I2SPXTAC7CL5PK2A/events.json","paper":"https://pith.science/paper/POJ6HK2C"},"agent_actions":{"view_html":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A","download_json":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A.json","view_paper":"https://pith.science/paper/POJ6HK2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04713&json=true","fetch_graph":"https://pith.science/api/pith-number/POJ6HK2CA6I2SPXTAC7CL5PK2A/graph.json","fetch_events":"https://pith.science/api/pith-number/POJ6HK2CA6I2SPXTAC7CL5PK2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A/action/storage_attestation","attest_author":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A/action/author_attestation","sign_citation":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A/action/citation_signature","submit_replication":"https://pith.science/pith/POJ6HK2CA6I2SPXTAC7CL5PK2A/action/replication_record"}},"created_at":"2026-07-05T04:39:02.638740+00:00","updated_at":"2026-07-05T04:39:02.638740+00:00"}