{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YGJOVP2NVOFU5IBJJL6ERMRRN6","short_pith_number":"pith:YGJOVP2N","schema_version":"1.0","canonical_sha256":"c192eabf4dab8b4ea0294afc48b2316fb55baca423176cf31cb90c3ef8cf09b2","source":{"kind":"arxiv","id":"2210.05391","version":2},"attestation_state":"computed","paper":{"title":"PP-StructureV2: A Stronger Document Analysis System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxia Li, Dianhai Yu, Jun Zhou, Lingfeng Zhu, Mengtao An, Ruoyu Guo, Xiaoguang Hu, Yi Liu, Yuning Du","submitted_at":"2022-10-11T12:07:32Z","abstract_excerpt":"A large amount of document data exists in unstructured form such as raw images without any text information. Designing a practical document image analysis system is a meaningful but challenging task. In previous work, we proposed an intelligent document analysis system PP-Structure. In order to further upgrade the function and performance of PP-Structure, we propose PP-StructureV2 in this work, which contains two subsystems: Layout Information Extraction and Key Information Extraction. Firstly, we integrate Image Direction Correction module and Layout Restoration module to enhance the function"},"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":"2210.05391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T12:07:32Z","cross_cats_sorted":[],"title_canon_sha256":"f076410fc4c077c4fec36257c6f25051539c8a0915af2b7937d7dddd3e37f0ef","abstract_canon_sha256":"6bb0af54c2d2766288955bbd8c17f76ecfc53acb81068ff175d259cd9171993b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:15.588791Z","signature_b64":"dWNF2thxuL+AD/z3wktWPlkIs+BlyeRt1SncIIm3NhdxTTa4lxjgYg7ByFYhiFqt50yPVaaaTUWb6TX0PtRjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c192eabf4dab8b4ea0294afc48b2316fb55baca423176cf31cb90c3ef8cf09b2","last_reissued_at":"2026-07-05T05:06:15.588265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:15.588265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PP-StructureV2: A Stronger Document Analysis System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxia Li, Dianhai Yu, Jun Zhou, Lingfeng Zhu, Mengtao An, Ruoyu Guo, Xiaoguang Hu, Yi Liu, Yuning Du","submitted_at":"2022-10-11T12:07:32Z","abstract_excerpt":"A large amount of document data exists in unstructured form such as raw images without any text information. Designing a practical document image analysis system is a meaningful but challenging task. In previous work, we proposed an intelligent document analysis system PP-Structure. In order to further upgrade the function and performance of PP-Structure, we propose PP-StructureV2 in this work, which contains two subsystems: Layout Information Extraction and Key Information Extraction. Firstly, we integrate Image Direction Correction module and Layout Restoration module to enhance the function"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05391","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/2210.05391/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":"2210.05391","created_at":"2026-07-05T05:06:15.588348+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05391v2","created_at":"2026-07-05T05:06:15.588348+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05391","created_at":"2026-07-05T05:06:15.588348+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGJOVP2NVOFU","created_at":"2026-07-05T05:06:15.588348+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGJOVP2NVOFU5IBJ","created_at":"2026-07-05T05:06:15.588348+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGJOVP2N","created_at":"2026-07-05T05:06:15.588348+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12623","citing_title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05595","citing_title":"PaddleOCR 3.0 Technical Report","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12623","citing_title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6","json":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6.json","graph_json":"https://pith.science/api/pith-number/YGJOVP2NVOFU5IBJJL6ERMRRN6/graph.json","events_json":"https://pith.science/api/pith-number/YGJOVP2NVOFU5IBJJL6ERMRRN6/events.json","paper":"https://pith.science/paper/YGJOVP2N"},"agent_actions":{"view_html":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6","download_json":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6.json","view_paper":"https://pith.science/paper/YGJOVP2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05391&json=true","fetch_graph":"https://pith.science/api/pith-number/YGJOVP2NVOFU5IBJJL6ERMRRN6/graph.json","fetch_events":"https://pith.science/api/pith-number/YGJOVP2NVOFU5IBJJL6ERMRRN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6/action/storage_attestation","attest_author":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6/action/author_attestation","sign_citation":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6/action/citation_signature","submit_replication":"https://pith.science/pith/YGJOVP2NVOFU5IBJJL6ERMRRN6/action/replication_record"}},"created_at":"2026-07-05T05:06:15.588348+00:00","updated_at":"2026-07-05T05:06:15.588348+00:00"}