{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3C3SNEHZHM65ZNNPNQDTT7UMU2","short_pith_number":"pith:3C3SNEHZ","schema_version":"1.0","canonical_sha256":"d8b72690f93b3ddcb5af6c0739fe8ca69822ac55b8c35dcec7fde30d73416b5c","source":{"kind":"arxiv","id":"2212.09621","version":1},"attestation_state":"computed","paper":{"title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoli Bai, Jiansheng Wei, Liangwei Wang, Lu Hou, Nian Xie, Qun Liu, Rongfu Zheng, Shuang Liu, Wentao Li, Xiaojun Meng, Xin Jiang, Zhiguang Liu","submitted_at":"2022-12-19T17:00:54Z","abstract_excerpt":"Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document"},"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":"2212.09621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T17:00:54Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5331287269c6826669bbc864a17263507007c9c29501b447bf6bcd8b4d9973bd","abstract_canon_sha256":"1a9a627dd89ae392f8fc63c19807832c4d07c21ed704307ce7ff2d06c70917d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:29.406640Z","signature_b64":"Vv/JMGIw7ecekFOly8dhxFUo3rX1GnKw0x4jPyTjnBXtecaJJQZ4EKCZePGTT1AR6S7CFbfLRe8L71pG029iDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8b72690f93b3ddcb5af6c0739fe8ca69822ac55b8c35dcec7fde30d73416b5c","last_reissued_at":"2026-07-05T05:26:29.406212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:29.406212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoli Bai, Jiansheng Wei, Liangwei Wang, Lu Hou, Nian Xie, Qun Liu, Rongfu Zheng, Shuang Liu, Wentao Li, Xiaojun Meng, Xin Jiang, Zhiguang Liu","submitted_at":"2022-12-19T17:00:54Z","abstract_excerpt":"Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the document textline, as an intrinsic granularity in VDU, has seldom been explored so far. A document textline usually contains words that are spatially and semantically correlated, which can be easily obtained from OCR engines. In this paper, we propose Wukong-Reader, trained with new pre-training objectives to leverage the structural knowledge nested in document"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09621","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/2212.09621/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":"2212.09621","created_at":"2026-07-05T05:26:29.406268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09621v1","created_at":"2026-07-05T05:26:29.406268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09621","created_at":"2026-07-05T05:26:29.406268+00:00"},{"alias_kind":"pith_short_12","alias_value":"3C3SNEHZHM65","created_at":"2026-07-05T05:26:29.406268+00:00"},{"alias_kind":"pith_short_16","alias_value":"3C3SNEHZHM65ZNNP","created_at":"2026-07-05T05:26:29.406268+00:00"},{"alias_kind":"pith_short_8","alias_value":"3C3SNEHZ","created_at":"2026-07-05T05:26:29.406268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22186","citing_title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2","json":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2.json","graph_json":"https://pith.science/api/pith-number/3C3SNEHZHM65ZNNPNQDTT7UMU2/graph.json","events_json":"https://pith.science/api/pith-number/3C3SNEHZHM65ZNNPNQDTT7UMU2/events.json","paper":"https://pith.science/paper/3C3SNEHZ"},"agent_actions":{"view_html":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2","download_json":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2.json","view_paper":"https://pith.science/paper/3C3SNEHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09621&json=true","fetch_graph":"https://pith.science/api/pith-number/3C3SNEHZHM65ZNNPNQDTT7UMU2/graph.json","fetch_events":"https://pith.science/api/pith-number/3C3SNEHZHM65ZNNPNQDTT7UMU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2/action/storage_attestation","attest_author":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2/action/author_attestation","sign_citation":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2/action/citation_signature","submit_replication":"https://pith.science/pith/3C3SNEHZHM65ZNNPNQDTT7UMU2/action/replication_record"}},"created_at":"2026-07-05T05:26:29.406268+00:00","updated_at":"2026-07-05T05:26:29.406268+00:00"}