{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OKEA4EC6SD2J7BXQUDSHE44QFS","short_pith_number":"pith:OKEA4EC6","schema_version":"1.0","canonical_sha256":"72880e105e90f49f86f0a0e47273902c970a87d7dfc8257910927f89ddfd991f","source":{"kind":"arxiv","id":"2603.11044","version":2},"attestation_state":"computed","paper":{"title":"LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingtao Fu, Gaoyang Zhang, Peng Zhang, Siyi Qian, Xiongfei Bai, Xudong Yang, Yichen Lu","submitted_at":"2026-03-11T17:59:42Z","abstract_excerpt":"In this paper, we propose LingDT-VL-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, LingDT-VL-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of"},"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":"2603.11044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-11T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"4a17b1eba900eddd4fbfc1803419324d235002a401213c3112c8acabda6ffdfb","abstract_canon_sha256":"36dd08f7680af0a225c6c3163b0258ead5de79b278d7ba319f4e9596d8acc966"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:26.840612Z","signature_b64":"bw2dF+/yiiwJOlpnpKJWYPZUxNshqdmrv8t49QARwxCmZvNsEn5Pq/aStVoEPt05hmbxJYLZ0xgFNquNwl3mAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72880e105e90f49f86f0a0e47273902c970a87d7dfc8257910927f89ddfd991f","last_reissued_at":"2026-07-08T01:18:26.840103Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:26.840103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingtao Fu, Gaoyang Zhang, Peng Zhang, Siyi Qian, Xiongfei Bai, Xudong Yang, Yichen Lu","submitted_at":"2026-03-11T17:59:42Z","abstract_excerpt":"In this paper, we propose LingDT-VL-OCR, a document parsing system tailored to financial-domain documents, transforming ultra-long financial PDFs into semantically consistent, highly accurate, structured outputs with auditing-grade provenance. To address finance-specific challenges such as complex layouts, cross-page structural discontinuities, and cell-level referencing capability, LingDT-VL-OCR combines (1) a Cross-page Contents Consolidation algorithm to restore continuity across pages and a Document-level Heading Hierarchy Reconstruction (DHR) module to build a globally consistent Table of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.11044","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/2603.11044/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":"2603.11044","created_at":"2026-07-08T01:18:26.840164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.11044v2","created_at":"2026-07-08T01:18:26.840164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11044","created_at":"2026-07-08T01:18:26.840164+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKEA4EC6SD2J","created_at":"2026-07-08T01:18:26.840164+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKEA4EC6SD2J7BXQ","created_at":"2026-07-08T01:18:26.840164+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKEA4EC6","created_at":"2026-07-08T01:18:26.840164+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/OKEA4EC6SD2J7BXQUDSHE44QFS","json":"https://pith.science/pith/OKEA4EC6SD2J7BXQUDSHE44QFS.json","graph_json":"https://pith.science/api/pith-number/OKEA4EC6SD2J7BXQUDSHE44QFS/graph.json","events_json":"https://pith.science/api/pith-number/OKEA4EC6SD2J7BXQUDSHE44QFS/events.json","paper":"https://pith.science/paper/OKEA4EC6"},"agent_actions":{"view_html":"https://pith.science/pith/OKEA4EC6SD2J7BXQUDSHE44QFS","download_json":"https://pith.science/pith/OKEA4EC6SD2J7BXQUDSHE44QFS.json","view_paper":"https://pith.science/paper/OKEA4EC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.11044&json=true","fetch_graph":"https://pith.science/api/pith-number/OKEA4EC6SD2J7BXQUDSHE44QFS/graph.json","fetch_events":"https://pith.science/api/pith-number/OKEA4EC6SD2J7BXQUDSHE44QFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKEA4EC6SD2J7BXQUDSHE44QFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKEA4EC6SD2J7BXQUDSHE44QFS/action/storage_attestation","attest_author":"https://pith.science/pith/OKEA4EC6SD2J7BXQUDSHE44QFS/action/author_attestation","sign_citation":"https://pith.science/pith/OKEA4EC6SD2J7BXQUDSHE44QFS/action/citation_signature","submit_replication":"https://pith.science/pith/OKEA4EC6SD2J7BXQUDSHE44QFS/action/replication_record"}},"created_at":"2026-07-08T01:18:26.840164+00:00","updated_at":"2026-07-08T01:18:26.840164+00:00"}