{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XB6JZ5DIXVPWKCJ5MLKKZ3TTO7","short_pith_number":"pith:XB6JZ5DI","schema_version":"1.0","canonical_sha256":"b87c9cf468bd5f65093d62d4acee7377e65713c5c12c579b786f8bdc0812810e","source":{"kind":"arxiv","id":"2605.24530","version":1},"attestation_state":"computed","paper":{"title":"Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Wang, Chunyu Yang, Hao Sun, Jiayan Guo, Jinsong Ni, Yan Zhang, Yingyan Hou","submitted_at":"2026-05-23T11:48:28Z","abstract_excerpt":"Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to errors, while recent parsing-free visual methods often struggle to capture fine-grained textual semantics in text-rich scenarios. To address these limitations, we propose \\textbf{Unveil}, a novel visual-textual embedding framework that effectively integrates textual and visual features for robust document representation. Through knowledge distillation, we t"},"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":"2605.24530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T11:48:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"405b542f8eac91ea09949b56c3a11bf27f89c79e9c11ba0ccf0ada2ad69439f8","abstract_canon_sha256":"e8a02d13de25561671124bce31cc0f2482a3209be0caf9a735bee5dac7c8f87f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:44.782582Z","signature_b64":"kApkGYfIrSquCxkaZutcbh2Il6VCUpYeuO6QFTUp7+cKDxeg8BXa0izSYzAhrhNuuR+tuwALETWI3KDfQP9nCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b87c9cf468bd5f65093d62d4acee7377e65713c5c12c579b786f8bdc0812810e","last_reissued_at":"2026-05-26T01:03:44.781756Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:44.781756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Wang, Chunyu Yang, Hao Sun, Jiayan Guo, Jinsong Ni, Yan Zhang, Yingyan Hou","submitted_at":"2026-05-23T11:48:28Z","abstract_excerpt":"Document retrieval in real-world scenarios faces significant challenges due to diverse document formats and modalities. Traditional text-based approaches rely on tailored parsing techniques that disregard layout information and are prone to errors, while recent parsing-free visual methods often struggle to capture fine-grained textual semantics in text-rich scenarios. To address these limitations, we propose \\textbf{Unveil}, a novel visual-textual embedding framework that effectively integrates textual and visual features for robust document representation. Through knowledge distillation, we t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24530","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/2605.24530/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":"2605.24530","created_at":"2026-05-26T01:03:44.781898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24530v1","created_at":"2026-05-26T01:03:44.781898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24530","created_at":"2026-05-26T01:03:44.781898+00:00"},{"alias_kind":"pith_short_12","alias_value":"XB6JZ5DIXVPW","created_at":"2026-05-26T01:03:44.781898+00:00"},{"alias_kind":"pith_short_16","alias_value":"XB6JZ5DIXVPWKCJ5","created_at":"2026-05-26T01:03:44.781898+00:00"},{"alias_kind":"pith_short_8","alias_value":"XB6JZ5DI","created_at":"2026-05-26T01:03:44.781898+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/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7","json":"https://pith.science/pith/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7.json","graph_json":"https://pith.science/api/pith-number/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/graph.json","events_json":"https://pith.science/api/pith-number/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/events.json","paper":"https://pith.science/paper/XB6JZ5DI"},"agent_actions":{"view_html":"https://pith.science/pith/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7","download_json":"https://pith.science/pith/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7.json","view_paper":"https://pith.science/paper/XB6JZ5DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24530&json=true","fetch_graph":"https://pith.science/api/pith-number/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/graph.json","fetch_events":"https://pith.science/api/pith-number/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/action/storage_attestation","attest_author":"https://pith.science/pith/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/action/author_attestation","sign_citation":"https://pith.science/pith/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/action/citation_signature","submit_replication":"https://pith.science/pith/XB6JZ5DIXVPWKCJ5MLKKZ3TTO7/action/replication_record"}},"created_at":"2026-05-26T01:03:44.781898+00:00","updated_at":"2026-05-26T01:03:44.781898+00:00"}