{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XB6JZ5DIXVPWKCJ5MLKKZ3TTO7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e8a02d13de25561671124bce31cc0f2482a3209be0caf9a735bee5dac7c8f87f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T11:48:28Z","title_canon_sha256":"405b542f8eac91ea09949b56c3a11bf27f89c79e9c11ba0ccf0ada2ad69439f8"},"schema_version":"1.0","source":{"id":"2605.24530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24530","created_at":"2026-05-26T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24530v1","created_at":"2026-05-26T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24530","created_at":"2026-05-26T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"XB6JZ5DIXVPW","created_at":"2026-05-26T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"XB6JZ5DIXVPWKCJ5","created_at":"2026-05-26T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"XB6JZ5DI","created_at":"2026-05-26T01:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:d02557a424328d1220167f906f3cf80c87f8cdabfc4747bf713b5f1836323a3e","target":"graph","created_at":"2026-05-26T01:03:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.24530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Wang, Chunyu Yang, Hao Sun, Jiayan Guo, Jinsong Ni, Yan Zhang, Yingyan Hou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T11:48:28Z","title":"Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24530","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b6772ae13ba71112ab28dfe41f6920b8708abc97c553a6f7465f21af3764c470","target":"record","created_at":"2026-05-26T01:03:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e8a02d13de25561671124bce31cc0f2482a3209be0caf9a735bee5dac7c8f87f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T11:48:28Z","title_canon_sha256":"405b542f8eac91ea09949b56c3a11bf27f89c79e9c11ba0ccf0ada2ad69439f8"},"schema_version":"1.0","source":{"id":"2605.24530","kind":"arxiv","version":1}},"canonical_sha256":"b87c9cf468bd5f65093d62d4acee7377e65713c5c12c579b786f8bdc0812810e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b87c9cf468bd5f65093d62d4acee7377e65713c5c12c579b786f8bdc0812810e","first_computed_at":"2026-05-26T01:03:44.781756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:44.781756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kApkGYfIrSquCxkaZutcbh2Il6VCUpYeuO6QFTUp7+cKDxeg8BXa0izSYzAhrhNuuR+tuwALETWI3KDfQP9nCA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:44.782582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6772ae13ba71112ab28dfe41f6920b8708abc97c553a6f7465f21af3764c470","sha256:d02557a424328d1220167f906f3cf80c87f8cdabfc4747bf713b5f1836323a3e"],"state_sha256":"5b5c3acd70b42f7d158a93dc64e47ece509312ec92ba7f1d792eab34857b6f8f"}