{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:65SVTELMDUSKNL35DEB3GUA6OK","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":"6f08f904e418dde2a282a90e26ce5be22fcba298dd3181f70f1f966f7aa2c5d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-10T21:44:43Z","title_canon_sha256":"d6a68b8e8ddd8ca5419f53357e9fae0e901abd8362a2381c69a41f2500468053"},"schema_version":"1.0","source":{"id":"2508.07493","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07493","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07493v2","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07493","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"pith_short_12","alias_value":"65SVTELMDUSK","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"pith_short_16","alias_value":"65SVTELMDUSKNL35","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"pith_short_8","alias_value":"65SVTELM","created_at":"2026-07-05T11:58:34Z"}],"graph_snapshots":[{"event_id":"sha256:d2083bcdbb8582382fa35e8ddcb36e036e7d820c827f9d412dc51d578bdd4312","target":"graph","created_at":"2026-07-05T11:58:34Z","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/2508.07493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most organizational data in this world are stored as documents, and visual retrieval plays a crucial role in unlocking the collective intelligence from all these documents. However, existing benchmarks focus on English-only document retrieval or only consider multilingual question-answering on a single-page image. To bridge this gap, we introduce VisR-Bench, a multilingual benchmark designed for question-driven multimodal retrieval in long documents. Our benchmark comprises over 35K high-quality QA pairs across 1.2K documents, enabling fine-grained evaluation of multimodal retrieval. VisR-Benc","authors_text":"Changyou Chen, Chenguang Wang, Jian Chen, Jihyung Kil, Ming Li, Ruiyi Zhang, Ryan Rossi, Tianyi Zhou, Tong Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-10T21:44:43Z","title":"VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07493","kind":"arxiv","version":2},"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:f4785829cc4fa84fe7ea165addbb62edece8d8461363b1ad9baec16f17b9b4b5","target":"record","created_at":"2026-07-05T11:58:34Z","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":"6f08f904e418dde2a282a90e26ce5be22fcba298dd3181f70f1f966f7aa2c5d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-10T21:44:43Z","title_canon_sha256":"d6a68b8e8ddd8ca5419f53357e9fae0e901abd8362a2381c69a41f2500468053"},"schema_version":"1.0","source":{"id":"2508.07493","kind":"arxiv","version":2}},"canonical_sha256":"f76559916c1d24a6af7d1903b3501e7282a622eddaa9a50960df4c60c647e070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f76559916c1d24a6af7d1903b3501e7282a622eddaa9a50960df4c60c647e070","first_computed_at":"2026-07-05T11:58:34.369718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:34.369718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K0xxYIyAjv7EZiCUfZaYvTT5+OhfntItu88c/PUilcZUQLihMVTu1xK7Sr6Y9I/F24SzCpS+BRA0t78TdSrkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:34.370171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07493","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4785829cc4fa84fe7ea165addbb62edece8d8461363b1ad9baec16f17b9b4b5","sha256:d2083bcdbb8582382fa35e8ddcb36e036e7d820c827f9d412dc51d578bdd4312"],"state_sha256":"93da703133719c61e9d3b2a61c41b78d4a4213cbd0c2bb5b0e588a0596f99bd6"}