{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L4AIDSHJ6PDRH2Q2BAFH4HNOP3","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":"2703ea609d1add5892732a0e8a5a5144bc11e25f7c5228faed51719e2098827f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T06:24:55Z","title_canon_sha256":"ab6b38f9d8fb02c4721c54f5fc63297b37a6768c46a02c36c503744bc0f1040b"},"schema_version":"1.0","source":{"id":"2412.10704","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10704","created_at":"2026-07-05T10:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10704v2","created_at":"2026-07-05T10:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10704","created_at":"2026-07-05T10:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"L4AIDSHJ6PDR","created_at":"2026-07-05T10:12:24Z"},{"alias_kind":"pith_short_16","alias_value":"L4AIDSHJ6PDRH2Q2","created_at":"2026-07-05T10:12:24Z"},{"alias_kind":"pith_short_8","alias_value":"L4AIDSHJ","created_at":"2026-07-05T10:12:24Z"}],"graph_snapshots":[{"event_id":"sha256:0370e9b8a0bc3cd1389f7d0cb6b08d75584216478089846072edac3137f733e6","target":"graph","created_at":"2026-07-05T10:12:24Z","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/2412.10704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding information from a collection of multiple documents, particularly those with visually rich elements, is important for document-grounded question answering. This paper introduces VisDoMBench, the first comprehensive benchmark designed to evaluate QA systems in multi-document settings with rich multimodal content, including tables, charts, and presentation slides. We propose VisDoMRAG, a novel multimodal Retrieval Augmented Generation (RAG) approach that simultaneously utilizes visual and textual RAG, combining robust visual retrieval capabilities with sophisticated linguistic reas","authors_text":"Dinesh Manocha, Franck Dernoncourt, Kanika Goswami, Manan Suri, Puneet Mathur, Ryan A. Rossi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T06:24:55Z","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10704","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":"sha256:3c7a48af022765846a652dfbef96578b0b7d1931ee02ccdd50dac30a4bf8b3d3","target":"record","created_at":"2026-07-05T10:12:24Z","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":"2703ea609d1add5892732a0e8a5a5144bc11e25f7c5228faed51719e2098827f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T06:24:55Z","title_canon_sha256":"ab6b38f9d8fb02c4721c54f5fc63297b37a6768c46a02c36c503744bc0f1040b"},"schema_version":"1.0","source":{"id":"2412.10704","kind":"arxiv","version":2}},"canonical_sha256":"5f0081c8e9f3c713ea1a080a7e1dae7edc92160392847e21a908825da0f5d33f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f0081c8e9f3c713ea1a080a7e1dae7edc92160392847e21a908825da0f5d33f","first_computed_at":"2026-07-05T10:12:24.398209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:24.398209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pS+yO4a23xhF+o6ezSmDOzobZSciovJA/aOPKj1pRD/snSArycEyWHcGEh0GDSkdAwROlnRs9nypwCxh2TKnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:24.398688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10704","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c7a48af022765846a652dfbef96578b0b7d1931ee02ccdd50dac30a4bf8b3d3","sha256:0370e9b8a0bc3cd1389f7d0cb6b08d75584216478089846072edac3137f733e6"],"state_sha256":"2b7e612f0a13be5e1dfb896b5ee5906baa9cd66769b07d4f99c9a9fa5acf6100"}