{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:55F667VFM54DWKH2QLQKFR2M5A","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":"72ace27fd513ad41bdbd51ff02639f9531bdff41fcb70a41cd50e3b4dad48421","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:55:02Z","title_canon_sha256":"4ca5a4e70e58b2fb18d178c01807a13b9a6690e935dd28e1c4791b240b14169b"},"schema_version":"1.0","source":{"id":"2410.08182","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08182","created_at":"2026-07-05T10:35:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08182v2","created_at":"2026-07-05T10:35:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08182","created_at":"2026-07-05T10:35:38Z"},{"alias_kind":"pith_short_12","alias_value":"55F667VFM54D","created_at":"2026-07-05T10:35:38Z"},{"alias_kind":"pith_short_16","alias_value":"55F667VFM54DWKH2","created_at":"2026-07-05T10:35:38Z"},{"alias_kind":"pith_short_8","alias_value":"55F667VF","created_at":"2026-07-05T10:35:38Z"}],"graph_snapshots":[{"event_id":"sha256:6ba8a68a5dab73e9fba0f54a9238ef3291f93ce4d79c39ce4fcb070a88d5ccc3","target":"graph","created_at":"2026-07-05T10:35:38Z","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/2410.08182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing multimodal retrieval benchmarks primarily focus on evaluating whether models can retrieve and utilize external textual knowledge for question answering. However, there are scenarios where retrieving visual information is either more beneficial or easier to access than textual data. In this paper, we introduce a multimodal retrieval-augmented generation benchmark, MRAG-Bench, in which we systematically identify and categorize scenarios where visually augmented knowledge is better than textual knowledge, for instance, more images from varying viewpoints. MRAG-Bench consists of 16,130 im","authors_text":"Jia-Chen Gu, Kai-Wei Chang, Mohsen Fayyaz, Nanyun Peng, Pan Lu, Wenbo Hu, Zi-Yi Dou","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:55:02Z","title":"MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08182","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:eeb00a1a887f7e758dd43faa46274ebef803c2a0a4c7cc3b7a4d34a0449ba59b","target":"record","created_at":"2026-07-05T10:35:38Z","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":"72ace27fd513ad41bdbd51ff02639f9531bdff41fcb70a41cd50e3b4dad48421","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:55:02Z","title_canon_sha256":"4ca5a4e70e58b2fb18d178c01807a13b9a6690e935dd28e1c4791b240b14169b"},"schema_version":"1.0","source":{"id":"2410.08182","kind":"arxiv","version":2}},"canonical_sha256":"ef4bef7ea567783b28fa82e0a2c74ce80ecfe568a7824fcceee400569ee9e4db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef4bef7ea567783b28fa82e0a2c74ce80ecfe568a7824fcceee400569ee9e4db","first_computed_at":"2026-07-05T10:35:38.445434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:38.445434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3QNx07R4BMvQeD46rn/2hC5tfra/+8T5JOm+2VGE2zSBITqh4nR9sZ5F33ZbBTKkfGDjefXrf5iuhJD5evvICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:38.446282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08182","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeb00a1a887f7e758dd43faa46274ebef803c2a0a4c7cc3b7a4d34a0449ba59b","sha256:6ba8a68a5dab73e9fba0f54a9238ef3291f93ce4d79c39ce4fcb070a88d5ccc3"],"state_sha256":"b5d41ebaf846741580f95bcf245bc71180f0bb36ebba1462dc55170637d45ae9"}