{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:55F667VFM54DWKH2QLQKFR2M5A","short_pith_number":"pith:55F667VF","schema_version":"1.0","canonical_sha256":"ef4bef7ea567783b28fa82e0a2c74ce80ecfe568a7824fcceee400569ee9e4db","source":{"kind":"arxiv","id":"2410.08182","version":2},"attestation_state":"computed","paper":{"title":"MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jia-Chen Gu, Kai-Wei Chang, Mohsen Fayyaz, Nanyun Peng, Pan Lu, Wenbo Hu, Zi-Yi Dou","submitted_at":"2024-10-10T17:55:02Z","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"},"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":"2410.08182","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:55:02Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4ca5a4e70e58b2fb18d178c01807a13b9a6690e935dd28e1c4791b240b14169b","abstract_canon_sha256":"72ace27fd513ad41bdbd51ff02639f9531bdff41fcb70a41cd50e3b4dad48421"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:38.446282Z","signature_b64":"3QNx07R4BMvQeD46rn/2hC5tfra/+8T5JOm+2VGE2zSBITqh4nR9sZ5F33ZbBTKkfGDjefXrf5iuhJD5evvICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef4bef7ea567783b28fa82e0a2c74ce80ecfe568a7824fcceee400569ee9e4db","last_reissued_at":"2026-07-05T10:35:38.445434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:38.445434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jia-Chen Gu, Kai-Wei Chang, Mohsen Fayyaz, Nanyun Peng, Pan Lu, Wenbo Hu, Zi-Yi Dou","submitted_at":"2024-10-10T17:55:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08182","kind":"arxiv","version":2},"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/2410.08182/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":"2410.08182","created_at":"2026-07-05T10:35:38.445539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08182v2","created_at":"2026-07-05T10:35:38.445539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08182","created_at":"2026-07-05T10:35:38.445539+00:00"},{"alias_kind":"pith_short_12","alias_value":"55F667VFM54D","created_at":"2026-07-05T10:35:38.445539+00:00"},{"alias_kind":"pith_short_16","alias_value":"55F667VFM54DWKH2","created_at":"2026-07-05T10:35:38.445539+00:00"},{"alias_kind":"pith_short_8","alias_value":"55F667VF","created_at":"2026-07-05T10:35:38.445539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14906","citing_title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17946","citing_title":"SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17946","citing_title":"SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20291","citing_title":"VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00104","citing_title":"R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13277","citing_title":"Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16930","citing_title":"CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A","json":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A.json","graph_json":"https://pith.science/api/pith-number/55F667VFM54DWKH2QLQKFR2M5A/graph.json","events_json":"https://pith.science/api/pith-number/55F667VFM54DWKH2QLQKFR2M5A/events.json","paper":"https://pith.science/paper/55F667VF"},"agent_actions":{"view_html":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A","download_json":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A.json","view_paper":"https://pith.science/paper/55F667VF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08182&json=true","fetch_graph":"https://pith.science/api/pith-number/55F667VFM54DWKH2QLQKFR2M5A/graph.json","fetch_events":"https://pith.science/api/pith-number/55F667VFM54DWKH2QLQKFR2M5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A/action/storage_attestation","attest_author":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A/action/author_attestation","sign_citation":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A/action/citation_signature","submit_replication":"https://pith.science/pith/55F667VFM54DWKH2QLQKFR2M5A/action/replication_record"}},"created_at":"2026-07-05T10:35:38.445539+00:00","updated_at":"2026-07-05T10:35:38.445539+00:00"}