{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NC3XXKTQGDHMM4SPB242RMT23E","short_pith_number":"pith:NC3XXKTQ","schema_version":"1.0","canonical_sha256":"68b77baa7030cec6724f0eb9a8b27ad91c617f4b578d1909849feed2b1abe7d7","source":{"kind":"arxiv","id":"2411.15041","version":1},"attestation_state":"computed","paper":{"title":"mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bing Li, Chunfeng Yuan, Jin Ma, Junfu Pu, Tao Zhang, Weiming Hu, Ying Shan, Yuxin Chen, Yuxuan Zhao, Zehua Xie, Zhongang Qi, Ziqi Zhang, Zongyang Ma","submitted_at":"2024-11-22T16:15:50Z","abstract_excerpt":"Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based VQA tasks, such as INFOSEEK and Encyclopedic-VQA, due to their limited and frozen knowledge scope, often leading to ambiguous and inaccurate responses. Thus, multimodal Retrieval-Augmented Generation (mRAG) is naturally introduced to provide MLLMs with comprehensive and up-to-date knowledge, effectively expanding the knowledge scope. However, current mRAG methods have inherent drawbacks, including: 1) Performing retrieval even when external knowledge is not needed. 2) Lacking of identification of evidence th"},"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":"2411.15041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-22T16:15:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d1aef9ba279663bd2ec75b89acc8f4dfea1371be8081c4626049bd74cbd5dab1","abstract_canon_sha256":"9c7debec433eb624e1e8ac60feb41a759bcfee4b0ad5615981228a9d9c90ad89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:15.598973Z","signature_b64":"ogUIfirtlpgbq/IcFAebN5aTqJPqhUlEUjGoejelh9TmJ/VqiW1b+jFumAdgJxyczz9cmqIDuLV0AIQmlMD9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68b77baa7030cec6724f0eb9a8b27ad91c617f4b578d1909849feed2b1abe7d7","last_reissued_at":"2026-07-05T09:39:15.598620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:15.598620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bing Li, Chunfeng Yuan, Jin Ma, Junfu Pu, Tao Zhang, Weiming Hu, Ying Shan, Yuxin Chen, Yuxuan Zhao, Zehua Xie, Zhongang Qi, Ziqi Zhang, Zongyang Ma","submitted_at":"2024-11-22T16:15:50Z","abstract_excerpt":"Advanced Multimodal Large Language Models (MLLMs) struggle with recent Knowledge-based VQA tasks, such as INFOSEEK and Encyclopedic-VQA, due to their limited and frozen knowledge scope, often leading to ambiguous and inaccurate responses. Thus, multimodal Retrieval-Augmented Generation (mRAG) is naturally introduced to provide MLLMs with comprehensive and up-to-date knowledge, effectively expanding the knowledge scope. However, current mRAG methods have inherent drawbacks, including: 1) Performing retrieval even when external knowledge is not needed. 2) Lacking of identification of evidence th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15041","kind":"arxiv","version":1},"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/2411.15041/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":"2411.15041","created_at":"2026-07-05T09:39:15.598674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15041v1","created_at":"2026-07-05T09:39:15.598674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15041","created_at":"2026-07-05T09:39:15.598674+00:00"},{"alias_kind":"pith_short_12","alias_value":"NC3XXKTQGDHM","created_at":"2026-07-05T09:39:15.598674+00:00"},{"alias_kind":"pith_short_16","alias_value":"NC3XXKTQGDHMM4SP","created_at":"2026-07-05T09:39:15.598674+00:00"},{"alias_kind":"pith_short_8","alias_value":"NC3XXKTQ","created_at":"2026-07-05T09:39:15.598674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07383","citing_title":"MMAgent-R$^2$: Learning to Rerank and Reject for Agentic mRAG","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23881","citing_title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29602","citing_title":"CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22095","citing_title":"Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05318","citing_title":"mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00798","citing_title":"Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13856","citing_title":"QKVQA: Question-Focused Filtering for Knowledge-based VQA","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05818","citing_title":"WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E","json":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E.json","graph_json":"https://pith.science/api/pith-number/NC3XXKTQGDHMM4SPB242RMT23E/graph.json","events_json":"https://pith.science/api/pith-number/NC3XXKTQGDHMM4SPB242RMT23E/events.json","paper":"https://pith.science/paper/NC3XXKTQ"},"agent_actions":{"view_html":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E","download_json":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E.json","view_paper":"https://pith.science/paper/NC3XXKTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15041&json=true","fetch_graph":"https://pith.science/api/pith-number/NC3XXKTQGDHMM4SPB242RMT23E/graph.json","fetch_events":"https://pith.science/api/pith-number/NC3XXKTQGDHMM4SPB242RMT23E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E/action/storage_attestation","attest_author":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E/action/author_attestation","sign_citation":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E/action/citation_signature","submit_replication":"https://pith.science/pith/NC3XXKTQGDHMM4SPB242RMT23E/action/replication_record"}},"created_at":"2026-07-05T09:39:15.598674+00:00","updated_at":"2026-07-05T09:39:15.598674+00:00"}