{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NC3XXKTQGDHMM4SPB242RMT23E","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":"9c7debec433eb624e1e8ac60feb41a759bcfee4b0ad5615981228a9d9c90ad89","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-22T16:15:50Z","title_canon_sha256":"d1aef9ba279663bd2ec75b89acc8f4dfea1371be8081c4626049bd74cbd5dab1"},"schema_version":"1.0","source":{"id":"2411.15041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15041","created_at":"2026-07-05T09:39:15Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15041v1","created_at":"2026-07-05T09:39:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15041","created_at":"2026-07-05T09:39:15Z"},{"alias_kind":"pith_short_12","alias_value":"NC3XXKTQGDHM","created_at":"2026-07-05T09:39:15Z"},{"alias_kind":"pith_short_16","alias_value":"NC3XXKTQGDHMM4SP","created_at":"2026-07-05T09:39:15Z"},{"alias_kind":"pith_short_8","alias_value":"NC3XXKTQ","created_at":"2026-07-05T09:39:15Z"}],"graph_snapshots":[{"event_id":"sha256:a3340e3f0d9e9db0d0c481d684dca9ad2b333c90a3383cb63d119c13ecac2bab","target":"graph","created_at":"2026-07-05T09:39:15Z","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/2411.15041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-22T16:15:50Z","title":"mR$^2$AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15041","kind":"arxiv","version":1},"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:b25afe197fa0ead6bde6435bcebb781a7b8ffa2d85119fcfd52360a3c9de3392","target":"record","created_at":"2026-07-05T09:39:15Z","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":"9c7debec433eb624e1e8ac60feb41a759bcfee4b0ad5615981228a9d9c90ad89","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-22T16:15:50Z","title_canon_sha256":"d1aef9ba279663bd2ec75b89acc8f4dfea1371be8081c4626049bd74cbd5dab1"},"schema_version":"1.0","source":{"id":"2411.15041","kind":"arxiv","version":1}},"canonical_sha256":"68b77baa7030cec6724f0eb9a8b27ad91c617f4b578d1909849feed2b1abe7d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68b77baa7030cec6724f0eb9a8b27ad91c617f4b578d1909849feed2b1abe7d7","first_computed_at":"2026-07-05T09:39:15.598620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:15.598620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ogUIfirtlpgbq/IcFAebN5aTqJPqhUlEUjGoejelh9TmJ/VqiW1b+jFumAdgJxyczz9cmqIDuLV0AIQmlMD9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:15.598973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b25afe197fa0ead6bde6435bcebb781a7b8ffa2d85119fcfd52360a3c9de3392","sha256:a3340e3f0d9e9db0d0c481d684dca9ad2b333c90a3383cb63d119c13ecac2bab"],"state_sha256":"fab045bcee69d741eb94626cad633adc29587b045d0369eed46f3a7640a15be8"}