{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BW7N2FYEYDLW5PKA4YOG45GKBE","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":"0ca09bae10b8f5013bbb3983851b06cf20daedfb3340b6b50b034846a4edd3a1","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T16:07:24Z","title_canon_sha256":"61df4eee60e2835864276e821160cbd141325e663e8e9b0fde210ca790087366"},"schema_version":"1.0","source":{"id":"2502.04176","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04176","created_at":"2026-07-05T10:51:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04176v2","created_at":"2026-07-05T10:51:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04176","created_at":"2026-07-05T10:51:32Z"},{"alias_kind":"pith_short_12","alias_value":"BW7N2FYEYDLW","created_at":"2026-07-05T10:51:32Z"},{"alias_kind":"pith_short_16","alias_value":"BW7N2FYEYDLW5PKA","created_at":"2026-07-05T10:51:32Z"},{"alias_kind":"pith_short_8","alias_value":"BW7N2FYE","created_at":"2026-07-05T10:51:32Z"}],"graph_snapshots":[{"event_id":"sha256:274cb67aaecc4050a05c3eab639010ae0264a3d3e972d2bdf06933612312df35","target":"graph","created_at":"2026-07-05T10:51:32Z","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/2502.04176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Retrieval-Augmented Generation (RAG) have significantly improved response accuracy and relevance by incorporating external knowledge into Large Language Models (LLMs). However, existing RAG methods primarily focus on generating text-only answers, even in Multimodal Retrieval-Augmented Generation (MRAG) scenarios, where multimodal elements are retrieved to assist in generating text answers. To address this, we introduce the Multimodal Retrieval-Augmented Multimodal Generation (MRAMG) task, in which we aim to generate multimodal answers that combine both text and images, fully","authors_text":"Binghui Li, Chong Chen, Qinhan Yu, Wentao Zhang, Zhengren Wang, Zhiyou Xiao","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T16:07:24Z","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04176","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":"sha256:2d811cb9b87d106cc551ca26737b7d81293033e868189d74d72b676db89b8e32","target":"record","created_at":"2026-07-05T10:51:32Z","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":"0ca09bae10b8f5013bbb3983851b06cf20daedfb3340b6b50b034846a4edd3a1","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-06T16:07:24Z","title_canon_sha256":"61df4eee60e2835864276e821160cbd141325e663e8e9b0fde210ca790087366"},"schema_version":"1.0","source":{"id":"2502.04176","kind":"arxiv","version":2}},"canonical_sha256":"0dbedd1704c0d76ebd40e61c6e74ca0920424a0a266653eeab071fe54735a604","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dbedd1704c0d76ebd40e61c6e74ca0920424a0a266653eeab071fe54735a604","first_computed_at":"2026-07-05T10:51:32.228164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:32.228164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IMLF7bir4d3i/uMJKiBJTIxx3d6igu503gINAFzqWUQxK2pMEnc12dARpDDTMlwR8EVBzI6qte0aq7ZxqoQ9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:32.228670Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04176","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d811cb9b87d106cc551ca26737b7d81293033e868189d74d72b676db89b8e32","sha256:274cb67aaecc4050a05c3eab639010ae0264a3d3e972d2bdf06933612312df35"],"state_sha256":"165e80651e12c37167e7e967d8f006777109550940a025218ad43323f7a6bd42"}