{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BYSED45SMYEL5MOXC6PTHYUOV4","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":"c2a8fbae1b5fc51ebd73f75b00f60efb36cb04a4f4b465840b7539214f9ead96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T13:20:19Z","title_canon_sha256":"6fb01fdacd63545fc8f4ab5a20cfc3e14bc5dd781977dffbbef935ffd0e7dae5"},"schema_version":"1.0","source":{"id":"2411.16365","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16365","created_at":"2026-07-05T11:08:13Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16365v4","created_at":"2026-07-05T11:08:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16365","created_at":"2026-07-05T11:08:13Z"},{"alias_kind":"pith_short_12","alias_value":"BYSED45SMYEL","created_at":"2026-07-05T11:08:13Z"},{"alias_kind":"pith_short_16","alias_value":"BYSED45SMYEL5MOX","created_at":"2026-07-05T11:08:13Z"},{"alias_kind":"pith_short_8","alias_value":"BYSED45S","created_at":"2026-07-05T11:08:13Z"}],"graph_snapshots":[{"event_id":"sha256:718b97acac7b2d5e37b8d23b22daf91966216cc12474791e2e6b32d6af3709f6","target":"graph","created_at":"2026-07-05T11:08:13Z","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/2411.16365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a systematic investigation of Multi-modal Retrieval Augmented Multi-modal Generation (M$^2$RAG), a novel task that enables foundation models to process multi-modal web content and generate multi-modal responses, which exhibits better information density and readability. Despite its potential impact, M$^2$RAG remains understudied, lacking comprehensive analysis and high-quality data resources. To address this gap, we establish a comprehensive benchmark through a rigorous data curation pipeline, and employ text-modal metrics and multi-modal metrics based on foundation models for evalu","authors_text":"Heyan Huang, Rong-Cheng Tu, Tian Lan, Tong Zhang, Xian-Ling Mao, Yong Hu, Yu-Shi Zhu, Zhijing Wu, Zi-Ao Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T13:20:19Z","title":"Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16365","kind":"arxiv","version":4},"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":"sha256:7991157180f67327fd215dd3d13e6face6d1b7059244a57becc73e7b1bf76609","target":"record","created_at":"2026-07-05T11:08:13Z","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":"c2a8fbae1b5fc51ebd73f75b00f60efb36cb04a4f4b465840b7539214f9ead96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T13:20:19Z","title_canon_sha256":"6fb01fdacd63545fc8f4ab5a20cfc3e14bc5dd781977dffbbef935ffd0e7dae5"},"schema_version":"1.0","source":{"id":"2411.16365","kind":"arxiv","version":4}},"canonical_sha256":"0e2441f3b26608beb1d7179f33e28eaf32463b18100646fc77c3c580fcd64ff6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e2441f3b26608beb1d7179f33e28eaf32463b18100646fc77c3c580fcd64ff6","first_computed_at":"2026-07-05T11:08:13.721334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:13.721334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ulvss5UFaJ2bWmGzeMyq2pgBKVZ8rQjkSpSLZO3Lg+8sOKlLhnXZ+fDs8hNQglSdLWenAO6u3UAUYQABFWuLDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:13.721787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16365","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7991157180f67327fd215dd3d13e6face6d1b7059244a57becc73e7b1bf76609","sha256:718b97acac7b2d5e37b8d23b22daf91966216cc12474791e2e6b32d6af3709f6"],"state_sha256":"0675ee54d992756a48408df1b79c7e9fa200945ca176381a93abf22de2b5f669"}