{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5EMSR34YNQY5DZNXAWFOKMRFWI","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":"43d45ef304023c107ed79796662f28660b1a25464f172f73aacc9c00b1b331a9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T12:57:42Z","title_canon_sha256":"879c3385de43daa98cde621c2a2db39313f7db655d789d0d6c504b7cf345502a"},"schema_version":"1.0","source":{"id":"2407.02233","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02233","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02233v2","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02233","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"5EMSR34YNQY5","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"5EMSR34YNQY5DZNX","created_at":"2026-07-05T09:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"5EMSR34Y","created_at":"2026-07-05T09:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:6c3f9bad439a4d831e28f94126849e96bc50e8dfa86372a6b82cd4dfd1d925a6","target":"graph","created_at":"2026-07-05T09:15:34Z","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/2407.02233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Retrieval Augmented Generation (MMRAG) is a powerful approach to question-answering over multimodal documents. A key challenge with evaluating MMRAG is the paucity of high-quality datasets matching the question styles and modalities of interest. In light of this, we propose SMMQG, a synthetic data generation framework. SMMQG leverages interplay between a retriever, large language model (LLM) and large multimodal model (LMM) to generate question and answer pairs directly from multimodal documents, with the questions conforming to specified styles and modalities. We use SMMQG to gener","authors_text":"Graham Neubig, Ian Wu, Simon Rosenberg, Sina Pakazad, Sravan Jayanthi, Tongshuang Wu, Vijay Viswanathan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T12:57:42Z","title":"Synthetic Multimodal Question Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02233","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":"sha256:8cbe0ad6b80fc5a2fcc56c3e919f1e32d63bfcb9a23bacffa9dfd367a6298d11","target":"record","created_at":"2026-07-05T09:15:34Z","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":"43d45ef304023c107ed79796662f28660b1a25464f172f73aacc9c00b1b331a9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T12:57:42Z","title_canon_sha256":"879c3385de43daa98cde621c2a2db39313f7db655d789d0d6c504b7cf345502a"},"schema_version":"1.0","source":{"id":"2407.02233","kind":"arxiv","version":2}},"canonical_sha256":"e91928ef986c31d1e5b7058ae53225b22e128f5ce1c9c7c50bf2151e8c392ae4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e91928ef986c31d1e5b7058ae53225b22e128f5ce1c9c7c50bf2151e8c392ae4","first_computed_at":"2026-07-05T09:15:34.658133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:34.658133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"loJkwwt0nNBXiNPiFzv6L6LV9y7RYY3KcWBgLhQ8iTfkaZw6TwXBHkvhZ7LIXsuSfa+SHs8XfuRYxvQtkih6Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:34.658706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02233","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cbe0ad6b80fc5a2fcc56c3e919f1e32d63bfcb9a23bacffa9dfd367a6298d11","sha256:6c3f9bad439a4d831e28f94126849e96bc50e8dfa86372a6b82cd4dfd1d925a6"],"state_sha256":"68cc91606d2b7d3f80b257d827eb7080d29de33cdec22113351011f9f4b56649"}