{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OUR2IJR5WZWXEX4U6UCBRDITAN","short_pith_number":"pith:OUR2IJR5","schema_version":"1.0","canonical_sha256":"7523a4263db66d725f94f504188d13035cea10a28fe280c90543cbfe8aa65ea5","source":{"kind":"arxiv","id":"2406.19593","version":2},"attestation_state":"computed","paper":{"title":"SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Kris W Pan, Man Luo, Phillip Howard, Tien Pei Chou, Vasudev Lal, Xin Su","submitted_at":"2024-06-28T01:14:43Z","abstract_excerpt":"Multimodal retrieval augmented generation (RAG) plays a crucial role in domains such as knowledge-based visual question answering (KB-VQA), where external knowledge is needed to answer a question. However, existing multimodal LLMs (MLLMs) are not designed for context-augmented generation, limiting their effectiveness in such tasks. While synthetic data generation has recently gained attention for training MLLMs, its application for context-augmented generation remains underexplored. To address this gap, we introduce SK-VQA, a large-scale synthetic multimodal dataset containing over 2 million v"},"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":"2406.19593","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T01:14:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"120b096fe9b68c5ed4582c77105a1a89213c4b942f47c8fbec88cb4d09da7a2c","abstract_canon_sha256":"d32f79b9c5bc277bcc0bd9328f5ea3d5b3fd8e42f0889d518e3cfaf6b80e813d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:39.122806Z","signature_b64":"KoBmBuuTP2F933AonPb0vhb+FHPqMybagGKPie4/q0IjGxGoE5GSXCzTLxNcu3tjWDaivqWVUgd+tbJ8/n6kBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7523a4263db66d725f94f504188d13035cea10a28fe280c90543cbfe8aa65ea5","last_reissued_at":"2026-07-05T11:18:39.122368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:39.122368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Kris W Pan, Man Luo, Phillip Howard, Tien Pei Chou, Vasudev Lal, Xin Su","submitted_at":"2024-06-28T01:14:43Z","abstract_excerpt":"Multimodal retrieval augmented generation (RAG) plays a crucial role in domains such as knowledge-based visual question answering (KB-VQA), where external knowledge is needed to answer a question. However, existing multimodal LLMs (MLLMs) are not designed for context-augmented generation, limiting their effectiveness in such tasks. While synthetic data generation has recently gained attention for training MLLMs, its application for context-augmented generation remains underexplored. To address this gap, we introduce SK-VQA, a large-scale synthetic multimodal dataset containing over 2 million v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19593","kind":"arxiv","version":2},"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/2406.19593/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":"2406.19593","created_at":"2026-07-05T11:18:39.122427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19593v2","created_at":"2026-07-05T11:18:39.122427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19593","created_at":"2026-07-05T11:18:39.122427+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUR2IJR5WZWX","created_at":"2026-07-05T11:18:39.122427+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUR2IJR5WZWXEX4U","created_at":"2026-07-05T11:18:39.122427+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUR2IJR5","created_at":"2026-07-05T11:18:39.122427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22933","citing_title":"Augmented Vision-Language Models: A Systematic Review","ref_index":106,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN","json":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN.json","graph_json":"https://pith.science/api/pith-number/OUR2IJR5WZWXEX4U6UCBRDITAN/graph.json","events_json":"https://pith.science/api/pith-number/OUR2IJR5WZWXEX4U6UCBRDITAN/events.json","paper":"https://pith.science/paper/OUR2IJR5"},"agent_actions":{"view_html":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN","download_json":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN.json","view_paper":"https://pith.science/paper/OUR2IJR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19593&json=true","fetch_graph":"https://pith.science/api/pith-number/OUR2IJR5WZWXEX4U6UCBRDITAN/graph.json","fetch_events":"https://pith.science/api/pith-number/OUR2IJR5WZWXEX4U6UCBRDITAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/action/storage_attestation","attest_author":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/action/author_attestation","sign_citation":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/action/citation_signature","submit_replication":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/action/replication_record"}},"created_at":"2026-07-05T11:18:39.122427+00:00","updated_at":"2026-07-05T11:18:39.122427+00:00"}