{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OUR2IJR5WZWXEX4U6UCBRDITAN","short_pith_number":"pith:OUR2IJR5","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"},"canonical_sha256":"7523a4263db66d725f94f504188d13035cea10a28fe280c90543cbfe8aa65ea5","source":{"kind":"arxiv","id":"2406.19593","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19593","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19593v2","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19593","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_12","alias_value":"OUR2IJR5WZWX","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_16","alias_value":"OUR2IJR5WZWXEX4U","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_8","alias_value":"OUR2IJR5","created_at":"2026-07-05T11:18:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OUR2IJR5WZWXEX4U6UCBRDITAN","target":"record","payload":{"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"},"canonical_sha256":"7523a4263db66d725f94f504188d13035cea10a28fe280c90543cbfe8aa65ea5","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"},"source_kind":"arxiv","source_id":"2406.19593","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O9trC9kx2p2bw9p3HJqBlvBfCUQUFxFLFXMzdYN5hngRKOM78zupV7ouaOPhOJXCC0vJuCTzWzySleE2Uz1yCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:28:33.142345Z"},"content_sha256":"dc267e136e3c68c999443bbc32217de224dbdf658427e22534f49cd7528e4aa8","schema_version":"1.0","event_id":"sha256:dc267e136e3c68c999443bbc32217de224dbdf658427e22534f49cd7528e4aa8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OUR2IJR5WZWXEX4U6UCBRDITAN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YV7PvJHuqiwVZop8lFdYXu+WeyRxBCaBwStNwL7/izUInbK3LEq0TPQMfSCN2+kbdm6XsqwkpuCRMw29GNq0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:28:33.142721Z"},"content_sha256":"79eb037d0f935ddb252a15ed9d81271eb6e5580c6975647153bea37aa37e9cc0","schema_version":"1.0","event_id":"sha256:79eb037d0f935ddb252a15ed9d81271eb6e5580c6975647153bea37aa37e9cc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/bundle.json","state_url":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T10:28:33Z","links":{"resolver":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN","bundle":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/bundle.json","state":"https://pith.science/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUR2IJR5WZWXEX4U6UCBRDITAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OUR2IJR5WZWXEX4U6UCBRDITAN","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":"d32f79b9c5bc277bcc0bd9328f5ea3d5b3fd8e42f0889d518e3cfaf6b80e813d","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T01:14:43Z","title_canon_sha256":"120b096fe9b68c5ed4582c77105a1a89213c4b942f47c8fbec88cb4d09da7a2c"},"schema_version":"1.0","source":{"id":"2406.19593","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19593","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19593v2","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19593","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_12","alias_value":"OUR2IJR5WZWX","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_16","alias_value":"OUR2IJR5WZWXEX4U","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_8","alias_value":"OUR2IJR5","created_at":"2026-07-05T11:18:39Z"}],"graph_snapshots":[{"event_id":"sha256:79eb037d0f935ddb252a15ed9d81271eb6e5580c6975647153bea37aa37e9cc0","target":"graph","created_at":"2026-07-05T11:18:39Z","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/2406.19593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kris W Pan, Man Luo, Phillip Howard, Tien Pei Chou, Vasudev Lal, Xin Su","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T01:14:43Z","title":"SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19593","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:dc267e136e3c68c999443bbc32217de224dbdf658427e22534f49cd7528e4aa8","target":"record","created_at":"2026-07-05T11:18:39Z","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":"d32f79b9c5bc277bcc0bd9328f5ea3d5b3fd8e42f0889d518e3cfaf6b80e813d","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T01:14:43Z","title_canon_sha256":"120b096fe9b68c5ed4582c77105a1a89213c4b942f47c8fbec88cb4d09da7a2c"},"schema_version":"1.0","source":{"id":"2406.19593","kind":"arxiv","version":2}},"canonical_sha256":"7523a4263db66d725f94f504188d13035cea10a28fe280c90543cbfe8aa65ea5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7523a4263db66d725f94f504188d13035cea10a28fe280c90543cbfe8aa65ea5","first_computed_at":"2026-07-05T11:18:39.122368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:39.122368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KoBmBuuTP2F933AonPb0vhb+FHPqMybagGKPie4/q0IjGxGoE5GSXCzTLxNcu3tjWDaivqWVUgd+tbJ8/n6kBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:39.122806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19593","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc267e136e3c68c999443bbc32217de224dbdf658427e22534f49cd7528e4aa8","sha256:79eb037d0f935ddb252a15ed9d81271eb6e5580c6975647153bea37aa37e9cc0"],"state_sha256":"db39c4a4b5d3bb6967fe652f34f8ebbbd49c5702105a4d1bf91d90a7f40050c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sw0iW9UJR8FwrALsCvvQh2rAQXbLeobrY33vPyQst3H9tN1TzlI4QvZ3Y24W7RVF/BYxPOHV/QwmEB06QVJeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:28:33.144648Z","bundle_sha256":"df1bbf9c8be58331f86229082ef070a421aa9cfcaf6096d0a94d962756828ed4"}}