{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QBYGIDJFWPIESBY6IM5WRY2ZAR","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":"12912e695cfb4eb001350d50d1ea567f6fb3ad2eedfe300ea88ed2030f8a8b9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T11:21:05Z","title_canon_sha256":"37a419d58fea8e0628175a306689f80cef54e7f5498f14065f36032e126e495a"},"schema_version":"1.0","source":{"id":"2308.12714","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12714","created_at":"2026-07-05T07:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12714v3","created_at":"2026-07-05T07:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12714","created_at":"2026-07-05T07:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"QBYGIDJFWPIE","created_at":"2026-07-05T07:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"QBYGIDJFWPIESBY6","created_at":"2026-07-05T07:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"QBYGIDJF","created_at":"2026-07-05T07:40:56Z"}],"graph_snapshots":[{"event_id":"sha256:28b0f27ea36ec38a366e7bd061d407a7e2d5cd799a0ead3fa37823384142e0fb","target":"graph","created_at":"2026-07-05T07:40:56Z","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/2308.12714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a challenge. The current leading paradigm, such as LLaVA, relies on language-only GPT-4 to generate data, which requires pre-annotated image captions and detection bounding boxes, suffering from understanding image details. A practical solution to this problem would be to utilize the available multimodal large language models (MLLMs) to generate instruction data","authors_text":"Bin Wang, Conghui He, Fan Wu, Huaping Zhong, Jiahui Peng, Jiaqi Wang, Pan Zhang, Weijia Li, Wei Li, Xiao Han, Xiaoyi Dong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T11:21:05Z","title":"VIGC: Visual Instruction Generation and Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12714","kind":"arxiv","version":3},"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":"sha256:8ac79781db4407c436f7d15fbb01e34b9b610e801cb7c02471b2afe94e58296b","target":"record","created_at":"2026-07-05T07:40:56Z","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":"12912e695cfb4eb001350d50d1ea567f6fb3ad2eedfe300ea88ed2030f8a8b9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T11:21:05Z","title_canon_sha256":"37a419d58fea8e0628175a306689f80cef54e7f5498f14065f36032e126e495a"},"schema_version":"1.0","source":{"id":"2308.12714","kind":"arxiv","version":3}},"canonical_sha256":"8070640d25b3d049071e433b68e359044d298dd6ffc13241bad76ac49c99589d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8070640d25b3d049071e433b68e359044d298dd6ffc13241bad76ac49c99589d","first_computed_at":"2026-07-05T07:40:56.253320Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:56.253320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wWFHy633C9Q8PE9ybFakT73wcthU+Xibod63KocINqcZCap943J0jnu63MK7TSpVDEhbUFGfJe45RlbaJg21Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:56.253759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12714","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ac79781db4407c436f7d15fbb01e34b9b610e801cb7c02471b2afe94e58296b","sha256:28b0f27ea36ec38a366e7bd061d407a7e2d5cd799a0ead3fa37823384142e0fb"],"state_sha256":"34a1b5f987408727754e9857312c4346027cd843bacf5691e5b5c6704f198bbd"}