{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QBYGIDJFWPIESBY6IM5WRY2ZAR","short_pith_number":"pith:QBYGIDJF","schema_version":"1.0","canonical_sha256":"8070640d25b3d049071e433b68e359044d298dd6ffc13241bad76ac49c99589d","source":{"kind":"arxiv","id":"2308.12714","version":3},"attestation_state":"computed","paper":{"title":"VIGC: Visual Instruction Generation and Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Fan Wu, Huaping Zhong, Jiahui Peng, Jiaqi Wang, Pan Zhang, Weijia Li, Wei Li, Xiao Han, Xiaoyi Dong","submitted_at":"2023-08-24T11:21:05Z","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"},"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":"2308.12714","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-24T11:21:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37a419d58fea8e0628175a306689f80cef54e7f5498f14065f36032e126e495a","abstract_canon_sha256":"12912e695cfb4eb001350d50d1ea567f6fb3ad2eedfe300ea88ed2030f8a8b9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:56.253759Z","signature_b64":"wWFHy633C9Q8PE9ybFakT73wcthU+Xibod63KocINqcZCap943J0jnu63MK7TSpVDEhbUFGfJe45RlbaJg21Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8070640d25b3d049071e433b68e359044d298dd6ffc13241bad76ac49c99589d","last_reissued_at":"2026-07-05T07:40:56.253320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:56.253320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIGC: Visual Instruction Generation and Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Fan Wu, Huaping Zhong, Jiahui Peng, Jiaqi Wang, Pan Zhang, Weijia Li, Wei Li, Xiao Han, Xiaoyi Dong","submitted_at":"2023-08-24T11:21:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12714","kind":"arxiv","version":3},"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/2308.12714/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":"2308.12714","created_at":"2026-07-05T07:40:56.253380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12714v3","created_at":"2026-07-05T07:40:56.253380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12714","created_at":"2026-07-05T07:40:56.253380+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBYGIDJFWPIE","created_at":"2026-07-05T07:40:56.253380+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBYGIDJFWPIESBY6","created_at":"2026-07-05T07:40:56.253380+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBYGIDJF","created_at":"2026-07-05T07:40:56.253380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.03766","citing_title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16839","citing_title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2310.14566","citing_title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":161,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR","json":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR.json","graph_json":"https://pith.science/api/pith-number/QBYGIDJFWPIESBY6IM5WRY2ZAR/graph.json","events_json":"https://pith.science/api/pith-number/QBYGIDJFWPIESBY6IM5WRY2ZAR/events.json","paper":"https://pith.science/paper/QBYGIDJF"},"agent_actions":{"view_html":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR","download_json":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR.json","view_paper":"https://pith.science/paper/QBYGIDJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12714&json=true","fetch_graph":"https://pith.science/api/pith-number/QBYGIDJFWPIESBY6IM5WRY2ZAR/graph.json","fetch_events":"https://pith.science/api/pith-number/QBYGIDJFWPIESBY6IM5WRY2ZAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR/action/storage_attestation","attest_author":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR/action/author_attestation","sign_citation":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR/action/citation_signature","submit_replication":"https://pith.science/pith/QBYGIDJFWPIESBY6IM5WRY2ZAR/action/replication_record"}},"created_at":"2026-07-05T07:40:56.253380+00:00","updated_at":"2026-07-05T07:40:56.253380+00:00"}