{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QFA7IZPAOHACHYAWGLCZGGFLYW","short_pith_number":"pith:QFA7IZPA","schema_version":"1.0","canonical_sha256":"8141f465e071c023e01632c59318abc59a00b53a7df690c972c1c9158ed4e468","source":{"kind":"arxiv","id":"2407.15838","version":2},"attestation_state":"computed","paper":{"title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tian, Jifeng Dai, Lewei Lu, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yangzhou Liu, Yue Cao, Yu Qiao, Zhangwei Gao, Zhe Chen","submitted_at":"2024-07-22T17:55:22Z","abstract_excerpt":"Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of Vision Large Language Models (VLLMs). However, existing visual instruction tuning datasets include the following limitations: (1) Instruction annotation quality: despite existing VLLMs exhibiting strong performance, instructions generated by those advanced VLLMs may still suffer from inaccuracies, such as hallucinations. (2) Instructions and image diversity: the limited range of instruction types and the lack of diversity in image data may impact the model's ability to generate diversified and c"},"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":"2407.15838","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:55:22Z","cross_cats_sorted":[],"title_canon_sha256":"c5597d2847b634975868722d89f06f2d48f276ca7ca42de505ea375182c155f7","abstract_canon_sha256":"28d3e4ba6e7c335fa241189c4c88050e14592dccbefe856df0541ed9d6154ef8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:08.380850Z","signature_b64":"qpJ7sKDMhuD/oTYdFbS7CBwxOjXuLT1dIJFH2wQBemkGBZxBg6M3QalCSuvLZQ0eFTq2ZXpMUbAyVF4KESnFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8141f465e071c023e01632c59318abc59a00b53a7df690c972c1c9158ed4e468","last_reissued_at":"2026-07-05T09:49:08.380354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:08.380354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tian, Jifeng Dai, Lewei Lu, Tong Lu, Weiyun Wang, Wenhai Wang, Xizhou Zhu, Yangzhou Liu, Yue Cao, Yu Qiao, Zhangwei Gao, Zhe Chen","submitted_at":"2024-07-22T17:55:22Z","abstract_excerpt":"Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of Vision Large Language Models (VLLMs). However, existing visual instruction tuning datasets include the following limitations: (1) Instruction annotation quality: despite existing VLLMs exhibiting strong performance, instructions generated by those advanced VLLMs may still suffer from inaccuracies, such as hallucinations. (2) Instructions and image diversity: the limited range of instruction types and the lack of diversity in image data may impact the model's ability to generate diversified and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15838","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/2407.15838/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":"2407.15838","created_at":"2026-07-05T09:49:08.380415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15838v2","created_at":"2026-07-05T09:49:08.380415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15838","created_at":"2026-07-05T09:49:08.380415+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFA7IZPAOHAC","created_at":"2026-07-05T09:49:08.380415+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFA7IZPAOHACHYAW","created_at":"2026-07-05T09:49:08.380415+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFA7IZPA","created_at":"2026-07-05T09:49:08.380415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.04468","citing_title":"NVILA: Efficient Frontier Visual Language Models","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10442","citing_title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":155,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW","json":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW.json","graph_json":"https://pith.science/api/pith-number/QFA7IZPAOHACHYAWGLCZGGFLYW/graph.json","events_json":"https://pith.science/api/pith-number/QFA7IZPAOHACHYAWGLCZGGFLYW/events.json","paper":"https://pith.science/paper/QFA7IZPA"},"agent_actions":{"view_html":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW","download_json":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW.json","view_paper":"https://pith.science/paper/QFA7IZPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15838&json=true","fetch_graph":"https://pith.science/api/pith-number/QFA7IZPAOHACHYAWGLCZGGFLYW/graph.json","fetch_events":"https://pith.science/api/pith-number/QFA7IZPAOHACHYAWGLCZGGFLYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW/action/storage_attestation","attest_author":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW/action/author_attestation","sign_citation":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW/action/citation_signature","submit_replication":"https://pith.science/pith/QFA7IZPAOHACHYAWGLCZGGFLYW/action/replication_record"}},"created_at":"2026-07-05T09:49:08.380415+00:00","updated_at":"2026-07-05T09:49:08.380415+00:00"}