{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QFA7IZPAOHACHYAWGLCZGGFLYW","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":"28d3e4ba6e7c335fa241189c4c88050e14592dccbefe856df0541ed9d6154ef8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:55:22Z","title_canon_sha256":"c5597d2847b634975868722d89f06f2d48f276ca7ca42de505ea375182c155f7"},"schema_version":"1.0","source":{"id":"2407.15838","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15838","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15838v2","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15838","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"pith_short_12","alias_value":"QFA7IZPAOHAC","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"pith_short_16","alias_value":"QFA7IZPAOHACHYAW","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"pith_short_8","alias_value":"QFA7IZPA","created_at":"2026-07-05T09:49:08Z"}],"graph_snapshots":[{"event_id":"sha256:8d2a2a151baffdbee02f0bb73c5822661548f0d2a47ec7f99453cf459221360b","target":"graph","created_at":"2026-07-05T09:49:08Z","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/2407.15838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:55:22Z","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15838","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:a118096994c2afa651d4725900dc1a11fbcf57e8028e8643d0770c16c71cb344","target":"record","created_at":"2026-07-05T09:49:08Z","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":"28d3e4ba6e7c335fa241189c4c88050e14592dccbefe856df0541ed9d6154ef8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:55:22Z","title_canon_sha256":"c5597d2847b634975868722d89f06f2d48f276ca7ca42de505ea375182c155f7"},"schema_version":"1.0","source":{"id":"2407.15838","kind":"arxiv","version":2}},"canonical_sha256":"8141f465e071c023e01632c59318abc59a00b53a7df690c972c1c9158ed4e468","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8141f465e071c023e01632c59318abc59a00b53a7df690c972c1c9158ed4e468","first_computed_at":"2026-07-05T09:49:08.380354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:08.380354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qpJ7sKDMhuD/oTYdFbS7CBwxOjXuLT1dIJFH2wQBemkGBZxBg6M3QalCSuvLZQ0eFTq2ZXpMUbAyVF4KESnFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:08.380850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15838","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a118096994c2afa651d4725900dc1a11fbcf57e8028e8643d0770c16c71cb344","sha256:8d2a2a151baffdbee02f0bb73c5822661548f0d2a47ec7f99453cf459221360b"],"state_sha256":"c11bf0ec4080edbd0e150d5f6c20c117af3abf81afcd8e24cdc0be12bf6a24a9"}