{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JMQ2GASYN625KFTYM5R72I3WUM","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":"7de6a85bf0d671cb30fa0eb8894efca522cdbf809ef196245aa1598396b863ea","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T12:35:37Z","title_canon_sha256":"98ca6caad83b7bda63f9f7711930accbd560f87a35694f631401651a39c1a42a"},"schema_version":"1.0","source":{"id":"2306.04387","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04387","created_at":"2026-07-05T06:18:52Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04387v2","created_at":"2026-07-05T06:18:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04387","created_at":"2026-07-05T06:18:52Z"},{"alias_kind":"pith_short_12","alias_value":"JMQ2GASYN625","created_at":"2026-07-05T06:18:52Z"},{"alias_kind":"pith_short_16","alias_value":"JMQ2GASYN625KFTY","created_at":"2026-07-05T06:18:52Z"},{"alias_kind":"pith_short_8","alias_value":"JMQ2GASY","created_at":"2026-07-05T06:18:52Z"}],"graph_snapshots":[{"event_id":"sha256:f9cdd5ef16c989e8e5df8ee24b8b343b7d7132616d57afbf8e4b6230e2013316","target":"graph","created_at":"2026-07-05T06:18:52Z","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/2306.04387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning has significantly advanced large language models (LLMs) such as ChatGPT, enabling them to align with human instructions across diverse tasks. However, progress in open vision-language models (VLMs) has been limited due to the scarcity of high-quality instruction datasets. To tackle this challenge and promote research in the vision-language field, we introduce the Multi-Modal, Multilingual Instruction Tuning (M$^3$IT) dataset, designed to optimize VLM alignment with human instructions. Our M$^3$IT dataset comprises 40 carefully curated datasets, including 2.4 million instance","authors_text":"Jingjing Xu, Lei Li, Liang Chen, Lingpeng Kong, Mukai Li, Peiyi Wang, Qi Liu, Shicheng Li, Shuhuai Ren, Xu Sun, Yazheng Yang, Yuwei Yin","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T12:35:37Z","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04387","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":"sha256:09a6e01fe4d974161b7403fe1e451c9c09ac35b10b668b99ab9da8e53fa4a08c","target":"record","created_at":"2026-07-05T06:18:52Z","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":"7de6a85bf0d671cb30fa0eb8894efca522cdbf809ef196245aa1598396b863ea","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T12:35:37Z","title_canon_sha256":"98ca6caad83b7bda63f9f7711930accbd560f87a35694f631401651a39c1a42a"},"schema_version":"1.0","source":{"id":"2306.04387","kind":"arxiv","version":2}},"canonical_sha256":"4b21a302586fb5d516786763fd2376a30b1c8396bd907275d5140e54ff25cebd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b21a302586fb5d516786763fd2376a30b1c8396bd907275d5140e54ff25cebd","first_computed_at":"2026-07-05T06:18:52.971605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:52.971605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"04mBemjVC8hfJlycVqvutOg4UCJR0MYPGn8236pB3z17Yxb1dZNex982MyRLgZznTuS25AeFGN0nvMXmtVe/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:52.972047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04387","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09a6e01fe4d974161b7403fe1e451c9c09ac35b10b668b99ab9da8e53fa4a08c","sha256:f9cdd5ef16c989e8e5df8ee24b8b343b7d7132616d57afbf8e4b6230e2013316"],"state_sha256":"7f2bc37ca4860a89908958ce509999fd963c3a477c5772531e1729a3fd975c55"}