{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JMQ2GASYN625KFTYM5R72I3WUM","short_pith_number":"pith:JMQ2GASY","schema_version":"1.0","canonical_sha256":"4b21a302586fb5d516786763fd2376a30b1c8396bd907275d5140e54ff25cebd","source":{"kind":"arxiv","id":"2306.04387","version":2},"attestation_state":"computed","paper":{"title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2023-06-07T12:35:37Z","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"},"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":"2306.04387","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T12:35:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"98ca6caad83b7bda63f9f7711930accbd560f87a35694f631401651a39c1a42a","abstract_canon_sha256":"7de6a85bf0d671cb30fa0eb8894efca522cdbf809ef196245aa1598396b863ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:52.972047Z","signature_b64":"04mBemjVC8hfJlycVqvutOg4UCJR0MYPGn8236pB3z17Yxb1dZNex982MyRLgZznTuS25AeFGN0nvMXmtVe/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b21a302586fb5d516786763fd2376a30b1c8396bd907275d5140e54ff25cebd","last_reissued_at":"2026-07-05T06:18:52.971605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:52.971605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2023-06-07T12:35:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04387","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/2306.04387/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":"2306.04387","created_at":"2026-07-05T06:18:52.971664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04387v2","created_at":"2026-07-05T06:18:52.971664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04387","created_at":"2026-07-05T06:18:52.971664+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMQ2GASYN625","created_at":"2026-07-05T06:18:52.971664+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMQ2GASYN625KFTY","created_at":"2026-07-05T06:18:52.971664+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMQ2GASY","created_at":"2026-07-05T06:18:52.971664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":282,"is_internal_anchor":false},{"citing_arxiv_id":"2311.17005","citing_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2305.17926","citing_title":"Large Language Models are not Fair Evaluators","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2402.11411","citing_title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2311.01378","citing_title":"Vision-Language Foundation Models as Effective Robot Imitators","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16502","citing_title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2305.03726","citing_title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2312.08935","citing_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08212","citing_title":"Vision-Language Foundation Models for Comprehensive Automated Pavement Condition Assessment","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM","json":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM.json","graph_json":"https://pith.science/api/pith-number/JMQ2GASYN625KFTYM5R72I3WUM/graph.json","events_json":"https://pith.science/api/pith-number/JMQ2GASYN625KFTYM5R72I3WUM/events.json","paper":"https://pith.science/paper/JMQ2GASY"},"agent_actions":{"view_html":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM","download_json":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM.json","view_paper":"https://pith.science/paper/JMQ2GASY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04387&json=true","fetch_graph":"https://pith.science/api/pith-number/JMQ2GASYN625KFTYM5R72I3WUM/graph.json","fetch_events":"https://pith.science/api/pith-number/JMQ2GASYN625KFTYM5R72I3WUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM/action/storage_attestation","attest_author":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM/action/author_attestation","sign_citation":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM/action/citation_signature","submit_replication":"https://pith.science/pith/JMQ2GASYN625KFTYM5R72I3WUM/action/replication_record"}},"created_at":"2026-07-05T06:18:52.971664+00:00","updated_at":"2026-07-05T06:18:52.971664+00:00"}