{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RSIDTLTR4IX7YB2JJEYIMKPRAX","short_pith_number":"pith:RSIDTLTR","schema_version":"1.0","canonical_sha256":"8c9039ae71e22ffc074949308629f105c411f5a371f8eaaa565a70629241476e","source":{"kind":"arxiv","id":"2406.11271","version":5},"attestation_state":"computed","paper":{"title":"MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anas Awadalla, Caiming Xiong, Etash Kumar Guha, Hannah Lee, Le Xue, Ludwig Schmidt, Manli Shu, Matt Jordan, Mohamed Awadalla, Oscar Lo, Ran Xu, Sheng Shen, Silvio Savarese, Yejin Choi","submitted_at":"2024-06-17T07:21:36Z","abstract_excerpt":"Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs). Despite the rapid progression of open-source LMMs, there remains a pronounced scarcity of large-scale, diverse open-source multimodal interleaved datasets. In response, we introduce MINT-1T, the most extensive and diverse open-source Multimodal INTerleaved dataset to date. MINT-1T comprises one trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sour"},"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":"2406.11271","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T07:21:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0fd7c753712c7c28b6f104304fa7e75c964a1dcbd41c32476f5c14157e5500a2","abstract_canon_sha256":"0e15fc15c5dce975b37489b1bfc909ead0d1de603a2f47fc534faf398c6ee448"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:51.621086Z","signature_b64":"oL2XyxIwf/X0CGfffRtLGgZUQRJTfQ6Dob1l7I1LFBEDxq9IsIj8uIfDVRdJ3U+ZbREU1BrvR6YR3wdu2LSEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c9039ae71e22ffc074949308629f105c411f5a371f8eaaa565a70629241476e","last_reissued_at":"2026-07-05T09:28:51.620599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:51.620599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anas Awadalla, Caiming Xiong, Etash Kumar Guha, Hannah Lee, Le Xue, Ludwig Schmidt, Manli Shu, Matt Jordan, Mohamed Awadalla, Oscar Lo, Ran Xu, Sheng Shen, Silvio Savarese, Yejin Choi","submitted_at":"2024-06-17T07:21:36Z","abstract_excerpt":"Multimodal interleaved datasets featuring free-form interleaved sequences of images and text are crucial for training frontier large multimodal models (LMMs). Despite the rapid progression of open-source LMMs, there remains a pronounced scarcity of large-scale, diverse open-source multimodal interleaved datasets. In response, we introduce MINT-1T, the most extensive and diverse open-source Multimodal INTerleaved dataset to date. MINT-1T comprises one trillion text tokens and 3.4 billion images, a 10x scale-up from existing open-source datasets. Additionally, we include previously untapped sour"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11271","kind":"arxiv","version":5},"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/2406.11271/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":"2406.11271","created_at":"2026-07-05T09:28:51.620655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11271v5","created_at":"2026-07-05T09:28:51.620655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11271","created_at":"2026-07-05T09:28:51.620655+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSIDTLTR4IX7","created_at":"2026-07-05T09:28:51.620655+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSIDTLTR4IX7YB2J","created_at":"2026-07-05T09:28:51.620655+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSIDTLTR","created_at":"2026-07-05T09:28:51.620655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00958","citing_title":"2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX","json":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX.json","graph_json":"https://pith.science/api/pith-number/RSIDTLTR4IX7YB2JJEYIMKPRAX/graph.json","events_json":"https://pith.science/api/pith-number/RSIDTLTR4IX7YB2JJEYIMKPRAX/events.json","paper":"https://pith.science/paper/RSIDTLTR"},"agent_actions":{"view_html":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX","download_json":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX.json","view_paper":"https://pith.science/paper/RSIDTLTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11271&json=true","fetch_graph":"https://pith.science/api/pith-number/RSIDTLTR4IX7YB2JJEYIMKPRAX/graph.json","fetch_events":"https://pith.science/api/pith-number/RSIDTLTR4IX7YB2JJEYIMKPRAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX/action/storage_attestation","attest_author":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX/action/author_attestation","sign_citation":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX/action/citation_signature","submit_replication":"https://pith.science/pith/RSIDTLTR4IX7YB2JJEYIMKPRAX/action/replication_record"}},"created_at":"2026-07-05T09:28:51.620655+00:00","updated_at":"2026-07-05T09:28:51.620655+00:00"}