{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R5QWLZJHBEA6WBP266YQS7IQFP","short_pith_number":"pith:R5QWLZJH","schema_version":"1.0","canonical_sha256":"8f6165e5270901eb05faf7b1097d102bd04dc03284c534c799898dd93c4b3549","source":{"kind":"arxiv","id":"2306.16527","version":2},"attestation_state":"computed","paper":{"title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Alexander M. Rush, Amanpreet Singh, Anton Lozhkov, Douwe Kiela, Hugo Lauren\\c{c}on, L\\'eo Tronchon, Lucile Saulnier, Matthieu Cord, Siddharth Karamcheti, Stas Bekman, Thomas Wang, Victor Sanh","submitted_at":"2023-06-21T14:01:01Z","abstract_excerpt":"Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released, and the collection process has not been fully specified. We introduce the OBELICS dataset, an open web-scale filtered dataset of interleaved image-text documents comprising 141 million web pages extracted from Common Crawl, 353 million associated images, and 115 billion text tokens. We describe the dataset creation process, present comprehensive filtering r"},"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":"2306.16527","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-21T14:01:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fb93f3001efb87a0649bba334f269d74f616d4298e9141dab6fedb73c99d0967","abstract_canon_sha256":"d05aaf4ef49f0214a8dbc2e33f2347831daec2993f20956844c03a6dc0926774"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:03.632643Z","signature_b64":"k/a/HKmY08XUCM1GELyDWXnEJiOIJCTt6nugOdVEr4sEBcmJw+zEcQD6u2a2DQEjhS1xH9TjTPQQexTHFuUvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f6165e5270901eb05faf7b1097d102bd04dc03284c534c799898dd93c4b3549","last_reissued_at":"2026-07-05T06:43:03.631729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:03.631729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Alexander M. Rush, Amanpreet Singh, Anton Lozhkov, Douwe Kiela, Hugo Lauren\\c{c}on, L\\'eo Tronchon, Lucile Saulnier, Matthieu Cord, Siddharth Karamcheti, Stas Bekman, Thomas Wang, Victor Sanh","submitted_at":"2023-06-21T14:01:01Z","abstract_excerpt":"Large multimodal models trained on natural documents, which interleave images and text, outperform models trained on image-text pairs on various multimodal benchmarks. However, the datasets used to train these models have not been released, and the collection process has not been fully specified. We introduce the OBELICS dataset, an open web-scale filtered dataset of interleaved image-text documents comprising 141 million web pages extracted from Common Crawl, 353 million associated images, and 115 billion text tokens. We describe the dataset creation process, present comprehensive filtering r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16527","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/2306.16527/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":"2306.16527","created_at":"2026-07-05T06:43:03.632093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.16527v2","created_at":"2026-07-05T06:43:03.632093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16527","created_at":"2026-07-05T06:43:03.632093+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5QWLZJHBEA6","created_at":"2026-07-05T06:43:03.632093+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5QWLZJHBEA6WBP2","created_at":"2026-07-05T06:43:03.632093+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5QWLZJH","created_at":"2026-07-05T06:43:03.632093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07639","citing_title":"MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2402.03766","citing_title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2312.16886","citing_title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2309.14525","citing_title":"Aligning Large Multimodal Models with Factually Augmented RLHF","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2311.10122","citing_title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2308.01390","citing_title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07726","citing_title":"PaliGemma: A versatile 3B VLM for transfer","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12508","citing_title":"From Attenuation to Attention: Variational Information Flow Manipulation for Fine-Grained Visual Perception","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2405.09818","citing_title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP","json":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP.json","graph_json":"https://pith.science/api/pith-number/R5QWLZJHBEA6WBP266YQS7IQFP/graph.json","events_json":"https://pith.science/api/pith-number/R5QWLZJHBEA6WBP266YQS7IQFP/events.json","paper":"https://pith.science/paper/R5QWLZJH"},"agent_actions":{"view_html":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP","download_json":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP.json","view_paper":"https://pith.science/paper/R5QWLZJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.16527&json=true","fetch_graph":"https://pith.science/api/pith-number/R5QWLZJHBEA6WBP266YQS7IQFP/graph.json","fetch_events":"https://pith.science/api/pith-number/R5QWLZJHBEA6WBP266YQS7IQFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/action/storage_attestation","attest_author":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/action/author_attestation","sign_citation":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/action/citation_signature","submit_replication":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/action/replication_record"}},"created_at":"2026-07-05T06:43:03.632093+00:00","updated_at":"2026-07-05T06:43:03.632093+00:00"}