{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:R5QWLZJHBEA6WBP266YQS7IQFP","short_pith_number":"pith:R5QWLZJH","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"},"canonical_sha256":"8f6165e5270901eb05faf7b1097d102bd04dc03284c534c799898dd93c4b3549","source":{"kind":"arxiv","id":"2306.16527","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16527","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16527v2","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16527","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"R5QWLZJHBEA6","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_16","alias_value":"R5QWLZJHBEA6WBP2","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_8","alias_value":"R5QWLZJH","created_at":"2026-07-05T06:43:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:R5QWLZJHBEA6WBP266YQS7IQFP","target":"record","payload":{"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"},"canonical_sha256":"8f6165e5270901eb05faf7b1097d102bd04dc03284c534c799898dd93c4b3549","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"},"source_kind":"arxiv","source_id":"2306.16527","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDqqIWsCQ0li7lTRtDxtnxlHeSl/14AKGtGZ9ejz43BH4FPqytC11XHBpxF7bXNLlAHPe1jTEgJC1REL/xFUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:03:36.706410Z"},"content_sha256":"55a7772b13710dc1ceca91014c95300c8d83248586bc064a0e249a2286ce73f8","schema_version":"1.0","event_id":"sha256:55a7772b13710dc1ceca91014c95300c8d83248586bc064a0e249a2286ce73f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:R5QWLZJHBEA6WBP266YQS7IQFP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOhVupxGuezMvwbC8Fo6L/Q7ck+JLNB7dVTG7SWMGh9oPOMHXY6OR/klSpJQuql0Yg8enk3ugO1AtV/tD6jpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:03:36.707415Z"},"content_sha256":"2d07564c0404109455d791813b3ba89866405fc8d8bd17dfd6595a561dd7de66","schema_version":"1.0","event_id":"sha256:2d07564c0404109455d791813b3ba89866405fc8d8bd17dfd6595a561dd7de66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/bundle.json","state_url":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5QWLZJHBEA6WBP266YQS7IQFP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T10:03:36Z","links":{"resolver":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP","bundle":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/bundle.json","state":"https://pith.science/pith/R5QWLZJHBEA6WBP266YQS7IQFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5QWLZJHBEA6WBP266YQS7IQFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R5QWLZJHBEA6WBP266YQS7IQFP","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":"d05aaf4ef49f0214a8dbc2e33f2347831daec2993f20956844c03a6dc0926774","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-21T14:01:01Z","title_canon_sha256":"fb93f3001efb87a0649bba334f269d74f616d4298e9141dab6fedb73c99d0967"},"schema_version":"1.0","source":{"id":"2306.16527","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16527","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16527v2","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16527","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"R5QWLZJHBEA6","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_16","alias_value":"R5QWLZJHBEA6WBP2","created_at":"2026-07-05T06:43:03Z"},{"alias_kind":"pith_short_8","alias_value":"R5QWLZJH","created_at":"2026-07-05T06:43:03Z"}],"graph_snapshots":[{"event_id":"sha256:2d07564c0404109455d791813b3ba89866405fc8d8bd17dfd6595a561dd7de66","target":"graph","created_at":"2026-07-05T06:43:03Z","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/2306.16527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-21T14:01:01Z","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16527","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":"sha256:55a7772b13710dc1ceca91014c95300c8d83248586bc064a0e249a2286ce73f8","target":"record","created_at":"2026-07-05T06:43:03Z","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":"d05aaf4ef49f0214a8dbc2e33f2347831daec2993f20956844c03a6dc0926774","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-06-21T14:01:01Z","title_canon_sha256":"fb93f3001efb87a0649bba334f269d74f616d4298e9141dab6fedb73c99d0967"},"schema_version":"1.0","source":{"id":"2306.16527","kind":"arxiv","version":2}},"canonical_sha256":"8f6165e5270901eb05faf7b1097d102bd04dc03284c534c799898dd93c4b3549","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f6165e5270901eb05faf7b1097d102bd04dc03284c534c799898dd93c4b3549","first_computed_at":"2026-07-05T06:43:03.631729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:03.631729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k/a/HKmY08XUCM1GELyDWXnEJiOIJCTt6nugOdVEr4sEBcmJw+zEcQD6u2a2DQEjhS1xH9TjTPQQexTHFuUvAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:03.632643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.16527","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55a7772b13710dc1ceca91014c95300c8d83248586bc064a0e249a2286ce73f8","sha256:2d07564c0404109455d791813b3ba89866405fc8d8bd17dfd6595a561dd7de66"],"state_sha256":"81e3dd74ddfe3af4fd7cd3826b44e34e83b9395cd8150950f77244752fa9923d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PiL9tHUyGuKvVlbCwVI6Y9BmjBtfF2MLblsxMQ9t8LD/neRi6nznJZHoZbZZHQpV7TdEOnDN7qOli5AF3bfEBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:03:36.713921Z","bundle_sha256":"5882fd061098fab6393b61f4120ba86e4cb47ed88560ed5bdf5b15e3cd6555c4"}}