{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UJAICKRPBMMFRBDCKOVJ6PVDNW","short_pith_number":"pith:UJAICKRP","canonical_record":{"source":{"id":"2304.14108","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T11:37:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2c8c482ae4d53fb18c4964d459993dac1ccec497a052df01f536a1029aa6bb00","abstract_canon_sha256":"25f261d185a33dd5947f1e8d2550fb79f1877531e49cc16153a24e6aa8002e67"},"schema_version":"1.0"},"canonical_sha256":"a240812a2f0b1858846253aa9f3ea36db7ba1b6ec3f648d36b217e50301cf6a9","source":{"kind":"arxiv","id":"2304.14108","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14108","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14108v5","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14108","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"UJAICKRPBMMF","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"UJAICKRPBMMFRBDC","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"UJAICKRP","created_at":"2026-07-05T07:03:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UJAICKRPBMMFRBDCKOVJ6PVDNW","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14108","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T11:37:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2c8c482ae4d53fb18c4964d459993dac1ccec497a052df01f536a1029aa6bb00","abstract_canon_sha256":"25f261d185a33dd5947f1e8d2550fb79f1877531e49cc16153a24e6aa8002e67"},"schema_version":"1.0"},"canonical_sha256":"a240812a2f0b1858846253aa9f3ea36db7ba1b6ec3f648d36b217e50301cf6a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:10.064774Z","signature_b64":"oMqNYsCKBQFXytnNRrP+kZfUhrwR/XbBEsDE69OyJ9auZoWJjZ1y8403U6FxO/V8eBmt099amYU/5OtAlb17DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a240812a2f0b1858846253aa9f3ea36db7ba1b6ec3f648d36b217e50301cf6a9","last_reissued_at":"2026-07-05T07:03:10.064273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:10.064273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14108","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0PGPun1LsdxtPIMPlldcLTGm4cbnusp5luMlNc1+PPpLyLQVuFf331iMEYmNMOJwc1yQHRkhYAUsgshNZCXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:10:37.252671Z"},"content_sha256":"4e28c632b3fbd070df052307405c08f0bb55cd8a635621663abe451cf1954625","schema_version":"1.0","event_id":"sha256:4e28c632b3fbd070df052307405c08f0bb55cd8a635621663abe451cf1954625"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UJAICKRPBMMFRBDCKOVJ6PVDNW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DataComp: In search of the next generation of multimodal datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Ratner, Alex Dimakis, Alex Fang, Ali Farhadi, Dhruba Ghosh, Eyal Orgad, Gabriel Ilharco, Georgios Smyrnis, Giannis Daras, Hannaneh Hajishirzi, Jenia Jitsev, Jieyu Zhang, Jonathan Hayase, Kalyani Marathe, Ludwig Schmidt, Mehdi Cherti, Mitchell Wortsman, Olga Saukh, Pang Wei Koh, Rahim Entezari, Ranjay Krishna, Richard Vencu, Romain Beaumont, Ryan Marten, Samir Yitzhak Gadre, Sarah Pratt, Sewoong Oh, Shuran Song, Stephen Mussmann, Thao Nguyen, Vaishaal Shankar, Vivek Ramanujan, Yair Carmon, Yonatan Bitton","submitted_at":"2023-04-27T11:37:18Z","abstract_excerpt":"Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the ML ecosystem, we introduce DataComp, a testbed for dataset experiments centered around a new candidate pool of 12.8 billion image-text pairs from Common Crawl. Participants in our benchmark design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing the res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14108","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/2304.14108/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":"2026-07-05T07:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3hKrFDJ/HNYmf94eI+S0yqPr3CSV4ZN9zLgRZo1Y2RzCCPjZQgr8UUCLVDZyaom5feyEB4EdYjesqKHW8U1PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:10:37.254286Z"},"content_sha256":"93ad029f532c3b96088703439e68bd27614c184f16d8c288c83640fd68ee423c","schema_version":"1.0","event_id":"sha256:93ad029f532c3b96088703439e68bd27614c184f16d8c288c83640fd68ee423c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJAICKRPBMMFRBDCKOVJ6PVDNW/bundle.json","state_url":"https://pith.science/pith/UJAICKRPBMMFRBDCKOVJ6PVDNW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJAICKRPBMMFRBDCKOVJ6PVDNW/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":"2026-08-05T16:10:37Z","links":{"resolver":"https://pith.science/pith/UJAICKRPBMMFRBDCKOVJ6PVDNW","bundle":"https://pith.science/pith/UJAICKRPBMMFRBDCKOVJ6PVDNW/bundle.json","state":"https://pith.science/pith/UJAICKRPBMMFRBDCKOVJ6PVDNW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJAICKRPBMMFRBDCKOVJ6PVDNW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UJAICKRPBMMFRBDCKOVJ6PVDNW","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":"25f261d185a33dd5947f1e8d2550fb79f1877531e49cc16153a24e6aa8002e67","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T11:37:18Z","title_canon_sha256":"2c8c482ae4d53fb18c4964d459993dac1ccec497a052df01f536a1029aa6bb00"},"schema_version":"1.0","source":{"id":"2304.14108","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14108","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14108v5","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14108","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"UJAICKRPBMMF","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"UJAICKRPBMMFRBDC","created_at":"2026-07-05T07:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"UJAICKRP","created_at":"2026-07-05T07:03:10Z"}],"graph_snapshots":[{"event_id":"sha256:93ad029f532c3b96088703439e68bd27614c184f16d8c288c83640fd68ee423c","target":"graph","created_at":"2026-07-05T07:03:10Z","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/2304.14108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the ML ecosystem, we introduce DataComp, a testbed for dataset experiments centered around a new candidate pool of 12.8 billion image-text pairs from Common Crawl. Participants in our benchmark design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing the res","authors_text":"Alexander Ratner, Alex Dimakis, Alex Fang, Ali Farhadi, Dhruba Ghosh, Eyal Orgad, Gabriel Ilharco, Georgios Smyrnis, Giannis Daras, Hannaneh Hajishirzi, Jenia Jitsev, Jieyu Zhang, Jonathan Hayase, Kalyani Marathe, Ludwig Schmidt, Mehdi Cherti, Mitchell Wortsman, Olga Saukh, Pang Wei Koh, Rahim Entezari, Ranjay Krishna, Richard Vencu, Romain Beaumont, Ryan Marten, Samir Yitzhak Gadre, Sarah Pratt, Sewoong Oh, Shuran Song, Stephen Mussmann, Thao Nguyen, Vaishaal Shankar, Vivek Ramanujan, Yair Carmon, Yonatan Bitton","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T11:37:18Z","title":"DataComp: In search of the next generation of multimodal datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14108","kind":"arxiv","version":5},"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":"sha256:4e28c632b3fbd070df052307405c08f0bb55cd8a635621663abe451cf1954625","target":"record","created_at":"2026-07-05T07:03:10Z","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":"25f261d185a33dd5947f1e8d2550fb79f1877531e49cc16153a24e6aa8002e67","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-27T11:37:18Z","title_canon_sha256":"2c8c482ae4d53fb18c4964d459993dac1ccec497a052df01f536a1029aa6bb00"},"schema_version":"1.0","source":{"id":"2304.14108","kind":"arxiv","version":5}},"canonical_sha256":"a240812a2f0b1858846253aa9f3ea36db7ba1b6ec3f648d36b217e50301cf6a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a240812a2f0b1858846253aa9f3ea36db7ba1b6ec3f648d36b217e50301cf6a9","first_computed_at":"2026-07-05T07:03:10.064273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:10.064273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oMqNYsCKBQFXytnNRrP+kZfUhrwR/XbBEsDE69OyJ9auZoWJjZ1y8403U6FxO/V8eBmt099amYU/5OtAlb17DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:10.064774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14108","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e28c632b3fbd070df052307405c08f0bb55cd8a635621663abe451cf1954625","sha256:93ad029f532c3b96088703439e68bd27614c184f16d8c288c83640fd68ee423c"],"state_sha256":"f1c07517ce1752f6df4eaddb349ad33fe2eab8f71d4c687ca46610944aa032d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZyXtydremCKjyrNzR8i0fsC3EtTYc+k45qsIEHCWcdmNf3ERLdd9MhCPWhvaJ9X8dM+kOnfJnsGTBxjmd4EzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:10:37.261336Z","bundle_sha256":"b7d15edbe6afaeef52936191a57f04702738fec3bce2b11bd7709448fdffc93c"}}