{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HIOPOGBL5KBH2MMS3452RWFKCO","short_pith_number":"pith:HIOPOGBL","canonical_record":{"source":{"id":"2502.07617","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T15:05:33Z","cross_cats_sorted":[],"title_canon_sha256":"0024a178d8630d3977835be800f4c6e5806810f5bc6dd357723d7a62cf3c9bdb","abstract_canon_sha256":"a3f9bb6445095ea6824ee5d067ceae8b2492a8a35a3012dcad8b5f96493d2d33"},"schema_version":"1.0"},"canonical_sha256":"3a1cf7182bea827d3192df3ba8d8aa13a563c9bc399f26d39512261f5250fcd9","source":{"kind":"arxiv","id":"2502.07617","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07617","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07617v2","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07617","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"HIOPOGBL5KBH","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"HIOPOGBL5KBH2MMS","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"HIOPOGBL","created_at":"2026-06-02T02:04:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HIOPOGBL5KBH2MMS3452RWFKCO","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07617","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T15:05:33Z","cross_cats_sorted":[],"title_canon_sha256":"0024a178d8630d3977835be800f4c6e5806810f5bc6dd357723d7a62cf3c9bdb","abstract_canon_sha256":"a3f9bb6445095ea6824ee5d067ceae8b2492a8a35a3012dcad8b5f96493d2d33"},"schema_version":"1.0"},"canonical_sha256":"3a1cf7182bea827d3192df3ba8d8aa13a563c9bc399f26d39512261f5250fcd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:05.124152Z","signature_b64":"fnCTbhWt6EJ2T8uP2fd9eQbHxoSWvTKNukZF4PTwQgLwuWaXY1siR5mrhv84flO2Rku9qOtGolsgV7sbBuntBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a1cf7182bea827d3192df3ba8d8aa13a563c9bc399f26d39512261f5250fcd9","last_reissued_at":"2026-06-02T02:04:05.123664Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:05.123664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07617","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":"2026-06-02T02:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"62fiYpWGWa1E7jJIf+8cZecXccZvYcqrMUi07b2mSsRCsx6hBpf5YwDap07LfOJ+OULYy4zdiYEzjt4Fa/AcBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T23:02:52.188983Z"},"content_sha256":"88a5450e7c2d6794d514cc3541e5291834347d73b3ff4ec57fb5f0b5ba067d8c","schema_version":"1.0","event_id":"sha256:88a5450e7c2d6794d514cc3541e5291834347d73b3ff4ec57fb5f0b5ba067d8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HIOPOGBL5KBH2MMS3452RWFKCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Salz, Ibrahim Alabdulmohsin, Keran Rong, Xiaohua Zhai, Xiao Wang, Zhe Li","submitted_at":"2025-02-11T15:05:33Z","abstract_excerpt":"We provide an empirical investigation of the potential of pre-training vision-language models on an unprecedented scale: 100 billion examples. We find that model performance tends to saturate at this scale on many common Western-centric classification and retrieval benchmarks, such as COCO Captions. Nevertheless, tasks of cultural diversity achieve more substantial gains from the 100-billion scale web data, thanks to its coverage of long-tail concepts. Furthermore, we analyze the model's multilinguality and show gains in low-resource languages as well. In addition, we observe that reducing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07617","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/2502.07617/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":"2026-06-02T02:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ocjd7eTSHU9AoSSapWyI94IkPK6CSH22kf6ETUUELJUtO/i1z9gk+zYYrDCAykXYQ9UVOY3DPQ6ZzO+FHwJpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T23:02:52.189594Z"},"content_sha256":"8eb7c3e8da990a3838e716e9efd8cffd88dd1093bef25a15f9d4995d4c15427a","schema_version":"1.0","event_id":"sha256:8eb7c3e8da990a3838e716e9efd8cffd88dd1093bef25a15f9d4995d4c15427a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HIOPOGBL5KBH2MMS3452RWFKCO/bundle.json","state_url":"https://pith.science/pith/HIOPOGBL5KBH2MMS3452RWFKCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HIOPOGBL5KBH2MMS3452RWFKCO/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":"2026-06-04T23:02:52Z","links":{"resolver":"https://pith.science/pith/HIOPOGBL5KBH2MMS3452RWFKCO","bundle":"https://pith.science/pith/HIOPOGBL5KBH2MMS3452RWFKCO/bundle.json","state":"https://pith.science/pith/HIOPOGBL5KBH2MMS3452RWFKCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HIOPOGBL5KBH2MMS3452RWFKCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HIOPOGBL5KBH2MMS3452RWFKCO","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":"a3f9bb6445095ea6824ee5d067ceae8b2492a8a35a3012dcad8b5f96493d2d33","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T15:05:33Z","title_canon_sha256":"0024a178d8630d3977835be800f4c6e5806810f5bc6dd357723d7a62cf3c9bdb"},"schema_version":"1.0","source":{"id":"2502.07617","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07617","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07617v2","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07617","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"HIOPOGBL5KBH","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"HIOPOGBL5KBH2MMS","created_at":"2026-06-02T02:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"HIOPOGBL","created_at":"2026-06-02T02:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:8eb7c3e8da990a3838e716e9efd8cffd88dd1093bef25a15f9d4995d4c15427a","target":"graph","created_at":"2026-06-02T02:04:05Z","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/2502.07617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We provide an empirical investigation of the potential of pre-training vision-language models on an unprecedented scale: 100 billion examples. We find that model performance tends to saturate at this scale on many common Western-centric classification and retrieval benchmarks, such as COCO Captions. Nevertheless, tasks of cultural diversity achieve more substantial gains from the 100-billion scale web data, thanks to its coverage of long-tail concepts. Furthermore, we analyze the model's multilinguality and show gains in low-resource languages as well. In addition, we observe that reducing the","authors_text":"Daniel Salz, Ibrahim Alabdulmohsin, Keran Rong, Xiaohua Zhai, Xiao Wang, Zhe Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T15:05:33Z","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07617","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":"sha256:88a5450e7c2d6794d514cc3541e5291834347d73b3ff4ec57fb5f0b5ba067d8c","target":"record","created_at":"2026-06-02T02:04:05Z","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":"a3f9bb6445095ea6824ee5d067ceae8b2492a8a35a3012dcad8b5f96493d2d33","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-11T15:05:33Z","title_canon_sha256":"0024a178d8630d3977835be800f4c6e5806810f5bc6dd357723d7a62cf3c9bdb"},"schema_version":"1.0","source":{"id":"2502.07617","kind":"arxiv","version":2}},"canonical_sha256":"3a1cf7182bea827d3192df3ba8d8aa13a563c9bc399f26d39512261f5250fcd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a1cf7182bea827d3192df3ba8d8aa13a563c9bc399f26d39512261f5250fcd9","first_computed_at":"2026-06-02T02:04:05.123664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:05.123664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fnCTbhWt6EJ2T8uP2fd9eQbHxoSWvTKNukZF4PTwQgLwuWaXY1siR5mrhv84flO2Rku9qOtGolsgV7sbBuntBw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:05.124152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07617","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88a5450e7c2d6794d514cc3541e5291834347d73b3ff4ec57fb5f0b5ba067d8c","sha256:8eb7c3e8da990a3838e716e9efd8cffd88dd1093bef25a15f9d4995d4c15427a"],"state_sha256":"b3de5b9c33cb70325c61bd64457c8fa49a98357703e35f26d38a899756ceed78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsK+u9VzK4LnvdeWi25Oegt4tqRjwugJkrOcSAasb2gGbWlxECuOVFA7kmhrklswyNZRtTY+DmXqOXGrVx2WDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T23:02:52.192831Z","bundle_sha256":"9f586b0958dd7129a46cc2ecb25207adc29484c11f13f6f74a17681907a32c78"}}