{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VCBJOQ2E63VA2GNLGMGZLQMH4Z","short_pith_number":"pith:VCBJOQ2E","canonical_record":{"source":{"id":"2410.02740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:54:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"478b2b72fa02efa44e3763f4f149e95c7ca8bc880be0adcc72cf5ebb9ea3dc7e","abstract_canon_sha256":"94fb001ad9c5d2638129a3cfcb967af7e1efd76be11e664ea4601bec695f26f0"},"schema_version":"1.0"},"canonical_sha256":"a882974344f6ea0d19ab330d95c187e666359c5d7b99c8dc9f76f064c554e9c9","source":{"kind":"arxiv","id":"2410.02740","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02740","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02740v1","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02740","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"VCBJOQ2E63VA","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"VCBJOQ2E63VA2GNL","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"VCBJOQ2E","created_at":"2026-07-05T09:15:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VCBJOQ2E63VA2GNLGMGZLQMH4Z","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:54:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"478b2b72fa02efa44e3763f4f149e95c7ca8bc880be0adcc72cf5ebb9ea3dc7e","abstract_canon_sha256":"94fb001ad9c5d2638129a3cfcb967af7e1efd76be11e664ea4601bec695f26f0"},"schema_version":"1.0"},"canonical_sha256":"a882974344f6ea0d19ab330d95c187e666359c5d7b99c8dc9f76f064c554e9c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:24.721401Z","signature_b64":"10wmsyxUl0X55sbAGSoUhQ920RhXm4xjly1AMUMzf94Z8F5IX9ornQ3Aks553tH0nfsMh4CZGZFbR5BF+eVMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a882974344f6ea0d19ab330d95c187e666359c5d7b99c8dc9f76f064c554e9c9","last_reissued_at":"2026-07-05T09:15:24.720931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:24.720931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02740","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZjHkMVzMiTTJ+VoqZ1LO8IWb2kOshTzFAEiJjM3iHBeAA7ndXRUhO9mcAj5ESSpeyntAK9C5hAnF3TD7B6kDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T22:01:00.170708Z"},"content_sha256":"2e7c07c546f35d9d6f9742cdf03cdfa49c10c221ca39d71eede583b9cb165706","schema_version":"1.0","event_id":"sha256:2e7c07c546f35d9d6f9742cdf03cdfa49c10c221ca39d71eede583b9cb165706"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VCBJOQ2E63VA2GNLGMGZLQMH4Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bowen Zhang, Chen Chen, Haotian Zhang, Hong-You Chen, Juan Lao Tebar, Meng Cao, Peter Grasch, Vasileios Saveris, Wenze Hu, Yinfei Yang, Zhe Gan, Zhengfeng Lai","submitted_at":"2024-10-03T17:54:52Z","abstract_excerpt":"Recent advancements in multimodal models highlight the value of rewritten captions for improving performance, yet key challenges remain. For example, while synthetic captions often provide superior quality and image-text alignment, it is not clear whether they can fully replace AltTexts: the role of synthetic captions and their interaction with original web-crawled AltTexts in pre-training is still not well understood. Moreover, different multimodal foundation models may have unique preferences for specific caption formats, but efforts to identify the optimal captions for each model remain lim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02740","kind":"arxiv","version":1},"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/2410.02740/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":"2026-07-05T09:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7/KvPxFFMyLV6wykTJPsE5JMpMi61LfKte80t4Y4/t5ezOPeg2fGh5zl7V3Gv4yMGPGqQem3Oj6RQW5MBbCfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T22:01:00.171359Z"},"content_sha256":"2410ea999fcba50a49dbd66c5bf5583574471199aff10d581990c7028f0f165a","schema_version":"1.0","event_id":"sha256:2410ea999fcba50a49dbd66c5bf5583574471199aff10d581990c7028f0f165a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VCBJOQ2E63VA2GNLGMGZLQMH4Z/bundle.json","state_url":"https://pith.science/pith/VCBJOQ2E63VA2GNLGMGZLQMH4Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VCBJOQ2E63VA2GNLGMGZLQMH4Z/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":"2026-08-13T22:01:00Z","links":{"resolver":"https://pith.science/pith/VCBJOQ2E63VA2GNLGMGZLQMH4Z","bundle":"https://pith.science/pith/VCBJOQ2E63VA2GNLGMGZLQMH4Z/bundle.json","state":"https://pith.science/pith/VCBJOQ2E63VA2GNLGMGZLQMH4Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VCBJOQ2E63VA2GNLGMGZLQMH4Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VCBJOQ2E63VA2GNLGMGZLQMH4Z","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":"94fb001ad9c5d2638129a3cfcb967af7e1efd76be11e664ea4601bec695f26f0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:54:52Z","title_canon_sha256":"478b2b72fa02efa44e3763f4f149e95c7ca8bc880be0adcc72cf5ebb9ea3dc7e"},"schema_version":"1.0","source":{"id":"2410.02740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02740","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02740v1","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02740","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"VCBJOQ2E63VA","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"VCBJOQ2E63VA2GNL","created_at":"2026-07-05T09:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"VCBJOQ2E","created_at":"2026-07-05T09:15:24Z"}],"graph_snapshots":[{"event_id":"sha256:2410ea999fcba50a49dbd66c5bf5583574471199aff10d581990c7028f0f165a","target":"graph","created_at":"2026-07-05T09:15:24Z","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/2410.02740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in multimodal models highlight the value of rewritten captions for improving performance, yet key challenges remain. For example, while synthetic captions often provide superior quality and image-text alignment, it is not clear whether they can fully replace AltTexts: the role of synthetic captions and their interaction with original web-crawled AltTexts in pre-training is still not well understood. Moreover, different multimodal foundation models may have unique preferences for specific caption formats, but efforts to identify the optimal captions for each model remain lim","authors_text":"Bowen Zhang, Chen Chen, Haotian Zhang, Hong-You Chen, Juan Lao Tebar, Meng Cao, Peter Grasch, Vasileios Saveris, Wenze Hu, Yinfei Yang, Zhe Gan, Zhengfeng Lai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:54:52Z","title":"Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02740","kind":"arxiv","version":1},"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":"sha256:2e7c07c546f35d9d6f9742cdf03cdfa49c10c221ca39d71eede583b9cb165706","target":"record","created_at":"2026-07-05T09:15:24Z","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":"94fb001ad9c5d2638129a3cfcb967af7e1efd76be11e664ea4601bec695f26f0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-03T17:54:52Z","title_canon_sha256":"478b2b72fa02efa44e3763f4f149e95c7ca8bc880be0adcc72cf5ebb9ea3dc7e"},"schema_version":"1.0","source":{"id":"2410.02740","kind":"arxiv","version":1}},"canonical_sha256":"a882974344f6ea0d19ab330d95c187e666359c5d7b99c8dc9f76f064c554e9c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a882974344f6ea0d19ab330d95c187e666359c5d7b99c8dc9f76f064c554e9c9","first_computed_at":"2026-07-05T09:15:24.720931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:24.720931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"10wmsyxUl0X55sbAGSoUhQ920RhXm4xjly1AMUMzf94Z8F5IX9ornQ3Aks553tH0nfsMh4CZGZFbR5BF+eVMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:24.721401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e7c07c546f35d9d6f9742cdf03cdfa49c10c221ca39d71eede583b9cb165706","sha256:2410ea999fcba50a49dbd66c5bf5583574471199aff10d581990c7028f0f165a"],"state_sha256":"e65e62d32d0359d169a2f6bab3de0d685a461e9388e019a495ac93a7999aa564"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NDetFnvtmSTT8h+hY3vq2h9Xq04+rK3+yBsv06y9yrzG1xmfpI0KAxQhkBBFZoPcT4/x6GkG48wrJCiSBUZiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T22:01:00.188313Z","bundle_sha256":"7acd0e9b6836baad2b0e8215f0219f036684a8c504e906663585b85a16e8c31a"}}