{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZORZOCXUB2XY3WQI65CMRRBNSF","short_pith_number":"pith:ZORZOCXU","canonical_record":{"source":{"id":"2310.07699","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:49:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cc299c3e8c08591848418bc2dc55c21a98224ca7a9a2b25d0771522e5136fcd1","abstract_canon_sha256":"c58a5808ec519d4d91c1f2e4779b2e73686833183a8abbe25d5e702938a2943a"},"schema_version":"1.0"},"canonical_sha256":"cba3970af40eaf8dda08f744c8c42d914be8c5645c4ee368ffb15ab96e127619","source":{"kind":"arxiv","id":"2310.07699","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07699","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07699v3","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07699","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZORZOCXUB2XY","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"pith_short_16","alias_value":"ZORZOCXUB2XY3WQI","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"pith_short_8","alias_value":"ZORZOCXU","created_at":"2026-07-05T07:55:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZORZOCXUB2XY3WQI65CMRRBNSF","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07699","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:49:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cc299c3e8c08591848418bc2dc55c21a98224ca7a9a2b25d0771522e5136fcd1","abstract_canon_sha256":"c58a5808ec519d4d91c1f2e4779b2e73686833183a8abbe25d5e702938a2943a"},"schema_version":"1.0"},"canonical_sha256":"cba3970af40eaf8dda08f744c8c42d914be8c5645c4ee368ffb15ab96e127619","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:45.416129Z","signature_b64":"S1F8wUX4QFh4o5YDm9BgYjMhYKE5vriyHjG14RX3+eMixbgauxRdqx3uRHe1NeGknRh3U0mtulL2yu+XXNe4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cba3970af40eaf8dda08f744c8c42d914be8c5645c4ee368ffb15ab96e127619","last_reissued_at":"2026-07-05T07:55:45.415408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:45.415408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07699","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:55:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mDWvO1/gxayDX6zmt826Eks6FgQWcdhnSZFXRd2ARNAPVzCFM8ePzk8BblfzAQAhiPxm4oE+CSZfsXXwZAhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:22:11.678795Z"},"content_sha256":"e21306833cd1224e205ad061bbf54008b4553cb657f76a13c47bdd8dd6a0789b","schema_version":"1.0","event_id":"sha256:e21306833cd1224e205ad061bbf54008b4553cb657f76a13c47bdd8dd6a0789b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZORZOCXUB2XY3WQI65CMRRBNSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aleksei Timofeev, Bowen Zhang, Chen-Nee Chuah, Haoping Bai, Haotian Zhang, Jiulong Shan, Meng Cao, Wentao Wu, Xianzhi Du, Yinfei Yang, Zhe Gan, Zhengfeng Lai","submitted_at":"2023-10-11T17:49:13Z","abstract_excerpt":"Large-scale web-crawled datasets are fundamental for the success of pre-training vision-language models, such as CLIP. However, the inherent noise and potential irrelevance of web-crawled AltTexts pose challenges in achieving precise image-text alignment. Existing methods utilizing large language models (LLMs) for caption rewriting have shown promise on small, curated datasets like CC3M and CC12M. This study introduces a scalable pipeline for noisy caption rewriting. Unlike recent LLM rewriting techniques, we emphasize the incorporation of visual concepts into captions, termed as Visual-enrich"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07699","kind":"arxiv","version":3},"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/2310.07699/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":"2026-07-05T07:55:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVNyAOh1CBIyLbTY8DnJZPVfoVDYO/EJ3kqqqRR4ieCC8L+W4nPSTUHEE09KJLywctiv2Uo+C1j/VbDyC7CJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:22:11.679179Z"},"content_sha256":"acf26cc33938ae80edf68d181797d2512083522fba347b7ed96110291da91992","schema_version":"1.0","event_id":"sha256:acf26cc33938ae80edf68d181797d2512083522fba347b7ed96110291da91992"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZORZOCXUB2XY3WQI65CMRRBNSF/bundle.json","state_url":"https://pith.science/pith/ZORZOCXUB2XY3WQI65CMRRBNSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZORZOCXUB2XY3WQI65CMRRBNSF/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":"2026-07-06T17:22:11Z","links":{"resolver":"https://pith.science/pith/ZORZOCXUB2XY3WQI65CMRRBNSF","bundle":"https://pith.science/pith/ZORZOCXUB2XY3WQI65CMRRBNSF/bundle.json","state":"https://pith.science/pith/ZORZOCXUB2XY3WQI65CMRRBNSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZORZOCXUB2XY3WQI65CMRRBNSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZORZOCXUB2XY3WQI65CMRRBNSF","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":"c58a5808ec519d4d91c1f2e4779b2e73686833183a8abbe25d5e702938a2943a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:49:13Z","title_canon_sha256":"cc299c3e8c08591848418bc2dc55c21a98224ca7a9a2b25d0771522e5136fcd1"},"schema_version":"1.0","source":{"id":"2310.07699","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07699","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07699v3","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07699","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZORZOCXUB2XY","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"pith_short_16","alias_value":"ZORZOCXUB2XY3WQI","created_at":"2026-07-05T07:55:45Z"},{"alias_kind":"pith_short_8","alias_value":"ZORZOCXU","created_at":"2026-07-05T07:55:45Z"}],"graph_snapshots":[{"event_id":"sha256:acf26cc33938ae80edf68d181797d2512083522fba347b7ed96110291da91992","target":"graph","created_at":"2026-07-05T07:55:45Z","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/2310.07699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale web-crawled datasets are fundamental for the success of pre-training vision-language models, such as CLIP. However, the inherent noise and potential irrelevance of web-crawled AltTexts pose challenges in achieving precise image-text alignment. Existing methods utilizing large language models (LLMs) for caption rewriting have shown promise on small, curated datasets like CC3M and CC12M. This study introduces a scalable pipeline for noisy caption rewriting. Unlike recent LLM rewriting techniques, we emphasize the incorporation of visual concepts into captions, termed as Visual-enrich","authors_text":"Aleksei Timofeev, Bowen Zhang, Chen-Nee Chuah, Haoping Bai, Haotian Zhang, Jiulong Shan, Meng Cao, Wentao Wu, Xianzhi Du, Yinfei Yang, Zhe Gan, Zhengfeng Lai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:49:13Z","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07699","kind":"arxiv","version":3},"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:e21306833cd1224e205ad061bbf54008b4553cb657f76a13c47bdd8dd6a0789b","target":"record","created_at":"2026-07-05T07:55:45Z","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":"c58a5808ec519d4d91c1f2e4779b2e73686833183a8abbe25d5e702938a2943a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T17:49:13Z","title_canon_sha256":"cc299c3e8c08591848418bc2dc55c21a98224ca7a9a2b25d0771522e5136fcd1"},"schema_version":"1.0","source":{"id":"2310.07699","kind":"arxiv","version":3}},"canonical_sha256":"cba3970af40eaf8dda08f744c8c42d914be8c5645c4ee368ffb15ab96e127619","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cba3970af40eaf8dda08f744c8c42d914be8c5645c4ee368ffb15ab96e127619","first_computed_at":"2026-07-05T07:55:45.415408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:45.415408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S1F8wUX4QFh4o5YDm9BgYjMhYKE5vriyHjG14RX3+eMixbgauxRdqx3uRHe1NeGknRh3U0mtulL2yu+XXNe4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:45.416129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07699","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e21306833cd1224e205ad061bbf54008b4553cb657f76a13c47bdd8dd6a0789b","sha256:acf26cc33938ae80edf68d181797d2512083522fba347b7ed96110291da91992"],"state_sha256":"3495fe6d02906f089a16624ba3789c55e2080dda9ceb8786fb64d60656aeaa68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BSU/KeeZblmg5bmAFxl3QfU9HgiFeu+F+XtS+E23Ms6OIEDATAlSyUrb3g3a3Sz6Fg+MouXC4HEzPlI+K9ACCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:22:11.681251Z","bundle_sha256":"ccc4397bf3f29c4e00b0c50086df57224da3617673dbe7eb179fa85e12af8c02"}}