{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DJUMRPH3ZEBIRJ2G6VKLAVDH3B","short_pith_number":"pith:DJUMRPH3","canonical_record":{"source":{"id":"2507.22431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T07:21:36Z","cross_cats_sorted":[],"title_canon_sha256":"dcded3a346134c9f73a07191291210801126b1c1d6ef55fe12d2fd8cd7a73b64","abstract_canon_sha256":"f5de720de4575274652036274e5aa57bf1059f841a94e8de02b41c436b9654ec"},"schema_version":"1.0"},"canonical_sha256":"1a68c8bcfbc90288a746f554b05467d84dfcc1c833325e4387af219431c509f4","source":{"kind":"arxiv","id":"2507.22431","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22431","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22431v1","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22431","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"DJUMRPH3ZEBI","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"DJUMRPH3ZEBIRJ2G","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"DJUMRPH3","created_at":"2026-07-05T11:45:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DJUMRPH3ZEBIRJ2G6VKLAVDH3B","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T07:21:36Z","cross_cats_sorted":[],"title_canon_sha256":"dcded3a346134c9f73a07191291210801126b1c1d6ef55fe12d2fd8cd7a73b64","abstract_canon_sha256":"f5de720de4575274652036274e5aa57bf1059f841a94e8de02b41c436b9654ec"},"schema_version":"1.0"},"canonical_sha256":"1a68c8bcfbc90288a746f554b05467d84dfcc1c833325e4387af219431c509f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:41.964766Z","signature_b64":"x2qiqblBTXtFaNQAVQGHtW81d4V+RWXxAEzn4TSxXEXMN2Yy5SRw1WXD3nYHWOPljYS6Na7Wns3iuc+wNUrxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a68c8bcfbc90288a746f554b05467d84dfcc1c833325e4387af219431c509f4","last_reissued_at":"2026-07-05T11:45:41.964247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:41.964247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22431","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":"2026-07-05T11:45:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BsXPLGiD3cKTZ/qedcAdi/zDFfiWi8CvO2sOPvts6XkhJGeU2M6+mcAIXn8VQ6LeHsJ7mxZMHLdU/Jqw6zAfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:58:57.837057Z"},"content_sha256":"d9f21de72b256db53f243b1e52908f40dee508093dd37146e118381bed4a052d","schema_version":"1.0","event_id":"sha256:d9f21de72b256db53f243b1e52908f40dee508093dd37146e118381bed4a052d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DJUMRPH3ZEBIRJ2G6VKLAVDH3B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengyun Rao, Guangting Wang, Huaian Chen, Ke Mei, Xiaoxiao Ma, Yi Jin, Zhixiang Wei","submitted_at":"2025-07-30T07:21:36Z","abstract_excerpt":"Large-scale but noisy image-text pair data have paved the way for the success of Contrastive Language-Image Pretraining (CLIP). As the foundation vision encoder, CLIP in turn serves as the cornerstone for most large vision-language models (LVLMs). This interdependence naturally raises an interesting question: Can we reciprocally leverage LVLMs to enhance the quality of image-text pair data, thereby opening the possibility of a self-reinforcing cycle for continuous improvement? In this work, we take a significant step toward this vision by introducing an LVLM-driven data refinement pipeline. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22431","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/2507.22431/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":"2026-07-05T11:45:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzZzn7sxSsh6YEwgR+lMtlSdH3YunjiQy+6DmY5xaQzn8UfNIGyNUscTSZ2GXfTD3tIdGE08CRIs8SNeBVP9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:58:57.838124Z"},"content_sha256":"6e56bebb6d1482a6d5c683646f6a9f3e33a00bdaadbe4de0b7156421d3c34678","schema_version":"1.0","event_id":"sha256:6e56bebb6d1482a6d5c683646f6a9f3e33a00bdaadbe4de0b7156421d3c34678"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DJUMRPH3ZEBIRJ2G6VKLAVDH3B/bundle.json","state_url":"https://pith.science/pith/DJUMRPH3ZEBIRJ2G6VKLAVDH3B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DJUMRPH3ZEBIRJ2G6VKLAVDH3B/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":"2026-08-17T12:58:57Z","links":{"resolver":"https://pith.science/pith/DJUMRPH3ZEBIRJ2G6VKLAVDH3B","bundle":"https://pith.science/pith/DJUMRPH3ZEBIRJ2G6VKLAVDH3B/bundle.json","state":"https://pith.science/pith/DJUMRPH3ZEBIRJ2G6VKLAVDH3B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DJUMRPH3ZEBIRJ2G6VKLAVDH3B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DJUMRPH3ZEBIRJ2G6VKLAVDH3B","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":"f5de720de4575274652036274e5aa57bf1059f841a94e8de02b41c436b9654ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T07:21:36Z","title_canon_sha256":"dcded3a346134c9f73a07191291210801126b1c1d6ef55fe12d2fd8cd7a73b64"},"schema_version":"1.0","source":{"id":"2507.22431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22431","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22431v1","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22431","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"pith_short_12","alias_value":"DJUMRPH3ZEBI","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"pith_short_16","alias_value":"DJUMRPH3ZEBIRJ2G","created_at":"2026-07-05T11:45:41Z"},{"alias_kind":"pith_short_8","alias_value":"DJUMRPH3","created_at":"2026-07-05T11:45:41Z"}],"graph_snapshots":[{"event_id":"sha256:6e56bebb6d1482a6d5c683646f6a9f3e33a00bdaadbe4de0b7156421d3c34678","target":"graph","created_at":"2026-07-05T11:45:41Z","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/2507.22431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale but noisy image-text pair data have paved the way for the success of Contrastive Language-Image Pretraining (CLIP). As the foundation vision encoder, CLIP in turn serves as the cornerstone for most large vision-language models (LVLMs). This interdependence naturally raises an interesting question: Can we reciprocally leverage LVLMs to enhance the quality of image-text pair data, thereby opening the possibility of a self-reinforcing cycle for continuous improvement? In this work, we take a significant step toward this vision by introducing an LVLM-driven data refinement pipeline. Ou","authors_text":"Fengyun Rao, Guangting Wang, Huaian Chen, Ke Mei, Xiaoxiao Ma, Yi Jin, Zhixiang Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T07:21:36Z","title":"HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets and CLIP Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22431","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:d9f21de72b256db53f243b1e52908f40dee508093dd37146e118381bed4a052d","target":"record","created_at":"2026-07-05T11:45:41Z","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":"f5de720de4575274652036274e5aa57bf1059f841a94e8de02b41c436b9654ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T07:21:36Z","title_canon_sha256":"dcded3a346134c9f73a07191291210801126b1c1d6ef55fe12d2fd8cd7a73b64"},"schema_version":"1.0","source":{"id":"2507.22431","kind":"arxiv","version":1}},"canonical_sha256":"1a68c8bcfbc90288a746f554b05467d84dfcc1c833325e4387af219431c509f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a68c8bcfbc90288a746f554b05467d84dfcc1c833325e4387af219431c509f4","first_computed_at":"2026-07-05T11:45:41.964247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:41.964247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x2qiqblBTXtFaNQAVQGHtW81d4V+RWXxAEzn4TSxXEXMN2Yy5SRw1WXD3nYHWOPljYS6Na7Wns3iuc+wNUrxDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:41.964766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9f21de72b256db53f243b1e52908f40dee508093dd37146e118381bed4a052d","sha256:6e56bebb6d1482a6d5c683646f6a9f3e33a00bdaadbe4de0b7156421d3c34678"],"state_sha256":"def9d2c76a869b136fde61f39609a314cd425028b476448ebe32480afde99f65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P24Ju6eHBFSfayvVpsZk3xo5eXIDjtr+EBDVJTDdUD4nsgd428QNtuiNR5y5vmcYcVafnfpDCc7G4cYJba0DAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:58:57.847793Z","bundle_sha256":"f74886c666ba64d66691988e5f99f05dfb5320bb06de210a14babe430b2d07ff"}}