{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5RQZVUR6SVFKFO4BPGDBZJM6QN","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":"16fba1b2fcb35df4ce2a18afa2baccfda11d326ef12af62494035e6e6a1b1e93","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T17:59:58Z","title_canon_sha256":"4b7a1f5155ed61daf34ce36a2c788297c056dc9e28c054131eec9944d3c05b1e"},"schema_version":"1.0","source":{"id":"2507.22062","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22062","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22062v3","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22062","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"5RQZVUR6SVFK","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"5RQZVUR6SVFKFO4B","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"5RQZVUR6","created_at":"2026-07-05T11:46:46Z"}],"graph_snapshots":[{"event_id":"sha256:342b4f3d2a91dc9e4f67a56cb826f098185dc17d502ad8321462f0776c8d65df","target":"graph","created_at":"2026-07-05T11:46:46Z","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/2507.22062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) is a popular foundation model, supporting from zero-shot classification, retrieval to encoders for multimodal large language models (MLLMs). Although CLIP is successfully trained on billion-scale image-text pairs from the English world, scaling CLIP's training further to learning from the worldwide web data is still challenging: (1) no curation method is available to handle data points from non-English world; (2) the English performance from existing multilingual CLIP is worse than its English-only counterpart, i.e., \"curse of multilinguality\" that","authors_text":"Ching-Feng Yeh, Dong Wang, Hu Xu, James Glass, Jason Weston, Kehan Lyu, Lifei Huang, Luke Zettlemoyer, Ramya Raghavendra, Saining Xie, Shang-Wen Li, Wen-tau Yih, Xinlei Chen, Yang Li, Yung-Sung Chuang, Zhuang Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T17:59:58Z","title":"Meta CLIP 2: A Worldwide Scaling Recipe"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22062","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:bd941140693ed715dca0ee76da9fa0b729a1cbf451bde7da85292b1df0226534","target":"record","created_at":"2026-07-05T11:46:46Z","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":"16fba1b2fcb35df4ce2a18afa2baccfda11d326ef12af62494035e6e6a1b1e93","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T17:59:58Z","title_canon_sha256":"4b7a1f5155ed61daf34ce36a2c788297c056dc9e28c054131eec9944d3c05b1e"},"schema_version":"1.0","source":{"id":"2507.22062","kind":"arxiv","version":3}},"canonical_sha256":"ec619ad23e954aa2bb8179861ca59e835201365af357c693efa83074afa5a80b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec619ad23e954aa2bb8179861ca59e835201365af357c693efa83074afa5a80b","first_computed_at":"2026-07-05T11:46:46.095683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:46.095683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rj6MzgIJ9vdVaMQ3bhF53oIdT1GUN4x5wJaRqTME4pNu9amCEAriAeF6RxZtsDkdy/5Y+p213sAMgZSOxmlLCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:46.096139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22062","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd941140693ed715dca0ee76da9fa0b729a1cbf451bde7da85292b1df0226534","sha256:342b4f3d2a91dc9e4f67a56cb826f098185dc17d502ad8321462f0776c8d65df"],"state_sha256":"f6136efb4022e6b14c9a3e398d367b9901cd0d12782deb6641338c3bb549cbbf"}