{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DEGDVVSHO2EB4V6Q2OSEYAS72U","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":"9f52e1aed1d4f41ede9ef656b5b1d9fe6a17eba19103b04585c2af6ac5f970ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T08:30:53Z","title_canon_sha256":"f587cf672a6bfeed977b03f69fd8e42f1b65300df2690b08607953a1457ecdfa"},"schema_version":"1.0","source":{"id":"2104.00332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00332","created_at":"2026-07-05T02:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00332v1","created_at":"2026-07-05T02:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00332","created_at":"2026-07-05T02:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"DEGDVVSHO2EB","created_at":"2026-07-05T02:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"DEGDVVSHO2EB4V6Q","created_at":"2026-07-05T02:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"DEGDVVSH","created_at":"2026-07-05T02:28:26Z"}],"graph_snapshots":[{"event_id":"sha256:8ad68f2be5becfa0e341cd0f0893301dba30ff860e5934959a28156aa4a3bf04","target":"graph","created_at":"2026-07-05T02:28:26Z","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/2104.00332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-language pre-training has achieved impressive success in learning multimodal representations between vision and language. To generalize this success to non-English languages, we introduce UC2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning. To tackle the scarcity problem of multilingual captions for image datasets, we first augment existing English-only datasets with other languages via machine translation (MT). Then we extend the standard Masked Language Modeling and Image-Text Matching training objectives to multilingual set","authors_text":"Jingjing Liu, Linjie Li, Luowei Zhou, Mingyang Zhou, Shuohang Wang, Yu Cheng, Zhou Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T08:30:53Z","title":"UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00332","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:ea99e93c8c8c2fd3026fbe8fcd3cf9f1584bc34967407e606204ed07352fcc3b","target":"record","created_at":"2026-07-05T02:28:26Z","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":"9f52e1aed1d4f41ede9ef656b5b1d9fe6a17eba19103b04585c2af6ac5f970ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T08:30:53Z","title_canon_sha256":"f587cf672a6bfeed977b03f69fd8e42f1b65300df2690b08607953a1457ecdfa"},"schema_version":"1.0","source":{"id":"2104.00332","kind":"arxiv","version":1}},"canonical_sha256":"190c3ad64776881e57d0d3a44c025fd52a66c0c55746da403016138dc4118d21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"190c3ad64776881e57d0d3a44c025fd52a66c0c55746da403016138dc4118d21","first_computed_at":"2026-07-05T02:28:26.540643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:26.540643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wiiFe19L2GRDqOim2QZxuf2isDCi2Lrbwa+xKN2ePUtu6zMnF0PYu8Iq+d0yRCNt0lT/XBe8M00dsYMXax0ADw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:26.541147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea99e93c8c8c2fd3026fbe8fcd3cf9f1584bc34967407e606204ed07352fcc3b","sha256:8ad68f2be5becfa0e341cd0f0893301dba30ff860e5934959a28156aa4a3bf04"],"state_sha256":"cb0eb706a74033772ad513aa3e0cc87409c921fe6ca68ab059bf1144659066b8"}