{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DEGDVVSHO2EB4V6Q2OSEYAS72U","short_pith_number":"pith:DEGDVVSH","schema_version":"1.0","canonical_sha256":"190c3ad64776881e57d0d3a44c025fd52a66c0c55746da403016138dc4118d21","source":{"kind":"arxiv","id":"2104.00332","version":1},"attestation_state":"computed","paper":{"title":"UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingjing Liu, Linjie Li, Luowei Zhou, Mingyang Zhou, Shuohang Wang, Yu Cheng, Zhou Yu","submitted_at":"2021-04-01T08:30:53Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2104.00332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T08:30:53Z","cross_cats_sorted":[],"title_canon_sha256":"f587cf672a6bfeed977b03f69fd8e42f1b65300df2690b08607953a1457ecdfa","abstract_canon_sha256":"9f52e1aed1d4f41ede9ef656b5b1d9fe6a17eba19103b04585c2af6ac5f970ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:26.541147Z","signature_b64":"wiiFe19L2GRDqOim2QZxuf2isDCi2Lrbwa+xKN2ePUtu6zMnF0PYu8Iq+d0yRCNt0lT/XBe8M00dsYMXax0ADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"190c3ad64776881e57d0d3a44c025fd52a66c0c55746da403016138dc4118d21","last_reissued_at":"2026-07-05T02:28:26.540643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:26.540643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingjing Liu, Linjie Li, Luowei Zhou, Mingyang Zhou, Shuohang Wang, Yu Cheng, Zhou Yu","submitted_at":"2021-04-01T08:30:53Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00332","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/2104.00332/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.00332","created_at":"2026-07-05T02:28:26.540702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00332v1","created_at":"2026-07-05T02:28:26.540702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00332","created_at":"2026-07-05T02:28:26.540702+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEGDVVSHO2EB","created_at":"2026-07-05T02:28:26.540702+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEGDVVSHO2EB4V6Q","created_at":"2026-07-05T02:28:26.540702+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEGDVVSH","created_at":"2026-07-05T02:28:26.540702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U","json":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U.json","graph_json":"https://pith.science/api/pith-number/DEGDVVSHO2EB4V6Q2OSEYAS72U/graph.json","events_json":"https://pith.science/api/pith-number/DEGDVVSHO2EB4V6Q2OSEYAS72U/events.json","paper":"https://pith.science/paper/DEGDVVSH"},"agent_actions":{"view_html":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U","download_json":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U.json","view_paper":"https://pith.science/paper/DEGDVVSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00332&json=true","fetch_graph":"https://pith.science/api/pith-number/DEGDVVSHO2EB4V6Q2OSEYAS72U/graph.json","fetch_events":"https://pith.science/api/pith-number/DEGDVVSHO2EB4V6Q2OSEYAS72U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U/action/storage_attestation","attest_author":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U/action/author_attestation","sign_citation":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U/action/citation_signature","submit_replication":"https://pith.science/pith/DEGDVVSHO2EB4V6Q2OSEYAS72U/action/replication_record"}},"created_at":"2026-07-05T02:28:26.540702+00:00","updated_at":"2026-07-05T02:28:26.540702+00:00"}