{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NED5KLAG7TJAI5NO2VNXFQNANM","short_pith_number":"pith:NED5KLAG","schema_version":"1.0","canonical_sha256":"6907d52c06fcd20475aed55b72c1a06b0bf069ca79d4dad39336d317c9271989","source":{"kind":"arxiv","id":"1907.04307","version":1},"attestation_state":"computed","paper":{"title":"Multilingual Universal Sentence Encoder for Semantic Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amin Ahmad, Brian Strope, Chris Tar, Daniel Cer, Gustavo Hernandez Abrego, Jax Law, Mandy Guo, Noah Constant, Ray Kurzweil, Steve Yuan, Yinfei Yang, Yun-hsuan Sung","submitted_at":"2019-07-09T17:46:17Z","abstract_excerpt":"We introduce two pre-trained retrieval focused multilingual sentence encoding models, respectively based on the Transformer and CNN model architectures. The models embed text from 16 languages into a single semantic space using a multi-task trained dual-encoder that learns tied representations using translation based bridge tasks (Chidambaram al., 2018). The models provide performance that is competitive with the state-of-the-art on: semantic retrieval (SR), translation pair bitext retrieval (BR) and retrieval question answering (ReQA). On English transfer learning tasks, our sentence-level em"},"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":"1907.04307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T17:46:17Z","cross_cats_sorted":[],"title_canon_sha256":"4ad0fac23e95c2da55e6096ff3ee66b877943c752a1749a6d1209a7c573543fe","abstract_canon_sha256":"6c25ca26dee571059f578eee866d70325c6b2665912986377cb9442e8d57f9be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:02.704560Z","signature_b64":"+J3e8xxRhz7WJxTtJqMNvipQCbxPbYt0omFciKb2Om3nbpEsJLl7jlZzJklxpHaShUIl2wp+OwZbpnQDXF3IDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6907d52c06fcd20475aed55b72c1a06b0bf069ca79d4dad39336d317c9271989","last_reissued_at":"2026-05-17T23:41:02.703809Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:02.703809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Universal Sentence Encoder for Semantic Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amin Ahmad, Brian Strope, Chris Tar, Daniel Cer, Gustavo Hernandez Abrego, Jax Law, Mandy Guo, Noah Constant, Ray Kurzweil, Steve Yuan, Yinfei Yang, Yun-hsuan Sung","submitted_at":"2019-07-09T17:46:17Z","abstract_excerpt":"We introduce two pre-trained retrieval focused multilingual sentence encoding models, respectively based on the Transformer and CNN model architectures. The models embed text from 16 languages into a single semantic space using a multi-task trained dual-encoder that learns tied representations using translation based bridge tasks (Chidambaram al., 2018). The models provide performance that is competitive with the state-of-the-art on: semantic retrieval (SR), translation pair bitext retrieval (BR) and retrieval question answering (ReQA). On English transfer learning tasks, our sentence-level em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04307","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":""},"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":"1907.04307","created_at":"2026-05-17T23:41:02.703928+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.04307v1","created_at":"2026-05-17T23:41:02.703928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04307","created_at":"2026-05-17T23:41:02.703928+00:00"},{"alias_kind":"pith_short_12","alias_value":"NED5KLAG7TJA","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NED5KLAG7TJAI5NO","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NED5KLAG","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21096","citing_title":"Multilingual and Domain-Agnostic Tip-of-the-Tongue Query Generation for Simulated Evaluation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03065","citing_title":"OGPO: Sample Efficient Full-Finetuning of Generative Control Policies","ref_index":185,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM","json":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM.json","graph_json":"https://pith.science/api/pith-number/NED5KLAG7TJAI5NO2VNXFQNANM/graph.json","events_json":"https://pith.science/api/pith-number/NED5KLAG7TJAI5NO2VNXFQNANM/events.json","paper":"https://pith.science/paper/NED5KLAG"},"agent_actions":{"view_html":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM","download_json":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM.json","view_paper":"https://pith.science/paper/NED5KLAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.04307&json=true","fetch_graph":"https://pith.science/api/pith-number/NED5KLAG7TJAI5NO2VNXFQNANM/graph.json","fetch_events":"https://pith.science/api/pith-number/NED5KLAG7TJAI5NO2VNXFQNANM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM/action/storage_attestation","attest_author":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM/action/author_attestation","sign_citation":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM/action/citation_signature","submit_replication":"https://pith.science/pith/NED5KLAG7TJAI5NO2VNXFQNANM/action/replication_record"}},"created_at":"2026-05-17T23:41:02.703928+00:00","updated_at":"2026-05-17T23:41:02.703928+00:00"}