{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HSDOJXMTLLVC3YK6J35H6VNSE7","short_pith_number":"pith:HSDOJXMT","schema_version":"1.0","canonical_sha256":"3c86e4dd935aea2de15e4efa7f55b227ea69fea3f336b8ed66dfe09bab5953b8","source":{"kind":"arxiv","id":"1810.12836","version":4},"attestation_state":"computed","paper":{"title":"Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Strope, Daniel Cer, Muthuraman Chidambaram, Ray Kurzweil, Steve Yuan, Yinfei Yang, Yun-hsuan Sung","submitted_at":"2018-10-30T16:18:05Z","abstract_excerpt":"A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the performance from training on English tasks to non-English tasks, despite little to no task-specific non-English data. In this paper, we explore a natural setup for learning cross-lingual sentence representations: the dual-encoder. We provide a comprehensive evaluation of our cross-lingual representations on a number of monolingual, cross-lingual, and zero-shot/few-"},"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":"1810.12836","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T16:18:05Z","cross_cats_sorted":[],"title_canon_sha256":"af0548d79e20ad92739816ed0444de936ad76201c203c35fc21803124e5dfc54","abstract_canon_sha256":"693a2f6f57b91cc8434b02bd10e6942b6c5ecc8bfd047c3197ad1bf1b0fd6aae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:50:53.524681Z","signature_b64":"u6gehxPu+27gRjE7rGBqh2WWyYoe4vj+hIZftQEnUmxAMa3tiSV12c5Yplj2AB32RADW3REyrS7pVLtM3y7yCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c86e4dd935aea2de15e4efa7f55b227ea69fea3f336b8ed66dfe09bab5953b8","last_reissued_at":"2026-07-04T23:50:53.524180Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:50:53.524180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Strope, Daniel Cer, Muthuraman Chidambaram, Ray Kurzweil, Steve Yuan, Yinfei Yang, Yun-hsuan Sung","submitted_at":"2018-10-30T16:18:05Z","abstract_excerpt":"A significant roadblock in multilingual neural language modeling is the lack of labeled non-English data. One potential method for overcoming this issue is learning cross-lingual text representations that can be used to transfer the performance from training on English tasks to non-English tasks, despite little to no task-specific non-English data. In this paper, we explore a natural setup for learning cross-lingual sentence representations: the dual-encoder. We provide a comprehensive evaluation of our cross-lingual representations on a number of monolingual, cross-lingual, and zero-shot/few-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12836","kind":"arxiv","version":4},"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/1810.12836/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":"1810.12836","created_at":"2026-07-04T23:50:53.524238+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12836v4","created_at":"2026-07-04T23:50:53.524238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12836","created_at":"2026-07-04T23:50:53.524238+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSDOJXMTLLVC","created_at":"2026-07-04T23:50:53.524238+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSDOJXMTLLVC3YK6","created_at":"2026-07-04T23:50:53.524238+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSDOJXMT","created_at":"2026-07-04T23:50:53.524238+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/HSDOJXMTLLVC3YK6J35H6VNSE7","json":"https://pith.science/pith/HSDOJXMTLLVC3YK6J35H6VNSE7.json","graph_json":"https://pith.science/api/pith-number/HSDOJXMTLLVC3YK6J35H6VNSE7/graph.json","events_json":"https://pith.science/api/pith-number/HSDOJXMTLLVC3YK6J35H6VNSE7/events.json","paper":"https://pith.science/paper/HSDOJXMT"},"agent_actions":{"view_html":"https://pith.science/pith/HSDOJXMTLLVC3YK6J35H6VNSE7","download_json":"https://pith.science/pith/HSDOJXMTLLVC3YK6J35H6VNSE7.json","view_paper":"https://pith.science/paper/HSDOJXMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12836&json=true","fetch_graph":"https://pith.science/api/pith-number/HSDOJXMTLLVC3YK6J35H6VNSE7/graph.json","fetch_events":"https://pith.science/api/pith-number/HSDOJXMTLLVC3YK6J35H6VNSE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSDOJXMTLLVC3YK6J35H6VNSE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSDOJXMTLLVC3YK6J35H6VNSE7/action/storage_attestation","attest_author":"https://pith.science/pith/HSDOJXMTLLVC3YK6J35H6VNSE7/action/author_attestation","sign_citation":"https://pith.science/pith/HSDOJXMTLLVC3YK6J35H6VNSE7/action/citation_signature","submit_replication":"https://pith.science/pith/HSDOJXMTLLVC3YK6J35H6VNSE7/action/replication_record"}},"created_at":"2026-07-04T23:50:53.524238+00:00","updated_at":"2026-07-04T23:50:53.524238+00:00"}