{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XUXTJHNNRPB2VQQ5CDFIYSXOPA","short_pith_number":"pith:XUXTJHNN","schema_version":"1.0","canonical_sha256":"bd2f349dad8bc3aac21d10ca8c4aee780ee086bae075c12ac3aee5bae32ab3bb","source":{"kind":"arxiv","id":"1812.10464","version":2},"attestation_state":"computed","paper":{"title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Holger Schwenk, Mikel Artetxe","submitted_at":"2018-12-26T18:58:39Z","abstract_excerpt":"We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a single BiLSTM encoder with a shared BPE vocabulary for all languages, which is coupled with an auxiliary decoder and trained on publicly available parallel corpora. This enables us to learn a classifier on top of the resulting embeddings using English annotated data only, and transfer it to any of the 93 languages without any modification. Our experiments in cross-lingual natural language inferenc"},"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":"1812.10464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-26T18:58:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7ff350c0e9cd087070f469894d002dec4dc13e7a7fa7ed90dec4893ef74a33da","abstract_canon_sha256":"43d4e2f604f49c86349bfc0605dfdeedcc99047f971f723c3230785db5237d10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:33.712225Z","signature_b64":"PIe2h4VV8i4SnZzufUrvb6p3X1K3IZrdoHK1PWadajcrFZQk1uXZ4odTIWovBkybLZOKcWZk2R/xEw0+JBYrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd2f349dad8bc3aac21d10ca8c4aee780ee086bae075c12ac3aee5bae32ab3bb","last_reissued_at":"2026-07-05T03:43:33.711761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:33.711761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Holger Schwenk, Mikel Artetxe","submitted_at":"2018-12-26T18:58:39Z","abstract_excerpt":"We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts. Our system uses a single BiLSTM encoder with a shared BPE vocabulary for all languages, which is coupled with an auxiliary decoder and trained on publicly available parallel corpora. This enables us to learn a classifier on top of the resulting embeddings using English annotated data only, and transfer it to any of the 93 languages without any modification. Our experiments in cross-lingual natural language inferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10464","kind":"arxiv","version":2},"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/1812.10464/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":"1812.10464","created_at":"2026-07-05T03:43:33.711812+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10464v2","created_at":"2026-07-05T03:43:33.711812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10464","created_at":"2026-07-05T03:43:33.711812+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUXTJHNNRPB2","created_at":"2026-07-05T03:43:33.711812+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUXTJHNNRPB2VQQ5","created_at":"2026-07-05T03:43:33.711812+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUXTJHNN","created_at":"2026-07-05T03:43:33.711812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.08885","citing_title":"Low-Resource Corpus Filtering using Multilingual Sentence Embeddings","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09111","citing_title":"PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA","json":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA.json","graph_json":"https://pith.science/api/pith-number/XUXTJHNNRPB2VQQ5CDFIYSXOPA/graph.json","events_json":"https://pith.science/api/pith-number/XUXTJHNNRPB2VQQ5CDFIYSXOPA/events.json","paper":"https://pith.science/paper/XUXTJHNN"},"agent_actions":{"view_html":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA","download_json":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA.json","view_paper":"https://pith.science/paper/XUXTJHNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10464&json=true","fetch_graph":"https://pith.science/api/pith-number/XUXTJHNNRPB2VQQ5CDFIYSXOPA/graph.json","fetch_events":"https://pith.science/api/pith-number/XUXTJHNNRPB2VQQ5CDFIYSXOPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA/action/storage_attestation","attest_author":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA/action/author_attestation","sign_citation":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA/action/citation_signature","submit_replication":"https://pith.science/pith/XUXTJHNNRPB2VQQ5CDFIYSXOPA/action/replication_record"}},"created_at":"2026-07-05T03:43:33.711812+00:00","updated_at":"2026-07-05T03:43:33.711812+00:00"}