{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZZ6JBC5EAUXVU7KDQC5WR24DIZ","short_pith_number":"pith:ZZ6JBC5E","schema_version":"1.0","canonical_sha256":"ce7c908ba4052f5a7d4380bb68eb83464bbfe646d79e8a7385b33351f6c5c7e5","source":{"kind":"arxiv","id":"2007.01852","version":2},"attestation_state":"computed","paper":{"title":"Language-agnostic BERT Sentence Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Cer, Fangxiaoyu Feng, Naveen Arivazhagan, Wei Wang, Yinfei Yang","submitted_at":"2020-07-03T17:58:42Z","abstract_excerpt":"While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings have yet to be explored. We systematically investigate methods for learning multilingual sentence embeddings by combining the best methods for learning monolingual and cross-lingual representations including: masked language modeling (MLM), translation language modeling (TLM) (Conneau and Lample, 2019), dual encoder translation ranking (Guo et al., 2018), and additive margin softma"},"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":"2007.01852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-03T17:58:42Z","cross_cats_sorted":[],"title_canon_sha256":"e3e17a66eda9bee14f19fd87ff02065140449cf64e32ef3d6b8440a83ac84c77","abstract_canon_sha256":"f24127d7788dbe074d25756335502d45998eda6aa2e4ff57fd50dad664fb86a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:36.960306Z","signature_b64":"9Dhpfn2E+VWW+ayhVA/rWHLSz3IoSFlYV6zHZc9U25L38CHeVtWuOZ/jGMA+BEbu+GM/eKyna48cAUpmAQKrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce7c908ba4052f5a7d4380bb68eb83464bbfe646d79e8a7385b33351f6c5c7e5","last_reissued_at":"2026-07-05T04:02:36.959920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:36.959920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-agnostic BERT Sentence Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Cer, Fangxiaoyu Feng, Naveen Arivazhagan, Wei Wang, Yinfei Yang","submitted_at":"2020-07-03T17:58:42Z","abstract_excerpt":"While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings have yet to be explored. We systematically investigate methods for learning multilingual sentence embeddings by combining the best methods for learning monolingual and cross-lingual representations including: masked language modeling (MLM), translation language modeling (TLM) (Conneau and Lample, 2019), dual encoder translation ranking (Guo et al., 2018), and additive margin softma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01852","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/2007.01852/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":"2007.01852","created_at":"2026-07-05T04:02:36.959974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01852v2","created_at":"2026-07-05T04:02:36.959974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01852","created_at":"2026-07-05T04:02:36.959974+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZ6JBC5EAUXV","created_at":"2026-07-05T04:02:36.959974+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZ6JBC5EAUXVU7KD","created_at":"2026-07-05T04:02:36.959974+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZ6JBC5E","created_at":"2026-07-05T04:02:36.959974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26575","citing_title":"Hubness, Not Anisotropy, Drives Cross-Lingual Retrieval Asymmetry in Multilingual Embedding Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22202","citing_title":"Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22660","citing_title":"Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17173","citing_title":"Why Do Safety Guardrails Degrade Across Languages?","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16621","citing_title":"The Role of Vocabularies in Learning Sparse Representations for Ranking","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2211.05100","citing_title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","ref_index":158,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21555","citing_title":"Finding Meaning in Embeddings: Concept Separation Curves","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18584","citing_title":"MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10590","citing_title":"Bridging Linguistic Gaps: Cross-Lingual Mapping in Pre-Training and Dataset for Enhanced Multilingual LLM Performance","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ","json":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ.json","graph_json":"https://pith.science/api/pith-number/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/graph.json","events_json":"https://pith.science/api/pith-number/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/events.json","paper":"https://pith.science/paper/ZZ6JBC5E"},"agent_actions":{"view_html":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ","download_json":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ.json","view_paper":"https://pith.science/paper/ZZ6JBC5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01852&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZZ6JBC5EAUXVU7KDQC5WR24DIZ/action/replication_record"}},"created_at":"2026-07-05T04:02:36.959974+00:00","updated_at":"2026-07-05T04:02:36.959974+00:00"}