{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:34AQPFFLHPUP6DTOFLX5TIKEN7","short_pith_number":"pith:34AQPFFL","schema_version":"1.0","canonical_sha256":"df010794ab3be8ff0e6e2aefd9a1446ffa9b1ddb35a8c1112b54f39aae145ef3","source":{"kind":"arxiv","id":"1602.01925","version":2},"attestation_state":"computed","paper":{"title":"Massively Multilingual Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Dyer, George Mulcaire, Guillaume Lample, Noah A. Smith, Waleed Ammar, Yulia Tsvetkov","submitted_at":"2016-02-05T04:26:38Z","abstract_excerpt":"We introduce new methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space. Our estimation methods, multiCluster and multiCCA, use dictionaries and monolingual data; they do not require parallel data. Our new evaluation method, multiQVEC-CCA, is shown to correlate better than previous ones with two downstream tasks (text categorization and parsing). We also describe a web portal for evaluation that will facilitate further research in this area, along with open-source releases of all our methods."},"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":"1602.01925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-02-05T04:26:38Z","cross_cats_sorted":[],"title_canon_sha256":"fdc6c19e35dce77b61ce7fb811ca3068de4ec97c13e09a23ca8974be4a371a24","abstract_canon_sha256":"a504e7e7b133ebe4aa1b35bc585c574a6e442c766d1e3eb52b0d9a07eea7bf7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:17.377696Z","signature_b64":"R+8hpX1gEURCNtJES/TvZmuDx3qfd3PO4cddfVZ4o1/u8RZH5/mPKBKInzwgZLcZV70wTzjV6GRbKv2BS52mCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df010794ab3be8ff0e6e2aefd9a1446ffa9b1ddb35a8c1112b54f39aae145ef3","last_reissued_at":"2026-05-18T01:14:17.377076Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:17.377076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively Multilingual Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Dyer, George Mulcaire, Guillaume Lample, Noah A. Smith, Waleed Ammar, Yulia Tsvetkov","submitted_at":"2016-02-05T04:26:38Z","abstract_excerpt":"We introduce new methods for estimating and evaluating embeddings of words in more than fifty languages in a single shared embedding space. Our estimation methods, multiCluster and multiCCA, use dictionaries and monolingual data; they do not require parallel data. Our new evaluation method, multiQVEC-CCA, is shown to correlate better than previous ones with two downstream tasks (text categorization and parsing). We also describe a web portal for evaluation that will facilitate further research in this area, along with open-source releases of all our methods."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.01925","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":""},"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":"1602.01925","created_at":"2026-05-18T01:14:17.377161+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.01925v2","created_at":"2026-05-18T01:14:17.377161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.01925","created_at":"2026-05-18T01:14:17.377161+00:00"},{"alias_kind":"pith_short_12","alias_value":"34AQPFFLHPUP","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"34AQPFFLHPUP6DTO","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"34AQPFFL","created_at":"2026-05-18T12:29:55.572404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20835","citing_title":"Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7","json":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7.json","graph_json":"https://pith.science/api/pith-number/34AQPFFLHPUP6DTOFLX5TIKEN7/graph.json","events_json":"https://pith.science/api/pith-number/34AQPFFLHPUP6DTOFLX5TIKEN7/events.json","paper":"https://pith.science/paper/34AQPFFL"},"agent_actions":{"view_html":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7","download_json":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7.json","view_paper":"https://pith.science/paper/34AQPFFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.01925&json=true","fetch_graph":"https://pith.science/api/pith-number/34AQPFFLHPUP6DTOFLX5TIKEN7/graph.json","fetch_events":"https://pith.science/api/pith-number/34AQPFFLHPUP6DTOFLX5TIKEN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7/action/storage_attestation","attest_author":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7/action/author_attestation","sign_citation":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7/action/citation_signature","submit_replication":"https://pith.science/pith/34AQPFFLHPUP6DTOFLX5TIKEN7/action/replication_record"}},"created_at":"2026-05-18T01:14:17.377161+00:00","updated_at":"2026-05-18T01:14:17.377161+00:00"}