{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:J7UHP3RIHAZZEWKFSBOMZYMREG","short_pith_number":"pith:J7UHP3RI","schema_version":"1.0","canonical_sha256":"4fe877ee283833925945905ccce19121a98930e3f584a410cb2031ffb6ed2560","source":{"kind":"arxiv","id":"1309.4168","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Similarities among Languages for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilya Sutskever, Quoc V. Le, Tomas Mikolov","submitted_at":"2013-09-17T03:23:13Z","abstract_excerpt":"Dictionaries and phrase tables are the basis of modern statistical machine translation systems. This paper develops a method that can automate the process of generating and extending dictionaries and phrase tables. Our method can translate missing word and phrase entries by learning language structures based on large monolingual data and mapping between languages from small bilingual data. It uses distributed representation of words and learns a linear mapping between vector spaces of languages. Despite its simplicity, our method is surprisingly effective: we can achieve almost 90% precision@5"},"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":"1309.4168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-09-17T03:23:13Z","cross_cats_sorted":[],"title_canon_sha256":"72234cb33a37ba32750fd40a4566d248c750e7fed032a886b364e81f8efd15f9","abstract_canon_sha256":"a703b95f8c82f9c5ec231cfa38045df6c46ae192acb3f3418b2aef02f6118d79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:13:09.375209Z","signature_b64":"x8mKQARd17lLD+7inp011axkydVO8ibQbaYCJRPCvAhF1xdKMfKmeo/36ODvJtFnlFqBEggOKR5LmPgZpi6zDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fe877ee283833925945905ccce19121a98930e3f584a410cb2031ffb6ed2560","last_reissued_at":"2026-05-18T03:13:09.374526Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:13:09.374526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Similarities among Languages for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilya Sutskever, Quoc V. Le, Tomas Mikolov","submitted_at":"2013-09-17T03:23:13Z","abstract_excerpt":"Dictionaries and phrase tables are the basis of modern statistical machine translation systems. This paper develops a method that can automate the process of generating and extending dictionaries and phrase tables. Our method can translate missing word and phrase entries by learning language structures based on large monolingual data and mapping between languages from small bilingual data. It uses distributed representation of words and learns a linear mapping between vector spaces of languages. Despite its simplicity, our method is surprisingly effective: we can achieve almost 90% precision@5"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1309.4168","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":"1309.4168","created_at":"2026-05-18T03:13:09.374610+00:00"},{"alias_kind":"arxiv_version","alias_value":"1309.4168v1","created_at":"2026-05-18T03:13:09.374610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1309.4168","created_at":"2026-05-18T03:13:09.374610+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7UHP3RIHAZZ","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7UHP3RIHAZZEWKF","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7UHP3RI","created_at":"2026-05-18T12:27:49.015174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.08579","citing_title":"On the Spectral Geometry of Cross-Modal Representations: A Functional Map Diagnostic for Multimodal Alignment","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2311.03658","citing_title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20835","citing_title":"Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG","json":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG.json","graph_json":"https://pith.science/api/pith-number/J7UHP3RIHAZZEWKFSBOMZYMREG/graph.json","events_json":"https://pith.science/api/pith-number/J7UHP3RIHAZZEWKFSBOMZYMREG/events.json","paper":"https://pith.science/paper/J7UHP3RI"},"agent_actions":{"view_html":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG","download_json":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG.json","view_paper":"https://pith.science/paper/J7UHP3RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1309.4168&json=true","fetch_graph":"https://pith.science/api/pith-number/J7UHP3RIHAZZEWKFSBOMZYMREG/graph.json","fetch_events":"https://pith.science/api/pith-number/J7UHP3RIHAZZEWKFSBOMZYMREG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG/action/storage_attestation","attest_author":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG/action/author_attestation","sign_citation":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG/action/citation_signature","submit_replication":"https://pith.science/pith/J7UHP3RIHAZZEWKFSBOMZYMREG/action/replication_record"}},"created_at":"2026-05-18T03:13:09.374610+00:00","updated_at":"2026-05-18T03:13:09.374610+00:00"}