{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y6TJ6DITWNUNEBQOKDN5PFMJMP","short_pith_number":"pith:Y6TJ6DIT","schema_version":"1.0","canonical_sha256":"c7a69f0d13b368d2060e50dbd7958963ed17607ac1ff49124be69609ffbfdad3","source":{"kind":"arxiv","id":"1809.04686","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akiko Eriguchi, Hideto Kazawa, Melvin Johnson, Orhan Firat, Wolfgang Macherey","submitted_at":"2018-09-12T21:34:03Z","abstract_excerpt":"Transferring representations from large supervised tasks to downstream tasks has shown promising results in AI fields such as Computer Vision and Natural Language Processing (NLP). In parallel, the recent progress in Machine Translation (MT) has enabled one to train multilingual Neural MT (NMT) systems that can translate between multiple languages and are also capable of performing zero-shot translation. However, little attention has been paid to leveraging representations learned by a multilingual NMT system to enable zero-shot multilinguality in other NLP tasks. In this paper, we demonstrate"},"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":"1809.04686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-12T21:34:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c57341582c5368e78188f779519dbe8d22b9d3c852c4d73e15b48ea295e38eaf","abstract_canon_sha256":"9207d13f7411d795e1a7e4e92560057bfd1a0eff80ce73ef82b68a587c03b3af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:50.012279Z","signature_b64":"VLWqH3Kpdvv6agcRdzR/E6BA83MlnzfnSbEqOIlqChDCSyRq38Cc7+eW1NzUemiJeGrEEiR6zDPHvRfFKB3PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7a69f0d13b368d2060e50dbd7958963ed17607ac1ff49124be69609ffbfdad3","last_reissued_at":"2026-05-18T00:05:50.011653Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:50.011653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Cross-lingual Classification Using Multilingual Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akiko Eriguchi, Hideto Kazawa, Melvin Johnson, Orhan Firat, Wolfgang Macherey","submitted_at":"2018-09-12T21:34:03Z","abstract_excerpt":"Transferring representations from large supervised tasks to downstream tasks has shown promising results in AI fields such as Computer Vision and Natural Language Processing (NLP). In parallel, the recent progress in Machine Translation (MT) has enabled one to train multilingual Neural MT (NMT) systems that can translate between multiple languages and are also capable of performing zero-shot translation. However, little attention has been paid to leveraging representations learned by a multilingual NMT system to enable zero-shot multilinguality in other NLP tasks. In this paper, we demonstrate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04686","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":"1809.04686","created_at":"2026-05-18T00:05:50.011744+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.04686v1","created_at":"2026-05-18T00:05:50.011744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04686","created_at":"2026-05-18T00:05:50.011744+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6TJ6DITWNUN","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6TJ6DITWNUNEBQO","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6TJ6DIT","created_at":"2026-05-18T12:33:04.347982+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":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP","json":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP.json","graph_json":"https://pith.science/api/pith-number/Y6TJ6DITWNUNEBQOKDN5PFMJMP/graph.json","events_json":"https://pith.science/api/pith-number/Y6TJ6DITWNUNEBQOKDN5PFMJMP/events.json","paper":"https://pith.science/paper/Y6TJ6DIT"},"agent_actions":{"view_html":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP","download_json":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP.json","view_paper":"https://pith.science/paper/Y6TJ6DIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.04686&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6TJ6DITWNUNEBQOKDN5PFMJMP/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6TJ6DITWNUNEBQOKDN5PFMJMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP/action/storage_attestation","attest_author":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP/action/author_attestation","sign_citation":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP/action/citation_signature","submit_replication":"https://pith.science/pith/Y6TJ6DITWNUNEBQOKDN5PFMJMP/action/replication_record"}},"created_at":"2026-05-18T00:05:50.011744+00:00","updated_at":"2026-05-18T00:05:50.011744+00:00"}