{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7OLACY42R2KAM6NBINUP7DVUOS","short_pith_number":"pith:7OLACY42","schema_version":"1.0","canonical_sha256":"fb9601639a8e940679a14368ff8eb47484588dceb365c5bc01e2698837cc75de","source":{"kind":"arxiv","id":"1907.05019","version":1},"attestation_state":"computed","paper":{"title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankur Bapna, Colin Cherry, Dmitry Lepikhin, George Foster, Maxim Krikun, Melvin Johnson, Mia Xu Chen, Naveen Arivazhagan, Orhan Firat, Wolfgang Macherey, Yonghui Wu, Yuan Cao, Zhifeng Chen","submitted_at":"2019-07-11T06:47:30Z","abstract_excerpt":"We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained on over 25 billion examples. Our system demonstrates effective transfer learning ability, significantly improving translation quality of low-resource languages, while keeping high-resource language translation quality on-par with competitive bilingual baselines. We provide in-depth analysis of various aspects of model building that "},"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":"1907.05019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-11T06:47:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de16e7575f5ea7d2c5f1365ee5f2f61f2cfdb9b93b66b6a601bcbd16ac5ed0b6","abstract_canon_sha256":"ee22f6f554c751e0be2f28eba8f671f7756942485eab9c5403527ed1737ae93c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:54.122830Z","signature_b64":"+mlgeHlp1/gMcne1BM1hAINYUCC6Gz47KczbgJull63ycMM8/1Ugz8U7ytcvcL2ObGN37ktMCyL1oL1aJSkPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb9601639a8e940679a14368ff8eb47484588dceb365c5bc01e2698837cc75de","last_reissued_at":"2026-05-17T23:40:54.122118Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:54.122118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankur Bapna, Colin Cherry, Dmitry Lepikhin, George Foster, Maxim Krikun, Melvin Johnson, Mia Xu Chen, Naveen Arivazhagan, Orhan Firat, Wolfgang Macherey, Yonghui Wu, Yuan Cao, Zhifeng Chen","submitted_at":"2019-07-11T06:47:30Z","abstract_excerpt":"We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal by building a single massively multilingual NMT model handling 103 languages trained on over 25 billion examples. Our system demonstrates effective transfer learning ability, significantly improving translation quality of low-resource languages, while keeping high-resource language translation quality on-par with competitive bilingual baselines. We provide in-depth analysis of various aspects of model building that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05019","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":"1907.05019","created_at":"2026-05-17T23:40:54.122234+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05019v1","created_at":"2026-05-17T23:40:54.122234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05019","created_at":"2026-05-17T23:40:54.122234+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OLACY42R2KA","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OLACY42R2KAM6NB","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OLACY42","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2310.02277","citing_title":"Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs \"Difficult\" Downstream Tasks in LLMs","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2412.04497","citing_title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2305.15717","citing_title":"The False Promise of Imitating Proprietary LLMs","ref_index":266,"is_internal_anchor":true},{"citing_arxiv_id":"1911.02116","citing_title":"Unsupervised Cross-lingual Representation Learning at Scale","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2402.19173","citing_title":"StarCoder 2 and The Stack v2: The Next Generation","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"1910.10683","citing_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20720","citing_title":"COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06859","citing_title":"Knowledge Transfer Scaling Laws for 3D Medical Imaging","ref_index":2,"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":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS","json":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS.json","graph_json":"https://pith.science/api/pith-number/7OLACY42R2KAM6NBINUP7DVUOS/graph.json","events_json":"https://pith.science/api/pith-number/7OLACY42R2KAM6NBINUP7DVUOS/events.json","paper":"https://pith.science/paper/7OLACY42"},"agent_actions":{"view_html":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS","download_json":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS.json","view_paper":"https://pith.science/paper/7OLACY42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05019&json=true","fetch_graph":"https://pith.science/api/pith-number/7OLACY42R2KAM6NBINUP7DVUOS/graph.json","fetch_events":"https://pith.science/api/pith-number/7OLACY42R2KAM6NBINUP7DVUOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS/action/storage_attestation","attest_author":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS/action/author_attestation","sign_citation":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS/action/citation_signature","submit_replication":"https://pith.science/pith/7OLACY42R2KAM6NBINUP7DVUOS/action/replication_record"}},"created_at":"2026-05-17T23:40:54.122234+00:00","updated_at":"2026-05-17T23:40:54.122234+00:00"}