{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B4VXIW46MANVK55W5APYXFOCL2","short_pith_number":"pith:B4VXIW46","schema_version":"1.0","canonical_sha256":"0f2b745b9e601b5577b6e81f8b95c25ea8d4025e32ac9a246254224378c63d87","source":{"kind":"arxiv","id":"2010.10239","version":1},"attestation_state":"computed","paper":{"title":"Complete Multilingual Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Markus Freitag, Orhan Firat","submitted_at":"2020-10-20T13:03:48Z","abstract_excerpt":"Multilingual Neural Machine Translation (MNMT) models are commonly trained on a joint set of bilingual corpora which is acutely English-centric (i.e. English either as the source or target language). While direct data between two languages that are non-English is explicitly available at times, its use is not common. In this paper, we first take a step back and look at the commonly used bilingual corpora (WMT), and resurface the existence and importance of implicit structure that existed in it: multi-way alignment across examples (the same sentence in more than two languages). We set out to stu"},"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":"2010.10239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-20T13:03:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"69e7f2e7eb0b61d226b57e9f7c63f07d33d59383870ade777cd615378ee9c02e","abstract_canon_sha256":"9f7670f0a1e8e90c59e52d76d2ca0e52a283816eca4f972a6edd1e0d6f189528"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:28.628815Z","signature_b64":"LUZ3gv1Kv54ZQPC2NgQp07fdv5/Qjko4kb+5rMWbsx6HUvCdtm38/yMPenHXBaLnAI9GhBe/ROdcNYJUPAX8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f2b745b9e601b5577b6e81f8b95c25ea8d4025e32ac9a246254224378c63d87","last_reissued_at":"2026-07-05T01:44:28.628368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:28.628368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complete Multilingual Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Markus Freitag, Orhan Firat","submitted_at":"2020-10-20T13:03:48Z","abstract_excerpt":"Multilingual Neural Machine Translation (MNMT) models are commonly trained on a joint set of bilingual corpora which is acutely English-centric (i.e. English either as the source or target language). While direct data between two languages that are non-English is explicitly available at times, its use is not common. In this paper, we first take a step back and look at the commonly used bilingual corpora (WMT), and resurface the existence and importance of implicit structure that existed in it: multi-way alignment across examples (the same sentence in more than two languages). We set out to stu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10239","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.10239/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":"2010.10239","created_at":"2026-07-05T01:44:28.628427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.10239v1","created_at":"2026-07-05T01:44:28.628427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10239","created_at":"2026-07-05T01:44:28.628427+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4VXIW46MANV","created_at":"2026-07-05T01:44:28.628427+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4VXIW46MANVK55W","created_at":"2026-07-05T01:44:28.628427+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4VXIW46","created_at":"2026-07-05T01:44:28.628427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2204.02311","citing_title":"PaLM: Scaling Language Modeling with Pathways","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2","json":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2.json","graph_json":"https://pith.science/api/pith-number/B4VXIW46MANVK55W5APYXFOCL2/graph.json","events_json":"https://pith.science/api/pith-number/B4VXIW46MANVK55W5APYXFOCL2/events.json","paper":"https://pith.science/paper/B4VXIW46"},"agent_actions":{"view_html":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2","download_json":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2.json","view_paper":"https://pith.science/paper/B4VXIW46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.10239&json=true","fetch_graph":"https://pith.science/api/pith-number/B4VXIW46MANVK55W5APYXFOCL2/graph.json","fetch_events":"https://pith.science/api/pith-number/B4VXIW46MANVK55W5APYXFOCL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2/action/storage_attestation","attest_author":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2/action/author_attestation","sign_citation":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2/action/citation_signature","submit_replication":"https://pith.science/pith/B4VXIW46MANVK55W5APYXFOCL2/action/replication_record"}},"created_at":"2026-07-05T01:44:28.628427+00:00","updated_at":"2026-07-05T01:44:28.628427+00:00"}