{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MYYIOPP3BQDYRBMHJR6EJETE6U","short_pith_number":"pith:MYYIOPP3","schema_version":"1.0","canonical_sha256":"6630873dfb0c078885874c7c449264f50f9689c053fef7cfd1de395f3e085502","source":{"kind":"arxiv","id":"2108.02401","version":2},"attestation_state":"computed","paper":{"title":"WeChat Neural Machine Translation Systems for WMT21","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ernan Li, Fandong Meng, Jie Zhou, Jinan Xu, Peng Li, Qiu Ran, Xianfeng Zeng, Yijin Liu","submitted_at":"2021-08-05T06:38:48Z","abstract_excerpt":"This paper introduces WeChat AI's participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German. Our systems are based on the Transformer (Vaswani et al., 2017) with several novel and effective variants. In our experiments, we employ data filtering, large-scale synthetic data generation (i.e., back-translation, knowledge distillation, forward-translation, iterative in-domain knowledge transfer), advanced finetuning approaches, and boosted Self-BLEU based model ensemble. Our constrained systems achieve 36.9, 46.9, 27.8 and 3"},"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":"2108.02401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-05T06:38:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e9839f976d15b4f114133c7b7289176183da3d277426eb084ca1b077d2c9602","abstract_canon_sha256":"4ab96c5b543c2ae6836e19a180a690d080ea26ee19e8e1ece8454984226a2eea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:31.642185Z","signature_b64":"r8VGhYT+9UClvO4v+eDlTRUv4G5sgM4Zd6s6eWC4tk3IzXyIU5BBjWVaahSp8smnqYq2eGaYy3nNoMZiMH+pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6630873dfb0c078885874c7c449264f50f9689c053fef7cfd1de395f3e085502","last_reissued_at":"2026-07-05T03:13:31.641731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:31.641731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WeChat Neural Machine Translation Systems for WMT21","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ernan Li, Fandong Meng, Jie Zhou, Jinan Xu, Peng Li, Qiu Ran, Xianfeng Zeng, Yijin Liu","submitted_at":"2021-08-05T06:38:48Z","abstract_excerpt":"This paper introduces WeChat AI's participation in WMT 2021 shared news translation task on English->Chinese, English->Japanese, Japanese->English and English->German. Our systems are based on the Transformer (Vaswani et al., 2017) with several novel and effective variants. In our experiments, we employ data filtering, large-scale synthetic data generation (i.e., back-translation, knowledge distillation, forward-translation, iterative in-domain knowledge transfer), advanced finetuning approaches, and boosted Self-BLEU based model ensemble. Our constrained systems achieve 36.9, 46.9, 27.8 and 3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.02401","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.02401/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":"2108.02401","created_at":"2026-07-05T03:13:31.641795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.02401v2","created_at":"2026-07-05T03:13:31.641795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.02401","created_at":"2026-07-05T03:13:31.641795+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYYIOPP3BQDY","created_at":"2026-07-05T03:13:31.641795+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYYIOPP3BQDYRBMH","created_at":"2026-07-05T03:13:31.641795+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYYIOPP3","created_at":"2026-07-05T03:13:31.641795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U","json":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U.json","graph_json":"https://pith.science/api/pith-number/MYYIOPP3BQDYRBMHJR6EJETE6U/graph.json","events_json":"https://pith.science/api/pith-number/MYYIOPP3BQDYRBMHJR6EJETE6U/events.json","paper":"https://pith.science/paper/MYYIOPP3"},"agent_actions":{"view_html":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U","download_json":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U.json","view_paper":"https://pith.science/paper/MYYIOPP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.02401&json=true","fetch_graph":"https://pith.science/api/pith-number/MYYIOPP3BQDYRBMHJR6EJETE6U/graph.json","fetch_events":"https://pith.science/api/pith-number/MYYIOPP3BQDYRBMHJR6EJETE6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U/action/storage_attestation","attest_author":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U/action/author_attestation","sign_citation":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U/action/citation_signature","submit_replication":"https://pith.science/pith/MYYIOPP3BQDYRBMHJR6EJETE6U/action/replication_record"}},"created_at":"2026-07-05T03:13:31.641795+00:00","updated_at":"2026-07-05T03:13:31.641795+00:00"}