{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2LANJRY3MSVA6K5J5SXXDPNBOT","short_pith_number":"pith:2LANJRY3","schema_version":"1.0","canonical_sha256":"d2c0d4c71b64aa0f2ba9ecaf71bda174d77939caafddb7b9c7cc26c25f5a9ecb","source":{"kind":"arxiv","id":"2106.13627","version":1},"attestation_state":"computed","paper":{"title":"Language Models are Good Translators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maosong Sun, Shuo Wang, Wenxuan Wang, Yang Liu, Zhaopeng Tu, Zhixing Tan","submitted_at":"2021-06-25T13:30:29Z","abstract_excerpt":"Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of large-scale pre-trained language models on machine translation in a limited scenario, we firstly demonstrate that a single language model (LM4MT) can achieve comparable performance with strong encoder-decoder NMT models on standard machine translation benchmarks, using the same training data and similar amount of model parameters. LM4MT can also easily utilize source-side texts as additional supervision. Though modelin"},"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":"2106.13627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T13:30:29Z","cross_cats_sorted":[],"title_canon_sha256":"80b81ca26c33e7249a656c6b095ffdfc3f7f8e9e18957cbe1ad41dd1ce4cb516","abstract_canon_sha256":"bd0e2fd8799b0981008c2f2ac9fdaf5913f3a3f5219a0dee8d252d4256c32280"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:24.274544Z","signature_b64":"lZizgi6Ty5VMfn/HRdvaVrk35jYUh5xb+cAg6DVLPRmh+5oTPp2qkSN+mtPEx6CvCC34p8MRa2697escazJcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2c0d4c71b64aa0f2ba9ecaf71bda174d77939caafddb7b9c7cc26c25f5a9ecb","last_reissued_at":"2026-07-05T02:52:24.274034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:24.274034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models are Good Translators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maosong Sun, Shuo Wang, Wenxuan Wang, Yang Liu, Zhaopeng Tu, Zhixing Tan","submitted_at":"2021-06-25T13:30:29Z","abstract_excerpt":"Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of large-scale pre-trained language models on machine translation in a limited scenario, we firstly demonstrate that a single language model (LM4MT) can achieve comparable performance with strong encoder-decoder NMT models on standard machine translation benchmarks, using the same training data and similar amount of model parameters. LM4MT can also easily utilize source-side texts as additional supervision. Though modelin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13627","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/2106.13627/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":"2106.13627","created_at":"2026-07-05T02:52:24.274096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13627v1","created_at":"2026-07-05T02:52:24.274096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13627","created_at":"2026-07-05T02:52:24.274096+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LANJRY3MSVA","created_at":"2026-07-05T02:52:24.274096+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LANJRY3MSVA6K5J","created_at":"2026-07-05T02:52:24.274096+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LANJRY3","created_at":"2026-07-05T02:52:24.274096+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/2LANJRY3MSVA6K5J5SXXDPNBOT","json":"https://pith.science/pith/2LANJRY3MSVA6K5J5SXXDPNBOT.json","graph_json":"https://pith.science/api/pith-number/2LANJRY3MSVA6K5J5SXXDPNBOT/graph.json","events_json":"https://pith.science/api/pith-number/2LANJRY3MSVA6K5J5SXXDPNBOT/events.json","paper":"https://pith.science/paper/2LANJRY3"},"agent_actions":{"view_html":"https://pith.science/pith/2LANJRY3MSVA6K5J5SXXDPNBOT","download_json":"https://pith.science/pith/2LANJRY3MSVA6K5J5SXXDPNBOT.json","view_paper":"https://pith.science/paper/2LANJRY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13627&json=true","fetch_graph":"https://pith.science/api/pith-number/2LANJRY3MSVA6K5J5SXXDPNBOT/graph.json","fetch_events":"https://pith.science/api/pith-number/2LANJRY3MSVA6K5J5SXXDPNBOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LANJRY3MSVA6K5J5SXXDPNBOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LANJRY3MSVA6K5J5SXXDPNBOT/action/storage_attestation","attest_author":"https://pith.science/pith/2LANJRY3MSVA6K5J5SXXDPNBOT/action/author_attestation","sign_citation":"https://pith.science/pith/2LANJRY3MSVA6K5J5SXXDPNBOT/action/citation_signature","submit_replication":"https://pith.science/pith/2LANJRY3MSVA6K5J5SXXDPNBOT/action/replication_record"}},"created_at":"2026-07-05T02:52:24.274096+00:00","updated_at":"2026-07-05T02:52:24.274096+00:00"}