{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PZBZNGZRMJGPOVV3DPL2WETODT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bc87efeeba3627e7135bf2c81946d721a1537254bf7cf0995e143342704aedef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T17:35:34Z","title_canon_sha256":"adb4557a3ddd93724c44fa7d0f8eacc0f482fa24d4cf1335977a9d659d173b9a"},"schema_version":"1.0","source":{"id":"2110.05448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05448","created_at":"2026-07-05T03:21:35Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05448v1","created_at":"2026-07-05T03:21:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05448","created_at":"2026-07-05T03:21:35Z"},{"alias_kind":"pith_short_12","alias_value":"PZBZNGZRMJGP","created_at":"2026-07-05T03:21:35Z"},{"alias_kind":"pith_short_16","alias_value":"PZBZNGZRMJGPOVV3","created_at":"2026-07-05T03:21:35Z"},{"alias_kind":"pith_short_8","alias_value":"PZBZNGZR","created_at":"2026-07-05T03:21:35Z"}],"graph_snapshots":[{"event_id":"sha256:e13a71c73b3b02d0edaf1488fe76ace65ede336666434ab4442b2dbcfb977462","target":"graph","created_at":"2026-07-05T03:21:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.05448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first use the zero-shot translation ability of large pre-trained language models to generate translations for a small set of unlabeled sentences. We then amplify these zero-shot translations by using them as few-shot demonstrations for sampling a larger synthetic dataset. This dataset is distilled by discarding the few-shot demonstrations and then fine-tuning. Durin","authors_text":"Aditya Ramesh, Alec Radford, Alex Ray, Arvind Neelakantan, Harrison Edwards, Igor Babuschkin, Ilya Sutskever, Jesse Michael Han, Pranav Shyam, Stanislas Polu, Tao Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T17:35:34Z","title":"Unsupervised Neural Machine Translation with Generative Language Models Only"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05448","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:44670a49f2c039f8b34d7180308bd560b16520127d8d52d508289788ef51c500","target":"record","created_at":"2026-07-05T03:21:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bc87efeeba3627e7135bf2c81946d721a1537254bf7cf0995e143342704aedef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T17:35:34Z","title_canon_sha256":"adb4557a3ddd93724c44fa7d0f8eacc0f482fa24d4cf1335977a9d659d173b9a"},"schema_version":"1.0","source":{"id":"2110.05448","kind":"arxiv","version":1}},"canonical_sha256":"7e43969b31624cf756bb1bd7ab126e1cd3c39b8dde899bfdcd27d54ebd8bcb93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e43969b31624cf756bb1bd7ab126e1cd3c39b8dde899bfdcd27d54ebd8bcb93","first_computed_at":"2026-07-05T03:21:35.166507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:35.166507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UlSQ9NjbV+T6RGBNuBTRoN+rGcbgjsr6qmvNS16HjCnrxXJymGL2ckNi1JcqZBCNPxDX500SBNTRKBGR+bsICA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:35.166942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44670a49f2c039f8b34d7180308bd560b16520127d8d52d508289788ef51c500","sha256:e13a71c73b3b02d0edaf1488fe76ace65ede336666434ab4442b2dbcfb977462"],"state_sha256":"7cf5805b6dfb3c60b6ce3a0341f595dfbca6796f6ac7851df01c56a138d61249"}