{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:V3ES232PZSJPCUEFJOJETND4BV","short_pith_number":"pith:V3ES232P","canonical_record":{"source":{"id":"1909.11861","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-26T03:06:47Z","cross_cats_sorted":[],"title_canon_sha256":"ee0542b66133d392a6e4352ae41cdf37362732d20e6ed578c0c15128d53d353a","abstract_canon_sha256":"37ab686ab998983dd460031d353a139b4e1cd21a660939c58ae7c2ceeaf5b917"},"schema_version":"1.0"},"canonical_sha256":"aec92d6f4fcc92f150854b9249b47c0d724baab33c2c0616c28246ac34173f64","source":{"kind":"arxiv","id":"1909.11861","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11861","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11861v3","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11861","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_12","alias_value":"V3ES232PZSJP","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_16","alias_value":"V3ES232PZSJPCUEF","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_8","alias_value":"V3ES232P","created_at":"2026-07-05T00:10:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:V3ES232PZSJPCUEFJOJETND4BV","target":"record","payload":{"canonical_record":{"source":{"id":"1909.11861","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-26T03:06:47Z","cross_cats_sorted":[],"title_canon_sha256":"ee0542b66133d392a6e4352ae41cdf37362732d20e6ed578c0c15128d53d353a","abstract_canon_sha256":"37ab686ab998983dd460031d353a139b4e1cd21a660939c58ae7c2ceeaf5b917"},"schema_version":"1.0"},"canonical_sha256":"aec92d6f4fcc92f150854b9249b47c0d724baab33c2c0616c28246ac34173f64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:04.484384Z","signature_b64":"90fHabU8QnfiCqM9yvvzKVDAIw2la3qG4KJz5SIsrHl18CU6+Z0rnxUYdYDD63nCvp/4YF91Sf36bM3ozm7rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aec92d6f4fcc92f150854b9249b47c0d724baab33c2c0616c28246ac34173f64","last_reissued_at":"2026-07-05T00:10:04.483933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:04.483933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.11861","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:10:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1LaFX8TqNZmtff9hWzDFFBZ1EhEWFOC4sVIMArQC1Eq762bKN6X4ZSzSP8weNzqbmKX/HlVwHZ6ZO1qd6MDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T04:31:22.246743Z"},"content_sha256":"39e09ed18378440cb557d6184f2a2af178de6e597062b80205c8a9b3ccdf9007","schema_version":"1.0","event_id":"sha256:39e09ed18378440cb557d6184f2a2af178de6e597062b80205c8a9b3ccdf9007"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:V3ES232PZSJPCUEFJOJETND4BV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arianna Yuan, Fei Wu, Jiwei Li, Xiangyuan Ren, Xiaoya Li, Yuxian Meng, Zijun Sun","submitted_at":"2019-09-26T03:06:47Z","abstract_excerpt":"In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude. Unprecedented challenges emerge in this situation compared to previous NMT work, including severe noise in the data and prohibitively long training time. We propose practical solutions to handle these issues and demonstrate that large-scale pretraining significantly improves NMT performance. We are able to push the BLEU score of WMT17 Chinese-English dataset to 32."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11861","kind":"arxiv","version":3},"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/1909.11861/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:10:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ca/EmrGb26Z9NInUW1Yex4G//4upcmybh+7qzd1UwG95YOih1N5APaBab2Q5pu6LLnnL8dTcgZSpng8UdTcZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T04:31:22.247119Z"},"content_sha256":"9701f19fdf941c0f28e94f137465a7a8449162cc0e74105165680c9ce82ac042","schema_version":"1.0","event_id":"sha256:9701f19fdf941c0f28e94f137465a7a8449162cc0e74105165680c9ce82ac042"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V3ES232PZSJPCUEFJOJETND4BV/bundle.json","state_url":"https://pith.science/pith/V3ES232PZSJPCUEFJOJETND4BV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V3ES232PZSJPCUEFJOJETND4BV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-27T04:31:22Z","links":{"resolver":"https://pith.science/pith/V3ES232PZSJPCUEFJOJETND4BV","bundle":"https://pith.science/pith/V3ES232PZSJPCUEFJOJETND4BV/bundle.json","state":"https://pith.science/pith/V3ES232PZSJPCUEFJOJETND4BV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V3ES232PZSJPCUEFJOJETND4BV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:V3ES232PZSJPCUEFJOJETND4BV","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":"37ab686ab998983dd460031d353a139b4e1cd21a660939c58ae7c2ceeaf5b917","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-26T03:06:47Z","title_canon_sha256":"ee0542b66133d392a6e4352ae41cdf37362732d20e6ed578c0c15128d53d353a"},"schema_version":"1.0","source":{"id":"1909.11861","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11861","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11861v3","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11861","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_12","alias_value":"V3ES232PZSJP","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_16","alias_value":"V3ES232PZSJPCUEF","created_at":"2026-07-05T00:10:04Z"},{"alias_kind":"pith_short_8","alias_value":"V3ES232P","created_at":"2026-07-05T00:10:04Z"}],"graph_snapshots":[{"event_id":"sha256:9701f19fdf941c0f28e94f137465a7a8449162cc0e74105165680c9ce82ac042","target":"graph","created_at":"2026-07-05T00:10:04Z","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/1909.11861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate the problem of training neural machine translation (NMT) systems with a dataset of more than 40 billion bilingual sentence pairs, which is larger than the largest dataset to date by orders of magnitude. Unprecedented challenges emerge in this situation compared to previous NMT work, including severe noise in the data and prohibitively long training time. We propose practical solutions to handle these issues and demonstrate that large-scale pretraining significantly improves NMT performance. We are able to push the BLEU score of WMT17 Chinese-English dataset to 32.","authors_text":"Arianna Yuan, Fei Wu, Jiwei Li, Xiangyuan Ren, Xiaoya Li, Yuxian Meng, Zijun Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-26T03:06:47Z","title":"Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11861","kind":"arxiv","version":3},"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":"sha256:39e09ed18378440cb557d6184f2a2af178de6e597062b80205c8a9b3ccdf9007","target":"record","created_at":"2026-07-05T00:10:04Z","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":"37ab686ab998983dd460031d353a139b4e1cd21a660939c58ae7c2ceeaf5b917","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-26T03:06:47Z","title_canon_sha256":"ee0542b66133d392a6e4352ae41cdf37362732d20e6ed578c0c15128d53d353a"},"schema_version":"1.0","source":{"id":"1909.11861","kind":"arxiv","version":3}},"canonical_sha256":"aec92d6f4fcc92f150854b9249b47c0d724baab33c2c0616c28246ac34173f64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aec92d6f4fcc92f150854b9249b47c0d724baab33c2c0616c28246ac34173f64","first_computed_at":"2026-07-05T00:10:04.483933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:04.483933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"90fHabU8QnfiCqM9yvvzKVDAIw2la3qG4KJz5SIsrHl18CU6+Z0rnxUYdYDD63nCvp/4YF91Sf36bM3ozm7rDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:04.484384Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11861","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39e09ed18378440cb557d6184f2a2af178de6e597062b80205c8a9b3ccdf9007","sha256:9701f19fdf941c0f28e94f137465a7a8449162cc0e74105165680c9ce82ac042"],"state_sha256":"e554ad67254ff5f60ce28da9a949b1fcfad1a23b65a0905323128cd752f700a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2dK/+8G/HpdiVwSPDMpT7noXIvOxsbVyF8uVGdtsicmp8z5HUMEKnMRYd2JEXYvo1PSKA7qSVQnlPu/R62ODw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T04:31:22.249382Z","bundle_sha256":"671b370f5669e42c41e9985f0e3ebf8b2f0bf754e68c7e041f6619ce97cb4ea3"}}