{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KAT5TF5TGLGVN6D3LF2NH6OTD2","short_pith_number":"pith:KAT5TF5T","canonical_record":{"source":{"id":"2408.06537","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T00:06:56Z","cross_cats_sorted":[],"title_canon_sha256":"0ea56aae97c09e3e8ca27d352c98064f96acefb65738be3d4421e6ff74953d8b","abstract_canon_sha256":"b07c7a6a1daa9ff3ca959f2968e6a3f0c0702da3e15ddaacdc0610b79f6be6b9"},"schema_version":"1.0"},"canonical_sha256":"5027d997b332cd56f87b5974d3f9d31e90910af6492749b1f684368a7fbc2ce1","source":{"kind":"arxiv","id":"2408.06537","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06537","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06537v5","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06537","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"pith_short_12","alias_value":"KAT5TF5TGLGV","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"pith_short_16","alias_value":"KAT5TF5TGLGVN6D3","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"pith_short_8","alias_value":"KAT5TF5T","created_at":"2026-07-05T09:39:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KAT5TF5TGLGVN6D3LF2NH6OTD2","target":"record","payload":{"canonical_record":{"source":{"id":"2408.06537","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T00:06:56Z","cross_cats_sorted":[],"title_canon_sha256":"0ea56aae97c09e3e8ca27d352c98064f96acefb65738be3d4421e6ff74953d8b","abstract_canon_sha256":"b07c7a6a1daa9ff3ca959f2968e6a3f0c0702da3e15ddaacdc0610b79f6be6b9"},"schema_version":"1.0"},"canonical_sha256":"5027d997b332cd56f87b5974d3f9d31e90910af6492749b1f684368a7fbc2ce1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:25.918055Z","signature_b64":"g7tyK5HEMkcXWHh1lYssJyPZN38FdH895e5SG5/iKTUnVfI2pjXI1pJJkrd1/czjcgQcz1IvSU5+hIBouF+kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5027d997b332cd56f87b5974d3f9d31e90910af6492749b1f684368a7fbc2ce1","last_reissued_at":"2026-07-05T09:39:25.917479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:25.917479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.06537","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:39:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m7Obg+nS3O0oTQgo80rgo/HNzVd3cFjFRUeDivsJZGSFsfiGF8RH5ytHCGfJv4u6YPVmuh76jOdQSGVChkUwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:59:32.924348Z"},"content_sha256":"5d7ca816e9dbb84ffccdef09db32ca576380409e6613f0bad819ccb3bf6c6ad0","schema_version":"1.0","event_id":"sha256:5d7ca816e9dbb84ffccdef09db32ca576380409e6613f0bad819ccb3bf6c6ad0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KAT5TF5TGLGVN6D3LF2NH6OTD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Vilar, Mara Finkelstein, Markus Freitag","submitted_at":"2024-08-13T00:06:56Z","abstract_excerpt":"Recent research in neural machine translation (NMT) has shown that training on high-quality machine-generated data can outperform training on human-generated data. This work accompanies the first-ever release of a LLM-generated, MBR-decoded and QE-reranked dataset with both sentence-level and multi-sentence examples. We perform extensive experiments to demonstrate the quality of our dataset in terms of its downstream impact on NMT model performance. We find that training from scratch on our (machine-generated) dataset outperforms training on the (web-crawled) WMT'23 training dataset (which is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06537","kind":"arxiv","version":5},"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/2408.06537/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":"2026-07-05T09:39:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WvVMNdogG7BLtJbr14IYOajw+X4hjZzn3nwZMQTmFds2PGKGUQ+AIu490N1PuBsCtuW8+Xpm+olYWcOw+gsMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:59:32.925227Z"},"content_sha256":"c813ba3c95b74d3e7473ab1b807a62eabe0fcb4634131091e187b5f52d84affa","schema_version":"1.0","event_id":"sha256:c813ba3c95b74d3e7473ab1b807a62eabe0fcb4634131091e187b5f52d84affa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KAT5TF5TGLGVN6D3LF2NH6OTD2/bundle.json","state_url":"https://pith.science/pith/KAT5TF5TGLGVN6D3LF2NH6OTD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KAT5TF5TGLGVN6D3LF2NH6OTD2/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":"2026-08-05T04:59:32Z","links":{"resolver":"https://pith.science/pith/KAT5TF5TGLGVN6D3LF2NH6OTD2","bundle":"https://pith.science/pith/KAT5TF5TGLGVN6D3LF2NH6OTD2/bundle.json","state":"https://pith.science/pith/KAT5TF5TGLGVN6D3LF2NH6OTD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KAT5TF5TGLGVN6D3LF2NH6OTD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KAT5TF5TGLGVN6D3LF2NH6OTD2","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":"b07c7a6a1daa9ff3ca959f2968e6a3f0c0702da3e15ddaacdc0610b79f6be6b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T00:06:56Z","title_canon_sha256":"0ea56aae97c09e3e8ca27d352c98064f96acefb65738be3d4421e6ff74953d8b"},"schema_version":"1.0","source":{"id":"2408.06537","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06537","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06537v5","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06537","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"pith_short_12","alias_value":"KAT5TF5TGLGV","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"pith_short_16","alias_value":"KAT5TF5TGLGVN6D3","created_at":"2026-07-05T09:39:25Z"},{"alias_kind":"pith_short_8","alias_value":"KAT5TF5T","created_at":"2026-07-05T09:39:25Z"}],"graph_snapshots":[{"event_id":"sha256:c813ba3c95b74d3e7473ab1b807a62eabe0fcb4634131091e187b5f52d84affa","target":"graph","created_at":"2026-07-05T09:39:25Z","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/2408.06537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research in neural machine translation (NMT) has shown that training on high-quality machine-generated data can outperform training on human-generated data. This work accompanies the first-ever release of a LLM-generated, MBR-decoded and QE-reranked dataset with both sentence-level and multi-sentence examples. We perform extensive experiments to demonstrate the quality of our dataset in terms of its downstream impact on NMT model performance. We find that training from scratch on our (machine-generated) dataset outperforms training on the (web-crawled) WMT'23 training dataset (which is ","authors_text":"David Vilar, Mara Finkelstein, Markus Freitag","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T00:06:56Z","title":"Introducing the NewsPaLM MBR and QE Dataset: LLM-Generated High-Quality Parallel Data Outperforms Traditional Web-Crawled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06537","kind":"arxiv","version":5},"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":"sha256:5d7ca816e9dbb84ffccdef09db32ca576380409e6613f0bad819ccb3bf6c6ad0","target":"record","created_at":"2026-07-05T09:39:25Z","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":"b07c7a6a1daa9ff3ca959f2968e6a3f0c0702da3e15ddaacdc0610b79f6be6b9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T00:06:56Z","title_canon_sha256":"0ea56aae97c09e3e8ca27d352c98064f96acefb65738be3d4421e6ff74953d8b"},"schema_version":"1.0","source":{"id":"2408.06537","kind":"arxiv","version":5}},"canonical_sha256":"5027d997b332cd56f87b5974d3f9d31e90910af6492749b1f684368a7fbc2ce1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5027d997b332cd56f87b5974d3f9d31e90910af6492749b1f684368a7fbc2ce1","first_computed_at":"2026-07-05T09:39:25.917479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:25.917479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g7tyK5HEMkcXWHh1lYssJyPZN38FdH895e5SG5/iKTUnVfI2pjXI1pJJkrd1/czjcgQcz1IvSU5+hIBouF+kBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:25.918055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06537","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d7ca816e9dbb84ffccdef09db32ca576380409e6613f0bad819ccb3bf6c6ad0","sha256:c813ba3c95b74d3e7473ab1b807a62eabe0fcb4634131091e187b5f52d84affa"],"state_sha256":"d4f1140f770d7752b49f33b8f78c010cebf61ae6bd5d6a1ca5bd9934e9303294"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66EzYVhYLSE8JFlFW0lJo6K6Kwy1Lj6iL7V96wlNudbkYyIIYED/eOTElirAY8IvqyNo9Q0G7V+lKfFnyW6cDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:59:32.930585Z","bundle_sha256":"ef694b28c6f2f8a6576a235d5fb79c560311deda3ec764e6eaa52880d14e187a"}}