{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OT3JPYJADI3XWKO2DQOXSW5WHU","short_pith_number":"pith:OT3JPYJA","canonical_record":{"source":{"id":"2311.05350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:21:34Z","cross_cats_sorted":[],"title_canon_sha256":"6d9a03227aa4ba1d6d28a8dc2f290b4ac94e6876138c7da3437944d553cb0ef0","abstract_canon_sha256":"75d39907ea9c2fff80b6fba0ba61bde1b722aef6e2b40f3660f35eea48317f6f"},"schema_version":"1.0"},"canonical_sha256":"74f697e1201a377b29da1c1d795bb63d3b2ba3e61b7bee8949f5de24bb071f6a","source":{"kind":"arxiv","id":"2311.05350","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05350","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05350v1","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05350","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_12","alias_value":"OT3JPYJADI3X","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_16","alias_value":"OT3JPYJADI3XWKO2","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_8","alias_value":"OT3JPYJA","created_at":"2026-07-05T07:10:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OT3JPYJADI3XWKO2DQOXSW5WHU","target":"record","payload":{"canonical_record":{"source":{"id":"2311.05350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:21:34Z","cross_cats_sorted":[],"title_canon_sha256":"6d9a03227aa4ba1d6d28a8dc2f290b4ac94e6876138c7da3437944d553cb0ef0","abstract_canon_sha256":"75d39907ea9c2fff80b6fba0ba61bde1b722aef6e2b40f3660f35eea48317f6f"},"schema_version":"1.0"},"canonical_sha256":"74f697e1201a377b29da1c1d795bb63d3b2ba3e61b7bee8949f5de24bb071f6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:58.399585Z","signature_b64":"lLuo9C11mcP4MXlvF0driyGciusYHIyLAgSSXP/3F8HX0oqiIjgBMDUgpd63PMq7soB/fSt9HvBbDP3RLr/OAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74f697e1201a377b29da1c1d795bb63d3b2ba3e61b7bee8949f5de24bb071f6a","last_reissued_at":"2026-07-05T07:10:58.399091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:58.399091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.05350","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yKqtLJz6GCZGQHkz7R/VKr9aBWn8vQik4tMJF8Tu+HuGOshFduvBfMZWs7XoUbpEFh0O4QvwDRmgVZW1lvhDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:26:12.181647Z"},"content_sha256":"4e2d7f788f62192623b2d2ade01d80ffaa7faadcae995a44bb05e551776df120","schema_version":"1.0","event_id":"sha256:4e2d7f788f62192623b2d2ade01d80ffaa7faadcae995a44bb05e551776df120"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OT3JPYJADI3XWKO2DQOXSW5WHU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"There's no Data Like Better Data: Using QE Metrics for MT Data Filtering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Deutsch, David Vilar, Jan-Thorsten Peter, Juraj Juraska, Mara Finkelstein, Markus Freitag","submitted_at":"2023-11-09T13:21:34Z","abstract_excerpt":"Quality Estimation (QE), the evaluation of machine translation output without the need of explicit references, has seen big improvements in the last years with the use of neural metrics. In this paper we analyze the viability of using QE metrics for filtering out bad quality sentence pairs in the training data of neural machine translation systems~(NMT). While most corpus filtering methods are focused on detecting noisy examples in collections of texts, usually huge amounts of web crawled data, QE models are trained to discriminate more fine-grained quality differences. We show that by selecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05350","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/2311.05350/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":"2026-07-05T07:10:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8U9qIooJjbj3AgW2olQPysa05YofPz13ZMSziaU13eAP1NQbFA5b4yBlaqIO/zkNqpoHHGP2E7tbJLI/hQ6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:26:12.182258Z"},"content_sha256":"cce023107c95e02b13c6f1726edc73f397890d9e1e9863d67e5652836fe2d9bb","schema_version":"1.0","event_id":"sha256:cce023107c95e02b13c6f1726edc73f397890d9e1e9863d67e5652836fe2d9bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OT3JPYJADI3XWKO2DQOXSW5WHU/bundle.json","state_url":"https://pith.science/pith/OT3JPYJADI3XWKO2DQOXSW5WHU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OT3JPYJADI3XWKO2DQOXSW5WHU/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":"2026-08-06T01:26:12Z","links":{"resolver":"https://pith.science/pith/OT3JPYJADI3XWKO2DQOXSW5WHU","bundle":"https://pith.science/pith/OT3JPYJADI3XWKO2DQOXSW5WHU/bundle.json","state":"https://pith.science/pith/OT3JPYJADI3XWKO2DQOXSW5WHU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OT3JPYJADI3XWKO2DQOXSW5WHU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OT3JPYJADI3XWKO2DQOXSW5WHU","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":"75d39907ea9c2fff80b6fba0ba61bde1b722aef6e2b40f3660f35eea48317f6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:21:34Z","title_canon_sha256":"6d9a03227aa4ba1d6d28a8dc2f290b4ac94e6876138c7da3437944d553cb0ef0"},"schema_version":"1.0","source":{"id":"2311.05350","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05350","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05350v1","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05350","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_12","alias_value":"OT3JPYJADI3X","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_16","alias_value":"OT3JPYJADI3XWKO2","created_at":"2026-07-05T07:10:58Z"},{"alias_kind":"pith_short_8","alias_value":"OT3JPYJA","created_at":"2026-07-05T07:10:58Z"}],"graph_snapshots":[{"event_id":"sha256:cce023107c95e02b13c6f1726edc73f397890d9e1e9863d67e5652836fe2d9bb","target":"graph","created_at":"2026-07-05T07:10:58Z","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/2311.05350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quality Estimation (QE), the evaluation of machine translation output without the need of explicit references, has seen big improvements in the last years with the use of neural metrics. In this paper we analyze the viability of using QE metrics for filtering out bad quality sentence pairs in the training data of neural machine translation systems~(NMT). While most corpus filtering methods are focused on detecting noisy examples in collections of texts, usually huge amounts of web crawled data, QE models are trained to discriminate more fine-grained quality differences. We show that by selecti","authors_text":"Daniel Deutsch, David Vilar, Jan-Thorsten Peter, Juraj Juraska, Mara Finkelstein, Markus Freitag","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:21:34Z","title":"There's no Data Like Better Data: Using QE Metrics for MT Data Filtering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05350","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":"sha256:4e2d7f788f62192623b2d2ade01d80ffaa7faadcae995a44bb05e551776df120","target":"record","created_at":"2026-07-05T07:10:58Z","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":"75d39907ea9c2fff80b6fba0ba61bde1b722aef6e2b40f3660f35eea48317f6f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T13:21:34Z","title_canon_sha256":"6d9a03227aa4ba1d6d28a8dc2f290b4ac94e6876138c7da3437944d553cb0ef0"},"schema_version":"1.0","source":{"id":"2311.05350","kind":"arxiv","version":1}},"canonical_sha256":"74f697e1201a377b29da1c1d795bb63d3b2ba3e61b7bee8949f5de24bb071f6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74f697e1201a377b29da1c1d795bb63d3b2ba3e61b7bee8949f5de24bb071f6a","first_computed_at":"2026-07-05T07:10:58.399091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:58.399091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lLuo9C11mcP4MXlvF0driyGciusYHIyLAgSSXP/3F8HX0oqiIjgBMDUgpd63PMq7soB/fSt9HvBbDP3RLr/OAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:58.399585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05350","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e2d7f788f62192623b2d2ade01d80ffaa7faadcae995a44bb05e551776df120","sha256:cce023107c95e02b13c6f1726edc73f397890d9e1e9863d67e5652836fe2d9bb"],"state_sha256":"231a630b7aef1b20fc1d99d7af1476736ab0003ee81a5b1db2b4994f6401605e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dVSfTN/xtD0zL5qoP/OSIgY5c/TjVMKTvyLmpJjUA+LLH8eFK+IayRvLvwmBpSE/boYJTdI4OfwAN0jSiYdABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:26:12.187881Z","bundle_sha256":"1abc203b3ecb02489af7a43e2d94fbf269e9939c039ab83a60baa761d8c63490"}}