{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PSINHPDEP6RECHBXTZN2HF6TVZ","short_pith_number":"pith:PSINHPDE","schema_version":"1.0","canonical_sha256":"7c90d3bc647fa2411c379e5ba397d3ae5491abc61a73f4142dd48c4e3e47b635","source":{"kind":"arxiv","id":"2406.00049","version":2},"attestation_state":"computed","paper":{"title":"QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Ant\\'onio Farinhas, Gon\\c{c}alo R. A. Faria, Jos\\'e G. C. de Souza, Ricardo Rei, Sweta Agrawal","submitted_at":"2024-05-28T17:36:06Z","abstract_excerpt":"An important challenge in machine translation (MT) is to generate high-quality and diverse translations. Prior work has shown that the estimated likelihood from the MT model correlates poorly with translation quality. In contrast, quality evaluation metrics (such as COMET or BLEURT) exhibit high correlations with human judgments, which has motivated their use as rerankers (such as quality-aware and minimum Bayes risk decoding). However, relying on a single translation with high estimated quality increases the chances of \"gaming the metric''. In this paper, we address the problem of sampling a "},"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":"2406.00049","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T17:36:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b445452ddb3eb94df7dbebf1bd73933f7387edc8b68b7886762634b84ef234ce","abstract_canon_sha256":"10de5a13ac805dce0c4800637cceaa2952695ebadb3c4ceaf2a9fe682043266f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:05.109956Z","signature_b64":"utaODu4m3VonbrPypl+dMGEe9C8hWj3zPIT/FRrAoBSpkwVdUhy1+9n1U1iIXk5Z7g54WCeCiF94lxBKu0gNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c90d3bc647fa2411c379e5ba397d3ae5491abc61a73f4142dd48c4e3e47b635","last_reissued_at":"2026-07-05T09:21:05.109452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:05.109452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Ant\\'onio Farinhas, Gon\\c{c}alo R. A. Faria, Jos\\'e G. C. de Souza, Ricardo Rei, Sweta Agrawal","submitted_at":"2024-05-28T17:36:06Z","abstract_excerpt":"An important challenge in machine translation (MT) is to generate high-quality and diverse translations. Prior work has shown that the estimated likelihood from the MT model correlates poorly with translation quality. In contrast, quality evaluation metrics (such as COMET or BLEURT) exhibit high correlations with human judgments, which has motivated their use as rerankers (such as quality-aware and minimum Bayes risk decoding). However, relying on a single translation with high estimated quality increases the chances of \"gaming the metric''. In this paper, we address the problem of sampling a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00049","kind":"arxiv","version":2},"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/2406.00049/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":"2406.00049","created_at":"2026-07-05T09:21:05.109520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00049v2","created_at":"2026-07-05T09:21:05.109520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00049","created_at":"2026-07-05T09:21:05.109520+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSINHPDEP6RE","created_at":"2026-07-05T09:21:05.109520+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSINHPDEP6RECHBX","created_at":"2026-07-05T09:21:05.109520+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSINHPDE","created_at":"2026-07-05T09:21:05.109520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08561","citing_title":"Quality-Aware Decoding: Unifying Quality Estimation and Decoding","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ","json":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ.json","graph_json":"https://pith.science/api/pith-number/PSINHPDEP6RECHBXTZN2HF6TVZ/graph.json","events_json":"https://pith.science/api/pith-number/PSINHPDEP6RECHBXTZN2HF6TVZ/events.json","paper":"https://pith.science/paper/PSINHPDE"},"agent_actions":{"view_html":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ","download_json":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ.json","view_paper":"https://pith.science/paper/PSINHPDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00049&json=true","fetch_graph":"https://pith.science/api/pith-number/PSINHPDEP6RECHBXTZN2HF6TVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PSINHPDEP6RECHBXTZN2HF6TVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ/action/storage_attestation","attest_author":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ/action/author_attestation","sign_citation":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ/action/citation_signature","submit_replication":"https://pith.science/pith/PSINHPDEP6RECHBXTZN2HF6TVZ/action/replication_record"}},"created_at":"2026-07-05T09:21:05.109520+00:00","updated_at":"2026-07-05T09:21:05.109520+00:00"}