{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LNWSB4KVXPIU3PF5RT3462KZT7","short_pith_number":"pith:LNWSB4KV","schema_version":"1.0","canonical_sha256":"5b6d20f155bbd14dbcbd8cf7cf69599fc12a8fa273d47b3a02ca37a0bb9ff714","source":{"kind":"arxiv","id":"2203.00201","version":1},"attestation_state":"computed","paper":{"title":"RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baosong Yang, Dayiheng Liu, Yidan Zhang, Yu Wan, Zhenan He","submitted_at":"2022-03-01T03:12:17Z","abstract_excerpt":"Beam search is the most widely used decoding method for neural machine translation (NMT). In practice, the top-1 candidate with the highest log-probability among the n candidates is selected as the preferred one. However, this top-1 candidate may not be the best overall translation among the n-best list. Recently, Minimum Bayes Risk (MBR) decoding has been proposed to improve the quality for NMT, which seeks for a consensus translation that is closest on average to other candidates from the n-best list. We argue that MBR still suffers from the following problems: The utility function only cons"},"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":"2203.00201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T03:12:17Z","cross_cats_sorted":[],"title_canon_sha256":"82cb9088492b8794010aa39016df2188158485c9828416ab58b325a48f48a750","abstract_canon_sha256":"5e9691fcb4c583e52af878f08f6842870e86f51e3f18484da1d69e99dd8a24c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:14.992527Z","signature_b64":"saBjhGv1XBIlXloDGJWi1cXckCvRNenXx0+olvPqgysvGJH01RfCQmmEFtjdSQAdqn5gq06O3WmYdEdyYOLzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b6d20f155bbd14dbcbd8cf7cf69599fc12a8fa273d47b3a02ca37a0bb9ff714","last_reissued_at":"2026-07-05T04:01:14.992069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:14.992069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baosong Yang, Dayiheng Liu, Yidan Zhang, Yu Wan, Zhenan He","submitted_at":"2022-03-01T03:12:17Z","abstract_excerpt":"Beam search is the most widely used decoding method for neural machine translation (NMT). In practice, the top-1 candidate with the highest log-probability among the n candidates is selected as the preferred one. However, this top-1 candidate may not be the best overall translation among the n-best list. Recently, Minimum Bayes Risk (MBR) decoding has been proposed to improve the quality for NMT, which seeks for a consensus translation that is closest on average to other candidates from the n-best list. We argue that MBR still suffers from the following problems: The utility function only cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00201","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/2203.00201/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":"2203.00201","created_at":"2026-07-05T04:01:14.992128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.00201v1","created_at":"2026-07-05T04:01:14.992128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00201","created_at":"2026-07-05T04:01:14.992128+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNWSB4KVXPIU","created_at":"2026-07-05T04:01:14.992128+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNWSB4KVXPIU3PF5","created_at":"2026-07-05T04:01:14.992128+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNWSB4KV","created_at":"2026-07-05T04:01:14.992128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7","json":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7.json","graph_json":"https://pith.science/api/pith-number/LNWSB4KVXPIU3PF5RT3462KZT7/graph.json","events_json":"https://pith.science/api/pith-number/LNWSB4KVXPIU3PF5RT3462KZT7/events.json","paper":"https://pith.science/paper/LNWSB4KV"},"agent_actions":{"view_html":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7","download_json":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7.json","view_paper":"https://pith.science/paper/LNWSB4KV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.00201&json=true","fetch_graph":"https://pith.science/api/pith-number/LNWSB4KVXPIU3PF5RT3462KZT7/graph.json","fetch_events":"https://pith.science/api/pith-number/LNWSB4KVXPIU3PF5RT3462KZT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7/action/storage_attestation","attest_author":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7/action/author_attestation","sign_citation":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7/action/citation_signature","submit_replication":"https://pith.science/pith/LNWSB4KVXPIU3PF5RT3462KZT7/action/replication_record"}},"created_at":"2026-07-05T04:01:14.992128+00:00","updated_at":"2026-07-05T04:01:14.992128+00:00"}