{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P73THSSMQWE7STPSGFGMWBDO2T","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":"1d33c6a50ee824186c3c62a77ffda3aa6705a35f4ab0d951adf0950fbee39dec","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T18:59:47Z","title_canon_sha256":"b3b8262ebb6a09d842ca03eb3e0f342544467cd9f6061e61328448481498040b"},"schema_version":"1.0","source":{"id":"2501.13927","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13927","created_at":"2026-07-05T10:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13927v1","created_at":"2026-07-05T10:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13927","created_at":"2026-07-05T10:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"P73THSSMQWE7","created_at":"2026-07-05T10:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"P73THSSMQWE7STPS","created_at":"2026-07-05T10:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"P73THSSM","created_at":"2026-07-05T10:04:36Z"}],"graph_snapshots":[{"event_id":"sha256:d57d26b8222417fe39558c1278a3fbd7303d9f44c322f7743fc6dbf99beb1be4","target":"graph","created_at":"2026-07-05T10:04:36Z","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/2501.13927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of reinforcement learning from human feedback (RLHF). Direct Preference Optimization (DPO) has emerged as a simpler and more efficient alternative, but its performance depends heavily on the quality of preference data. To address this, we propose Confidence-Reward driven Preference Optimization (CRPO), a novel method that combines reward scores with model confidence to im","authors_text":"Guofeng Cui, Pichao Wang, Vimal Bhat, Yang Liu, Zemian Ke, Zhu Liu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T18:59:47Z","title":"CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13927","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":"sha256:569cd9d450aef19b400e4fb4155e1cea01a04be8c7bd9871c6a7907a5fbda0db","target":"record","created_at":"2026-07-05T10:04:36Z","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":"1d33c6a50ee824186c3c62a77ffda3aa6705a35f4ab0d951adf0950fbee39dec","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T18:59:47Z","title_canon_sha256":"b3b8262ebb6a09d842ca03eb3e0f342544467cd9f6061e61328448481498040b"},"schema_version":"1.0","source":{"id":"2501.13927","kind":"arxiv","version":1}},"canonical_sha256":"7ff733ca4c8589f94df2314ccb046ed4c1edc77be751c30ef2fbabbb36592faf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ff733ca4c8589f94df2314ccb046ed4c1edc77be751c30ef2fbabbb36592faf","first_computed_at":"2026-07-05T10:04:36.099826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:36.099826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k0WV2xUy9aQ7EIQ+arK/om2rMofhWN+hL37UE4OYZPctr5Mv/fToc0AerBgmwtilg20Miung4P3BJmFwDvI8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:36.100171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13927","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:569cd9d450aef19b400e4fb4155e1cea01a04be8c7bd9871c6a7907a5fbda0db","sha256:d57d26b8222417fe39558c1278a3fbd7303d9f44c322f7743fc6dbf99beb1be4"],"state_sha256":"3e6ba81d1941c31f7b0f35bb7db5a43c713e71362d7a98f8520804dbfa7b0c75"}