{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KIVSEI3CXEBJKDMRECVKNCUNWC","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":"b4b6d46008fcd350bd345fea611a4dcf778843ecc7005eb94c112abec059cb01","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T09:51:49Z","title_canon_sha256":"27fc468c5607fbebb5b32d63c4913ca2817bb434c82328f6af8608e10b4807f9"},"schema_version":"1.0","source":{"id":"2402.11525","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11525","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11525v3","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11525","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_12","alias_value":"KIVSEI3CXEBJ","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_16","alias_value":"KIVSEI3CXEBJKDMR","created_at":"2026-07-05T07:49:56Z"},{"alias_kind":"pith_short_8","alias_value":"KIVSEI3C","created_at":"2026-07-05T07:49:56Z"}],"graph_snapshots":[{"event_id":"sha256:66efc493ad6a9d2ccd33032ca1cb2fc521add4f37d7f8c1f633bc1ba02088666","target":"graph","created_at":"2026-07-05T07:49:56Z","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/2402.11525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Faithfulness, expressiveness, and elegance is the constant pursuit in machine translation. However, traditional metrics like \\textit{BLEU} do not strictly align with human preference of translation quality. In this paper, we explore leveraging reinforcement learning with human feedback (\\textit{RLHF}) to improve translation quality. It is non-trivial to collect a large high-quality dataset of human comparisons between translations, especially for low-resource languages. To address this issue, we propose a cost-effective preference learning strategy, optimizing reward models by distinguishing b","authors_text":"Can Zu, Jun Zhao, Lu Chen, Nuo Xu, Qi Zhang, Rui Zheng, Shihan Dou, Sixian Li, Tao Gui, Wenjuan Qin, Xuanjing Huang, Zhihao Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T09:51:49Z","title":"Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11525","kind":"arxiv","version":3},"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":"sha256:66117173eb554b9e90e5222f839852342730d16275a0e0f2a220d7a108ec12d9","target":"record","created_at":"2026-07-05T07:49:56Z","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":"b4b6d46008fcd350bd345fea611a4dcf778843ecc7005eb94c112abec059cb01","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T09:51:49Z","title_canon_sha256":"27fc468c5607fbebb5b32d63c4913ca2817bb434c82328f6af8608e10b4807f9"},"schema_version":"1.0","source":{"id":"2402.11525","kind":"arxiv","version":3}},"canonical_sha256":"522b222362b902950d9120aaa68a8db08d3acf7570e5c6cc804a604ee9bb76d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"522b222362b902950d9120aaa68a8db08d3acf7570e5c6cc804a604ee9bb76d0","first_computed_at":"2026-07-05T07:49:56.206915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:56.206915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c8xKUeRy5ok3bUlBM1ETWSR5erlAnfV4IPN5iIf2dV9Uh1f3qbPvBIWORvzcAhARH8gfUOgDaki1Nw4YkByZDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:56.207559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11525","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66117173eb554b9e90e5222f839852342730d16275a0e0f2a220d7a108ec12d9","sha256:66efc493ad6a9d2ccd33032ca1cb2fc521add4f37d7f8c1f633bc1ba02088666"],"state_sha256":"c107843f4b08661966bdab7a886bc51e7b51554ce5974e04d138af4d8125c85d"}