{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FBBRPPSJ2AVO4FMJTQMNON5BRQ","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":"2ca4ad7ec94dbe7b7a75ba58f2b344e7423e331813bc444235cea7372e7d2947","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T11:11:14Z","title_canon_sha256":"fafdbd8eb82d028c14928abecaec26c56e57b46ea53239ae9b2ca7f7a9fd634c"},"schema_version":"1.0","source":{"id":"2504.13630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13630","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13630v1","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13630","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"FBBRPPSJ2AVO","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"FBBRPPSJ2AVO4FMJ","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"FBBRPPSJ","created_at":"2026-07-05T10:50:59Z"}],"graph_snapshots":[{"event_id":"sha256:64bec666072779d288e3edfdb6dcaee1dcdd56b04d8f1063ccad4b2eea14603e","target":"graph","created_at":"2026-07-05T10:50:59Z","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/2504.13630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A key challenge in MT evaluation is the inherent noise and inconsistency of human ratings. Regression-based neural metrics struggle with this noise, while prompting LLMs shows promise at system-level evaluation but performs poorly at segment level. In this work, we propose ReMedy, a novel MT metric framework that reformulates translation evaluation as a reward modeling task. Instead of regressing on imperfect human ratings directly, ReMedy learns relative translation quality using pairwise preference data, resulting in a more reliable evaluation. In extensive experiments across WMT22-24 shared","authors_text":"Christof Monz, Shaomu Tan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T11:11:14Z","title":"Remedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13630","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":"sha256:89c66e8dbfec91d40d64391249b1c3402525ca843aeee2711b15e1324b323c2e","target":"record","created_at":"2026-07-05T10:50:59Z","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":"2ca4ad7ec94dbe7b7a75ba58f2b344e7423e331813bc444235cea7372e7d2947","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T11:11:14Z","title_canon_sha256":"fafdbd8eb82d028c14928abecaec26c56e57b46ea53239ae9b2ca7f7a9fd634c"},"schema_version":"1.0","source":{"id":"2504.13630","kind":"arxiv","version":1}},"canonical_sha256":"284317be49d02aee15899c18d737a18c00e664b86fb1dc3bde671ff8b22a8d2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"284317be49d02aee15899c18d737a18c00e664b86fb1dc3bde671ff8b22a8d2a","first_computed_at":"2026-07-05T10:50:59.360033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:59.360033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ezDuUzgLnfM64cmnoHc72Jv2eHsEbVhfYt3lW9JSMYC7FgCKLt9f6QpILqo4JnAV5p9d8E95VaAJqUb1deTNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:59.360506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89c66e8dbfec91d40d64391249b1c3402525ca843aeee2711b15e1324b323c2e","sha256:64bec666072779d288e3edfdb6dcaee1dcdd56b04d8f1063ccad4b2eea14603e"],"state_sha256":"c630482c475ccee41065ce900f7aa7190a4962fc5bf256958d7137376b218a0b"}