{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KTQLMCPIMRYTIWAULKDXVRSVCH","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":"4cc0acec9cf0c3b24637db00716ee7f16ca4d672bf1cb70083afea413028b293","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T17:00:13Z","title_canon_sha256":"ed0e2ba251e61b8aa52874f54490959512a720e673c3cadc2602211c98879e85"},"schema_version":"1.0","source":{"id":"2410.18027","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18027","created_at":"2026-07-05T10:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18027v2","created_at":"2026-07-05T10:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18027","created_at":"2026-07-05T10:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"KTQLMCPIMRYT","created_at":"2026-07-05T10:04:19Z"},{"alias_kind":"pith_short_16","alias_value":"KTQLMCPIMRYTIWAU","created_at":"2026-07-05T10:04:19Z"},{"alias_kind":"pith_short_8","alias_value":"KTQLMCPI","created_at":"2026-07-05T10:04:19Z"}],"graph_snapshots":[{"event_id":"sha256:72389dc83435306d8449f141015336013b912d73d9dd8801adb88b447654e281","target":"graph","created_at":"2026-07-05T10:04:19Z","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/2410.18027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with human feedback (RLHF) is shown to largely benefit from precise reward models (RMs). However, recent studies in reward modeling schemes are skewed towards English, limiting the applicability of RLHF in multilingual alignments. In this work, we investigate the cross-lingual transfer of RMs trained in diverse languages, primarily from English. Our experimental results demonstrate the strong cross-lingual transfer of English RMs, exceeding target language RMs by 3~4% average increase in Multilingual RewardBench. Furthermore, we analyze the cross-lingual transfer of RMs ","authors_text":"C\\'esar Rodr\\'iguez, James Thorne, Jiwoo Hong, Noah Lee, Rodrigo Mart\\'inez-Casta\\~no","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T17:00:13Z","title":"Cross-lingual Transfer of Reward Models in Multilingual Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18027","kind":"arxiv","version":2},"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":"sha256:313f8f8e1310e4239edfa674defa56e952b351515b9dc9aa8077e70a2c17393c","target":"record","created_at":"2026-07-05T10:04:19Z","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":"4cc0acec9cf0c3b24637db00716ee7f16ca4d672bf1cb70083afea413028b293","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T17:00:13Z","title_canon_sha256":"ed0e2ba251e61b8aa52874f54490959512a720e673c3cadc2602211c98879e85"},"schema_version":"1.0","source":{"id":"2410.18027","kind":"arxiv","version":2}},"canonical_sha256":"54e0b609e864713458145a877ac65511e4c36e554a70dec01eaf1cbbd9254d37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54e0b609e864713458145a877ac65511e4c36e554a70dec01eaf1cbbd9254d37","first_computed_at":"2026-07-05T10:04:19.008544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:19.008544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c86lxVHmsQzntupwD0Az/SVZAvTuvXj/MM+nn0ClYyvtY8GSfmDCjn+OB08rtP+ltYee8moM8fQgwArmA9MhDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:19.009101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18027","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:313f8f8e1310e4239edfa674defa56e952b351515b9dc9aa8077e70a2c17393c","sha256:72389dc83435306d8449f141015336013b912d73d9dd8801adb88b447654e281"],"state_sha256":"6382bdace14d95a32023f443fa058a1b3d1c11689235366831820074a932157c"}