{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CYEJOF4COFNCLH63JLJN5RUYQE","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":"3fc7025037d23ebf01772cda13cf92b6af637830a9cec6602a17cf722d7cfdd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T16:52:36Z","title_canon_sha256":"60e34aa50e8a763f96fff37105688a5d820e2937cd3175c04e9f9bbbda009b22"},"schema_version":"1.0","source":{"id":"2404.12318","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12318","created_at":"2026-07-05T09:19:55Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12318v2","created_at":"2026-07-05T09:19:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12318","created_at":"2026-07-05T09:19:55Z"},{"alias_kind":"pith_short_12","alias_value":"CYEJOF4COFNC","created_at":"2026-07-05T09:19:55Z"},{"alias_kind":"pith_short_16","alias_value":"CYEJOF4COFNCLH63","created_at":"2026-07-05T09:19:55Z"},{"alias_kind":"pith_short_8","alias_value":"CYEJOF4C","created_at":"2026-07-05T09:19:55Z"}],"graph_snapshots":[{"event_id":"sha256:edf9212cc0ae89dcc6e571d00c6a9f791b50e435c39662ea3841ee28b373e5a7","target":"graph","created_at":"2026-07-05T09:19:55Z","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/2404.12318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it challenging to extend this framework to diverse languages. In this work, we evaluate a simple approach for zero-shot cross-lingual alignment, where a reward model is trained on preference data in one source language and directly applied to other target languages. On summarization and open-ended dialog generation, we show that this method is consistently successful","authors_text":"Ahmad Beirami, Ananth Balashankar, Jacob Eisenstein, Yoon Kim, Zhaofeng Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T16:52:36Z","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12318","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":"sha256:1aed02f6f9dd7dd1a493d06ff6f4943fdba804de6ed14f3968bbceb8b6bd69f7","target":"record","created_at":"2026-07-05T09:19:55Z","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":"3fc7025037d23ebf01772cda13cf92b6af637830a9cec6602a17cf722d7cfdd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T16:52:36Z","title_canon_sha256":"60e34aa50e8a763f96fff37105688a5d820e2937cd3175c04e9f9bbbda009b22"},"schema_version":"1.0","source":{"id":"2404.12318","kind":"arxiv","version":2}},"canonical_sha256":"1608971782715a259fdb4ad2dec6988135fe6fb718cee313ad3ba3342e04346a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1608971782715a259fdb4ad2dec6988135fe6fb718cee313ad3ba3342e04346a","first_computed_at":"2026-07-05T09:19:55.345561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:55.345561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ET6tqy2C6qhEsnJbJ73+WxI25na6nhK4xuqVX4wNOPRwH6c14fg/iKYiNVdyWkVjmE5FMXtnjo2MNiDIuzTmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:55.346007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12318","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aed02f6f9dd7dd1a493d06ff6f4943fdba804de6ed14f3968bbceb8b6bd69f7","sha256:edf9212cc0ae89dcc6e571d00c6a9f791b50e435c39662ea3841ee28b373e5a7"],"state_sha256":"4a96adf5cae34be4cc9825cd2826245497979f2a8b7900d70f12b810330db23c"}