{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O2V7JVHF6KINLUR2XRWPUXMEHX","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":"9a9b3e8560928efc58a5e37d812a03c63fdb27c82c710cda54268f866374a4c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T22:38:39Z","title_canon_sha256":"6aee69252e087a4c521b6cd23e20cce4d9b3fe9db1152e4bbde1a68be1a136a7"},"schema_version":"1.0","source":{"id":"2607.13315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13315","created_at":"2026-07-16T00:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13315v1","created_at":"2026-07-16T00:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13315","created_at":"2026-07-16T00:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"O2V7JVHF6KIN","created_at":"2026-07-16T00:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"O2V7JVHF6KINLUR2","created_at":"2026-07-16T00:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"O2V7JVHF","created_at":"2026-07-16T00:22:11Z"}],"graph_snapshots":[{"event_id":"sha256:312e6c1823e49ef96a06592f399a1435a0c1527e725a921aab81d17f0e37d65e","target":"graph","created_at":"2026-07-16T00:22:11Z","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/2607.13315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical guarantees for both the meta-reward modeling and me","authors_text":"Debmalya Mandal, Ilija Bogunovic, Jiaying Lin, Long Tran-Thanh, Nam Phuong Tran, Seongho Son","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T22:38:39Z","title":"Meta-Learning Preferences for Multilingual LLM Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13315","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:dfb7f2ea55ff146ef513be6b77e57c14aad77f2a0f37e4fa8fae2f0a6e63cd16","target":"record","created_at":"2026-07-16T00:22:11Z","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":"9a9b3e8560928efc58a5e37d812a03c63fdb27c82c710cda54268f866374a4c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-14T22:38:39Z","title_canon_sha256":"6aee69252e087a4c521b6cd23e20cce4d9b3fe9db1152e4bbde1a68be1a136a7"},"schema_version":"1.0","source":{"id":"2607.13315","kind":"arxiv","version":1}},"canonical_sha256":"76abf4d4e5f290d5d23abc6cfa5d843dfd32e126c98bad0ff1f05e66fd2a48b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76abf4d4e5f290d5d23abc6cfa5d843dfd32e126c98bad0ff1f05e66fd2a48b9","first_computed_at":"2026-07-16T00:22:11.738147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:22:11.738147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9l5kBBLX62UT5R00zk4kiiG0zCOGR1l2d+x3Hd47DF9+KpBJJ+72lapztoYBDYpDl8/X8Qzqtf/X99HNHCTGAQ==","signature_status":"signed_v1","signed_at":"2026-07-16T00:22:11.738964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfb7f2ea55ff146ef513be6b77e57c14aad77f2a0f37e4fa8fae2f0a6e63cd16","sha256:312e6c1823e49ef96a06592f399a1435a0c1527e725a921aab81d17f0e37d65e"],"state_sha256":"42fd3e28df283978706553beb8493be49dd0d8cf6e4286c02aa278b9b47d31d9"}