{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AS4DAGOVD7LLWILH7EW3QV2F57","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":"0571f006cb58d663ac072e49867a19209018109bec6b4b93720f639eb2d5f22b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T07:18:44Z","title_canon_sha256":"da9ce3ffd428f926e5714d5c02a4488080a4bc54f8495edb581e7a4af439b7a0"},"schema_version":"1.0","source":{"id":"2606.09124","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09124","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09124v1","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09124","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"pith_short_12","alias_value":"AS4DAGOVD7LL","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"pith_short_16","alias_value":"AS4DAGOVD7LLWILH","created_at":"2026-06-09T02:08:00Z"},{"alias_kind":"pith_short_8","alias_value":"AS4DAGOV","created_at":"2026-06-09T02:08:00Z"}],"graph_snapshots":[{"event_id":"sha256:75308c1607109650a6305066ff604ea30891aa9c6f078d0a6b25a62ab346e424","target":"graph","created_at":"2026-06-09T02:08:00Z","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/2606.09124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness signals. However, many realistic language tasks are difficult to equip with reliable verifiers, motivating a growing reliance on reinforcement learning from human feedback (RLHF). In this setting, we argue that a closer examination of how human feedback should be interpreted is essential. We introduce Regret-based Preference Optimization $(\\textbf{RePO})$, which reframes RLHF through $\\textit{regret minimization}$ rathe","authors_text":"Geon-Hyeong Kim, Jungwoo Lee, Moontae Lee, Suhwan Kim, Taehyun Cho, Youngsoo Jang, Yu Jin Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T07:18:44Z","title":"A Regret Minimization Framework on Preference Learning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09124","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":"sha256:5503121b302bffb63b79232d1db0b017028f817dfd8018300d2525455baa0310","target":"record","created_at":"2026-06-09T02:08:00Z","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":"0571f006cb58d663ac072e49867a19209018109bec6b4b93720f639eb2d5f22b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T07:18:44Z","title_canon_sha256":"da9ce3ffd428f926e5714d5c02a4488080a4bc54f8495edb581e7a4af439b7a0"},"schema_version":"1.0","source":{"id":"2606.09124","kind":"arxiv","version":1}},"canonical_sha256":"04b83019d51fd6bb2167f92db85745efe887ff51c2757683345039ab9b841ac7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04b83019d51fd6bb2167f92db85745efe887ff51c2757683345039ab9b841ac7","first_computed_at":"2026-06-09T02:08:00.568654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:00.568654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qOBfwVmvL9d9liqKObXZnv1z8G7/xdY4ZqD0K9q+cgylfDtoQTEbb2rFXxF2fUwAyJeZJ8PE8p0srdoG0FIYCw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:00.569569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09124","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5503121b302bffb63b79232d1db0b017028f817dfd8018300d2525455baa0310","sha256:75308c1607109650a6305066ff604ea30891aa9c6f078d0a6b25a62ab346e424"],"state_sha256":"276ac7d323d0129b34446347f68eaf04591e3223999c03cfd22b38a27438f0f7"}