{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EMBLF33J2DQMOBCEPLZ2LHVL2U","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":"e61346bf055a3e243b5ae3d5065f4a01a8d79cafc555bf132896681fe0ffabee","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T08:55:16Z","title_canon_sha256":"f68e9f0dd4ae9d9b7c41f6395a228f2b09967f15c28550c832b4d8b71c4cf039"},"schema_version":"1.0","source":{"id":"2605.25604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25604","created_at":"2026-05-26T02:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25604v1","created_at":"2026-05-26T02:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25604","created_at":"2026-05-26T02:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"EMBLF33J2DQM","created_at":"2026-05-26T02:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"EMBLF33J2DQMOBCE","created_at":"2026-05-26T02:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"EMBLF33J","created_at":"2026-05-26T02:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:2778e0ae8d553d9df34f518c48839c46ea1c0fcd28fcb2830f4b8999224c6f0d","target":"graph","created_at":"2026-05-26T02:04:46Z","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/2605.25604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning has become a standard paradigm for aligning Large Language Models with human intent and task requirements. While Group Relative Policy Optimization offers an efficient, value-model-free alternative to Proximal Policy Optimization, adapting it to real-world multi-reward settings remains challenging. Standard scalarization practices, such as Reward Combination and Advantage Combination, suffer from significant drawbacks: Reward Combination frequently generates advantages with excessively large squared magnitudes that lead to training instability, while Advantage Combinatio","authors_text":"Chuzhan Hao, Guochao Jiang, Guofeng Quan, Guohua Liu, Jingyi Song, Yuewei Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T08:55:16Z","title":"DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25604","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":"sha256:6fb2d9d58b74aac8168629caf9cb0cf514adc399d2818a17ad5c69bc3e2a431c","target":"record","created_at":"2026-05-26T02:04:46Z","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":"e61346bf055a3e243b5ae3d5065f4a01a8d79cafc555bf132896681fe0ffabee","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T08:55:16Z","title_canon_sha256":"f68e9f0dd4ae9d9b7c41f6395a228f2b09967f15c28550c832b4d8b71c4cf039"},"schema_version":"1.0","source":{"id":"2605.25604","kind":"arxiv","version":1}},"canonical_sha256":"2302b2ef69d0e0c704447af3a59eabd528ef56afd23e398f107da270857b35c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2302b2ef69d0e0c704447af3a59eabd528ef56afd23e398f107da270857b35c1","first_computed_at":"2026-05-26T02:04:46.102837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:46.102837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QmP0PptmxuBcgJFzdh4WYlGUlo3TxfbtP8CboH6qLsmc+muQWJZuMXOTx+0lqJI26bMHvb2tn0uMe/wlsjk2AQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:46.103525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fb2d9d58b74aac8168629caf9cb0cf514adc399d2818a17ad5c69bc3e2a431c","sha256:2778e0ae8d553d9df34f518c48839c46ea1c0fcd28fcb2830f4b8999224c6f0d"],"state_sha256":"c76c4ea22bced737f8f32bb39d6efd427699fe9da3332d35c5f64fd874433580"}