{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7ZCBIX56TYBCPKLWPE32E4Z2RM","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":"3e2b7af543dafe8e013407c79ffdd2db05837cf53875a799896b08b8f492375f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T13:28:57Z","title_canon_sha256":"d72a6408d5b8109e434ea2d89dd72c54fd683b258c4cc7f659150970e767cb5f"},"schema_version":"1.0","source":{"id":"2506.02864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02864","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02864v1","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02864","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"pith_short_12","alias_value":"7ZCBIX56TYBC","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"pith_short_16","alias_value":"7ZCBIX56TYBCPKLW","created_at":"2026-07-05T11:15:10Z"},{"alias_kind":"pith_short_8","alias_value":"7ZCBIX56","created_at":"2026-07-05T11:15:10Z"}],"graph_snapshots":[{"event_id":"sha256:7541f3e93ac4c35cdc8e505c53ac38b0939287d5d89fdac990a859e5581ef6b2","target":"graph","created_at":"2026-07-05T11:15:10Z","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/2506.02864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies, including DeepSeek-R1 and Kimi-k1.5, have demonstrated that reinforcement learning with rule-based, binary-valued reward functions can significantly enhance the reasoning capabilities of large language models. These models primarily utilize REINFORCE-based policy optimization techniques, such as REINFORCE with baseline and group relative policy optimization (GRPO). However, a key limitation remains: current policy optimization methods either neglect reward normalization or employ static normalization strategies, which fail to adapt to the dynamic nature of policy updates during","authors_text":"Changyi Xiao, Mengdi Zhang, Yixin Cao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T13:28:57Z","title":"BNPO: Beta Normalization Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02864","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:be166daf25ee231f5af942e91e66f7c50f097dac701a1f5c7bb3676afc9ad011","target":"record","created_at":"2026-07-05T11:15:10Z","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":"3e2b7af543dafe8e013407c79ffdd2db05837cf53875a799896b08b8f492375f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T13:28:57Z","title_canon_sha256":"d72a6408d5b8109e434ea2d89dd72c54fd683b258c4cc7f659150970e767cb5f"},"schema_version":"1.0","source":{"id":"2506.02864","kind":"arxiv","version":1}},"canonical_sha256":"fe44145fbe9e0227a9767937a2733a8b0a96a87b2148fab9d72dd472cb289071","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe44145fbe9e0227a9767937a2733a8b0a96a87b2148fab9d72dd472cb289071","first_computed_at":"2026-07-05T11:15:10.643278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:10.643278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4UT1c1mCpQ6+js76lNyVyuiNTQI+AsTJkP6Lqm+4LgwGRkKGW2RsT4wCOLnAKiPC3NAxPYMOhmj4Zgg0dM73Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:10.643813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be166daf25ee231f5af942e91e66f7c50f097dac701a1f5c7bb3676afc9ad011","sha256:7541f3e93ac4c35cdc8e505c53ac38b0939287d5d89fdac990a859e5581ef6b2"],"state_sha256":"f38b432b71121925e0fb758f595111fa92007e57d217d4cad6124ad7c4ec42a1"}