{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7ZCBIX56TYBCPKLWPE32E4Z2RM","short_pith_number":"pith:7ZCBIX56","canonical_record":{"source":{"id":"2506.02864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T13:28:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d72a6408d5b8109e434ea2d89dd72c54fd683b258c4cc7f659150970e767cb5f","abstract_canon_sha256":"3e2b7af543dafe8e013407c79ffdd2db05837cf53875a799896b08b8f492375f"},"schema_version":"1.0"},"canonical_sha256":"fe44145fbe9e0227a9767937a2733a8b0a96a87b2148fab9d72dd472cb289071","source":{"kind":"arxiv","id":"2506.02864","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7ZCBIX56TYBCPKLWPE32E4Z2RM","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02864","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T13:28:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d72a6408d5b8109e434ea2d89dd72c54fd683b258c4cc7f659150970e767cb5f","abstract_canon_sha256":"3e2b7af543dafe8e013407c79ffdd2db05837cf53875a799896b08b8f492375f"},"schema_version":"1.0"},"canonical_sha256":"fe44145fbe9e0227a9767937a2733a8b0a96a87b2148fab9d72dd472cb289071","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:10.643813Z","signature_b64":"4UT1c1mCpQ6+js76lNyVyuiNTQI+AsTJkP6Lqm+4LgwGRkKGW2RsT4wCOLnAKiPC3NAxPYMOhmj4Zgg0dM73Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe44145fbe9e0227a9767937a2733a8b0a96a87b2148fab9d72dd472cb289071","last_reissued_at":"2026-07-05T11:15:10.643278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:10.643278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02864","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M/o2BOtGf1w5Ib17rwl8SmShx8HvZ5LEv63bjXHHCP/SyPEWRFH5dDopYquEWpe2TRfZc7+cbxzunC/wrlDqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T12:35:14.605024Z"},"content_sha256":"be166daf25ee231f5af942e91e66f7c50f097dac701a1f5c7bb3676afc9ad011","schema_version":"1.0","event_id":"sha256:be166daf25ee231f5af942e91e66f7c50f097dac701a1f5c7bb3676afc9ad011"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7ZCBIX56TYBCPKLWPE32E4Z2RM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BNPO: Beta Normalization Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changyi Xiao, Mengdi Zhang, Yixin Cao","submitted_at":"2025-06-03T13:28:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02864","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.02864/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a7LNKnCFSrxbZHTqq4l1bCEgNFSXqsGlNNiB95+DcU2mzgOJ6oLGSBAKFehXFdTI2vcm+F2bMmsQqB5yVP+YCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T12:35:14.605422Z"},"content_sha256":"7541f3e93ac4c35cdc8e505c53ac38b0939287d5d89fdac990a859e5581ef6b2","schema_version":"1.0","event_id":"sha256:7541f3e93ac4c35cdc8e505c53ac38b0939287d5d89fdac990a859e5581ef6b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ZCBIX56TYBCPKLWPE32E4Z2RM/bundle.json","state_url":"https://pith.science/pith/7ZCBIX56TYBCPKLWPE32E4Z2RM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ZCBIX56TYBCPKLWPE32E4Z2RM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-26T12:35:14Z","links":{"resolver":"https://pith.science/pith/7ZCBIX56TYBCPKLWPE32E4Z2RM","bundle":"https://pith.science/pith/7ZCBIX56TYBCPKLWPE32E4Z2RM/bundle.json","state":"https://pith.science/pith/7ZCBIX56TYBCPKLWPE32E4Z2RM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ZCBIX56TYBCPKLWPE32E4Z2RM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9fW3x4ut5QNTEJSMD+9udFNy/OIsVLxETwaYl5EvAmO5qibKeZdErdTAJPqY9HnybZk5nP1FLMcEtwNUKT4RCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T12:35:14.607615Z","bundle_sha256":"014df66e13575c9fb047d36713be8f2ae0387804e77a70cd91dcd44f28d8f852"}}