{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OIRBMQKPKC233OXY5F2IW2R5YR","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":"5e378fa41241c78e090f08362fcf9dd2093440f5c707649ee460e3ef4a449615","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T09:14:27Z","title_canon_sha256":"1c30e0338d212cc665fe8bd00d2bd1106f70791143beaa2a5d575d49320de3e7"},"schema_version":"1.0","source":{"id":"2607.03126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03126","created_at":"2026-07-07T01:16:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03126v1","created_at":"2026-07-07T01:16:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03126","created_at":"2026-07-07T01:16:43Z"},{"alias_kind":"pith_short_12","alias_value":"OIRBMQKPKC23","created_at":"2026-07-07T01:16:43Z"},{"alias_kind":"pith_short_16","alias_value":"OIRBMQKPKC233OXY","created_at":"2026-07-07T01:16:43Z"},{"alias_kind":"pith_short_8","alias_value":"OIRBMQKP","created_at":"2026-07-07T01:16:43Z"}],"graph_snapshots":[{"event_id":"sha256:be525a4405b7a4f125bd8cb9cfea0f590c9cb8c42a6691a9b6650d1bca29ea5b","target":"graph","created_at":"2026-07-07T01:16:43Z","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/2607.03126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has substantially improved the reasoning ability of large language models (LLMs), but sparse outcome rewards still make token-level credit assignment difficult. Existing scalable RL methods typically assign trajectory-level rewards uniformly across tokens, while recent entropy-aware approaches either rely on coarse detached heuristics or directly optimize true entropy, which can introduce non-local gradient components misaligned with sampled-token policy updates. We propose Adaptive Credit Policy Optimization (ACPO), a token-level credit assignment framework based o","authors_text":"Enlei Gong, Peng Jiang, Quan Chen, Yadong Mu, Yanhua Cheng, Yongzhi Li, Yuyang You, Zeyu Chen, Zijun Xie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T09:14:27Z","title":"ACPO: Adaptive Credit Policy Optimization via Fine-Grained Surrogate Entropy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03126","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":"sha256:5ef3a27084120ce5f4a991cc56ae508e59df60752e498ff046de3a174f6911dd","target":"record","created_at":"2026-07-07T01:16:43Z","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":"5e378fa41241c78e090f08362fcf9dd2093440f5c707649ee460e3ef4a449615","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T09:14:27Z","title_canon_sha256":"1c30e0338d212cc665fe8bd00d2bd1106f70791143beaa2a5d575d49320de3e7"},"schema_version":"1.0","source":{"id":"2607.03126","kind":"arxiv","version":1}},"canonical_sha256":"722216414f50b5bdbaf8e9748b6a3dc459e0eeff01707727840abe48fb0a4f13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"722216414f50b5bdbaf8e9748b6a3dc459e0eeff01707727840abe48fb0a4f13","first_computed_at":"2026-07-07T01:16:43.967512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:43.967512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8LEKVDtv0XjA0FgP8YROMDkazbzXJyjKzvog8pO+MGA9mKUIMNTKwFdmMJM5mZSiRztb8fcIzcbiB5ojBPWzCA==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:43.967965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ef3a27084120ce5f4a991cc56ae508e59df60752e498ff046de3a174f6911dd","sha256:be525a4405b7a4f125bd8cb9cfea0f590c9cb8c42a6691a9b6650d1bca29ea5b"],"state_sha256":"f40600b0c4292324405fde761893f7cca81d31c9c7c6c4fd5d10e9f119185243"}