{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MPY37EC35PND67VPTUSH5VMPIM","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":"11c63165d4d01f90cdbd20e62c85b206af88476be812139456a5e964bf6c117a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-15T09:01:53Z","title_canon_sha256":"3b56633fcee5ca25fdef4a5bd86f5f6bcde161572263b70e7cf7502e44d27478"},"schema_version":"1.0","source":{"id":"2601.10201","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.10201","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2601.10201v2","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.10201","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"MPY37EC35PND","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"MPY37EC35PND67VP","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"MPY37EC3","created_at":"2026-05-26T01:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:0c7f1d05fe39dcf2e9eb395239be5cd2ac55f7775d0212e48a8e6cb27f5ea7c8","target":"graph","created_at":"2026-05-26T01:02:30Z","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/2601.10201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group Relative Policy Optimization (GRPO) is widely used for critic-free Large Language Model (LLM) post-training, but its KL regularization is usually implemented as a local loss-side token penalty. We show that this misses the policy-gradient signal induced by autoregressive KL regularization. Unlike standard KL-regularized Reinforcement Learning (RL) objectives, GRPO's group normalization induces a non-linear prompt-level utility; for binary verifier rewards, this utility is $2\\arcsin\\sqrt p$. As a result, reward and KL cannot be fused before normalization without changing the implicit obje","authors_text":"Hao Bai, Jiarui Yao, Ruida Wang, Tong Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-15T09:01:53Z","title":"Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.10201","kind":"arxiv","version":2},"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:c4026fd08d34eddb570c3026bcbfa9ebc8b096522c43737b8c45c4e400160251","target":"record","created_at":"2026-05-26T01:02:30Z","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":"11c63165d4d01f90cdbd20e62c85b206af88476be812139456a5e964bf6c117a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-15T09:01:53Z","title_canon_sha256":"3b56633fcee5ca25fdef4a5bd86f5f6bcde161572263b70e7cf7502e44d27478"},"schema_version":"1.0","source":{"id":"2601.10201","kind":"arxiv","version":2}},"canonical_sha256":"63f1bf905bebda3f7eaf9d247ed58f431fb95d4fa470ae00a8fa736e9007e7d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63f1bf905bebda3f7eaf9d247ed58f431fb95d4fa470ae00a8fa736e9007e7d1","first_computed_at":"2026-05-26T01:02:30.735217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:30.735217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pKfhgs6mKd/wH8dgq7zdTtz4CNAG3OEXjFMDKBJb1K1dADa8NtHnEnpQeOes0Qno+l4pTJxfjmE0MRdx3IEtAQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:30.736039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.10201","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4026fd08d34eddb570c3026bcbfa9ebc8b096522c43737b8c45c4e400160251","sha256:0c7f1d05fe39dcf2e9eb395239be5cd2ac55f7775d0212e48a8e6cb27f5ea7c8"],"state_sha256":"5d08b9dce2a85a475e68ccc277fa655c931b2e68df026104634733f2fa32601e"}