{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UORISE2RFJ2FXVMNSI77L5WAOA","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":"3cf09e6653bfe1d689f6c2837d677563b8e7ee1926abcd14d2c3cc15d4f123d4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:20:46Z","title_canon_sha256":"dc23ef803de7f1fdb6ac59cdcf6b00040324e336854bfabe0ba12d4029858435"},"schema_version":"1.0","source":{"id":"2605.20722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20722","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20722v1","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20722","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"UORISE2RFJ2F","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"UORISE2RFJ2FXVMN","created_at":"2026-05-21T01:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"UORISE2R","created_at":"2026-05-21T01:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:cf544df19475ff06e4996d5725edbe7e73a562940b45511e4beec794ff0ee78e","target":"graph","created_at":"2026-05-21T01:04:50Z","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/2605.20722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning improves LLM reasoning, but PPO/GRPO typically use fixed clipping and decoding temperature, which makes training brittle and tuning-heavy. We propose Adaptive Group Policy Optimization (AGPO), a critic-free refinement of GRPO that uses group-level statistics to control both update magnitude and exploration. AGPO uses a shared probe-derived statistical state to drive two controllers: (i) adaptive clipping, which sets the trust-region size from reward dispersion and skewness, probe vote entropy, policy entropy, and step-wise KL drift; and (ii) bidirectional adaptive temper","authors_text":"Bokun Wang, Daren Zha, Jun Xiao, Miaobo Hu, Ruohan Wang, Shuhao Hu, Xiaobo Guo, Xin Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:20:46Z","title":"AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20722","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:bb41f7fc8c2236cd9c9c0e9700a8ca8ec74671b77c8938074c8a34c1be320d15","target":"record","created_at":"2026-05-21T01:04:50Z","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":"3cf09e6653bfe1d689f6c2837d677563b8e7ee1926abcd14d2c3cc15d4f123d4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:20:46Z","title_canon_sha256":"dc23ef803de7f1fdb6ac59cdcf6b00040324e336854bfabe0ba12d4029858435"},"schema_version":"1.0","source":{"id":"2605.20722","kind":"arxiv","version":1}},"canonical_sha256":"a3a28913512a745bd58d923ff5f6c0702cf67fa3883cae3281e39aa1365cb19f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3a28913512a745bd58d923ff5f6c0702cf67fa3883cae3281e39aa1365cb19f","first_computed_at":"2026-05-21T01:04:50.796406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:50.796406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L2SObAkbXzv2/BA6Ww93E6fkLSoE79Frc8yGOwYrc4rQR2ma8RC/EoDHIgh7M0Tw3g8Y3g+lKFz+y4bJ2MKQBQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:50.797142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb41f7fc8c2236cd9c9c0e9700a8ca8ec74671b77c8938074c8a34c1be320d15","sha256:cf544df19475ff06e4996d5725edbe7e73a562940b45511e4beec794ff0ee78e"],"state_sha256":"68835f2fbb0a0193c8e0f418fc8d5a50cf249bd173d191fe7b528b83cecdfe58"}