{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SVM75E4GSCCV3XFLQOYHUCVUSM","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":"c755c1c035c840129a9834880460b5f226999e9c70451ba74917ec2aa83253be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T20:52:03Z","title_canon_sha256":"e6a9e1f65b723b6f7166ef2143944a431c3237bb7cab18025c5635f11db1a8a1"},"schema_version":"1.0","source":{"id":"2606.23932","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23932","created_at":"2026-06-24T00:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23932v1","created_at":"2026-06-24T00:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23932","created_at":"2026-06-24T00:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"SVM75E4GSCCV","created_at":"2026-06-24T00:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"SVM75E4GSCCV3XFL","created_at":"2026-06-24T00:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"SVM75E4G","created_at":"2026-06-24T00:14:30Z"}],"graph_snapshots":[{"event_id":"sha256:60b7d40ab614d611745cc7892d68aa43804634c4fb0aa336866cf78e04abd348","target":"graph","created_at":"2026-06-24T00:14:30Z","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/2606.23932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proximal Policy Optimization (PPO) is the standard policy-gradient algorithm for on-policy reinforcement learning. The literature presents it in two forms, a clipped surrogate that bounds the importance ratio between successive policies and a Kullback-Leibler penalty between them. These forms are treated as separate algorithms with their own gradients, their own hyperparameters, and their own reference implementations, and a sizeable body of empirical work compares them. We show that the gradient of the clipped surrogate is reproduced exactly by a Kullback-Leibler surrogate whose coefficient v","authors_text":"Riccardo Colletti, Robin Holzinger","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T20:52:03Z","title":"KLip-PPO: A per-sample KL perspective on PPO-Clip"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23932","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":"sha256:766d21587cbbfca2a30dcdd30d099866dfa81563fbc803aa90d56eb3b742c35e","target":"record","created_at":"2026-06-24T00:14:30Z","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":"c755c1c035c840129a9834880460b5f226999e9c70451ba74917ec2aa83253be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T20:52:03Z","title_canon_sha256":"e6a9e1f65b723b6f7166ef2143944a431c3237bb7cab18025c5635f11db1a8a1"},"schema_version":"1.0","source":{"id":"2606.23932","kind":"arxiv","version":1}},"canonical_sha256":"9559fe938690855ddcab83b07a0ab4930f763b7d33a2dee260dd57bb4b8deefc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9559fe938690855ddcab83b07a0ab4930f763b7d33a2dee260dd57bb4b8deefc","first_computed_at":"2026-06-24T00:14:30.550907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T00:14:30.550907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DJFPwC9RDyyMJH+uo06XN31sCh/iKIRxpIEfYZ21YWEEQCsBGfhFMPpbvQmVaqP1PmjrfhS9s/TDPXRCL2BJDA==","signature_status":"signed_v1","signed_at":"2026-06-24T00:14:30.551335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23932","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:766d21587cbbfca2a30dcdd30d099866dfa81563fbc803aa90d56eb3b742c35e","sha256:60b7d40ab614d611745cc7892d68aa43804634c4fb0aa336866cf78e04abd348"],"state_sha256":"43233190ab9d3163749b4fe16059dc5867e0589350375fe576b7e07b8307bba5"}