{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NI6KV7LZRHKWTNINBWJOSOPWQY","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":"7280101a9a8111b477b7b0e819d2604fc1778c6089474ea5d4d56280b5096584","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T09:26:26Z","title_canon_sha256":"fa27d805494359bf7c5f962aa00bac2400c594eae5a509333b043e8baca497c3"},"schema_version":"1.0","source":{"id":"2606.03382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03382","created_at":"2026-06-03T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03382v1","created_at":"2026-06-03T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03382","created_at":"2026-06-03T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"NI6KV7LZRHKW","created_at":"2026-06-03T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"NI6KV7LZRHKWTNIN","created_at":"2026-06-03T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"NI6KV7LZ","created_at":"2026-06-03T01:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:123c549fddc69211a697c88912de67393703787eda8475949380516ea3c9f02d","target":"graph","created_at":"2026-06-03T01:05:56Z","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/2606.03382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments. The failure does not stem from insufficient model capacity or overly restrictive clipping. Instead, PPO performs persistent, directionally inefficient local updates, which indicates a lack of geometry-aware guidance for accumulating meaningful behavioral change and ultimately hindering transitions toward new behavior patterns. Although divergence-based regularization introduces partial geometric ","authors_text":"Aaron Courville, Bingxu Liu, Hao Wang, Jiashun Liu, Johan Obando-Ceron, Ling Pan, Pablo Samuel Castro, Runze Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T09:26:26Z","title":"Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03382","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":"sha256:0c00d1e6d9b1822e0806800d30d896edadd5bb71a5ccf0c15fb5980c0f684638","target":"record","created_at":"2026-06-03T01:05:56Z","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":"7280101a9a8111b477b7b0e819d2604fc1778c6089474ea5d4d56280b5096584","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T09:26:26Z","title_canon_sha256":"fa27d805494359bf7c5f962aa00bac2400c594eae5a509333b043e8baca497c3"},"schema_version":"1.0","source":{"id":"2606.03382","kind":"arxiv","version":1}},"canonical_sha256":"6a3caafd7989d569b50d0d92e939f6861c938f8f6a0b30be71b5819335d942cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a3caafd7989d569b50d0d92e939f6861c938f8f6a0b30be71b5819335d942cf","first_computed_at":"2026-06-03T01:05:56.473712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:56.473712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hd18kZ5dYapNjKmtgdmlybRVE+C43tcEv/RIYq5oo3GnSj+Vrw6RJZ3yNje8/d1iW+hle4M25F70kCLIvPj1Cg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:56.474119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c00d1e6d9b1822e0806800d30d896edadd5bb71a5ccf0c15fb5980c0f684638","sha256:123c549fddc69211a697c88912de67393703787eda8475949380516ea3c9f02d"],"state_sha256":"d54bf1fa47f479c849ba04ba363c91775c11e83aa5242d447d6859a1a9253245"}