{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JVHZQ3AKQL5RTMXTFB5NQS4ZJT","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":"b9966b5caf65b48669b9b8fc236f5c200e27978aa08539040c17e9a750af265b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T22:40:45Z","title_canon_sha256":"b98e99029f29f96c4ae5e4e4c8db53cb8950754abafeb6dd66dd805f417e56af"},"schema_version":"1.0","source":{"id":"2606.10228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10228","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10228v1","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10228","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"JVHZQ3AKQL5R","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"JVHZQ3AKQL5RTMXT","created_at":"2026-06-10T01:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"JVHZQ3AK","created_at":"2026-06-10T01:09:00Z"}],"graph_snapshots":[{"event_id":"sha256:37c2765831a1a95b9777a2d4aa2eea8dd4126918295ae5071e97d364eab94043","target":"graph","created_at":"2026-06-10T01:09:00Z","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/2606.10228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains. In this paper, we approach safe exploration through the lens of epistemic uncertainty, where the actor's sensitivity to parameter perturbations serves as a practical proxy for regions of high uncertainty. We propose Sharpness-Aware Policy Optimization (SHAPO), a sharpness-aware policy update rule that evaluates gradients at perturbed parameters, making policy updates pessimistic with respect to the actor's epistemic uncertainty. Analytically we show that this adjustment implicitly re","authors_text":"Kaustubh Mani, Liam Paull, Vincent Mai, Yann Pequignot","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T22:40:45Z","title":"SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10228","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:f3c421d1e934551babe22f491d4ce31b26f8a18e54946fa2a4068387918e972d","target":"record","created_at":"2026-06-10T01:09:00Z","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":"b9966b5caf65b48669b9b8fc236f5c200e27978aa08539040c17e9a750af265b","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T22:40:45Z","title_canon_sha256":"b98e99029f29f96c4ae5e4e4c8db53cb8950754abafeb6dd66dd805f417e56af"},"schema_version":"1.0","source":{"id":"2606.10228","kind":"arxiv","version":1}},"canonical_sha256":"4d4f986c0a82fb19b2f3287ad84b994cf05b11e1a902ddeb413115b2d650a77e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d4f986c0a82fb19b2f3287ad84b994cf05b11e1a902ddeb413115b2d650a77e","first_computed_at":"2026-06-10T01:09:00.628155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:00.628155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mBbnP0blFzCenv6GEb3Rl/4PZiHwGZAJYEIfeYPa6PkJJ2llbtAQBHG55eW5REtPfdHMnslUR5Mra+Wgj4QRAg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:00.628993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3c421d1e934551babe22f491d4ce31b26f8a18e54946fa2a4068387918e972d","sha256:37c2765831a1a95b9777a2d4aa2eea8dd4126918295ae5071e97d364eab94043"],"state_sha256":"2e2e742915b66a763a933c12db9fe99964f618fa226cd715389cf74c2b2800e4"}