{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PP33YNJ3H35SHBFX2L5CMDXUPC","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":"b61ca3565b4fe99941ffdbadef92297652aef0c5d1ca923733c8b0e8353a5131","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-24T02:36:42Z","title_canon_sha256":"72ee7c6df73ec1d133f9ed0f66b9302342611f0373ea3e8f7c05a7f78a66a1ac"},"schema_version":"1.0","source":{"id":"2309.13528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13528","created_at":"2026-07-05T06:53:54Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13528v1","created_at":"2026-07-05T06:53:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13528","created_at":"2026-07-05T06:53:54Z"},{"alias_kind":"pith_short_12","alias_value":"PP33YNJ3H35S","created_at":"2026-07-05T06:53:54Z"},{"alias_kind":"pith_short_16","alias_value":"PP33YNJ3H35SHBFX","created_at":"2026-07-05T06:53:54Z"},{"alias_kind":"pith_short_8","alias_value":"PP33YNJ3","created_at":"2026-07-05T06:53:54Z"}],"graph_snapshots":[{"event_id":"sha256:459aaeae78a3958607bb424cb61b292991e73f44081f13ff40322626912aaaf6","target":"graph","created_at":"2026-07-05T06:53:54Z","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/2309.13528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring safety is important for the practical deployment of reinforcement learning (RL). Various challenges must be addressed, such as handling stochasticity in the environments, providing rigorous guarantees of persistent state-wise safety satisfaction, and avoiding overly conservative behaviors that sacrifice performance. We propose a new framework, Reachability Estimation for Safe Policy Optimization (RESPO), for safety-constrained RL in general stochastic settings. In the feasible set where there exist violation-free policies, we optimize for rewards while maintaining persistent safety. O","authors_text":"Chenning Yu, Milan Ganai, Sicun Gao, Sylvia Herbert, Zheng Gong","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-24T02:36:42Z","title":"Iterative Reachability Estimation for Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13528","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":"sha256:2a551130a5d137287c96aad6773c9c3e6edab465f19e53fd305860d5d252a4cc","target":"record","created_at":"2026-07-05T06:53:54Z","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":"b61ca3565b4fe99941ffdbadef92297652aef0c5d1ca923733c8b0e8353a5131","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-24T02:36:42Z","title_canon_sha256":"72ee7c6df73ec1d133f9ed0f66b9302342611f0373ea3e8f7c05a7f78a66a1ac"},"schema_version":"1.0","source":{"id":"2309.13528","kind":"arxiv","version":1}},"canonical_sha256":"7bf7bc353b3efb2384b7d2fa260ef478af9dc105b1dc65ce85646e37b9a1272a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bf7bc353b3efb2384b7d2fa260ef478af9dc105b1dc65ce85646e37b9a1272a","first_computed_at":"2026-07-05T06:53:54.028282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:54.028282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3OX5lDP7UrkUT6QvOThYJPBKUi8Xc99x+KPOro/fZ5L0UtwzOaNbCDKMZmfmt17dBQOcOxu6FH0zwwAXOy2EBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:54.028800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.13528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a551130a5d137287c96aad6773c9c3e6edab465f19e53fd305860d5d252a4cc","sha256:459aaeae78a3958607bb424cb61b292991e73f44081f13ff40322626912aaaf6"],"state_sha256":"2959f09548d78595409763a2d39738b2b3527c83cfcdb21504611927023076ea"}