{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EVVMCAFCDVPKCP374MML7VYWL7","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":"082bac6bd7d219f18d0f73022df2b8c551f2be58ae9c4a9ca960a3734f6ef040","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-05T08:29:35Z","title_canon_sha256":"f3444b71b28c7a35e76ca0225fee09c295ab16410250ee9e6bffce94a545d712"},"schema_version":"1.0","source":{"id":"2310.03379","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03379","created_at":"2026-07-05T07:52:42Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03379v2","created_at":"2026-07-05T07:52:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03379","created_at":"2026-07-05T07:52:42Z"},{"alias_kind":"pith_short_12","alias_value":"EVVMCAFCDVPK","created_at":"2026-07-05T07:52:42Z"},{"alias_kind":"pith_short_16","alias_value":"EVVMCAFCDVPKCP37","created_at":"2026-07-05T07:52:42Z"},{"alias_kind":"pith_short_8","alias_value":"EVVMCAFC","created_at":"2026-07-05T07:52:42Z"}],"graph_snapshots":[{"event_id":"sha256:ca2f71570301a3d78d53490b422215005f8d90e6aa519e31aae4ff9b196fc63d","target":"graph","created_at":"2026-07-05T07:52:42Z","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/2310.03379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring safety in Reinforcement Learning (RL), typically framed as a Constrained Markov Decision Process (CMDP), is crucial for real-world exploration applications. Current approaches in handling CMDP struggle to balance optimality and feasibility, as direct optimization methods cannot ensure state-wise in-training safety, and projection-based methods correct actions inefficiently through lengthy iterations. To address these challenges, we propose Adaptive Chance-constrained Safeguards (ACS), an adaptive, model-free safe RL algorithm using the safety recovery rate as a surrogate chance constr","authors_text":"Binhao Chen, Chengliang Liu, Liang Gong, Tairan He, Xuhao Zhao, Zhaorun Chen, Zhuokai Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-05T08:29:35Z","title":"Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03379","kind":"arxiv","version":2},"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:a7898a9825b0c691a760841274c3354b16a4d4efb09ebc84a393acc5e6859777","target":"record","created_at":"2026-07-05T07:52:42Z","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":"082bac6bd7d219f18d0f73022df2b8c551f2be58ae9c4a9ca960a3734f6ef040","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-05T08:29:35Z","title_canon_sha256":"f3444b71b28c7a35e76ca0225fee09c295ab16410250ee9e6bffce94a545d712"},"schema_version":"1.0","source":{"id":"2310.03379","kind":"arxiv","version":2}},"canonical_sha256":"256ac100a21d5ea13f7fe318bfd7165fd2ea280a2a52a535a7715e64515576d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"256ac100a21d5ea13f7fe318bfd7165fd2ea280a2a52a535a7715e64515576d1","first_computed_at":"2026-07-05T07:52:42.053108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:42.053108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IRbrwjjPr2U3LsZQWvcXoNKqS65hqa4Iz8Nv5kkoBgxGBzQAvtC7IOhUEvIZU7olKOK+AyJD7LBrCfSZhd4PAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:42.053502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03379","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7898a9825b0c691a760841274c3354b16a4d4efb09ebc84a393acc5e6859777","sha256:ca2f71570301a3d78d53490b422215005f8d90e6aa519e31aae4ff9b196fc63d"],"state_sha256":"4beabea1a1f6a8aa66cb54a24e0b6a91c49f7ebe553a6ad13976291f6682802a"}