{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DAE66CUSXNUCXEDOLK4XISC3QC","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":"5a5de0740e95ee99025b8168d4a9e9a96e3f4d766ecd3470d29e77d1735e986f","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-12T06:30:17Z","title_canon_sha256":"d6d7d7792fc2238a2927ad322fc273bc4eae580720e29ec42dacbb7c06f49e66"},"schema_version":"1.0","source":{"id":"2212.05727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05727","created_at":"2026-07-05T05:24:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05727v1","created_at":"2026-07-05T05:24:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05727","created_at":"2026-07-05T05:24:19Z"},{"alias_kind":"pith_short_12","alias_value":"DAE66CUSXNUC","created_at":"2026-07-05T05:24:19Z"},{"alias_kind":"pith_short_16","alias_value":"DAE66CUSXNUCXEDO","created_at":"2026-07-05T05:24:19Z"},{"alias_kind":"pith_short_8","alias_value":"DAE66CUS","created_at":"2026-07-05T05:24:19Z"}],"graph_snapshots":[{"event_id":"sha256:570a9cae21e96388c1a62e012dc1b8395d45ba501640112a6647bab6d849d8ed","target":"graph","created_at":"2026-07-05T05:24:19Z","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/2212.05727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety comes first in many real-world applications involving autonomous agents. Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those algorithms that adheres to safety constraints at each decision step under complex and unknown dynamics. In this paper, we revisit prior work in this scope from the perspective of state-wise safe RL and categorize them as projection-based, recovery-based, and optimization-based approaches, respectively. Furthermore, we propose Unrolling Safety Layer (USL), a joint","authors_text":"Bo Yuan, Dacheng Tao, Linrui Zhang, Li Shen, Qin Zhang, Xueqian Wang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-12T06:30:17Z","title":"Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05727","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":"sha256:1099147f7e0410d3797da3f28ef7e853c8b16c9454730f77f4789b05bc6bb133","target":"record","created_at":"2026-07-05T05:24:19Z","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":"5a5de0740e95ee99025b8168d4a9e9a96e3f4d766ecd3470d29e77d1735e986f","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-12T06:30:17Z","title_canon_sha256":"d6d7d7792fc2238a2927ad322fc273bc4eae580720e29ec42dacbb7c06f49e66"},"schema_version":"1.0","source":{"id":"2212.05727","kind":"arxiv","version":1}},"canonical_sha256":"1809ef0a92bb682b906e5ab974485b80adbb3250a67a97a9d2a3f87b30f3df6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1809ef0a92bb682b906e5ab974485b80adbb3250a67a97a9d2a3f87b30f3df6e","first_computed_at":"2026-07-05T05:24:19.030242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:24:19.030242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l9rXzHPs0RC2tIbTnMjTfBWk25/WKdNZ+3a1WuEmkq7eI++lZ4IRPzV7599frLE1V2FJH8++Hs+l+layITX8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:24:19.030716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.05727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1099147f7e0410d3797da3f28ef7e853c8b16c9454730f77f4789b05bc6bb133","sha256:570a9cae21e96388c1a62e012dc1b8395d45ba501640112a6647bab6d849d8ed"],"state_sha256":"ee434023a28441b96913c819e9ea33d1290382dca2abc08ee741d71f99025e1a"}