{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6IWQFXZZE4B5BD5CCUPJBOGT6C","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":"aa1c3e3a1249983d0f46218886518090da14751dd71904abe5b49aeb61615283","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T02:28:50Z","title_canon_sha256":"38fd78ebaee19a01cfff25fab1b5790e80ceb34fa611f5055014e2425da41c24"},"schema_version":"1.0","source":{"id":"2412.08880","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08880","created_at":"2026-07-05T09:48:03Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08880v1","created_at":"2026-07-05T09:48:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08880","created_at":"2026-07-05T09:48:03Z"},{"alias_kind":"pith_short_12","alias_value":"6IWQFXZZE4B5","created_at":"2026-07-05T09:48:03Z"},{"alias_kind":"pith_short_16","alias_value":"6IWQFXZZE4B5BD5C","created_at":"2026-07-05T09:48:03Z"},{"alias_kind":"pith_short_8","alias_value":"6IWQFXZZ","created_at":"2026-07-05T09:48:03Z"}],"graph_snapshots":[{"event_id":"sha256:1540d3dd6a2ac843a63b46d1e476299a923a5eb63cec02ce2682972094acac7d","target":"graph","created_at":"2026-07-05T09:48:03Z","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/2412.08880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe offline reinforcement learning aims to learn policies that maximize cumulative rewards while adhering to safety constraints, using only offline data for training. A key challenge is balancing safety and performance, particularly when the policy encounters out-of-distribution (OOD) states and actions, which can lead to safety violations or overly conservative behavior during deployment. To address these challenges, we introduce Feasibility Informed Advantage Weighted Actor-Critic (FAWAC), a method that prioritizes persistent safety in constrained Markov decision processes (CMDPs). FAWAC fo","authors_text":"Cody Fleming, Prajwal Koirala, Soumik Sarkar, Zhanhong Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T02:28:50Z","title":"FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08880","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":"sha256:68181e17ef9f190ce96c527ff0f0ef15be090dfa49251fcdf391682142be84c9","target":"record","created_at":"2026-07-05T09:48:03Z","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":"aa1c3e3a1249983d0f46218886518090da14751dd71904abe5b49aeb61615283","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T02:28:50Z","title_canon_sha256":"38fd78ebaee19a01cfff25fab1b5790e80ceb34fa611f5055014e2425da41c24"},"schema_version":"1.0","source":{"id":"2412.08880","kind":"arxiv","version":1}},"canonical_sha256":"f22d02df392703d08fa2151e90b8d3f09e9cef179a369d37546cecedbed449f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f22d02df392703d08fa2151e90b8d3f09e9cef179a369d37546cecedbed449f6","first_computed_at":"2026-07-05T09:48:03.452682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:03.452682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"75b/nlUZNcU39u9tjrUA0Ud8lPQmWSdl+AmYV1A9K0yxUu/0pDmj4bR1QT9DExHtPX8/iIysGoBuX5pA6DPiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:03.453143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08880","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68181e17ef9f190ce96c527ff0f0ef15be090dfa49251fcdf391682142be84c9","sha256:1540d3dd6a2ac843a63b46d1e476299a923a5eb63cec02ce2682972094acac7d"],"state_sha256":"3e2f5026c4b7c1652e5128e3bda16cf03347a0d9e18135db52be2c159ec1d882"}