{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YBQEDX4NFEPCAHM3BYC3XZPLGR","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":"4b9482c985d3bf5c584b775b6ff09c47f0c0d0fd975cc51495089cc085f1b8ef","cross_cats_sorted":["cs.AI","cs.IT","cs.RO","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T00:48:20Z","title_canon_sha256":"cf5f9b80a41ee35db18c0b28352db1413206ea899e4780a54df31cc6fe0c2623"},"schema_version":"1.0","source":{"id":"2505.21852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21852","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21852v1","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21852","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_12","alias_value":"YBQEDX4NFEPC","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_16","alias_value":"YBQEDX4NFEPCAHM3","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_8","alias_value":"YBQEDX4N","created_at":"2026-07-05T11:11:04Z"}],"graph_snapshots":[{"event_id":"sha256:47efa26b8c1802fe4ce311a25369ffa0c68495be8aa86e6e1676834627f2b64f","target":"graph","created_at":"2026-07-05T11:11:04Z","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/2505.21852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A longstanding goal in safe reinforcement learning (RL) is a method to ensure the safety of a policy throughout the entire process, from learning to operation. However, existing safe RL paradigms inherently struggle to achieve this objective. We propose a method, called Provably Lifetime Safe RL (PLS), that integrates offline safe RL with safe policy deployment to address this challenge. Our proposed method learns a policy offline using return-conditioned supervised learning and then deploys the resulting policy while cautiously optimizing a limited set of parameters, known as target returns, ","authors_text":"Akifumi Wachi, Kohei Miyaguchi, Rei Sato, Takumi Tanabe, Youhei Akimoto","cross_cats":["cs.AI","cs.IT","cs.RO","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T00:48:20Z","title":"A Provable Approach for End-to-End Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21852","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":"sha256:08af0b957fec6522594c40da2975fc23533ee825db783a402865948408f715ab","target":"record","created_at":"2026-07-05T11:11:04Z","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":"4b9482c985d3bf5c584b775b6ff09c47f0c0d0fd975cc51495089cc085f1b8ef","cross_cats_sorted":["cs.AI","cs.IT","cs.RO","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T00:48:20Z","title_canon_sha256":"cf5f9b80a41ee35db18c0b28352db1413206ea899e4780a54df31cc6fe0c2623"},"schema_version":"1.0","source":{"id":"2505.21852","kind":"arxiv","version":1}},"canonical_sha256":"c06041df8d291e201d9b0e05bbe5eb344b201c1db865f9c05d6d9eb6d66fcb14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c06041df8d291e201d9b0e05bbe5eb344b201c1db865f9c05d6d9eb6d66fcb14","first_computed_at":"2026-07-05T11:11:04.788562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:04.788562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A4d1hwBm5/UQFgBvH1zG4AEpNJ7Q2uVlMVYM/2hm9uemjnnUMqGcWHKBoGGECbeGeheTx1yKlGJvsrYbEXtjCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:04.788958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08af0b957fec6522594c40da2975fc23533ee825db783a402865948408f715ab","sha256:47efa26b8c1802fe4ce311a25369ffa0c68495be8aa86e6e1676834627f2b64f"],"state_sha256":"327d04c3f4dba84ffa2dd08b5ff4d2ced382b4f5450c73c33448801260a29b4b"}