{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3O7WDVFPZMO2ZDSYCLN2WPQZ74","short_pith_number":"pith:3O7WDVFP","canonical_record":{"source":{"id":"2310.03225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T00:47:09Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"0d93fcfb3a3198d1e4f9672d5a83cb706c148958518fa39817fdb14eada7bb41","abstract_canon_sha256":"19a88207218c7dd615c70e68e246bace32a620725a4eb62f4fa24ffe267055a2"},"schema_version":"1.0"},"canonical_sha256":"dbbf61d4afcb1dac8e5812dbab3e19ff10eba6054bc879ba4311e6ecfd52c0f9","source":{"kind":"arxiv","id":"2310.03225","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03225","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03225v1","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03225","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"3O7WDVFPZMO2","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_16","alias_value":"3O7WDVFPZMO2ZDSY","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_8","alias_value":"3O7WDVFP","created_at":"2026-07-05T06:57:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3O7WDVFPZMO2ZDSYCLN2WPQZ74","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T00:47:09Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"0d93fcfb3a3198d1e4f9672d5a83cb706c148958518fa39817fdb14eada7bb41","abstract_canon_sha256":"19a88207218c7dd615c70e68e246bace32a620725a4eb62f4fa24ffe267055a2"},"schema_version":"1.0"},"canonical_sha256":"dbbf61d4afcb1dac8e5812dbab3e19ff10eba6054bc879ba4311e6ecfd52c0f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:30.412446Z","signature_b64":"TO1HMH2zhzpRu+2lxY8bvy19m0ptu5sVrJ3tK0uotU4w1iUTD0vAz2jerz3MBMrElte8R62NTexMk/LfDiP9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbbf61d4afcb1dac8e5812dbab3e19ff10eba6054bc879ba4311e6ecfd52c0f9","last_reissued_at":"2026-07-05T06:57:30.412056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:30.412056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03225","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:57:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6KaOJl7HcVPa8Q+XhusLZixNOFzynGfYOzPq2uFTQCEGZmlp8ij7W685EumSLRqfH2ss3YTD722fkpkh6GNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:49:55.552161Z"},"content_sha256":"9d0a5edccbe08b15ec06b5dac18617fa2c414b0962b7a68705e30b1548312daf","schema_version":"1.0","event_id":"sha256:9d0a5edccbe08b15ec06b5dac18617fa2c414b0962b7a68705e30b1548312daf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3O7WDVFPZMO2ZDSYCLN2WPQZ74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Akifumi Wachi, Kazumune Hashimoto, Wataru Hashimoto, Xun Shen","submitted_at":"2023-10-05T00:47:09Z","abstract_excerpt":"Safe exploration is essential for the practical use of reinforcement learning (RL) in many real-world scenarios. In this paper, we present a generalized safe exploration (GSE) problem as a unified formulation of common safe exploration problems. We then propose a solution of the GSE problem in the form of a meta-algorithm for safe exploration, MASE, which combines an unconstrained RL algorithm with an uncertainty quantifier to guarantee safety in the current episode while properly penalizing unsafe explorations before actual safety violation to discourage them in future episodes. The advantage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03225","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.03225/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:57:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qqtk5VITjZkh1uPCb+8Hh4EtdhqS/r5PxfrRkQWrK/TyG556KoeuY8HTlqaLOmZ8Sw3MmaWixxUbL9LX2EjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:49:55.552774Z"},"content_sha256":"3f08a723d3a1578d1682fc4759a09f2c2c2fabcf30753ceb5824494e5fcb1756","schema_version":"1.0","event_id":"sha256:3f08a723d3a1578d1682fc4759a09f2c2c2fabcf30753ceb5824494e5fcb1756"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3O7WDVFPZMO2ZDSYCLN2WPQZ74/bundle.json","state_url":"https://pith.science/pith/3O7WDVFPZMO2ZDSYCLN2WPQZ74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3O7WDVFPZMO2ZDSYCLN2WPQZ74/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T15:49:55Z","links":{"resolver":"https://pith.science/pith/3O7WDVFPZMO2ZDSYCLN2WPQZ74","bundle":"https://pith.science/pith/3O7WDVFPZMO2ZDSYCLN2WPQZ74/bundle.json","state":"https://pith.science/pith/3O7WDVFPZMO2ZDSYCLN2WPQZ74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3O7WDVFPZMO2ZDSYCLN2WPQZ74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3O7WDVFPZMO2ZDSYCLN2WPQZ74","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":"19a88207218c7dd615c70e68e246bace32a620725a4eb62f4fa24ffe267055a2","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T00:47:09Z","title_canon_sha256":"0d93fcfb3a3198d1e4f9672d5a83cb706c148958518fa39817fdb14eada7bb41"},"schema_version":"1.0","source":{"id":"2310.03225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03225","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03225v1","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03225","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_12","alias_value":"3O7WDVFPZMO2","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_16","alias_value":"3O7WDVFPZMO2ZDSY","created_at":"2026-07-05T06:57:30Z"},{"alias_kind":"pith_short_8","alias_value":"3O7WDVFP","created_at":"2026-07-05T06:57:30Z"}],"graph_snapshots":[{"event_id":"sha256:3f08a723d3a1578d1682fc4759a09f2c2c2fabcf30753ceb5824494e5fcb1756","target":"graph","created_at":"2026-07-05T06:57:30Z","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/2310.03225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe exploration is essential for the practical use of reinforcement learning (RL) in many real-world scenarios. In this paper, we present a generalized safe exploration (GSE) problem as a unified formulation of common safe exploration problems. We then propose a solution of the GSE problem in the form of a meta-algorithm for safe exploration, MASE, which combines an unconstrained RL algorithm with an uncertainty quantifier to guarantee safety in the current episode while properly penalizing unsafe explorations before actual safety violation to discourage them in future episodes. The advantage","authors_text":"Akifumi Wachi, Kazumune Hashimoto, Wataru Hashimoto, Xun Shen","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T00:47:09Z","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03225","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":"sha256:9d0a5edccbe08b15ec06b5dac18617fa2c414b0962b7a68705e30b1548312daf","target":"record","created_at":"2026-07-05T06:57:30Z","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":"19a88207218c7dd615c70e68e246bace32a620725a4eb62f4fa24ffe267055a2","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T00:47:09Z","title_canon_sha256":"0d93fcfb3a3198d1e4f9672d5a83cb706c148958518fa39817fdb14eada7bb41"},"schema_version":"1.0","source":{"id":"2310.03225","kind":"arxiv","version":1}},"canonical_sha256":"dbbf61d4afcb1dac8e5812dbab3e19ff10eba6054bc879ba4311e6ecfd52c0f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbbf61d4afcb1dac8e5812dbab3e19ff10eba6054bc879ba4311e6ecfd52c0f9","first_computed_at":"2026-07-05T06:57:30.412056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:30.412056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TO1HMH2zhzpRu+2lxY8bvy19m0ptu5sVrJ3tK0uotU4w1iUTD0vAz2jerz3MBMrElte8R62NTexMk/LfDiP9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:30.412446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d0a5edccbe08b15ec06b5dac18617fa2c414b0962b7a68705e30b1548312daf","sha256:3f08a723d3a1578d1682fc4759a09f2c2c2fabcf30753ceb5824494e5fcb1756"],"state_sha256":"4bbfa8ed7378713ab343920f9400dbbe25105a721a5535f382df43f0e88bd96e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qfYPNX3feKk3M4kB7/Q0tTCQ9etAC/cXN9imqIVUBXbyaOFwJDogP+4kmqn3cSiEn3Vkie44zlAY088rCy6BCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:49:55.556888Z","bundle_sha256":"3a009c3dd2310ee4caec2702317b7165c39c66147180d916a8a257f4edfe5723"}}