{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:4BW2QTQFQPOM34QHPHPSAVV3MV","short_pith_number":"pith:4BW2QTQF","canonical_record":{"source":{"id":"1805.07708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T05:12:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c9b3a0c4edd09a8c11e2a19b001fa3244c7a4156be51c6d320393fcc0d67e970","abstract_canon_sha256":"7467a9c45f2e6fbbfae2900ae7e224ec2cccf2ee777258852b52b58a8dab3bf4"},"schema_version":"1.0"},"canonical_sha256":"e06da84e0583dccdf20779df2056bb6555cc5f03af140a141d2a03ce69f57263","source":{"kind":"arxiv","id":"1805.07708","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07708","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07708v1","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07708","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"pith_short_12","alias_value":"4BW2QTQFQPOM","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4BW2QTQFQPOM34QH","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4BW2QTQF","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:4BW2QTQFQPOM34QHPHPSAVV3MV","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07708","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T05:12:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c9b3a0c4edd09a8c11e2a19b001fa3244c7a4156be51c6d320393fcc0d67e970","abstract_canon_sha256":"7467a9c45f2e6fbbfae2900ae7e224ec2cccf2ee777258852b52b58a8dab3bf4"},"schema_version":"1.0"},"canonical_sha256":"e06da84e0583dccdf20779df2056bb6555cc5f03af140a141d2a03ce69f57263","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:32.780500Z","signature_b64":"YiYIuvme1TRL67wSWnKqf4mlAJTkIl2DJFs24wUSA8KgDsVxOTQe4w7YUcWJndJoEtgjofDbnzbrxAaZdADADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e06da84e0583dccdf20779df2056bb6555cc5f03af140a141d2a03ce69f57263","last_reissued_at":"2026-05-18T00:15:32.779890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:32.779890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07708","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":"2026-05-18T00:15:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"16pksg/Y/qPOU9imfje1Qf09cVhmC6s93KLm8/7Vn0M9eisTEKoswD8Fn92ruOMxV2cqC1jvy+3o6RE4kuNDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:23:37.186444Z"},"content_sha256":"943f3aa50ee5403986d02e310ee3b5162296f11c4f5b9a52a2c78329c8a8fecd","schema_version":"1.0","event_id":"sha256:943f3aa50ee5403986d02e310ee3b5162296f11c4f5b9a52a2c78329c8a8fecd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:4BW2QTQFQPOM34QHPHPSAVV3MV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Lyapunov-based Approach to Safe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Edgar Duenez-Guzman, Mohammad Ghavamzadeh, Ofir Nachum, Yinlam Chow","submitted_at":"2018-05-20T05:12:04Z","abstract_excerpt":"In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance it is crucial to guarantee the safety of an agent during training as well as deployment (e.g. a robot should avoid taking actions - exploratory or not - which irrevocably harm its hardware). To incorporate safety in RL, we derive algorithms under the framework of constrained Markov decision problems (CMDPs), an extension of the standard Markov decision problems (MDPs) augmented "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07708","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":""},"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":"2026-05-18T00:15:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HYmG8mwpHZq/29TZEHbOWy9hBKuiGqBeFZaFU5UAAAiZiQHLNE0TWffzKsxGKenQGqskOhbIvkUZSmCMPtBZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:23:37.187043Z"},"content_sha256":"097ef036c885a87fac39e4d86c3d631f084735718b6ce2dce9bf29e034d31da1","schema_version":"1.0","event_id":"sha256:097ef036c885a87fac39e4d86c3d631f084735718b6ce2dce9bf29e034d31da1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BW2QTQFQPOM34QHPHPSAVV3MV/bundle.json","state_url":"https://pith.science/pith/4BW2QTQFQPOM34QHPHPSAVV3MV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BW2QTQFQPOM34QHPHPSAVV3MV/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":"2026-05-25T17:23:37Z","links":{"resolver":"https://pith.science/pith/4BW2QTQFQPOM34QHPHPSAVV3MV","bundle":"https://pith.science/pith/4BW2QTQFQPOM34QHPHPSAVV3MV/bundle.json","state":"https://pith.science/pith/4BW2QTQFQPOM34QHPHPSAVV3MV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BW2QTQFQPOM34QHPHPSAVV3MV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4BW2QTQFQPOM34QHPHPSAVV3MV","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":"7467a9c45f2e6fbbfae2900ae7e224ec2cccf2ee777258852b52b58a8dab3bf4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T05:12:04Z","title_canon_sha256":"c9b3a0c4edd09a8c11e2a19b001fa3244c7a4156be51c6d320393fcc0d67e970"},"schema_version":"1.0","source":{"id":"1805.07708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07708","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07708v1","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07708","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"pith_short_12","alias_value":"4BW2QTQFQPOM","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"4BW2QTQFQPOM34QH","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"4BW2QTQF","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:097ef036c885a87fac39e4d86c3d631f084735718b6ce2dce9bf29e034d31da1","target":"graph","created_at":"2026-05-18T00:15:32Z","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"},"paper":{"abstract_excerpt":"In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance it is crucial to guarantee the safety of an agent during training as well as deployment (e.g. a robot should avoid taking actions - exploratory or not - which irrevocably harm its hardware). To incorporate safety in RL, we derive algorithms under the framework of constrained Markov decision problems (CMDPs), an extension of the standard Markov decision problems (MDPs) augmented ","authors_text":"Edgar Duenez-Guzman, Mohammad Ghavamzadeh, Ofir Nachum, Yinlam Chow","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T05:12:04Z","title":"A Lyapunov-based Approach to Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07708","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":"sha256:943f3aa50ee5403986d02e310ee3b5162296f11c4f5b9a52a2c78329c8a8fecd","target":"record","created_at":"2026-05-18T00:15:32Z","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":"7467a9c45f2e6fbbfae2900ae7e224ec2cccf2ee777258852b52b58a8dab3bf4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-20T05:12:04Z","title_canon_sha256":"c9b3a0c4edd09a8c11e2a19b001fa3244c7a4156be51c6d320393fcc0d67e970"},"schema_version":"1.0","source":{"id":"1805.07708","kind":"arxiv","version":1}},"canonical_sha256":"e06da84e0583dccdf20779df2056bb6555cc5f03af140a141d2a03ce69f57263","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e06da84e0583dccdf20779df2056bb6555cc5f03af140a141d2a03ce69f57263","first_computed_at":"2026-05-18T00:15:32.779890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:32.779890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YiYIuvme1TRL67wSWnKqf4mlAJTkIl2DJFs24wUSA8KgDsVxOTQe4w7YUcWJndJoEtgjofDbnzbrxAaZdADADA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:32.780500Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:943f3aa50ee5403986d02e310ee3b5162296f11c4f5b9a52a2c78329c8a8fecd","sha256:097ef036c885a87fac39e4d86c3d631f084735718b6ce2dce9bf29e034d31da1"],"state_sha256":"57598b495417266b700a851281b92f53720697a81d9ad8bfa555f42a98f4fd09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kCRABdxrcl1eskb5RnijNEbAJCUZ+NHpw49cqTL7aTZS0YnRPxY90lA30xOq/CMoyAL3N+idbahIsMXMIV46Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:23:37.190816Z","bundle_sha256":"5d148edb4182b985b08cea02b7b62ed30f7f25ca42fdf67ff61381c7882c6b36"}}