{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:D6SRAWXBLCBYNMNZPYHWY4X6YX","short_pith_number":"pith:D6SRAWXB","canonical_record":{"source":{"id":"2201.07958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-20T02:33:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b268a9844b2312f2f200d5ac7e5090651198b994fe57e0117bd57f44b35213a","abstract_canon_sha256":"09400400fe8966fcb4c5db2f955e3272a3dc5854b51a27b96cc4c55b245a1c6b"},"schema_version":"1.0"},"canonical_sha256":"1fa5105ae1588386b1b97e0f6c72fec5d0b979552ec8f3aefc4dcc45cdb6e92a","source":{"kind":"arxiv","id":"2201.07958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.07958","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"arxiv_version","alias_value":"2201.07958v1","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07958","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"pith_short_12","alias_value":"D6SRAWXBLCBY","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"pith_short_16","alias_value":"D6SRAWXBLCBYNMNZ","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"pith_short_8","alias_value":"D6SRAWXB","created_at":"2026-07-05T03:50:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:D6SRAWXBLCBYNMNZPYHWY4X6YX","target":"record","payload":{"canonical_record":{"source":{"id":"2201.07958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-20T02:33:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b268a9844b2312f2f200d5ac7e5090651198b994fe57e0117bd57f44b35213a","abstract_canon_sha256":"09400400fe8966fcb4c5db2f955e3272a3dc5854b51a27b96cc4c55b245a1c6b"},"schema_version":"1.0"},"canonical_sha256":"1fa5105ae1588386b1b97e0f6c72fec5d0b979552ec8f3aefc4dcc45cdb6e92a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:07.158275Z","signature_b64":"8qJDRgXJ9I5WDtn67VR2lJyC8YR/HDO3OBnZAOmtzaRrpb2CD1mCL+J18dgKp8R9viPuIAjYJs79XajtTORqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fa5105ae1588386b1b97e0f6c72fec5d0b979552ec8f3aefc4dcc45cdb6e92a","last_reissued_at":"2026-07-05T03:50:07.157758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:07.157758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.07958","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":"2026-07-05T03:50:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Umpjocvj/sx5BZIWa1J9c+bFvGMF7aV9hvQxHp7MS5Aelg9Gc8wG5jqxl03xNvCJiExTKt9sb1GthPbFYFE6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:57:01.076667Z"},"content_sha256":"3dff47fe46f086a64e09bc447328c2e721e05c0e62fdb086e34e6fbe99c5ce42","schema_version":"1.0","event_id":"sha256:3dff47fe46f086a64e09bc447328c2e721e05c0e62fdb086e34e6fbe99c5ce42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:D6SRAWXBLCBYNMNZPYHWY4X6YX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recursive Constraints to Prevent Instability in Constrained Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jaeyoung Lee, Krzysztof Czarnecki, Sean Sedwards","submitted_at":"2022-01-20T02:33:24Z","abstract_excerpt":"We consider the challenge of finding a deterministic policy for a Markov decision process that uniformly (in all states) maximizes one reward subject to a probabilistic constraint over a different reward. Existing solutions do not fully address our precise problem definition, which nevertheless arises naturally in the context of safety-critical robotic systems. This class of problem is known to be hard, but the combined requirements of determinism and uniform optimality can create learning instability. In this work, after describing and motivating our problem with a simple example, we present "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07958","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/2201.07958/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":"2026-07-05T03:50:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iPs6OjFfSXTJH8yOJMEK1Lrj8Hsqb6caxM5eXJtmQBsvobGVvlajf+BWM6M85jgPSXQorXEn3vj2sNS87pcGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:57:01.077532Z"},"content_sha256":"e7a61434958eddc30ee78185fc3e2f38c80738e08d73454e3e50c9cd1f867a9d","schema_version":"1.0","event_id":"sha256:e7a61434958eddc30ee78185fc3e2f38c80738e08d73454e3e50c9cd1f867a9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D6SRAWXBLCBYNMNZPYHWY4X6YX/bundle.json","state_url":"https://pith.science/pith/D6SRAWXBLCBYNMNZPYHWY4X6YX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D6SRAWXBLCBYNMNZPYHWY4X6YX/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":"2026-08-14T06:57:01Z","links":{"resolver":"https://pith.science/pith/D6SRAWXBLCBYNMNZPYHWY4X6YX","bundle":"https://pith.science/pith/D6SRAWXBLCBYNMNZPYHWY4X6YX/bundle.json","state":"https://pith.science/pith/D6SRAWXBLCBYNMNZPYHWY4X6YX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D6SRAWXBLCBYNMNZPYHWY4X6YX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:D6SRAWXBLCBYNMNZPYHWY4X6YX","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":"09400400fe8966fcb4c5db2f955e3272a3dc5854b51a27b96cc4c55b245a1c6b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-20T02:33:24Z","title_canon_sha256":"7b268a9844b2312f2f200d5ac7e5090651198b994fe57e0117bd57f44b35213a"},"schema_version":"1.0","source":{"id":"2201.07958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.07958","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"arxiv_version","alias_value":"2201.07958v1","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07958","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"pith_short_12","alias_value":"D6SRAWXBLCBY","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"pith_short_16","alias_value":"D6SRAWXBLCBYNMNZ","created_at":"2026-07-05T03:50:07Z"},{"alias_kind":"pith_short_8","alias_value":"D6SRAWXB","created_at":"2026-07-05T03:50:07Z"}],"graph_snapshots":[{"event_id":"sha256:e7a61434958eddc30ee78185fc3e2f38c80738e08d73454e3e50c9cd1f867a9d","target":"graph","created_at":"2026-07-05T03:50:07Z","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/2201.07958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the challenge of finding a deterministic policy for a Markov decision process that uniformly (in all states) maximizes one reward subject to a probabilistic constraint over a different reward. Existing solutions do not fully address our precise problem definition, which nevertheless arises naturally in the context of safety-critical robotic systems. This class of problem is known to be hard, but the combined requirements of determinism and uniform optimality can create learning instability. In this work, after describing and motivating our problem with a simple example, we present ","authors_text":"Jaeyoung Lee, Krzysztof Czarnecki, Sean Sedwards","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-20T02:33:24Z","title":"Recursive Constraints to Prevent Instability in Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07958","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":"sha256:3dff47fe46f086a64e09bc447328c2e721e05c0e62fdb086e34e6fbe99c5ce42","target":"record","created_at":"2026-07-05T03:50:07Z","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":"09400400fe8966fcb4c5db2f955e3272a3dc5854b51a27b96cc4c55b245a1c6b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-20T02:33:24Z","title_canon_sha256":"7b268a9844b2312f2f200d5ac7e5090651198b994fe57e0117bd57f44b35213a"},"schema_version":"1.0","source":{"id":"2201.07958","kind":"arxiv","version":1}},"canonical_sha256":"1fa5105ae1588386b1b97e0f6c72fec5d0b979552ec8f3aefc4dcc45cdb6e92a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fa5105ae1588386b1b97e0f6c72fec5d0b979552ec8f3aefc4dcc45cdb6e92a","first_computed_at":"2026-07-05T03:50:07.157758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:50:07.157758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8qJDRgXJ9I5WDtn67VR2lJyC8YR/HDO3OBnZAOmtzaRrpb2CD1mCL+J18dgKp8R9viPuIAjYJs79XajtTORqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:50:07.158275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.07958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dff47fe46f086a64e09bc447328c2e721e05c0e62fdb086e34e6fbe99c5ce42","sha256:e7a61434958eddc30ee78185fc3e2f38c80738e08d73454e3e50c9cd1f867a9d"],"state_sha256":"d51e200b4f4a998cea98a3011f1db66715ddfade8e67db038e950db641087a4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h57ZIkX9n8AqYrIY1tusNXIBueLyy72GOnywbu/KhTS8aGAZXu++wAwP5HjJmU6DmXhRVXlG+6eNFriXFe7UAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T06:57:01.084949Z","bundle_sha256":"a48ba427e3e9c02cb0bd4cf3920b80d8e77dcc6d06bba193b2051864a042721b"}}