{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ROLIQJFJ5WNPSR77C2ODGTHDTP","short_pith_number":"pith:ROLIQJFJ","canonical_record":{"source":{"id":"2111.12316","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2021-11-24T07:58:14Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"958fdc9c6f8747141b6e28e55c56a7f9eeabab3b33e1c3269fa574e3dbd73fee","abstract_canon_sha256":"6058659a213fe8d5a325fbe3198c90729257d11a485c9d5b03a5079dafd5b585"},"schema_version":"1.0"},"canonical_sha256":"8b968824a9ed9af947ff169c334ce39bfcb63a32747de68a96fe7ecf6957cf79","source":{"kind":"arxiv","id":"2111.12316","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12316","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12316v2","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12316","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_12","alias_value":"ROLIQJFJ5WNP","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"ROLIQJFJ5WNPSR77","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"ROLIQJFJ","created_at":"2026-07-05T04:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ROLIQJFJ5WNPSR77C2ODGTHDTP","target":"record","payload":{"canonical_record":{"source":{"id":"2111.12316","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2021-11-24T07:58:14Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"958fdc9c6f8747141b6e28e55c56a7f9eeabab3b33e1c3269fa574e3dbd73fee","abstract_canon_sha256":"6058659a213fe8d5a325fbe3198c90729257d11a485c9d5b03a5079dafd5b585"},"schema_version":"1.0"},"canonical_sha256":"8b968824a9ed9af947ff169c334ce39bfcb63a32747de68a96fe7ecf6957cf79","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:53.930422Z","signature_b64":"7skLeWvb5gz/1HaQfFmSgVFS7CErtOT9AC15p4cxRqrAtCE8mgTdCwLfMH6BBHk2v1xDS/9xLllkJ8ZxkA+HBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b968824a9ed9af947ff169c334ce39bfcb63a32747de68a96fe7ecf6957cf79","last_reissued_at":"2026-07-05T04:30:53.929880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:53.929880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.12316","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:30:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dpfbS48kiRqq+SsyaXIgK/frP5+4M2TvusX7nJNO+TubPwYHInSenAWTXYLVEZtDR8T853caUcSlskBlShuXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T13:24:01.858064Z"},"content_sha256":"f48cc99e34b1f3d8554b41de2bf7d48d952ff368e1bfc4744d7c71169481c21b","schema_version":"1.0","event_id":"sha256:f48cc99e34b1f3d8554b41de2bf7d48d952ff368e1bfc4744d7c71169481c21b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ROLIQJFJ5WNPSR77C2ODGTHDTP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A note on stabilizing reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.DS","authors_text":"Grigory Yaremenko, Ilya Osokin, Pavel Osinenko","submitted_at":"2021-11-24T07:58:14Z","abstract_excerpt":"Reinforcement learning is a general methodology of adaptive optimal control that has attracted much attention in various fields ranging from video game industry to robot manipulators. Despite its remarkable performance demonstrations, plain reinforcement learning controllers do not guarantee stability which compromises their applicability in industry. To provide such guarantees, measures have to be taken. This gives rise to what could generally be called stabilizing reinforcement learning. Concrete approaches range from employment of human overseers to filter out unsafe actions to formally ver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12316","kind":"arxiv","version":2},"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/2111.12316/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":"2026-07-05T04:30:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S0KgepuXX2X8KtQluw2TNjGXtcOI0sHC3ZjB9UogAMAaylE8gO7fAT1PbXj3q9smhRRw+kt6CiDSE0lD51IXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T13:24:01.858697Z"},"content_sha256":"8539519b38ec58f3dffa371069c3694339501e46ffc9e516e0fee36b3661ec6b","schema_version":"1.0","event_id":"sha256:8539519b38ec58f3dffa371069c3694339501e46ffc9e516e0fee36b3661ec6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ROLIQJFJ5WNPSR77C2ODGTHDTP/bundle.json","state_url":"https://pith.science/pith/ROLIQJFJ5WNPSR77C2ODGTHDTP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ROLIQJFJ5WNPSR77C2ODGTHDTP/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":"2026-07-09T13:24:01Z","links":{"resolver":"https://pith.science/pith/ROLIQJFJ5WNPSR77C2ODGTHDTP","bundle":"https://pith.science/pith/ROLIQJFJ5WNPSR77C2ODGTHDTP/bundle.json","state":"https://pith.science/pith/ROLIQJFJ5WNPSR77C2ODGTHDTP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ROLIQJFJ5WNPSR77C2ODGTHDTP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ROLIQJFJ5WNPSR77C2ODGTHDTP","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":"6058659a213fe8d5a325fbe3198c90729257d11a485c9d5b03a5079dafd5b585","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2021-11-24T07:58:14Z","title_canon_sha256":"958fdc9c6f8747141b6e28e55c56a7f9eeabab3b33e1c3269fa574e3dbd73fee"},"schema_version":"1.0","source":{"id":"2111.12316","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12316","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12316v2","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12316","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_12","alias_value":"ROLIQJFJ5WNP","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"ROLIQJFJ5WNPSR77","created_at":"2026-07-05T04:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"ROLIQJFJ","created_at":"2026-07-05T04:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:8539519b38ec58f3dffa371069c3694339501e46ffc9e516e0fee36b3661ec6b","target":"graph","created_at":"2026-07-05T04:30:53Z","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/2111.12316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning is a general methodology of adaptive optimal control that has attracted much attention in various fields ranging from video game industry to robot manipulators. Despite its remarkable performance demonstrations, plain reinforcement learning controllers do not guarantee stability which compromises their applicability in industry. To provide such guarantees, measures have to be taken. This gives rise to what could generally be called stabilizing reinforcement learning. Concrete approaches range from employment of human overseers to filter out unsafe actions to formally ver","authors_text":"Grigory Yaremenko, Ilya Osokin, Pavel Osinenko","cross_cats":["cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2021-11-24T07:58:14Z","title":"A note on stabilizing reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12316","kind":"arxiv","version":2},"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:f48cc99e34b1f3d8554b41de2bf7d48d952ff368e1bfc4744d7c71169481c21b","target":"record","created_at":"2026-07-05T04:30:53Z","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":"6058659a213fe8d5a325fbe3198c90729257d11a485c9d5b03a5079dafd5b585","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2021-11-24T07:58:14Z","title_canon_sha256":"958fdc9c6f8747141b6e28e55c56a7f9eeabab3b33e1c3269fa574e3dbd73fee"},"schema_version":"1.0","source":{"id":"2111.12316","kind":"arxiv","version":2}},"canonical_sha256":"8b968824a9ed9af947ff169c334ce39bfcb63a32747de68a96fe7ecf6957cf79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b968824a9ed9af947ff169c334ce39bfcb63a32747de68a96fe7ecf6957cf79","first_computed_at":"2026-07-05T04:30:53.929880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:53.929880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7skLeWvb5gz/1HaQfFmSgVFS7CErtOT9AC15p4cxRqrAtCE8mgTdCwLfMH6BBHk2v1xDS/9xLllkJ8ZxkA+HBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:53.930422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.12316","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f48cc99e34b1f3d8554b41de2bf7d48d952ff368e1bfc4744d7c71169481c21b","sha256:8539519b38ec58f3dffa371069c3694339501e46ffc9e516e0fee36b3661ec6b"],"state_sha256":"92ae42ac78f0f09a5b5b828d916bc724603ecab0166ec9b8ce20c92156783649"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RFKJXh/xIifXaqENBn1rBrRJ2P83Gj2upXScr7JTV5S9QTwYwFH1reyeEyZrMs8bJKC8bIMQr2NFj4Ugp3K6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T13:24:01.861694Z","bundle_sha256":"8fab933d26280ba113c6180588246e776d2de18b8d139c1fac22fd64038bf9f0"}}