{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:APGYZ54G2DJXGJN7524VH2VCGG","short_pith_number":"pith:APGYZ54G","canonical_record":{"source":{"id":"2209.15090","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-09-29T20:49:25Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"548d48134dd51ecf3086936c12f569be0584bc43dc2af547fbc943f3f99ac1af","abstract_canon_sha256":"b1a55c22c0433ec52c11d28cebc541947ebcc6e29027e453f313ba74263462bf"},"schema_version":"1.0"},"canonical_sha256":"03cd8cf786d0d37325bfeeb953eaa2319d336492a8c4af51d60088e6be11b636","source":{"kind":"arxiv","id":"2209.15090","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15090","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15090v3","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15090","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"APGYZ54G2DJX","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"APGYZ54G2DJXGJN7","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"APGYZ54G","created_at":"2026-07-05T06:19:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:APGYZ54G2DJXGJN7524VH2VCGG","target":"record","payload":{"canonical_record":{"source":{"id":"2209.15090","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-09-29T20:49:25Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"548d48134dd51ecf3086936c12f569be0584bc43dc2af547fbc943f3f99ac1af","abstract_canon_sha256":"b1a55c22c0433ec52c11d28cebc541947ebcc6e29027e453f313ba74263462bf"},"schema_version":"1.0"},"canonical_sha256":"03cd8cf786d0d37325bfeeb953eaa2319d336492a8c4af51d60088e6be11b636","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:53.265129Z","signature_b64":"oA0IY9omGQfjgUKl94aQewXPnfOwiYGLCbfIorV1I8wXqZPcp0zYjoA+BO1/p8rns4NwFcB/B97qWfEk3n+zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03cd8cf786d0d37325bfeeb953eaa2319d336492a8c4af51d60088e6be11b636","last_reissued_at":"2026-07-05T06:19:53.264654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:53.264654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.15090","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KMIA8GkC6j8Vuat9mtvZ04ugjezetzecKu8s7DEioYajFNMDGwxErYid12XGMVDoaw+mbAU2GNqC2gCMolEyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:32:23.159063Z"},"content_sha256":"35af53bb58af13c84db5217df1d762b207fdb1710aafdf45a1eb40a57793cb40","schema_version":"1.0","event_id":"sha256:35af53bb58af13c84db5217df1d762b207fdb1710aafdf45a1eb40a57793cb40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:APGYZ54G2DJXGJN7524VH2VCGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Chao Huang, Qi Zhu, Ruochen Jiao, Simon Sinong Zhan, Wanxin Jin, Yixuan Wang, Zhaoran Wang, Zhilu Wang, Zhuoran Yang","submitted_at":"2022-09-29T20:49:25Z","abstract_excerpt":"It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions. Many popular safe RL methods such as those based on the Constrained Markov Decision Process (CMDP) paradigm formulate safety violations in a cost function and try to constrain the expectation of cumulative cost under a threshold. However, it is often difficult to effectively capture and enforce hard reachability-based safety constraints indirectly with such constraints on s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15090","kind":"arxiv","version":3},"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/2209.15090/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":"2026-07-05T06:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/jTOrgGXvbqEYIVTDw1xSDiVQeOIkGKT1oDD0P71H+Was8zp5XWtMDWKkoHlMHglHeKaqlMu3XSOFXpQ4TpJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:32:23.159582Z"},"content_sha256":"87c8e7197999d11d84030f91c107ba72836d3ec178147b1902e6755801395f8e","schema_version":"1.0","event_id":"sha256:87c8e7197999d11d84030f91c107ba72836d3ec178147b1902e6755801395f8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/APGYZ54G2DJXGJN7524VH2VCGG/bundle.json","state_url":"https://pith.science/pith/APGYZ54G2DJXGJN7524VH2VCGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/APGYZ54G2DJXGJN7524VH2VCGG/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":"2026-08-07T15:32:23Z","links":{"resolver":"https://pith.science/pith/APGYZ54G2DJXGJN7524VH2VCGG","bundle":"https://pith.science/pith/APGYZ54G2DJXGJN7524VH2VCGG/bundle.json","state":"https://pith.science/pith/APGYZ54G2DJXGJN7524VH2VCGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/APGYZ54G2DJXGJN7524VH2VCGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:APGYZ54G2DJXGJN7524VH2VCGG","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":"b1a55c22c0433ec52c11d28cebc541947ebcc6e29027e453f313ba74263462bf","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-09-29T20:49:25Z","title_canon_sha256":"548d48134dd51ecf3086936c12f569be0584bc43dc2af547fbc943f3f99ac1af"},"schema_version":"1.0","source":{"id":"2209.15090","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15090","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15090v3","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15090","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"APGYZ54G2DJX","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"APGYZ54G2DJXGJN7","created_at":"2026-07-05T06:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"APGYZ54G","created_at":"2026-07-05T06:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:87c8e7197999d11d84030f91c107ba72836d3ec178147b1902e6755801395f8e","target":"graph","created_at":"2026-07-05T06:19:53Z","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/2209.15090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions. Many popular safe RL methods such as those based on the Constrained Markov Decision Process (CMDP) paradigm formulate safety violations in a cost function and try to constrain the expectation of cumulative cost under a threshold. However, it is often difficult to effectively capture and enforce hard reachability-based safety constraints indirectly with such constraints on s","authors_text":"Chao Huang, Qi Zhu, Ruochen Jiao, Simon Sinong Zhan, Wanxin Jin, Yixuan Wang, Zhaoran Wang, Zhilu Wang, Zhuoran Yang","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-09-29T20:49:25Z","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15090","kind":"arxiv","version":3},"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":"sha256:35af53bb58af13c84db5217df1d762b207fdb1710aafdf45a1eb40a57793cb40","target":"record","created_at":"2026-07-05T06:19:53Z","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":"b1a55c22c0433ec52c11d28cebc541947ebcc6e29027e453f313ba74263462bf","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-09-29T20:49:25Z","title_canon_sha256":"548d48134dd51ecf3086936c12f569be0584bc43dc2af547fbc943f3f99ac1af"},"schema_version":"1.0","source":{"id":"2209.15090","kind":"arxiv","version":3}},"canonical_sha256":"03cd8cf786d0d37325bfeeb953eaa2319d336492a8c4af51d60088e6be11b636","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03cd8cf786d0d37325bfeeb953eaa2319d336492a8c4af51d60088e6be11b636","first_computed_at":"2026-07-05T06:19:53.264654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:53.264654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oA0IY9omGQfjgUKl94aQewXPnfOwiYGLCbfIorV1I8wXqZPcp0zYjoA+BO1/p8rns4NwFcB/B97qWfEk3n+zCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:53.265129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15090","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35af53bb58af13c84db5217df1d762b207fdb1710aafdf45a1eb40a57793cb40","sha256:87c8e7197999d11d84030f91c107ba72836d3ec178147b1902e6755801395f8e"],"state_sha256":"895b1c2706b1228ce03f521277506d01aff19d3b358e0f5a6659a80c9f0f7ab9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8YiSEnUNbyCqZlwzlZybqEmwCKhyG30wIMTFfRyppBhS5j4o06o6oHqXcFOj910XnkB/G/V0QP+ewSnN3bWmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:32:23.164037Z","bundle_sha256":"4993f91bfbbbf653047cf2eebb5c6cf674104520faf3ee1855252567df488213"}}