{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HGQKDIPEQMZI4K536RVFK4EZBR","short_pith_number":"pith:HGQKDIPE","canonical_record":{"source":{"id":"2112.00885","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T23:21:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38412dd5dde4b450902f2650177337f6f7b3d7e39c785775030bba40533fa548","abstract_canon_sha256":"221ba33e0d5a200e17da611d3074d8615c27a95ee8f30603804fc1f06d6697b6"},"schema_version":"1.0"},"canonical_sha256":"39a0a1a1e483328e2bbbf46a5570990c4800890b4995267f9c5a0ce8b9596d1a","source":{"kind":"arxiv","id":"2112.00885","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00885","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00885v3","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00885","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"pith_short_12","alias_value":"HGQKDIPEQMZI","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"pith_short_16","alias_value":"HGQKDIPEQMZI4K53","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"pith_short_8","alias_value":"HGQKDIPE","created_at":"2026-07-05T05:07:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HGQKDIPEQMZI4K536RVFK4EZBR","target":"record","payload":{"canonical_record":{"source":{"id":"2112.00885","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T23:21:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38412dd5dde4b450902f2650177337f6f7b3d7e39c785775030bba40533fa548","abstract_canon_sha256":"221ba33e0d5a200e17da611d3074d8615c27a95ee8f30603804fc1f06d6697b6"},"schema_version":"1.0"},"canonical_sha256":"39a0a1a1e483328e2bbbf46a5570990c4800890b4995267f9c5a0ce8b9596d1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:36.977743Z","signature_b64":"j5DeTskmVh3NwRRUxnYc9bhQUnsAai5+0j3VH1kRWnKrqgjzypZZ7jtYqC8mdtENeEQBqrp/pHT04gzqvbJ7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39a0a1a1e483328e2bbbf46a5570990c4800890b4995267f9c5a0ce8b9596d1a","last_reissued_at":"2026-07-05T05:07:36.977360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:36.977360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.00885","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":"2026-07-05T05:07:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jFWloGIT9eUVvD3Z/W7vL2GVQ6zZhkaFJG1DbPni6qZifqsnFNMcIJJiSmzRc5le+HF/x7XwajSOmT9mxmFACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:50:16.316253Z"},"content_sha256":"64cd5265658e6859f3c12f0925e26e07c8da6f7ce4fbaa45d24d5d1729b98383","schema_version":"1.0","event_id":"sha256:64cd5265658e6859f3c12f0925e26e07c8da6f7ce4fbaa45d24d5d1729b98383"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HGQKDIPEQMZI4K536RVFK4EZBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Archana Bura, Aria HasanzadeZonuzy, Dileep Kalathil, Jean-Francois Chamberland, Srinivas Shakkottai","submitted_at":"2021-12-01T23:21:48Z","abstract_excerpt":"Safe reinforcement learning is extremely challenging--not only must the agent explore an unknown environment, it must do so while ensuring no safety constraint violations. We formulate this safe reinforcement learning (RL) problem using the framework of a finite-horizon Constrained Markov Decision Process (CMDP) with an unknown transition probability function, where we model the safety requirements as constraints on the expected cumulative costs that must be satisfied during all episodes of learning. We propose a model-based safe RL algorithm that we call Doubly Optimistic and Pessimistic Expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00885","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/2112.00885/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":"2026-07-05T05:07:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xd5K3CiXXDXlnf3AKucTZVwrctQlv7OwAeDXs6ZCb09olaTAeLEM/MkxGVaSsrYmp1PNh1v7Q1Uy86lLdDpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:50:16.317202Z"},"content_sha256":"caf144fc35e51535d7ceeb4f852174f16f1d104381d0a499234a4add069a1900","schema_version":"1.0","event_id":"sha256:caf144fc35e51535d7ceeb4f852174f16f1d104381d0a499234a4add069a1900"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HGQKDIPEQMZI4K536RVFK4EZBR/bundle.json","state_url":"https://pith.science/pith/HGQKDIPEQMZI4K536RVFK4EZBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HGQKDIPEQMZI4K536RVFK4EZBR/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":"2026-08-09T07:50:16Z","links":{"resolver":"https://pith.science/pith/HGQKDIPEQMZI4K536RVFK4EZBR","bundle":"https://pith.science/pith/HGQKDIPEQMZI4K536RVFK4EZBR/bundle.json","state":"https://pith.science/pith/HGQKDIPEQMZI4K536RVFK4EZBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HGQKDIPEQMZI4K536RVFK4EZBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HGQKDIPEQMZI4K536RVFK4EZBR","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":"221ba33e0d5a200e17da611d3074d8615c27a95ee8f30603804fc1f06d6697b6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T23:21:48Z","title_canon_sha256":"38412dd5dde4b450902f2650177337f6f7b3d7e39c785775030bba40533fa548"},"schema_version":"1.0","source":{"id":"2112.00885","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.00885","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"arxiv_version","alias_value":"2112.00885v3","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00885","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"pith_short_12","alias_value":"HGQKDIPEQMZI","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"pith_short_16","alias_value":"HGQKDIPEQMZI4K53","created_at":"2026-07-05T05:07:36Z"},{"alias_kind":"pith_short_8","alias_value":"HGQKDIPE","created_at":"2026-07-05T05:07:36Z"}],"graph_snapshots":[{"event_id":"sha256:caf144fc35e51535d7ceeb4f852174f16f1d104381d0a499234a4add069a1900","target":"graph","created_at":"2026-07-05T05:07:36Z","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/2112.00885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning is extremely challenging--not only must the agent explore an unknown environment, it must do so while ensuring no safety constraint violations. We formulate this safe reinforcement learning (RL) problem using the framework of a finite-horizon Constrained Markov Decision Process (CMDP) with an unknown transition probability function, where we model the safety requirements as constraints on the expected cumulative costs that must be satisfied during all episodes of learning. We propose a model-based safe RL algorithm that we call Doubly Optimistic and Pessimistic Expl","authors_text":"Archana Bura, Aria HasanzadeZonuzy, Dileep Kalathil, Jean-Francois Chamberland, Srinivas Shakkottai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T23:21:48Z","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00885","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":"sha256:64cd5265658e6859f3c12f0925e26e07c8da6f7ce4fbaa45d24d5d1729b98383","target":"record","created_at":"2026-07-05T05:07:36Z","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":"221ba33e0d5a200e17da611d3074d8615c27a95ee8f30603804fc1f06d6697b6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-01T23:21:48Z","title_canon_sha256":"38412dd5dde4b450902f2650177337f6f7b3d7e39c785775030bba40533fa548"},"schema_version":"1.0","source":{"id":"2112.00885","kind":"arxiv","version":3}},"canonical_sha256":"39a0a1a1e483328e2bbbf46a5570990c4800890b4995267f9c5a0ce8b9596d1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39a0a1a1e483328e2bbbf46a5570990c4800890b4995267f9c5a0ce8b9596d1a","first_computed_at":"2026-07-05T05:07:36.977360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:36.977360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j5DeTskmVh3NwRRUxnYc9bhQUnsAai5+0j3VH1kRWnKrqgjzypZZ7jtYqC8mdtENeEQBqrp/pHT04gzqvbJ7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:36.977743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.00885","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64cd5265658e6859f3c12f0925e26e07c8da6f7ce4fbaa45d24d5d1729b98383","sha256:caf144fc35e51535d7ceeb4f852174f16f1d104381d0a499234a4add069a1900"],"state_sha256":"8a5ad848e8de56fab7e50605f88499d22e0249924f1905c7d8e5976f0db364ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzD7r0NRUfyaQJq7U0NzAXL3FAvtL7glROB6fS2l19j23WIJWpLCqb9XLM9hfAcHdzOxCrzU/8YLI1dffMFKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:50:16.324126Z","bundle_sha256":"213bf1367c80e6366bbebdf9bffdaf92089a65c75ebec1f7b4520c4169c5bafb"}}