{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZQ7QCQ3SAC22GKSCN374BBUN6H","short_pith_number":"pith:ZQ7QCQ3S","canonical_record":{"source":{"id":"2402.15776","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-24T09:47:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e4b7836af9beb8fa2ab2da8295f196ca9b033c6ce11743c9216e41df5d0bd24b","abstract_canon_sha256":"ffcae6de7ea67da7ae15e04e92046f8db248c9554bcae8af1bfc0d9f00070bf9"},"schema_version":"1.0"},"canonical_sha256":"cc3f01437200b5a32a426effc0868df1d29091b304913df0217d4f6ec98c65ad","source":{"kind":"arxiv","id":"2402.15776","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15776","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15776v3","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15776","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZQ7QCQ3SAC22","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZQ7QCQ3SAC22GKSC","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZQ7QCQ3S","created_at":"2026-07-05T08:46:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZQ7QCQ3SAC22GKSCN374BBUN6H","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15776","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-24T09:47:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e4b7836af9beb8fa2ab2da8295f196ca9b033c6ce11743c9216e41df5d0bd24b","abstract_canon_sha256":"ffcae6de7ea67da7ae15e04e92046f8db248c9554bcae8af1bfc0d9f00070bf9"},"schema_version":"1.0"},"canonical_sha256":"cc3f01437200b5a32a426effc0868df1d29091b304913df0217d4f6ec98c65ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:07.272650Z","signature_b64":"WdeboVS3s711M6j+ygMRqjSSnK2BwZRVMrtvIAm6ll/glGcm2qAoDN4uFmMvWdQa90HkqvRhRgV87fcbInsSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc3f01437200b5a32a426effc0868df1d29091b304913df0217d4f6ec98c65ad","last_reissued_at":"2026-07-05T08:46:07.272122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:07.272122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15776","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":"2026-07-05T08:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7oT2UaV+LY1hQ790LsppotFP/EES2+wHuRqKIck1YAK2qGKq+XUY8qedx2lfFZI51YW4Tz8YEmIg9hE5c1u/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:06:21.930612Z"},"content_sha256":"894a4c2cf88777fb2e71e3b121dbf3081b55399b0e2cc79e04a476c4ef9dc45b","schema_version":"1.0","event_id":"sha256:894a4c2cf88777fb2e71e3b121dbf3081b55399b0e2cc79e04a476c4ef9dc45b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZQ7QCQ3SAC22GKSCN374BBUN6H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Truly No-Regret Learning in Constrained MDPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian M\\\"uller, Giorgia Ramponi, Niao He, Pragnya Alatur, Volkan Cevher","submitted_at":"2024-02-24T09:47:46Z","abstract_excerpt":"Constrained Markov decision processes (CMDPs) are a common way to model safety constraints in reinforcement learning. State-of-the-art methods for efficiently solving CMDPs are based on primal-dual algorithms. For these algorithms, all currently known regret bounds allow for error cancellations -- one can compensate for a constraint violation in one round with a strict constraint satisfaction in another. This makes the online learning process unsafe since it only guarantees safety for the final (mixture) policy but not during learning. As Efroni et al. (2020) pointed out, it is an open questio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15776","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/2402.15776/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":"2026-07-05T08:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FuEnZxxvBTgxUOehc8NA7mRlhHmVyMdWoZOC431IjHhlpZd5p/NxVkNLJRir1A1e14pwzMV6yfHONRMYGqetCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:06:21.933924Z"},"content_sha256":"5079ba83036eaa2e53886aeeafe20669c4b21ebacaf7f8ec1c1d5ba2ef89388d","schema_version":"1.0","event_id":"sha256:5079ba83036eaa2e53886aeeafe20669c4b21ebacaf7f8ec1c1d5ba2ef89388d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQ7QCQ3SAC22GKSCN374BBUN6H/bundle.json","state_url":"https://pith.science/pith/ZQ7QCQ3SAC22GKSCN374BBUN6H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQ7QCQ3SAC22GKSCN374BBUN6H/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":"2026-08-06T01:06:21Z","links":{"resolver":"https://pith.science/pith/ZQ7QCQ3SAC22GKSCN374BBUN6H","bundle":"https://pith.science/pith/ZQ7QCQ3SAC22GKSCN374BBUN6H/bundle.json","state":"https://pith.science/pith/ZQ7QCQ3SAC22GKSCN374BBUN6H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQ7QCQ3SAC22GKSCN374BBUN6H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQ7QCQ3SAC22GKSCN374BBUN6H","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":"ffcae6de7ea67da7ae15e04e92046f8db248c9554bcae8af1bfc0d9f00070bf9","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-24T09:47:46Z","title_canon_sha256":"e4b7836af9beb8fa2ab2da8295f196ca9b033c6ce11743c9216e41df5d0bd24b"},"schema_version":"1.0","source":{"id":"2402.15776","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15776","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15776v3","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15776","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZQ7QCQ3SAC22","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZQ7QCQ3SAC22GKSC","created_at":"2026-07-05T08:46:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZQ7QCQ3S","created_at":"2026-07-05T08:46:07Z"}],"graph_snapshots":[{"event_id":"sha256:5079ba83036eaa2e53886aeeafe20669c4b21ebacaf7f8ec1c1d5ba2ef89388d","target":"graph","created_at":"2026-07-05T08:46:07Z","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/2402.15776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Constrained Markov decision processes (CMDPs) are a common way to model safety constraints in reinforcement learning. State-of-the-art methods for efficiently solving CMDPs are based on primal-dual algorithms. For these algorithms, all currently known regret bounds allow for error cancellations -- one can compensate for a constraint violation in one round with a strict constraint satisfaction in another. This makes the online learning process unsafe since it only guarantees safety for the final (mixture) policy but not during learning. As Efroni et al. (2020) pointed out, it is an open questio","authors_text":"Adrian M\\\"uller, Giorgia Ramponi, Niao He, Pragnya Alatur, Volkan Cevher","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-24T09:47:46Z","title":"Truly No-Regret Learning in Constrained MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15776","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":"sha256:894a4c2cf88777fb2e71e3b121dbf3081b55399b0e2cc79e04a476c4ef9dc45b","target":"record","created_at":"2026-07-05T08:46:07Z","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":"ffcae6de7ea67da7ae15e04e92046f8db248c9554bcae8af1bfc0d9f00070bf9","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-24T09:47:46Z","title_canon_sha256":"e4b7836af9beb8fa2ab2da8295f196ca9b033c6ce11743c9216e41df5d0bd24b"},"schema_version":"1.0","source":{"id":"2402.15776","kind":"arxiv","version":3}},"canonical_sha256":"cc3f01437200b5a32a426effc0868df1d29091b304913df0217d4f6ec98c65ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc3f01437200b5a32a426effc0868df1d29091b304913df0217d4f6ec98c65ad","first_computed_at":"2026-07-05T08:46:07.272122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:07.272122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WdeboVS3s711M6j+ygMRqjSSnK2BwZRVMrtvIAm6ll/glGcm2qAoDN4uFmMvWdQa90HkqvRhRgV87fcbInsSCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:07.272650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15776","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:894a4c2cf88777fb2e71e3b121dbf3081b55399b0e2cc79e04a476c4ef9dc45b","sha256:5079ba83036eaa2e53886aeeafe20669c4b21ebacaf7f8ec1c1d5ba2ef89388d"],"state_sha256":"faed77423b2bf38758f4f260c1e69231fcdec97dbd06b1af5e827d56352398d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+xoDiU5frYa0+nZO4sKmn9ZAWBOAT8e4MuJ1eMpzcNdvQasnTXL0wD7RLKss5HJVXeonnZa75mS4QP78EaXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:06:21.944958Z","bundle_sha256":"aa63f2f03341add83f12bcb7d3adea7e76c86d951e198ae81328d5cd0b365f97"}}