{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W4625GTPIQ6UJRQGC6LS2FWEYF","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":"e9b10140910f19f1dd8b39221d829b2f7b202d388cebe256d390affefe498317","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T10:10:57Z","title_canon_sha256":"6770a2236b1eed017de294aeb487923490611f1868c9d32671c240e85b42d303"},"schema_version":"1.0","source":{"id":"2306.07001","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07001","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07001v2","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07001","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"W4625GTPIQ6U","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"W4625GTPIQ6UJRQG","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"W4625GTP","created_at":"2026-07-05T06:46:05Z"}],"graph_snapshots":[{"event_id":"sha256:b2acc97c17bf9e34c2bfa78b8d1448024d9af1764f584f569d0644566b91b83a","target":"graph","created_at":"2026-07-05T06:46:05Z","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/2306.07001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Constrained Markov Decision Processes (CMDPs) are one of the common ways to model safe reinforcement learning problems, where constraint functions model the safety objectives. Lagrangian-based dual or primal-dual algorithms provide efficient methods for learning in CMDPs. For these algorithms, the currently known regret bounds in the finite-horizon setting allow for a \"cancellation of errors\"; one can compensate for a constraint violation in one episode with a strict constraint satisfaction in another. However, we do not consider such a behavior safe in practical applications. In this paper, w","authors_text":"Adrian M\\\"uller, Giorgia Ramponi, Niao He, Pragnya Alatur","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T10:10:57Z","title":"Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07001","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:caacf03caff6f8cb92c54a7989491993391e514ac68ef82c0f5412f62cd75582","target":"record","created_at":"2026-07-05T06:46:05Z","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":"e9b10140910f19f1dd8b39221d829b2f7b202d388cebe256d390affefe498317","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T10:10:57Z","title_canon_sha256":"6770a2236b1eed017de294aeb487923490611f1868c9d32671c240e85b42d303"},"schema_version":"1.0","source":{"id":"2306.07001","kind":"arxiv","version":2}},"canonical_sha256":"b73dae9a6f443d44c60617972d16c4c1564ebcd4fb1789164997629135ece1ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b73dae9a6f443d44c60617972d16c4c1564ebcd4fb1789164997629135ece1ee","first_computed_at":"2026-07-05T06:46:05.884173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:05.884173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FZ2gpYD0I560HbY+irUEQ/SbCJJqJnmKutEBwLCFQ8ILopa+1NkwXkNHOPStWEoao1cNFyZIvznCOhLy+xM9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:05.884689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07001","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:caacf03caff6f8cb92c54a7989491993391e514ac68ef82c0f5412f62cd75582","sha256:b2acc97c17bf9e34c2bfa78b8d1448024d9af1764f584f569d0644566b91b83a"],"state_sha256":"5681ad885dd05da2874200b8f51aea11b9445c1ccd2ec9b7ef218630d66bcf32"}