{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZCQJ2ZN7DSLOW2KPQMRMTABEDS","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":"9390b95f292473e236cfb7ca3786846af50280daa332f3cbcd72d580ee18c587","cross_cats_sorted":["cs.CR","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T15:12:23Z","title_canon_sha256":"b5ab40aecafd13475e76c1550015e055f6b8d13b78abb3564f89741e5e18e506"},"schema_version":"1.0","source":{"id":"2112.10599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.10599","created_at":"2026-07-05T03:42:17Z"},{"alias_kind":"arxiv_version","alias_value":"2112.10599v1","created_at":"2026-07-05T03:42:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10599","created_at":"2026-07-05T03:42:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZCQJ2ZN7DSLO","created_at":"2026-07-05T03:42:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZCQJ2ZN7DSLOW2KP","created_at":"2026-07-05T03:42:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZCQJ2ZN7","created_at":"2026-07-05T03:42:17Z"}],"graph_snapshots":[{"event_id":"sha256:afc8de80b79c781aef91c94e33caf511707af2f07b24617f81ba112a99424559","target":"graph","created_at":"2026-07-05T03:42:17Z","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/2112.10599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study regret minimization in finite horizon tabular Markov decision processes (MDPs) under the constraints of differential privacy (DP). This is motivated by the widespread applications of reinforcement learning (RL) in real-world sequential decision making problems, where protecting users' sensitive and private information is becoming paramount. We consider two variants of DP -- joint DP (JDP), where a centralized agent is responsible for protecting users' sensitive data and local DP (LDP), where information needs to be protected directly on the user side. We first propose two general fram","authors_text":"Sayak Ray Chowdhury, Xingyu Zhou","cross_cats":["cs.CR","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T15:12:23Z","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10599","kind":"arxiv","version":1},"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":"sha256:512640984632a27d3ac47a5e9bfbac06464443b54685cd0148540de0f2671fac","target":"record","created_at":"2026-07-05T03:42:17Z","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":"9390b95f292473e236cfb7ca3786846af50280daa332f3cbcd72d580ee18c587","cross_cats_sorted":["cs.CR","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-20T15:12:23Z","title_canon_sha256":"b5ab40aecafd13475e76c1550015e055f6b8d13b78abb3564f89741e5e18e506"},"schema_version":"1.0","source":{"id":"2112.10599","kind":"arxiv","version":1}},"canonical_sha256":"c8a09d65bf1c96eb694f8322c980241cad2f0eac47ce36198720696e7a270d72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8a09d65bf1c96eb694f8322c980241cad2f0eac47ce36198720696e7a270d72","first_computed_at":"2026-07-05T03:42:17.177418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:42:17.177418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uQaDkxxYAOtLkSVB41R1aggPCHjNDYVoRsijZfdqFK8yjvdy6DlNn+g0VKHT1Xc+4ZX+ebIQb0t0R/04GEm9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:42:17.180331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.10599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:512640984632a27d3ac47a5e9bfbac06464443b54685cd0148540de0f2671fac","sha256:afc8de80b79c781aef91c94e33caf511707af2f07b24617f81ba112a99424559"],"state_sha256":"dd8eab9aa9c8963b42850699f13d4d606f88fe1cb2711da04594cd794e0d98d4"}