{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:T4CBDYZOVZQLRRWIQD5TBP3IJK","short_pith_number":"pith:T4CBDYZO","canonical_record":{"source":{"id":"2106.14338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-27T23:41:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"70d7fe3beff0eac6f48e645dde287b52fc50d4577b7da1c43ce519a5a2d057e0","abstract_canon_sha256":"b8c1c5a52ec847893d5ee52d13959526da0413d6ca8923a0c446e7bb66ef369e"},"schema_version":"1.0"},"canonical_sha256":"9f0411e32eae60b8c6c880fb30bf684a9790fa44c4f0c543ad9142002d3f1cc7","source":{"kind":"arxiv","id":"2106.14338","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14338","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14338v1","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14338","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"T4CBDYZOVZQL","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"T4CBDYZOVZQLRRWI","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"T4CBDYZO","created_at":"2026-07-05T02:52:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:T4CBDYZOVZQLRRWIQD5TBP3IJK","target":"record","payload":{"canonical_record":{"source":{"id":"2106.14338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-27T23:41:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"70d7fe3beff0eac6f48e645dde287b52fc50d4577b7da1c43ce519a5a2d057e0","abstract_canon_sha256":"b8c1c5a52ec847893d5ee52d13959526da0413d6ca8923a0c446e7bb66ef369e"},"schema_version":"1.0"},"canonical_sha256":"9f0411e32eae60b8c6c880fb30bf684a9790fa44c4f0c543ad9142002d3f1cc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:49.529465Z","signature_b64":"CwaVuQS2wAUeKgzh72Wj5FJHAC3mbRE8Pn+Fb4alWFFYZKggEdBBKbpWgwA8hlfyK4weMUKuxWEUWr3P3pTuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f0411e32eae60b8c6c880fb30bf684a9790fa44c4f0c543ad9142002d3f1cc7","last_reissued_at":"2026-07-05T02:52:49.529073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:49.529073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.14338","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlzh6INZJf53KB5r7BmWyuFuwZoHAM4pwKLsP6nsZU5wDHBkZ5c37oLAST35tZvlyES77QHOmGF5EF3thsqjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:45:45.619237Z"},"content_sha256":"ff80b8dca00a1981f6e3d1c8a44e1b9e3c10ec7c2c6031b66ad1dfd5635c6ff3","schema_version":"1.0","event_id":"sha256:ff80b8dca00a1981f6e3d1c8a44e1b9e3c10ec7c2c6031b66ad1dfd5635c6ff3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:T4CBDYZOVZQLRRWIQD5TBP3IJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regret Analysis in Deterministic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Proutiere, Damianos Tranos","submitted_at":"2021-06-27T23:41:57Z","abstract_excerpt":"We consider Markov Decision Processes (MDPs) with deterministic transitions and study the problem of regret minimization, which is central to the analysis and design of optimal learning algorithms. We present logarithmic problem-specific regret lower bounds that explicitly depend on the system parameter (in contrast to previous minimax approaches) and thus, truly quantify the fundamental limit of performance achievable by any learning algorithm. Deterministic MDPs can be interpreted as graphs and analyzed in terms of their cycles, a fact which we leverage in order to identify a class of determ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14338","kind":"arxiv","version":1},"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/2106.14338/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":"2026-07-05T02:52:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pm0KyG1LDFzVujS+EMxf09SML8zjC6IY+NqLf7WYgAWOBuJ7dxJT9nVrIp8XiJXH9sd0f+/ZITq/Z6B33pTxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:45:45.619744Z"},"content_sha256":"5aa1b40583580aa6ce6a86e4d25cfa6f8a1bf31526949d660e25fafee7562640","schema_version":"1.0","event_id":"sha256:5aa1b40583580aa6ce6a86e4d25cfa6f8a1bf31526949d660e25fafee7562640"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T4CBDYZOVZQLRRWIQD5TBP3IJK/bundle.json","state_url":"https://pith.science/pith/T4CBDYZOVZQLRRWIQD5TBP3IJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T4CBDYZOVZQLRRWIQD5TBP3IJK/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":"2026-08-10T01:45:45Z","links":{"resolver":"https://pith.science/pith/T4CBDYZOVZQLRRWIQD5TBP3IJK","bundle":"https://pith.science/pith/T4CBDYZOVZQLRRWIQD5TBP3IJK/bundle.json","state":"https://pith.science/pith/T4CBDYZOVZQLRRWIQD5TBP3IJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T4CBDYZOVZQLRRWIQD5TBP3IJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:T4CBDYZOVZQLRRWIQD5TBP3IJK","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":"b8c1c5a52ec847893d5ee52d13959526da0413d6ca8923a0c446e7bb66ef369e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-27T23:41:57Z","title_canon_sha256":"70d7fe3beff0eac6f48e645dde287b52fc50d4577b7da1c43ce519a5a2d057e0"},"schema_version":"1.0","source":{"id":"2106.14338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.14338","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.14338v1","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14338","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"T4CBDYZOVZQL","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"T4CBDYZOVZQLRRWI","created_at":"2026-07-05T02:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"T4CBDYZO","created_at":"2026-07-05T02:52:49Z"}],"graph_snapshots":[{"event_id":"sha256:5aa1b40583580aa6ce6a86e4d25cfa6f8a1bf31526949d660e25fafee7562640","target":"graph","created_at":"2026-07-05T02:52:49Z","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/2106.14338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider Markov Decision Processes (MDPs) with deterministic transitions and study the problem of regret minimization, which is central to the analysis and design of optimal learning algorithms. We present logarithmic problem-specific regret lower bounds that explicitly depend on the system parameter (in contrast to previous minimax approaches) and thus, truly quantify the fundamental limit of performance achievable by any learning algorithm. Deterministic MDPs can be interpreted as graphs and analyzed in terms of their cycles, a fact which we leverage in order to identify a class of determ","authors_text":"Alexandre Proutiere, Damianos Tranos","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-27T23:41:57Z","title":"Regret Analysis in Deterministic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14338","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:ff80b8dca00a1981f6e3d1c8a44e1b9e3c10ec7c2c6031b66ad1dfd5635c6ff3","target":"record","created_at":"2026-07-05T02:52:49Z","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":"b8c1c5a52ec847893d5ee52d13959526da0413d6ca8923a0c446e7bb66ef369e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-27T23:41:57Z","title_canon_sha256":"70d7fe3beff0eac6f48e645dde287b52fc50d4577b7da1c43ce519a5a2d057e0"},"schema_version":"1.0","source":{"id":"2106.14338","kind":"arxiv","version":1}},"canonical_sha256":"9f0411e32eae60b8c6c880fb30bf684a9790fa44c4f0c543ad9142002d3f1cc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f0411e32eae60b8c6c880fb30bf684a9790fa44c4f0c543ad9142002d3f1cc7","first_computed_at":"2026-07-05T02:52:49.529073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:49.529073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CwaVuQS2wAUeKgzh72Wj5FJHAC3mbRE8Pn+Fb4alWFFYZKggEdBBKbpWgwA8hlfyK4weMUKuxWEUWr3P3pTuBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:49.529465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.14338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff80b8dca00a1981f6e3d1c8a44e1b9e3c10ec7c2c6031b66ad1dfd5635c6ff3","sha256:5aa1b40583580aa6ce6a86e4d25cfa6f8a1bf31526949d660e25fafee7562640"],"state_sha256":"05fe5a3f1520ece9ca7bbd3f27c36278dc3644ee1b342b35eb2ab59d5aea8b7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XxpUrC4pKjRxAr91pg7uUdQ2CS88UiqCjCILHhdIhDMdOP8fafBi9b5Wepc5CiwsDVytbjjl3ZcWmOC2XdGWCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:45:45.623684Z","bundle_sha256":"2ec64aeca6c7f4347af9c45c5883a33a5ac40b1233abaa60f682258a7dcc099e"}}