{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5O6JWWL7PHKROWAHZTEUNHGDRT","short_pith_number":"pith:5O6JWWL7","canonical_record":{"source":{"id":"2602.01295","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-01T15:50:59Z","cross_cats_sorted":[],"title_canon_sha256":"068ecaafa801a23df9819b0eab8767c94602abf0bcce248bd56e8c8d371cc6d5","abstract_canon_sha256":"e1fe177cc4de996ba21da38e32e7aee989694c8b8a2e49e49c4ecda47504aafc"},"schema_version":"1.0"},"canonical_sha256":"ebbc9b597f79d5175807ccc9469cc38cce91f41baf7ce1b4e861f395eee1fc9c","source":{"kind":"arxiv","id":"2602.01295","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01295","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01295v3","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01295","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_12","alias_value":"5O6JWWL7PHKR","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_16","alias_value":"5O6JWWL7PHKROWAH","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_8","alias_value":"5O6JWWL7","created_at":"2026-05-20T00:01:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5O6JWWL7PHKROWAHZTEUNHGDRT","target":"record","payload":{"canonical_record":{"source":{"id":"2602.01295","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-01T15:50:59Z","cross_cats_sorted":[],"title_canon_sha256":"068ecaafa801a23df9819b0eab8767c94602abf0bcce248bd56e8c8d371cc6d5","abstract_canon_sha256":"e1fe177cc4de996ba21da38e32e7aee989694c8b8a2e49e49c4ecda47504aafc"},"schema_version":"1.0"},"canonical_sha256":"ebbc9b597f79d5175807ccc9469cc38cce91f41baf7ce1b4e861f395eee1fc9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:39.491115Z","signature_b64":"hKkwx9DdqLuTw+u0CnjwZRosN25C7+6w4cflrBTRUMCfW7rBptaIAFSfge85BLv/ENxfeK4AjVyritepcayPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebbc9b597f79d5175807ccc9469cc38cce91f41baf7ce1b4e861f395eee1fc9c","last_reissued_at":"2026-05-20T00:01:39.490281Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:39.490281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.01295","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":"2026-05-20T00:01:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f4FnftSE0D/IuMmHVZNLHrHHaimOZL6MLfBw5pbHJYiLK7zEZ5Ni0DQ4XG3EnbSC93FBMpJIOxaBZDik4Wv5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:40:50.711168Z"},"content_sha256":"4991d0867bdfb9372f5e55160eaf49de7c677e976cba00c77172a8b3a5d6b676","schema_version":"1.0","event_id":"sha256:4991d0867bdfb9372f5e55160eaf49de7c677e976cba00c77172a8b3a5d6b676"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5O6JWWL7PHKROWAHZTEUNHGDRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiatai Huang, Longbo Huang, Yihan Du, Yu Chen, Yuhao Liu","submitted_at":"2026-02-01T15:50:59Z","abstract_excerpt":"We investigate episodic Markov Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity in adversarial regimes. In this work, we propose algorithms HT-FTRL-OM and HT-FTRL-UOB for HTMDPs that achieve Best-of-Both-Worlds (BoBW) guarantees: instance-independent regret in adversarial environments and logarithmic instance-dependent regret in self-bounding (including the stochastic case) environments. For the known transition setting, HT-FTRL-OM applies the Follow-The-Regularized-Leader (FTRL) framework over "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01295","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/2602.01295/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":"2026-05-20T00:01:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IM8UH8OBbWcgU0T2pLdKvu7zSsYaB2udHquqsZ0eIO/erIicj4AEZ8F3GpesKmbV2Me16kPHy1qTxaMUNcj8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T23:40:50.711656Z"},"content_sha256":"d4120d4d9d7ff735811d15653df5f2fc77fbcef9a34b544c3f7cc6123a654fd8","schema_version":"1.0","event_id":"sha256:d4120d4d9d7ff735811d15653df5f2fc77fbcef9a34b544c3f7cc6123a654fd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5O6JWWL7PHKROWAHZTEUNHGDRT/bundle.json","state_url":"https://pith.science/pith/5O6JWWL7PHKROWAHZTEUNHGDRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5O6JWWL7PHKROWAHZTEUNHGDRT/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":"2026-06-11T23:40:50Z","links":{"resolver":"https://pith.science/pith/5O6JWWL7PHKROWAHZTEUNHGDRT","bundle":"https://pith.science/pith/5O6JWWL7PHKROWAHZTEUNHGDRT/bundle.json","state":"https://pith.science/pith/5O6JWWL7PHKROWAHZTEUNHGDRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5O6JWWL7PHKROWAHZTEUNHGDRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5O6JWWL7PHKROWAHZTEUNHGDRT","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":"e1fe177cc4de996ba21da38e32e7aee989694c8b8a2e49e49c4ecda47504aafc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-01T15:50:59Z","title_canon_sha256":"068ecaafa801a23df9819b0eab8767c94602abf0bcce248bd56e8c8d371cc6d5"},"schema_version":"1.0","source":{"id":"2602.01295","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01295","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01295v3","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01295","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_12","alias_value":"5O6JWWL7PHKR","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_16","alias_value":"5O6JWWL7PHKROWAH","created_at":"2026-05-20T00:01:39Z"},{"alias_kind":"pith_short_8","alias_value":"5O6JWWL7","created_at":"2026-05-20T00:01:39Z"}],"graph_snapshots":[{"event_id":"sha256:d4120d4d9d7ff735811d15653df5f2fc77fbcef9a34b544c3f7cc6123a654fd8","target":"graph","created_at":"2026-05-20T00:01:39Z","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/2602.01295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate episodic Markov Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity in adversarial regimes. In this work, we propose algorithms HT-FTRL-OM and HT-FTRL-UOB for HTMDPs that achieve Best-of-Both-Worlds (BoBW) guarantees: instance-independent regret in adversarial environments and logarithmic instance-dependent regret in self-bounding (including the stochastic case) environments. For the known transition setting, HT-FTRL-OM applies the Follow-The-Regularized-Leader (FTRL) framework over ","authors_text":"Jiatai Huang, Longbo Huang, Yihan Du, Yu Chen, Yuhao Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-01T15:50:59Z","title":"Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01295","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":"sha256:4991d0867bdfb9372f5e55160eaf49de7c677e976cba00c77172a8b3a5d6b676","target":"record","created_at":"2026-05-20T00:01:39Z","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":"e1fe177cc4de996ba21da38e32e7aee989694c8b8a2e49e49c4ecda47504aafc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-01T15:50:59Z","title_canon_sha256":"068ecaafa801a23df9819b0eab8767c94602abf0bcce248bd56e8c8d371cc6d5"},"schema_version":"1.0","source":{"id":"2602.01295","kind":"arxiv","version":3}},"canonical_sha256":"ebbc9b597f79d5175807ccc9469cc38cce91f41baf7ce1b4e861f395eee1fc9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebbc9b597f79d5175807ccc9469cc38cce91f41baf7ce1b4e861f395eee1fc9c","first_computed_at":"2026-05-20T00:01:39.490281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:39.490281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hKkwx9DdqLuTw+u0CnjwZRosN25C7+6w4cflrBTRUMCfW7rBptaIAFSfge85BLv/ENxfeK4AjVyritepcayPBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:39.491115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.01295","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4991d0867bdfb9372f5e55160eaf49de7c677e976cba00c77172a8b3a5d6b676","sha256:d4120d4d9d7ff735811d15653df5f2fc77fbcef9a34b544c3f7cc6123a654fd8"],"state_sha256":"fd20f5770de5acb3b7d1d55470b37488a893663ac2de7706db809cb691ebb09e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2dmuKbf1i0UCFwc4FsltAidYfFfbjPGmNCnsQLEk+shuZQOPE1qV/pxpp/2Bsa7Cl1/tS16w5dt9N0oycXUwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T23:40:50.714812Z","bundle_sha256":"58762ac58b7f27f3fddec7cd1cfd535ae9ea4a3786b0ea41f34d0b374287d0a1"}}