{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KXFHC226THGVZMKYWA7ZFTGGZO","short_pith_number":"pith:KXFHC226","canonical_record":{"source":{"id":"2008.09251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T01:12:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"10acc1e234f93a01d97949c1583c6b8dea1d05e741d603e0b839d389c8e4eab5","abstract_canon_sha256":"b9cf6bc9a4ae257bf5a5e7d1ac16e83bd91f0f054b39fb19d7482171f728c06d"},"schema_version":"1.0"},"canonical_sha256":"55ca716b5e99cd5cb158b03f92ccc6cba1a67de6cd5545cb83000cf28c1a6b5e","source":{"kind":"arxiv","id":"2008.09251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09251","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09251v1","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09251","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"pith_short_12","alias_value":"KXFHC226THGV","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"pith_short_16","alias_value":"KXFHC226THGVZMKY","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"pith_short_8","alias_value":"KXFHC226","created_at":"2026-07-05T01:28:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KXFHC226THGVZMKYWA7ZFTGGZO","target":"record","payload":{"canonical_record":{"source":{"id":"2008.09251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T01:12:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"10acc1e234f93a01d97949c1583c6b8dea1d05e741d603e0b839d389c8e4eab5","abstract_canon_sha256":"b9cf6bc9a4ae257bf5a5e7d1ac16e83bd91f0f054b39fb19d7482171f728c06d"},"schema_version":"1.0"},"canonical_sha256":"55ca716b5e99cd5cb158b03f92ccc6cba1a67de6cd5545cb83000cf28c1a6b5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:42.431215Z","signature_b64":"KEY9KVHnx4khqH7Z5oEK0sVMjqebZ3cd088LEmvcErkyfMK+Gykidx9MmNQRex7DuhnLOx2RzYBg18Ld/e5EBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55ca716b5e99cd5cb158b03f92ccc6cba1a67de6cd5545cb83000cf28c1a6b5e","last_reissued_at":"2026-07-05T01:28:42.430816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:42.430816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.09251","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":"2026-07-05T01:28:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z7iMh+93vhgXzzVf2N5XC3ImAY3gclcIHTO+pIYz648v6WKNx+gGhNy4A0Ezv31kWK4iyTY7vjtHBrs4HCLbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T20:46:25.800267Z"},"content_sha256":"30454b5c7fbc0ba2b80bc499b23292933ad9d40af720aadd654bfe13addea50d","schema_version":"1.0","event_id":"sha256:30454b5c7fbc0ba2b80bc499b23292933ad9d40af720aadd654bfe13addea50d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KXFHC226THGVZMKYWA7ZFTGGZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Refined Analysis of FPL for Adversarial Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kefan Dong, Yuanhao Wang","submitted_at":"2020-08-21T01:12:10Z","abstract_excerpt":"We consider the adversarial Markov Decision Process (MDP) problem, where the rewards for the MDP can be adversarially chosen, and the transition function can be either known or unknown. In both settings, Follow-the-PerturbedLeader (FPL) based algorithms have been proposed in previous literature. However, the established regret bounds for FPL based algorithms are worse than algorithms based on mirrordescent. We improve the analysis of FPL based algorithms in both settings, matching the current best regret bounds using faster and simpler algorithms."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09251","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/2008.09251/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":"2026-07-05T01:28:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fjpJspvLoxhHFZPspegdCjyoW76naxYFCoJsQVKCTWkjQiGJnMXWkAOPcNo6dcVUSow3A7l1L1mZOL2AeUKADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T20:46:25.800664Z"},"content_sha256":"47da47144bdb986630faee9b16f74f3e544ab7be366c1e765a1783cc50667f90","schema_version":"1.0","event_id":"sha256:47da47144bdb986630faee9b16f74f3e544ab7be366c1e765a1783cc50667f90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXFHC226THGVZMKYWA7ZFTGGZO/bundle.json","state_url":"https://pith.science/pith/KXFHC226THGVZMKYWA7ZFTGGZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXFHC226THGVZMKYWA7ZFTGGZO/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":"2026-07-13T20:46:25Z","links":{"resolver":"https://pith.science/pith/KXFHC226THGVZMKYWA7ZFTGGZO","bundle":"https://pith.science/pith/KXFHC226THGVZMKYWA7ZFTGGZO/bundle.json","state":"https://pith.science/pith/KXFHC226THGVZMKYWA7ZFTGGZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXFHC226THGVZMKYWA7ZFTGGZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KXFHC226THGVZMKYWA7ZFTGGZO","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":"b9cf6bc9a4ae257bf5a5e7d1ac16e83bd91f0f054b39fb19d7482171f728c06d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T01:12:10Z","title_canon_sha256":"10acc1e234f93a01d97949c1583c6b8dea1d05e741d603e0b839d389c8e4eab5"},"schema_version":"1.0","source":{"id":"2008.09251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09251","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09251v1","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09251","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"pith_short_12","alias_value":"KXFHC226THGV","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"pith_short_16","alias_value":"KXFHC226THGVZMKY","created_at":"2026-07-05T01:28:42Z"},{"alias_kind":"pith_short_8","alias_value":"KXFHC226","created_at":"2026-07-05T01:28:42Z"}],"graph_snapshots":[{"event_id":"sha256:47da47144bdb986630faee9b16f74f3e544ab7be366c1e765a1783cc50667f90","target":"graph","created_at":"2026-07-05T01:28:42Z","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/2008.09251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the adversarial Markov Decision Process (MDP) problem, where the rewards for the MDP can be adversarially chosen, and the transition function can be either known or unknown. In both settings, Follow-the-PerturbedLeader (FPL) based algorithms have been proposed in previous literature. However, the established regret bounds for FPL based algorithms are worse than algorithms based on mirrordescent. We improve the analysis of FPL based algorithms in both settings, matching the current best regret bounds using faster and simpler algorithms.","authors_text":"Kefan Dong, Yuanhao Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T01:12:10Z","title":"Refined Analysis of FPL for Adversarial Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09251","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":"sha256:30454b5c7fbc0ba2b80bc499b23292933ad9d40af720aadd654bfe13addea50d","target":"record","created_at":"2026-07-05T01:28:42Z","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":"b9cf6bc9a4ae257bf5a5e7d1ac16e83bd91f0f054b39fb19d7482171f728c06d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T01:12:10Z","title_canon_sha256":"10acc1e234f93a01d97949c1583c6b8dea1d05e741d603e0b839d389c8e4eab5"},"schema_version":"1.0","source":{"id":"2008.09251","kind":"arxiv","version":1}},"canonical_sha256":"55ca716b5e99cd5cb158b03f92ccc6cba1a67de6cd5545cb83000cf28c1a6b5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55ca716b5e99cd5cb158b03f92ccc6cba1a67de6cd5545cb83000cf28c1a6b5e","first_computed_at":"2026-07-05T01:28:42.430816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:42.430816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KEY9KVHnx4khqH7Z5oEK0sVMjqebZ3cd088LEmvcErkyfMK+Gykidx9MmNQRex7DuhnLOx2RzYBg18Ld/e5EBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:42.431215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.09251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30454b5c7fbc0ba2b80bc499b23292933ad9d40af720aadd654bfe13addea50d","sha256:47da47144bdb986630faee9b16f74f3e544ab7be366c1e765a1783cc50667f90"],"state_sha256":"e8992e37979f9f2824d925d4eb07520ce9e5ba317b22d6cbf8dba0a1054b2a3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Et+dqjCDuHBMF2GF7cAsgMwF8m+jOR2sbbxQG0V/f0BwjBO2JytebQSn6ocMlUWgb58F6poV0/9NlMMmkcNgCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T20:46:25.802714Z","bundle_sha256":"ed27fd8d2eb51bb5f179508abe3f6feb7b242cfba1480235628c96b786a5df88"}}