{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:O65CXTN24QYUIMX3XWQKDHC32K","short_pith_number":"pith:O65CXTN2","canonical_record":{"source":{"id":"1911.08689","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T03:49:13Z","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"title_canon_sha256":"db1b787d12d56b7ed752446ed8fabdfdd7bcd152aeb0e636311385b43810ba33","abstract_canon_sha256":"039b1b42d855c8569cfba975135607b7c5c30f162dfe140df7d1d30c9e097c4a"},"schema_version":"1.0"},"canonical_sha256":"77ba2bcdbae4314432fbbda0a19c5bd2abeb1b5bdaa7e1e5f39d131c9bdcf481","source":{"kind":"arxiv","id":"1911.08689","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.08689","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"1911.08689v4","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08689","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"O65CXTN24QYU","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"O65CXTN24QYUIMX3","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"O65CXTN2","created_at":"2026-07-05T07:07:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:O65CXTN24QYUIMX3XWQKDHC32K","target":"record","payload":{"canonical_record":{"source":{"id":"1911.08689","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T03:49:13Z","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"title_canon_sha256":"db1b787d12d56b7ed752446ed8fabdfdd7bcd152aeb0e636311385b43810ba33","abstract_canon_sha256":"039b1b42d855c8569cfba975135607b7c5c30f162dfe140df7d1d30c9e097c4a"},"schema_version":"1.0"},"canonical_sha256":"77ba2bcdbae4314432fbbda0a19c5bd2abeb1b5bdaa7e1e5f39d131c9bdcf481","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:34.257559Z","signature_b64":"ZSH85VZ1GK7jUr2ROXMA7fyM8noGHkwECBUcguVTgaOI73NDQtEQirHYpw4swr4iCgWFsZWOueH3GMz67t1qCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77ba2bcdbae4314432fbbda0a19c5bd2abeb1b5bdaa7e1e5f39d131c9bdcf481","last_reissued_at":"2026-07-05T07:07:34.257087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:34.257087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.08689","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:07:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U1NmtisfsDLxJaWQbqIKUNQeTl2E94LhLw+uz+/Wx+WiVeP5zFgqbZv7sW8DjDnezxUKky1dvAt7MnIyaLXDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:26:30.700284Z"},"content_sha256":"2977207d994ba9253117e0b0810ae492a4a61e40b70abb40d59470e1b3d853b3","schema_version":"1.0","event_id":"sha256:2977207d994ba9253117e0b0810ae492a4a61e40b70abb40d59470e1b3d853b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:O65CXTN24QYUIMX3XWQKDHC32K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Corruption-robust exploration in episodic reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandrs Slivkins, Max Simchowitz, Thodoris Lykouris, Wen Sun","submitted_at":"2019-11-20T03:49:13Z","abstract_excerpt":"We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic bandits. We provide a framework which modifies the aggressive exploration enjoyed by existing reinforcement learning approaches based on \"optimism in the face of uncertainty\", by complementing them with principles from \"action elimination\". Importantly, our framework circumvents the major challenges posed by naively applying action elimination in the RL setting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08689","kind":"arxiv","version":4},"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/1911.08689/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":"2026-07-05T07:07:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3uk71QCuyChYp7vE3vwT79rSm/Ao2wCZpS/Bz086cyfCBazgPlRgBpjDlxJZIYwiUjwVv4KxdapvH3kADdmmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:26:30.702784Z"},"content_sha256":"fbb10dca3b870c4dfaa69f813048877f324420b2dae518195437905d64fa4f22","schema_version":"1.0","event_id":"sha256:fbb10dca3b870c4dfaa69f813048877f324420b2dae518195437905d64fa4f22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O65CXTN24QYUIMX3XWQKDHC32K/bundle.json","state_url":"https://pith.science/pith/O65CXTN24QYUIMX3XWQKDHC32K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O65CXTN24QYUIMX3XWQKDHC32K/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":"2026-08-08T22:26:30Z","links":{"resolver":"https://pith.science/pith/O65CXTN24QYUIMX3XWQKDHC32K","bundle":"https://pith.science/pith/O65CXTN24QYUIMX3XWQKDHC32K/bundle.json","state":"https://pith.science/pith/O65CXTN24QYUIMX3XWQKDHC32K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O65CXTN24QYUIMX3XWQKDHC32K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:O65CXTN24QYUIMX3XWQKDHC32K","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":"039b1b42d855c8569cfba975135607b7c5c30f162dfe140df7d1d30c9e097c4a","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T03:49:13Z","title_canon_sha256":"db1b787d12d56b7ed752446ed8fabdfdd7bcd152aeb0e636311385b43810ba33"},"schema_version":"1.0","source":{"id":"1911.08689","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.08689","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"1911.08689v4","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08689","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"O65CXTN24QYU","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"O65CXTN24QYUIMX3","created_at":"2026-07-05T07:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"O65CXTN2","created_at":"2026-07-05T07:07:34Z"}],"graph_snapshots":[{"event_id":"sha256:fbb10dca3b870c4dfaa69f813048877f324420b2dae518195437905d64fa4f22","target":"graph","created_at":"2026-07-05T07:07:34Z","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/1911.08689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic bandits. We provide a framework which modifies the aggressive exploration enjoyed by existing reinforcement learning approaches based on \"optimism in the face of uncertainty\", by complementing them with principles from \"action elimination\". Importantly, our framework circumvents the major challenges posed by naively applying action elimination in the RL setting","authors_text":"Aleksandrs Slivkins, Max Simchowitz, Thodoris Lykouris, Wen Sun","cross_cats":["cs.AI","cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T03:49:13Z","title":"Corruption-robust exploration in episodic reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08689","kind":"arxiv","version":4},"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":"sha256:2977207d994ba9253117e0b0810ae492a4a61e40b70abb40d59470e1b3d853b3","target":"record","created_at":"2026-07-05T07:07:34Z","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":"039b1b42d855c8569cfba975135607b7c5c30f162dfe140df7d1d30c9e097c4a","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-20T03:49:13Z","title_canon_sha256":"db1b787d12d56b7ed752446ed8fabdfdd7bcd152aeb0e636311385b43810ba33"},"schema_version":"1.0","source":{"id":"1911.08689","kind":"arxiv","version":4}},"canonical_sha256":"77ba2bcdbae4314432fbbda0a19c5bd2abeb1b5bdaa7e1e5f39d131c9bdcf481","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77ba2bcdbae4314432fbbda0a19c5bd2abeb1b5bdaa7e1e5f39d131c9bdcf481","first_computed_at":"2026-07-05T07:07:34.257087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:34.257087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZSH85VZ1GK7jUr2ROXMA7fyM8noGHkwECBUcguVTgaOI73NDQtEQirHYpw4swr4iCgWFsZWOueH3GMz67t1qCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:34.257559Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.08689","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2977207d994ba9253117e0b0810ae492a4a61e40b70abb40d59470e1b3d853b3","sha256:fbb10dca3b870c4dfaa69f813048877f324420b2dae518195437905d64fa4f22"],"state_sha256":"7d5ee9df78b21c9d4c158030c699c965e51a66d8e4e80247e18ea4c8e4aef050"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wZ0hiPwN5aQ56epo/2w//HaIvOShDgvD2uLGIVFxv2I+3VXiAjZOY8lLGJOjJ2Mv88kfmZAC0mj3OE3x59IgCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:26:30.735998Z","bundle_sha256":"f7732d223247422a8b603df6cf8d78f687aee6a2d193ffbc1237f459c9e59f1e"}}