{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7L5MO3JSZCJQTMEB67V55YUUQN","short_pith_number":"pith:7L5MO3JS","canonical_record":{"source":{"id":"1910.05654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T22:30:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3f86ac8407d1160af1060ed776f55d39285a062909ea56cac3818cf9ce7c1abf","abstract_canon_sha256":"93e589e00e0363af1e22f36ac42106258e47ab0c0c1d9f086479e39e7d3c6ad1"},"schema_version":"1.0"},"canonical_sha256":"fafac76d32c89309b081f7ebdee2948367bbe0cd027290c8b1792ca742b5692f","source":{"kind":"arxiv","id":"1910.05654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05654","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05654v1","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05654","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"7L5MO3JSZCJQ","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"7L5MO3JSZCJQTMEB","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"7L5MO3JS","created_at":"2026-07-05T00:11:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7L5MO3JSZCJQTMEB67V55YUUQN","target":"record","payload":{"canonical_record":{"source":{"id":"1910.05654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T22:30:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3f86ac8407d1160af1060ed776f55d39285a062909ea56cac3818cf9ce7c1abf","abstract_canon_sha256":"93e589e00e0363af1e22f36ac42106258e47ab0c0c1d9f086479e39e7d3c6ad1"},"schema_version":"1.0"},"canonical_sha256":"fafac76d32c89309b081f7ebdee2948367bbe0cd027290c8b1792ca742b5692f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:40.681172Z","signature_b64":"miARhm+C4NAjRQrGxa1oZg/zLhIYRWjIzGrx4RZAH/mQqM1ydE9olHR8D6s+ik/FslMk8MJjS4r41BxmmjJPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fafac76d32c89309b081f7ebdee2948367bbe0cd027290c8b1792ca742b5692f","last_reissued_at":"2026-07-05T00:11:40.680706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:40.680706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.05654","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":"2026-07-05T00:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FkNrSZSODOKo3yydFCZqhUu4Ru+QjVxGDPKouebrR0Lls6mEKdleA2OQxb/Hxv4fkVtWdPNgRVorkFLo8/mMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:16:37.955549Z"},"content_sha256":"f1d713e0e79beb9e05fd122221f54bbb78d9fc36e28a02f95434598ad008010d","schema_version":"1.0","event_id":"sha256:f1d713e0e79beb9e05fd122221f54bbb78d9fc36e28a02f95434598ad008010d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7L5MO3JSZCJQTMEB67V55YUUQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Thompson Sampling in Non-Episodic Restless Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ambuj Tewari, Marc Abeille, Young Hun Jung","submitted_at":"2019-10-12T22:30:24Z","abstract_excerpt":"Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a sub-linear, $O(\\sqrt{T}\\log T)$, regret bound for a variant of Thompson sampling. Our analysis applies in the infinite time horizon setting, resolving the open question raised by Jung and Tewari (2019) whose analysis is limited to the episodic case. We adopt their policy mapping framework, which allows our algorithm to be efficient and simultaneously keeps the re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05654","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/1910.05654/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":"2026-07-05T00:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sv4P0ikZ5oC+BjVzN8GQd5cqQfZoWcLs9x0aG/yeH/9smX3E0aACqrgETwVfTjESWvXoQ7LtlkDu2zp6jqvtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:16:37.956030Z"},"content_sha256":"f5f62e3ae94d1423e3f6d1e6ed3fb1a581a3d5326365b52051e5eaee25b85ad9","schema_version":"1.0","event_id":"sha256:f5f62e3ae94d1423e3f6d1e6ed3fb1a581a3d5326365b52051e5eaee25b85ad9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7L5MO3JSZCJQTMEB67V55YUUQN/bundle.json","state_url":"https://pith.science/pith/7L5MO3JSZCJQTMEB67V55YUUQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7L5MO3JSZCJQTMEB67V55YUUQN/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":"2026-08-05T08:16:37Z","links":{"resolver":"https://pith.science/pith/7L5MO3JSZCJQTMEB67V55YUUQN","bundle":"https://pith.science/pith/7L5MO3JSZCJQTMEB67V55YUUQN/bundle.json","state":"https://pith.science/pith/7L5MO3JSZCJQTMEB67V55YUUQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7L5MO3JSZCJQTMEB67V55YUUQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7L5MO3JSZCJQTMEB67V55YUUQN","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":"93e589e00e0363af1e22f36ac42106258e47ab0c0c1d9f086479e39e7d3c6ad1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T22:30:24Z","title_canon_sha256":"3f86ac8407d1160af1060ed776f55d39285a062909ea56cac3818cf9ce7c1abf"},"schema_version":"1.0","source":{"id":"1910.05654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05654","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05654v1","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05654","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"7L5MO3JSZCJQ","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"7L5MO3JSZCJQTMEB","created_at":"2026-07-05T00:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"7L5MO3JS","created_at":"2026-07-05T00:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:f5f62e3ae94d1423e3f6d1e6ed3fb1a581a3d5326365b52051e5eaee25b85ad9","target":"graph","created_at":"2026-07-05T00:11:40Z","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/1910.05654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a sub-linear, $O(\\sqrt{T}\\log T)$, regret bound for a variant of Thompson sampling. Our analysis applies in the infinite time horizon setting, resolving the open question raised by Jung and Tewari (2019) whose analysis is limited to the episodic case. We adopt their policy mapping framework, which allows our algorithm to be efficient and simultaneously keeps the re","authors_text":"Ambuj Tewari, Marc Abeille, Young Hun Jung","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T22:30:24Z","title":"Thompson Sampling in Non-Episodic Restless Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05654","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:f1d713e0e79beb9e05fd122221f54bbb78d9fc36e28a02f95434598ad008010d","target":"record","created_at":"2026-07-05T00:11:40Z","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":"93e589e00e0363af1e22f36ac42106258e47ab0c0c1d9f086479e39e7d3c6ad1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T22:30:24Z","title_canon_sha256":"3f86ac8407d1160af1060ed776f55d39285a062909ea56cac3818cf9ce7c1abf"},"schema_version":"1.0","source":{"id":"1910.05654","kind":"arxiv","version":1}},"canonical_sha256":"fafac76d32c89309b081f7ebdee2948367bbe0cd027290c8b1792ca742b5692f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fafac76d32c89309b081f7ebdee2948367bbe0cd027290c8b1792ca742b5692f","first_computed_at":"2026-07-05T00:11:40.680706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:40.680706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"miARhm+C4NAjRQrGxa1oZg/zLhIYRWjIzGrx4RZAH/mQqM1ydE9olHR8D6s+ik/FslMk8MJjS4r41BxmmjJPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:40.681172Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.05654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1d713e0e79beb9e05fd122221f54bbb78d9fc36e28a02f95434598ad008010d","sha256:f5f62e3ae94d1423e3f6d1e6ed3fb1a581a3d5326365b52051e5eaee25b85ad9"],"state_sha256":"b8f8cc3d1e48e48983b84c61568a4b742b8d5bce7174fde2ecf2a6fe4bd67f6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3bqLIQg+cemj2kdIWmGqRWacwptQ8buzXRlTF/ppiZO7oEKp07Gxm8zLWBUKzMLomjEKtSWkUegGnFGcnA5kAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:16:37.959464Z","bundle_sha256":"32b83501c422c1037710a3eb67dfa515522a708dd2c817c5b9b3b2d482670a45"}}