{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:RP7UX5NF4B45NBDYAFRFXEVK5D","short_pith_number":"pith:RP7UX5NF","canonical_record":{"source":{"id":"1107.4042","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-07-20T17:33:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a640af14f87f1612b4ccf2c28f9123d51e983435562b73a084d886c4f751e601","abstract_canon_sha256":"55004e825f47bd8a2cd236b715081e2a50e2d8c806a128158dcee006013f528c"},"schema_version":"1.0"},"canonical_sha256":"8bff4bf5a5e079d6847801625b92aae8dfc5c3b97c1c16f45163c912bee0a622","source":{"kind":"arxiv","id":"1107.4042","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.4042","created_at":"2026-05-18T02:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"1107.4042v3","created_at":"2026-05-18T02:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.4042","created_at":"2026-05-18T02:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"RP7UX5NF4B45","created_at":"2026-05-18T12:26:41Z"},{"alias_kind":"pith_short_16","alias_value":"RP7UX5NF4B45NBDY","created_at":"2026-05-18T12:26:41Z"},{"alias_kind":"pith_short_8","alias_value":"RP7UX5NF","created_at":"2026-05-18T12:26:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:RP7UX5NF4B45NBDYAFRFXEVK5D","target":"record","payload":{"canonical_record":{"source":{"id":"1107.4042","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-07-20T17:33:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a640af14f87f1612b4ccf2c28f9123d51e983435562b73a084d886c4f751e601","abstract_canon_sha256":"55004e825f47bd8a2cd236b715081e2a50e2d8c806a128158dcee006013f528c"},"schema_version":"1.0"},"canonical_sha256":"8bff4bf5a5e079d6847801625b92aae8dfc5c3b97c1c16f45163c912bee0a622","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:28:29.616582Z","signature_b64":"CXXZzOEhfGiGo7F4cLWvamaKW6GBDJiEjdi1utXQYD5fx7yUyzB2uJYuJTGIb3M5eX38SlzZwxPmmRd6EJP4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bff4bf5a5e079d6847801625b92aae8dfc5c3b97c1c16f45163c912bee0a622","last_reissued_at":"2026-05-18T02:28:29.616118Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:28:29.616118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1107.4042","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":"2026-05-18T02:28:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6j/ksseAUE6w2+5gMGR0ME0UrGiJmODfGSwtRLSCMcl9vaBxYQdqWOW7jNk5N3kCy/dVnoOIGOo8ZzNdtbXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:23:18.218971Z"},"content_sha256":"85fc98020fc429f8ff0dd31c3850cf7a8867a276c989879aaaabb87378aa5dfe","schema_version":"1.0","event_id":"sha256:85fc98020fc429f8ff0dd31c3850cf7a8867a276c989879aaaabb87378aa5dfe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:RP7UX5NF4B45NBDYAFRFXEVK5D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Adaptive Learning in Uncontrolled Restless Bandit Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Cem Tekin, Mingyan Liu","submitted_at":"2011-07-20T17:33:43Z","abstract_excerpt":"In this paper we consider the problem of learning the optimal policy for uncontrolled restless bandit problems. In an uncontrolled restless bandit problem, there is a finite set of arms, each of which when pulled yields a positive reward. There is a player who sequentially selects one of the arms at each time step. The goal of the player is to maximize its undiscounted reward over a time horizon T. The reward process of each arm is a finite state Markov chain, whose transition probabilities are unknown by the player. State transitions of each arm is independent of the selection of the player. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.4042","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":""},"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":"2026-05-18T02:28:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iTWnBfTaFTsKz7/clT+HRlMcSc7ksSeawrGOYslIhyhM8QCo3NEYgcm57ls4Dqsxj6m/fmUXarTEBenQ8yLkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:23:18.219632Z"},"content_sha256":"3051ddd0639672176046700b825310004e44f9e2a2f3e4b305d14f7e1d2189a9","schema_version":"1.0","event_id":"sha256:3051ddd0639672176046700b825310004e44f9e2a2f3e4b305d14f7e1d2189a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RP7UX5NF4B45NBDYAFRFXEVK5D/bundle.json","state_url":"https://pith.science/pith/RP7UX5NF4B45NBDYAFRFXEVK5D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RP7UX5NF4B45NBDYAFRFXEVK5D/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":"2026-05-29T16:23:18Z","links":{"resolver":"https://pith.science/pith/RP7UX5NF4B45NBDYAFRFXEVK5D","bundle":"https://pith.science/pith/RP7UX5NF4B45NBDYAFRFXEVK5D/bundle.json","state":"https://pith.science/pith/RP7UX5NF4B45NBDYAFRFXEVK5D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RP7UX5NF4B45NBDYAFRFXEVK5D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:RP7UX5NF4B45NBDYAFRFXEVK5D","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":"55004e825f47bd8a2cd236b715081e2a50e2d8c806a128158dcee006013f528c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-07-20T17:33:43Z","title_canon_sha256":"a640af14f87f1612b4ccf2c28f9123d51e983435562b73a084d886c4f751e601"},"schema_version":"1.0","source":{"id":"1107.4042","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1107.4042","created_at":"2026-05-18T02:28:29Z"},{"alias_kind":"arxiv_version","alias_value":"1107.4042v3","created_at":"2026-05-18T02:28:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1107.4042","created_at":"2026-05-18T02:28:29Z"},{"alias_kind":"pith_short_12","alias_value":"RP7UX5NF4B45","created_at":"2026-05-18T12:26:41Z"},{"alias_kind":"pith_short_16","alias_value":"RP7UX5NF4B45NBDY","created_at":"2026-05-18T12:26:41Z"},{"alias_kind":"pith_short_8","alias_value":"RP7UX5NF","created_at":"2026-05-18T12:26:41Z"}],"graph_snapshots":[{"event_id":"sha256:3051ddd0639672176046700b825310004e44f9e2a2f3e4b305d14f7e1d2189a9","target":"graph","created_at":"2026-05-18T02:28:29Z","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"},"paper":{"abstract_excerpt":"In this paper we consider the problem of learning the optimal policy for uncontrolled restless bandit problems. In an uncontrolled restless bandit problem, there is a finite set of arms, each of which when pulled yields a positive reward. There is a player who sequentially selects one of the arms at each time step. The goal of the player is to maximize its undiscounted reward over a time horizon T. The reward process of each arm is a finite state Markov chain, whose transition probabilities are unknown by the player. State transitions of each arm is independent of the selection of the player. ","authors_text":"Cem Tekin, Mingyan Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-07-20T17:33:43Z","title":"Optimal Adaptive Learning in Uncontrolled Restless Bandit Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1107.4042","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":"sha256:85fc98020fc429f8ff0dd31c3850cf7a8867a276c989879aaaabb87378aa5dfe","target":"record","created_at":"2026-05-18T02:28:29Z","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":"55004e825f47bd8a2cd236b715081e2a50e2d8c806a128158dcee006013f528c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-07-20T17:33:43Z","title_canon_sha256":"a640af14f87f1612b4ccf2c28f9123d51e983435562b73a084d886c4f751e601"},"schema_version":"1.0","source":{"id":"1107.4042","kind":"arxiv","version":3}},"canonical_sha256":"8bff4bf5a5e079d6847801625b92aae8dfc5c3b97c1c16f45163c912bee0a622","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bff4bf5a5e079d6847801625b92aae8dfc5c3b97c1c16f45163c912bee0a622","first_computed_at":"2026-05-18T02:28:29.616118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:28:29.616118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CXXZzOEhfGiGo7F4cLWvamaKW6GBDJiEjdi1utXQYD5fx7yUyzB2uJYuJTGIb3M5eX38SlzZwxPmmRd6EJP4CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:28:29.616582Z","signed_message":"canonical_sha256_bytes"},"source_id":"1107.4042","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85fc98020fc429f8ff0dd31c3850cf7a8867a276c989879aaaabb87378aa5dfe","sha256:3051ddd0639672176046700b825310004e44f9e2a2f3e4b305d14f7e1d2189a9"],"state_sha256":"ede3bf53ce7c8dc1ab2cd196c376fe1f6b59204e0f45b5cda52c129b329d642e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+CoTDWAQDZN/UdX9gZimwMXT8UDGa3ZVSLjsUspQpfvkaoS8l5HEcbLsaGUbNnsC1j6QyFoNqgs/6k7eX4/TCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:23:18.222883Z","bundle_sha256":"0f40681ad8ed05132b2717bf79496b1be4a2569694fbefaef4a9db476f833c58"}}