{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LONXKJEQB2GHXRM3MS37LX5W64","short_pith_number":"pith:LONXKJEQ","canonical_record":{"source":{"id":"2406.04766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T09:09:14Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e59ff73da5557ccd84b1d4a55e946861387dde33d588d0b1341cbc9669507f81","abstract_canon_sha256":"56588b191cd66cdc9708dcd5c1284ceb4df64dfd08b6615bdb29ca7545c3f6a7"},"schema_version":"1.0"},"canonical_sha256":"5b9b7524900e8c7bc59b64b7f5dfb6f73c533fbbaae59e85a2648009581a3e7b","source":{"kind":"arxiv","id":"2406.04766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04766","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04766v1","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04766","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"LONXKJEQB2GH","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"LONXKJEQB2GHXRM3","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"LONXKJEQ","created_at":"2026-07-05T08:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LONXKJEQB2GHXRM3MS37LX5W64","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T09:09:14Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e59ff73da5557ccd84b1d4a55e946861387dde33d588d0b1341cbc9669507f81","abstract_canon_sha256":"56588b191cd66cdc9708dcd5c1284ceb4df64dfd08b6615bdb29ca7545c3f6a7"},"schema_version":"1.0"},"canonical_sha256":"5b9b7524900e8c7bc59b64b7f5dfb6f73c533fbbaae59e85a2648009581a3e7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:49.158945Z","signature_b64":"1c9TlVpSAyoC9uTrSknAXoeYq82bOxNKxYbgOpYMxWhilccpbArPXaBWtDdDzNPTO3XlVwB+Mx2mPg3BAMPYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b9b7524900e8c7bc59b64b7f5dfb6f73c533fbbaae59e85a2648009581a3e7b","last_reissued_at":"2026-07-05T08:28:49.158556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:49.158556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04766","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":"2026-07-05T08:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gW6HFDqNNUlz0CDbgOVEMkyMiLJ7txMs1thKoq2ijVgpiiL2nBfL9aNikwrw8WZGlHWWVMGcfjT28+Ms7wMyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:53:11.925467Z"},"content_sha256":"0715d5adca2f0e3b2ba7168d50cc9d71ef83235f9b780251c526a6e776ec98bc","schema_version":"1.0","event_id":"sha256:0715d5adca2f0e3b2ba7168d50cc9d71ef83235f9b780251c526a6e776ec98bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LONXKJEQB2GHXRM3MS37LX5W64","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning and Regret Bounds for Admission Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ana Bu\\v{s}i\\'c, Jiamin Zhu, Lucas Weber","submitted_at":"2024-06-07T09:09:14Z","abstract_excerpt":"The expected regret of any reinforcement learning algorithm is lower bounded by $\\Omega\\left(\\sqrt{DXAT}\\right)$ for undiscounted returns, where $D$ is the diameter of the Markov decision process, $X$ the size of the state space, $A$ the size of the action space and $T$ the number of time steps. However, this lower bound is general. A smaller regret can be obtained by taking into account some specific knowledge of the problem structure. In this article, we consider an admission control problem to an $M/M/c/S$ queue with $m$ job classes and class-dependent rewards and holding costs. Queuing sys"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04766","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/2406.04766/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":"2026-07-05T08:28:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PS9kYpRW9d6+y9zsdKfdwBpKaJKQXKFSqdtTtECTuI4F5nqMLlVibeX3ozyhmhVxYn7yLA5Ys7PBUVGorkGqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:53:11.925834Z"},"content_sha256":"bebdd66ebbf69da6758dbf6ea8893c8292e1ad52847752082aa1d6426159d49a","schema_version":"1.0","event_id":"sha256:bebdd66ebbf69da6758dbf6ea8893c8292e1ad52847752082aa1d6426159d49a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/bundle.json","state_url":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LONXKJEQB2GHXRM3MS37LX5W64/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":"2026-07-07T03:53:11Z","links":{"resolver":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64","bundle":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/bundle.json","state":"https://pith.science/pith/LONXKJEQB2GHXRM3MS37LX5W64/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LONXKJEQB2GHXRM3MS37LX5W64/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LONXKJEQB2GHXRM3MS37LX5W64","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":"56588b191cd66cdc9708dcd5c1284ceb4df64dfd08b6615bdb29ca7545c3f6a7","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T09:09:14Z","title_canon_sha256":"e59ff73da5557ccd84b1d4a55e946861387dde33d588d0b1341cbc9669507f81"},"schema_version":"1.0","source":{"id":"2406.04766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04766","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04766v1","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04766","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_12","alias_value":"LONXKJEQB2GH","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"LONXKJEQB2GHXRM3","created_at":"2026-07-05T08:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"LONXKJEQ","created_at":"2026-07-05T08:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:bebdd66ebbf69da6758dbf6ea8893c8292e1ad52847752082aa1d6426159d49a","target":"graph","created_at":"2026-07-05T08:28:49Z","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/2406.04766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The expected regret of any reinforcement learning algorithm is lower bounded by $\\Omega\\left(\\sqrt{DXAT}\\right)$ for undiscounted returns, where $D$ is the diameter of the Markov decision process, $X$ the size of the state space, $A$ the size of the action space and $T$ the number of time steps. However, this lower bound is general. A smaller regret can be obtained by taking into account some specific knowledge of the problem structure. In this article, we consider an admission control problem to an $M/M/c/S$ queue with $m$ job classes and class-dependent rewards and holding costs. Queuing sys","authors_text":"Ana Bu\\v{s}i\\'c, Jiamin Zhu, Lucas Weber","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T09:09:14Z","title":"Reinforcement Learning and Regret Bounds for Admission Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04766","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":"sha256:0715d5adca2f0e3b2ba7168d50cc9d71ef83235f9b780251c526a6e776ec98bc","target":"record","created_at":"2026-07-05T08:28:49Z","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":"56588b191cd66cdc9708dcd5c1284ceb4df64dfd08b6615bdb29ca7545c3f6a7","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T09:09:14Z","title_canon_sha256":"e59ff73da5557ccd84b1d4a55e946861387dde33d588d0b1341cbc9669507f81"},"schema_version":"1.0","source":{"id":"2406.04766","kind":"arxiv","version":1}},"canonical_sha256":"5b9b7524900e8c7bc59b64b7f5dfb6f73c533fbbaae59e85a2648009581a3e7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b9b7524900e8c7bc59b64b7f5dfb6f73c533fbbaae59e85a2648009581a3e7b","first_computed_at":"2026-07-05T08:28:49.158556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:49.158556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1c9TlVpSAyoC9uTrSknAXoeYq82bOxNKxYbgOpYMxWhilccpbArPXaBWtDdDzNPTO3XlVwB+Mx2mPg3BAMPYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:49.158945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0715d5adca2f0e3b2ba7168d50cc9d71ef83235f9b780251c526a6e776ec98bc","sha256:bebdd66ebbf69da6758dbf6ea8893c8292e1ad52847752082aa1d6426159d49a"],"state_sha256":"d39b93a6a17738a4772a9753058bfa5a8df942f118336343c125f31f858f1994"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"On4uXQb6AqNedG42RRTyzJhIOlZdLL925p97kpOIxoguhdAu1BCz1FMhv6wkkF83KhRqSi/DfAgbAqKWG0HmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:53:11.927868Z","bundle_sha256":"5e77c4880712a66459228ea6f7d2c868a178d40e3a8834032b66bb9cd560bdd6"}}