{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IDOFISOOWXWA5MHMCCPJWCR33D","short_pith_number":"pith:IDOFISOO","canonical_record":{"source":{"id":"2201.10542","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-01-25T18:52:28Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"4fa33c3484f5bf539ffc389806454939f25954b4bb955d7f8fee10a631d9100f","abstract_canon_sha256":"4b6fa86bf06c2144cb2e7258be6a06d29f8147b588650b99b896db7455e213c3"},"schema_version":"1.0"},"canonical_sha256":"40dc5449ceb5ec0eb0ec109e9b0a3bd8e0f6f60a27c2d3638801ec4170e5fbd1","source":{"kind":"arxiv","id":"2201.10542","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10542","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10542v2","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10542","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"pith_short_12","alias_value":"IDOFISOOWXWA","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"pith_short_16","alias_value":"IDOFISOOWXWA5MHM","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"pith_short_8","alias_value":"IDOFISOO","created_at":"2026-07-05T05:54:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IDOFISOOWXWA5MHMCCPJWCR33D","target":"record","payload":{"canonical_record":{"source":{"id":"2201.10542","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-01-25T18:52:28Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"4fa33c3484f5bf539ffc389806454939f25954b4bb955d7f8fee10a631d9100f","abstract_canon_sha256":"4b6fa86bf06c2144cb2e7258be6a06d29f8147b588650b99b896db7455e213c3"},"schema_version":"1.0"},"canonical_sha256":"40dc5449ceb5ec0eb0ec109e9b0a3bd8e0f6f60a27c2d3638801ec4170e5fbd1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:11.290767Z","signature_b64":"ZOkBDi6bAtHOhM2vH7/N5nJ8FKfJx4L194j7u2MjraOccblzK4pshvp5Rqxey19o2tHlPJvjvAThWlm7U98bDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40dc5449ceb5ec0eb0ec109e9b0a3bd8e0f6f60a27c2d3638801ec4170e5fbd1","last_reissued_at":"2026-07-05T05:54:11.289866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:11.289866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.10542","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:54:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/sqfbWJuVv7GigqiZBzjrPYy4mBXCsc14TJZQSuz2FLmpmRCHSPg9Wn48zJ/snfNWViyTdmUdSWL1+GePEZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:52:55.450791Z"},"content_sha256":"e92421f95e3609643b9e5bf6d67a4db017b4e845537e418cccaccdf84d62f492","schema_version":"1.0","event_id":"sha256:e92421f95e3609643b9e5bf6d67a4db017b4e845537e418cccaccdf84d62f492"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IDOFISOOWXWA5MHMCCPJWCR33D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Akshay Mete, P. R. Kumar, Rahul Singh","submitted_at":"2022-01-25T18:52:28Z","abstract_excerpt":"We consider the problem of controlling an unknown stochastic linear system with quadratic costs - called the adaptive LQ control problem. We re-examine an approach called ''Reward Biased Maximum Likelihood Estimate'' (RBMLE) that was proposed more than forty years ago, and which predates the ''Upper Confidence Bound'' (UCB) method as well as the definition of ''regret'' for bandit problems. It simply added a term favoring parameters with larger rewards to the criterion for parameter estimation. We show how the RBMLE and UCB methods can be reconciled, and thereby propose an Augmented RBMLE-UCB "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10542","kind":"arxiv","version":2},"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/2201.10542/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":"2026-07-05T05:54:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2f9khyZTnaUDYPI6jvPXFkybXRArCxX9JUEeIL2E1cupo/zRg8r5SnKM7BTuQALgoEKjIwm28q0RRkVRLtu0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:52:55.451164Z"},"content_sha256":"ea3d43311dd765d6f08ec64cc24866ac4e29b52b138c7c646ccda6f422d8c279","schema_version":"1.0","event_id":"sha256:ea3d43311dd765d6f08ec64cc24866ac4e29b52b138c7c646ccda6f422d8c279"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDOFISOOWXWA5MHMCCPJWCR33D/bundle.json","state_url":"https://pith.science/pith/IDOFISOOWXWA5MHMCCPJWCR33D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDOFISOOWXWA5MHMCCPJWCR33D/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":"2026-07-06T16:52:55Z","links":{"resolver":"https://pith.science/pith/IDOFISOOWXWA5MHMCCPJWCR33D","bundle":"https://pith.science/pith/IDOFISOOWXWA5MHMCCPJWCR33D/bundle.json","state":"https://pith.science/pith/IDOFISOOWXWA5MHMCCPJWCR33D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDOFISOOWXWA5MHMCCPJWCR33D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IDOFISOOWXWA5MHMCCPJWCR33D","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":"4b6fa86bf06c2144cb2e7258be6a06d29f8147b588650b99b896db7455e213c3","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-01-25T18:52:28Z","title_canon_sha256":"4fa33c3484f5bf539ffc389806454939f25954b4bb955d7f8fee10a631d9100f"},"schema_version":"1.0","source":{"id":"2201.10542","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10542","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10542v2","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10542","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"pith_short_12","alias_value":"IDOFISOOWXWA","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"pith_short_16","alias_value":"IDOFISOOWXWA5MHM","created_at":"2026-07-05T05:54:11Z"},{"alias_kind":"pith_short_8","alias_value":"IDOFISOO","created_at":"2026-07-05T05:54:11Z"}],"graph_snapshots":[{"event_id":"sha256:ea3d43311dd765d6f08ec64cc24866ac4e29b52b138c7c646ccda6f422d8c279","target":"graph","created_at":"2026-07-05T05:54:11Z","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/2201.10542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of controlling an unknown stochastic linear system with quadratic costs - called the adaptive LQ control problem. We re-examine an approach called ''Reward Biased Maximum Likelihood Estimate'' (RBMLE) that was proposed more than forty years ago, and which predates the ''Upper Confidence Bound'' (UCB) method as well as the definition of ''regret'' for bandit problems. It simply added a term favoring parameters with larger rewards to the criterion for parameter estimation. We show how the RBMLE and UCB methods can be reconciled, and thereby propose an Augmented RBMLE-UCB ","authors_text":"Akshay Mete, P. R. Kumar, Rahul Singh","cross_cats":["cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-01-25T18:52:28Z","title":"Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10542","kind":"arxiv","version":2},"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:e92421f95e3609643b9e5bf6d67a4db017b4e845537e418cccaccdf84d62f492","target":"record","created_at":"2026-07-05T05:54:11Z","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":"4b6fa86bf06c2144cb2e7258be6a06d29f8147b588650b99b896db7455e213c3","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-01-25T18:52:28Z","title_canon_sha256":"4fa33c3484f5bf539ffc389806454939f25954b4bb955d7f8fee10a631d9100f"},"schema_version":"1.0","source":{"id":"2201.10542","kind":"arxiv","version":2}},"canonical_sha256":"40dc5449ceb5ec0eb0ec109e9b0a3bd8e0f6f60a27c2d3638801ec4170e5fbd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40dc5449ceb5ec0eb0ec109e9b0a3bd8e0f6f60a27c2d3638801ec4170e5fbd1","first_computed_at":"2026-07-05T05:54:11.289866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:11.289866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZOkBDi6bAtHOhM2vH7/N5nJ8FKfJx4L194j7u2MjraOccblzK4pshvp5Rqxey19o2tHlPJvjvAThWlm7U98bDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:11.290767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.10542","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e92421f95e3609643b9e5bf6d67a4db017b4e845537e418cccaccdf84d62f492","sha256:ea3d43311dd765d6f08ec64cc24866ac4e29b52b138c7c646ccda6f422d8c279"],"state_sha256":"d84e894f2e7edddee482e6605d9cadc029f4e4f970413406f1fdb77b74ba1aed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oB5Yb174NXjKcaPIeNNrJ2BvQxGgLuJXM1KlhQvNeIxA9taaUWTxKSANU1RkXhGPAhzAxVSD7cFkg2rrZiqkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:52:55.453159Z","bundle_sha256":"547d866991ae30446bb15b636defaffe511f6fa80b9746adf4c53d81a43173a1"}}