{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JXL4H4BW6PHSIROKSGWUO2333W","short_pith_number":"pith:JXL4H4BW","canonical_record":{"source":{"id":"2605.10493","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-11T12:51:13Z","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"6d72184e0ab33cde3ca6d29048eb457709801f43b14419d2ef63f3fabcca642d","abstract_canon_sha256":"deaf1ca73ddb14fba7ec8c4a1c5333ec960dac5fedcd8cb46cb2f4bce9d74935"},"schema_version":"1.0"},"canonical_sha256":"4dd7c3f036f3cf2445ca91ad476b7bddae2eb9923a71f4bdcc8c73f5488e23d6","source":{"kind":"arxiv","id":"2605.10493","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10493","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10493v2","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10493","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"JXL4H4BW6PHS","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"JXL4H4BW6PHSIROK","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"JXL4H4BW","created_at":"2026-05-22T01:03:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JXL4H4BW6PHSIROKSGWUO2333W","target":"record","payload":{"canonical_record":{"source":{"id":"2605.10493","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-11T12:51:13Z","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"6d72184e0ab33cde3ca6d29048eb457709801f43b14419d2ef63f3fabcca642d","abstract_canon_sha256":"deaf1ca73ddb14fba7ec8c4a1c5333ec960dac5fedcd8cb46cb2f4bce9d74935"},"schema_version":"1.0"},"canonical_sha256":"4dd7c3f036f3cf2445ca91ad476b7bddae2eb9923a71f4bdcc8c73f5488e23d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:20.128534Z","signature_b64":"EV8cxE3HMFUmUrOK4ubdvFjJqDA8hr9neUA4pyGZcKfdyJPOhVBT7sE0dt8Me6w8w9bJQ6WNSU7K+jUB0KmpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dd7c3f036f3cf2445ca91ad476b7bddae2eb9923a71f4bdcc8c73f5488e23d6","last_reissued_at":"2026-05-22T01:03:20.127932Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:20.127932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.10493","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":"2026-05-22T01:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTzHTYe+449555JrP2T0LDPCUiyWYGcKY+i8V8v8tipTwUlvh+HmpVqTWGCIonThIT8moX0h9q9zsQMZFvtFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:28:04.811582Z"},"content_sha256":"2825a8da6a6541ef9d311de0a8af5b81db1c7670310399ea7caee6682d667ea4","schema_version":"1.0","event_id":"sha256:2825a8da6a6541ef9d311de0a8af5b81db1c7670310399ea7caee6682d667ea4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JXL4H4BW6PHSIROKSGWUO2333W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A PAC-Bayes bound gives high-probability performance guarantees for any stochastic controller learned on unknown linear discrete-time systems.","cross_cats":["cs.SY","eess.SY","stat.ML"],"primary_cat":"math.OC","authors_text":"Jingge Zhu, Jonathan H. Manton, Ye Pu, Yujia Luo","submitted_at":"2026-05-11T12:51:13Z","abstract_excerpt":"This paper presents a PAC-Bayes framework for learning controllers for unknown stochastic linear discrete-time systems, where the system parameters are drawn from a fixed but unknown distribution. We derive a data-dependent high probability bound on the performance of any learned (stochastic) controller, and propose novel efficient learning algorithms with theoretical guarantees, which can be implemented for both finite and infinite controller spaces. Compared to prior work, our bound holds for unbounded quadratic cost. In the special case where LQG is optimal, our numerical results suggest th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We derive a data-dependent high probability bound on the performance of any learned (stochastic) controller, and propose novel efficient learning algorithms with theoretical guarantees, which can be implemented for both finite and infinite controller spaces. Compared to prior work, our bound holds for unbounded quadratic cost.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The system parameters are drawn from a fixed but unknown distribution, and the controller is allowed to be stochastic; if the true parameter distribution changes over time or if only deterministic controllers are permitted, the derived bound and algorithms no longer apply.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A PAC-Bayes method supplies high-probability bounds on the cost of any learned stochastic controller for unknown linear systems and gives efficient algorithms that work for both finite and infinite controller sets, including unbounded quadratic costs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A PAC-Bayes bound gives high-probability performance guarantees for any stochastic controller learned on unknown linear discrete-time systems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"16ea9f4d105085a90550c920e3bfcebba35c94a04d3fd177f9ce0e3811d6cf55"},"source":{"id":"2605.10493","kind":"arxiv","version":2},"verdict":{"id":"ba1259fb-8e4a-46c5-ace7-0c18f6dd6d0d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T05:12:43.369358Z","strongest_claim":"We derive a data-dependent high probability bound on the performance of any learned (stochastic) controller, and propose novel efficient learning algorithms with theoretical guarantees, which can be implemented for both finite and infinite controller spaces. Compared to prior work, our bound holds for unbounded quadratic cost.","one_line_summary":"A PAC-Bayes method supplies high-probability bounds on the cost of any learned stochastic controller for unknown linear systems and gives efficient algorithms that work for both finite and infinite controller sets, including unbounded quadratic costs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The system parameters are drawn from a fixed but unknown distribution, and the controller is allowed to be stochastic; if the true parameter distribution changes over time or if only deterministic controllers are permitted, the derived bound and algorithms no longer apply.","pith_extraction_headline":"A PAC-Bayes bound gives high-probability performance guarantees for any stochastic controller learned on unknown linear discrete-time systems."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10493/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:42:01.067724Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:42:45.848973Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:01:18.001371Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:14:33.410430Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9603f8bc5498b0c348ae917efb789cfffd16a81b5122b9b10da780e7fad40c8c"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9fcf7102bac323cb8d78742d6ff4d9462028d0f9b53c5112dbd793ce1ecb80d8"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ba1259fb-8e4a-46c5-ace7-0c18f6dd6d0d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdntWUCTsd85w0D0Y8Qmk+GMNCMPjKHoGrUhw3WwCgdPnVQO/PSei95H/WxAL4TnPsC+Pp/GrpT1dwJFGNGeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:28:04.812401Z"},"content_sha256":"96684d02a206f0c21fd71459b202aaa3bbe11a3fb3a635ddfce1c2a5de823c5d","schema_version":"1.0","event_id":"sha256:96684d02a206f0c21fd71459b202aaa3bbe11a3fb3a635ddfce1c2a5de823c5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JXL4H4BW6PHSIROKSGWUO2333W/bundle.json","state_url":"https://pith.science/pith/JXL4H4BW6PHSIROKSGWUO2333W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JXL4H4BW6PHSIROKSGWUO2333W/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":"2026-05-25T22:28:04Z","links":{"resolver":"https://pith.science/pith/JXL4H4BW6PHSIROKSGWUO2333W","bundle":"https://pith.science/pith/JXL4H4BW6PHSIROKSGWUO2333W/bundle.json","state":"https://pith.science/pith/JXL4H4BW6PHSIROKSGWUO2333W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JXL4H4BW6PHSIROKSGWUO2333W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JXL4H4BW6PHSIROKSGWUO2333W","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":"deaf1ca73ddb14fba7ec8c4a1c5333ec960dac5fedcd8cb46cb2f4bce9d74935","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-11T12:51:13Z","title_canon_sha256":"6d72184e0ab33cde3ca6d29048eb457709801f43b14419d2ef63f3fabcca642d"},"schema_version":"1.0","source":{"id":"2605.10493","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10493","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10493v2","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10493","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"JXL4H4BW6PHS","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"pith_short_16","alias_value":"JXL4H4BW6PHSIROK","created_at":"2026-05-22T01:03:20Z"},{"alias_kind":"pith_short_8","alias_value":"JXL4H4BW","created_at":"2026-05-22T01:03:20Z"}],"graph_snapshots":[{"event_id":"sha256:96684d02a206f0c21fd71459b202aaa3bbe11a3fb3a635ddfce1c2a5de823c5d","target":"graph","created_at":"2026-05-22T01:03:20Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We derive a data-dependent high probability bound on the performance of any learned (stochastic) controller, and propose novel efficient learning algorithms with theoretical guarantees, which can be implemented for both finite and infinite controller spaces. Compared to prior work, our bound holds for unbounded quadratic cost."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The system parameters are drawn from a fixed but unknown distribution, and the controller is allowed to be stochastic; if the true parameter distribution changes over time or if only deterministic controllers are permitted, the derived bound and algorithms no longer apply."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A PAC-Bayes method supplies high-probability bounds on the cost of any learned stochastic controller for unknown linear systems and gives efficient algorithms that work for both finite and infinite controller sets, including unbounded quadratic costs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A PAC-Bayes bound gives high-probability performance guarantees for any stochastic controller learned on unknown linear discrete-time systems."}],"snapshot_sha256":"16ea9f4d105085a90550c920e3bfcebba35c94a04d3fd177f9ce0e3811d6cf55"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9fcf7102bac323cb8d78742d6ff4d9462028d0f9b53c5112dbd793ce1ecb80d8"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T05:42:01.067724Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T14:42:45.848973Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T11:01:18.001371Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:14:33.410430Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10493/integrity.json","findings":[],"snapshot_sha256":"9603f8bc5498b0c348ae917efb789cfffd16a81b5122b9b10da780e7fad40c8c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a PAC-Bayes framework for learning controllers for unknown stochastic linear discrete-time systems, where the system parameters are drawn from a fixed but unknown distribution. We derive a data-dependent high probability bound on the performance of any learned (stochastic) controller, and propose novel efficient learning algorithms with theoretical guarantees, which can be implemented for both finite and infinite controller spaces. Compared to prior work, our bound holds for unbounded quadratic cost. In the special case where LQG is optimal, our numerical results suggest th","authors_text":"Jingge Zhu, Jonathan H. Manton, Ye Pu, Yujia Luo","cross_cats":["cs.SY","eess.SY","stat.ML"],"headline":"A PAC-Bayes bound gives high-probability performance guarantees for any stochastic controller learned on unknown linear discrete-time systems.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-11T12:51:13Z","title":"A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10493","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T05:12:43.369358Z","id":"ba1259fb-8e4a-46c5-ace7-0c18f6dd6d0d","model_set":{"reader":"grok-4.3"},"one_line_summary":"A PAC-Bayes method supplies high-probability bounds on the cost of any learned stochastic controller for unknown linear systems and gives efficient algorithms that work for both finite and infinite controller sets, including unbounded quadratic costs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A PAC-Bayes bound gives high-probability performance guarantees for any stochastic controller learned on unknown linear discrete-time systems.","strongest_claim":"We derive a data-dependent high probability bound on the performance of any learned (stochastic) controller, and propose novel efficient learning algorithms with theoretical guarantees, which can be implemented for both finite and infinite controller spaces. Compared to prior work, our bound holds for unbounded quadratic cost.","weakest_assumption":"The system parameters are drawn from a fixed but unknown distribution, and the controller is allowed to be stochastic; if the true parameter distribution changes over time or if only deterministic controllers are permitted, the derived bound and algorithms no longer apply."}},"verdict_id":"ba1259fb-8e4a-46c5-ace7-0c18f6dd6d0d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2825a8da6a6541ef9d311de0a8af5b81db1c7670310399ea7caee6682d667ea4","target":"record","created_at":"2026-05-22T01:03:20Z","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":"deaf1ca73ddb14fba7ec8c4a1c5333ec960dac5fedcd8cb46cb2f4bce9d74935","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-11T12:51:13Z","title_canon_sha256":"6d72184e0ab33cde3ca6d29048eb457709801f43b14419d2ef63f3fabcca642d"},"schema_version":"1.0","source":{"id":"2605.10493","kind":"arxiv","version":2}},"canonical_sha256":"4dd7c3f036f3cf2445ca91ad476b7bddae2eb9923a71f4bdcc8c73f5488e23d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dd7c3f036f3cf2445ca91ad476b7bddae2eb9923a71f4bdcc8c73f5488e23d6","first_computed_at":"2026-05-22T01:03:20.127932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:20.127932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EV8cxE3HMFUmUrOK4ubdvFjJqDA8hr9neUA4pyGZcKfdyJPOhVBT7sE0dt8Me6w8w9bJQ6WNSU7K+jUB0KmpAg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:20.128534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10493","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2825a8da6a6541ef9d311de0a8af5b81db1c7670310399ea7caee6682d667ea4","sha256:96684d02a206f0c21fd71459b202aaa3bbe11a3fb3a635ddfce1c2a5de823c5d"],"state_sha256":"3e10d81fc2a39d3c77a5c6d446228a5507f04498e370dcff20a6810968052157"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6fKoMT8Gc9Se6taVMk/5Hntwmn/h8YEZ45CWDhY/58AZS7EDPca2BfJ8MIFG991aZ9AxilD0TaUL/j73J+s5DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:28:04.816142Z","bundle_sha256":"4d72f99cae21083d6993ada0d016b8ce9139bf5fb7bf5d8ead023c17eae30e73"}}