{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CN5CHXFYUMY6VHJQYAJE6YVBCH","short_pith_number":"pith:CN5CHXFY","canonical_record":{"source":{"id":"2506.02613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-03T08:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"197ed9697e641c9cd0c27b13b943c23b6d4d2a0e83c1f1678852c6b500824718","abstract_canon_sha256":"5b2553487124c058ecb781eaef1f189d943bdb0e1f8196d9346cf84047924534"},"schema_version":"1.0"},"canonical_sha256":"137a23dcb8a331ea9d30c0124f62a111d50db73dc61b0e674af608ed8351ba91","source":{"kind":"arxiv","id":"2506.02613","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02613","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02613v1","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02613","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"CN5CHXFYUMY6","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"CN5CHXFYUMY6VHJQ","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"CN5CHXFY","created_at":"2026-07-05T11:15:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CN5CHXFYUMY6VHJQYAJE6YVBCH","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-03T08:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"197ed9697e641c9cd0c27b13b943c23b6d4d2a0e83c1f1678852c6b500824718","abstract_canon_sha256":"5b2553487124c058ecb781eaef1f189d943bdb0e1f8196d9346cf84047924534"},"schema_version":"1.0"},"canonical_sha256":"137a23dcb8a331ea9d30c0124f62a111d50db73dc61b0e674af608ed8351ba91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:05.372124Z","signature_b64":"4LmzHTK8U2ikIhpCdR01cX02NzOBimcam8i6m1i0MqCFTWrq5mZfx5tWcOeFlWSSE3PkBhUDJYux/CFj/a7jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"137a23dcb8a331ea9d30c0124f62a111d50db73dc61b0e674af608ed8351ba91","last_reissued_at":"2026-07-05T11:15:05.371684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:05.371684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02613","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":"2026-07-05T11:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RZbtD6ud1vrp2sblTeoZnc8K52T/QbOaaQrY4MSEcXi2zr2HOKOTbxeG/VNtuu4dovMiURSqrRZRtKQq+GJJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:49:48.821446Z"},"content_sha256":"73ea2e183e02588c8410e08ca37d962fb74365472754b61855305dd2330ed90a","schema_version":"1.0","event_id":"sha256:73ea2e183e02588c8410e08ca37d962fb74365472754b61855305dd2330ed90a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CN5CHXFYUMY6VHJQYAJE6YVBCH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning-based primal-dual optimal control of discrete-time stochastic systems with multiplicative noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Weihai Zhang, Xiushan Jiang","submitted_at":"2025-06-03T08:30:13Z","abstract_excerpt":"Reinforcement learning (RL) is an effective approach for solving optimal control problems without knowing the exact information of the system model. However, the classical Q-learning method, a model-free RL algorithm, has its limitations, such as lack of strict theoretical analysis and the need for artificial disturbances during implementation. This paper explores the partially model-free stochastic linear quadratic regulator (SLQR) problem for a system with multiplicative noise from the primal-dual perspective to address these challenges. This approach lays a strong theoretical foundation for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02613","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/2506.02613/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":"2026-07-05T11:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZrxohCge6FGjW6YAeFcNbadi5neJrMHzA2geIMOqN/VuJu7kzh0kEzo7dezqIJsU2h6O39OWFz2PxwXkjjVpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:49:48.822513Z"},"content_sha256":"e5528210c5bd483fdabf2c89913da075d4870ffc7db8e4c1e50579ed1f1172ba","schema_version":"1.0","event_id":"sha256:e5528210c5bd483fdabf2c89913da075d4870ffc7db8e4c1e50579ed1f1172ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CN5CHXFYUMY6VHJQYAJE6YVBCH/bundle.json","state_url":"https://pith.science/pith/CN5CHXFYUMY6VHJQYAJE6YVBCH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CN5CHXFYUMY6VHJQYAJE6YVBCH/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":"2026-08-18T15:49:48Z","links":{"resolver":"https://pith.science/pith/CN5CHXFYUMY6VHJQYAJE6YVBCH","bundle":"https://pith.science/pith/CN5CHXFYUMY6VHJQYAJE6YVBCH/bundle.json","state":"https://pith.science/pith/CN5CHXFYUMY6VHJQYAJE6YVBCH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CN5CHXFYUMY6VHJQYAJE6YVBCH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CN5CHXFYUMY6VHJQYAJE6YVBCH","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":"5b2553487124c058ecb781eaef1f189d943bdb0e1f8196d9346cf84047924534","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-03T08:30:13Z","title_canon_sha256":"197ed9697e641c9cd0c27b13b943c23b6d4d2a0e83c1f1678852c6b500824718"},"schema_version":"1.0","source":{"id":"2506.02613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02613","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02613v1","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02613","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"CN5CHXFYUMY6","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"CN5CHXFYUMY6VHJQ","created_at":"2026-07-05T11:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"CN5CHXFY","created_at":"2026-07-05T11:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:e5528210c5bd483fdabf2c89913da075d4870ffc7db8e4c1e50579ed1f1172ba","target":"graph","created_at":"2026-07-05T11:15:05Z","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/2506.02613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is an effective approach for solving optimal control problems without knowing the exact information of the system model. However, the classical Q-learning method, a model-free RL algorithm, has its limitations, such as lack of strict theoretical analysis and the need for artificial disturbances during implementation. This paper explores the partially model-free stochastic linear quadratic regulator (SLQR) problem for a system with multiplicative noise from the primal-dual perspective to address these challenges. This approach lays a strong theoretical foundation for","authors_text":"Weihai Zhang, Xiushan Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-03T08:30:13Z","title":"Learning-based primal-dual optimal control of discrete-time stochastic systems with multiplicative noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02613","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":"sha256:73ea2e183e02588c8410e08ca37d962fb74365472754b61855305dd2330ed90a","target":"record","created_at":"2026-07-05T11:15:05Z","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":"5b2553487124c058ecb781eaef1f189d943bdb0e1f8196d9346cf84047924534","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-06-03T08:30:13Z","title_canon_sha256":"197ed9697e641c9cd0c27b13b943c23b6d4d2a0e83c1f1678852c6b500824718"},"schema_version":"1.0","source":{"id":"2506.02613","kind":"arxiv","version":1}},"canonical_sha256":"137a23dcb8a331ea9d30c0124f62a111d50db73dc61b0e674af608ed8351ba91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"137a23dcb8a331ea9d30c0124f62a111d50db73dc61b0e674af608ed8351ba91","first_computed_at":"2026-07-05T11:15:05.371684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:05.371684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4LmzHTK8U2ikIhpCdR01cX02NzOBimcam8i6m1i0MqCFTWrq5mZfx5tWcOeFlWSSE3PkBhUDJYux/CFj/a7jBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:05.372124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73ea2e183e02588c8410e08ca37d962fb74365472754b61855305dd2330ed90a","sha256:e5528210c5bd483fdabf2c89913da075d4870ffc7db8e4c1e50579ed1f1172ba"],"state_sha256":"228a3cbff0fe9425debdb50a4664843e1cc47c97f46b3709ddcc84a071ec8a7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eCIa2/WtcsfSx4Cydv2zduGbzLVzySHQz6oKDcfygr9/Y0OhYMnsfGUKWWRsKwHv+gNw2CNTo17tItEalx2wAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:49:48.828872Z","bundle_sha256":"c2559a3c70f9aa333c8e58df431c37ce4fa6f5d11231871a10cda3e7d837023a"}}