{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TQMRDSKZ5X2X3NS3QELMGC2W6C","short_pith_number":"pith:TQMRDSKZ","canonical_record":{"source":{"id":"2306.09210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:47:50Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"546e5b9acfc4e3dddb09034f790636453e62b6770e1a3667f0c35ca393749469","abstract_canon_sha256":"92b62b371f6a928bffd5cd1bbd04dac302bf4bc2ae83da7ff6faec1a9a3e2239"},"schema_version":"1.0"},"canonical_sha256":"9c1911c959edf57db65b8116c30b56f088e2dca4e2e0d129e5f57babe2a15a1d","source":{"kind":"arxiv","id":"2306.09210","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09210","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09210v1","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09210","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"TQMRDSKZ5X2X","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"pith_short_16","alias_value":"TQMRDSKZ5X2X3NS3","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"pith_short_8","alias_value":"TQMRDSKZ","created_at":"2026-07-05T06:21:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TQMRDSKZ5X2X3NS3QELMGC2W6C","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:47:50Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"546e5b9acfc4e3dddb09034f790636453e62b6770e1a3667f0c35ca393749469","abstract_canon_sha256":"92b62b371f6a928bffd5cd1bbd04dac302bf4bc2ae83da7ff6faec1a9a3e2239"},"schema_version":"1.0"},"canonical_sha256":"9c1911c959edf57db65b8116c30b56f088e2dca4e2e0d129e5f57babe2a15a1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:09.765011Z","signature_b64":"V0qaQFB22LGIhYuBB8mKWXvAepK8Zv+kFpYi8FFYEKVf3yeoGUdw2aonPH7MK7vJ1cbUgZCGt5MJ3uY5SfyUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c1911c959edf57db65b8116c30b56f088e2dca4e2e0d129e5f57babe2a15a1d","last_reissued_at":"2026-07-05T06:21:09.764599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:09.764599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09210","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":"2026-07-05T06:21:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m911MewHsjOcVT/HspFUhSxbjAnU8/amVHIPNNu24L8v0+Rh7if8oBNfhex2vj+q7OB6lZin3w/KKBS3Qpa1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:16:37.704469Z"},"content_sha256":"05f3efcb76bf7d843d6af40617ec4e297482e118f942cccdc5b8bcf05c298a92","schema_version":"1.0","event_id":"sha256:05f3efcb76bf7d843d6af40617ec4e297482e118f942cccdc5b8bcf05c298a92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TQMRDSKZ5X2X3NS3QELMGC2W6C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Exploration for Model-Based RL in Nonlinear Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Wagenmaker, Guanya Shi, Kevin Jamieson","submitted_at":"2023-06-15T15:47:50Z","abstract_excerpt":"Learning to control unknown nonlinear dynamical systems is a fundamental problem in reinforcement learning and control theory. A commonly applied approach is to first explore the environment (exploration), learn an accurate model of it (system identification), and then compute an optimal controller with the minimum cost on this estimated system (policy optimization). While existing work has shown that it is possible to learn a uniformly good model of the system~\\citep{mania2020active}, in practice, if we aim to learn a good controller with a low cost on the actual system, certain system parame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09210","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/2306.09210/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":"2026-07-05T06:21:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIDSLcjldAAE9/L7DccZ4OhWHn/jKVw1xXZM4lk2HtmGz7iaPYYmb5mzgctz4bf40y/Ngusn/NUkWsnMxNCiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:16:37.704972Z"},"content_sha256":"afdd8c235ea8f24f871a76a9d2f093605be6b7c80a6bddecec547ac94ea766c1","schema_version":"1.0","event_id":"sha256:afdd8c235ea8f24f871a76a9d2f093605be6b7c80a6bddecec547ac94ea766c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQMRDSKZ5X2X3NS3QELMGC2W6C/bundle.json","state_url":"https://pith.science/pith/TQMRDSKZ5X2X3NS3QELMGC2W6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQMRDSKZ5X2X3NS3QELMGC2W6C/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":"2026-08-09T04:16:37Z","links":{"resolver":"https://pith.science/pith/TQMRDSKZ5X2X3NS3QELMGC2W6C","bundle":"https://pith.science/pith/TQMRDSKZ5X2X3NS3QELMGC2W6C/bundle.json","state":"https://pith.science/pith/TQMRDSKZ5X2X3NS3QELMGC2W6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQMRDSKZ5X2X3NS3QELMGC2W6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TQMRDSKZ5X2X3NS3QELMGC2W6C","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":"92b62b371f6a928bffd5cd1bbd04dac302bf4bc2ae83da7ff6faec1a9a3e2239","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:47:50Z","title_canon_sha256":"546e5b9acfc4e3dddb09034f790636453e62b6770e1a3667f0c35ca393749469"},"schema_version":"1.0","source":{"id":"2306.09210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09210","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09210v1","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09210","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"pith_short_12","alias_value":"TQMRDSKZ5X2X","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"pith_short_16","alias_value":"TQMRDSKZ5X2X3NS3","created_at":"2026-07-05T06:21:09Z"},{"alias_kind":"pith_short_8","alias_value":"TQMRDSKZ","created_at":"2026-07-05T06:21:09Z"}],"graph_snapshots":[{"event_id":"sha256:afdd8c235ea8f24f871a76a9d2f093605be6b7c80a6bddecec547ac94ea766c1","target":"graph","created_at":"2026-07-05T06:21:09Z","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/2306.09210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to control unknown nonlinear dynamical systems is a fundamental problem in reinforcement learning and control theory. A commonly applied approach is to first explore the environment (exploration), learn an accurate model of it (system identification), and then compute an optimal controller with the minimum cost on this estimated system (policy optimization). While existing work has shown that it is possible to learn a uniformly good model of the system~\\citep{mania2020active}, in practice, if we aim to learn a good controller with a low cost on the actual system, certain system parame","authors_text":"Andrew Wagenmaker, Guanya Shi, Kevin Jamieson","cross_cats":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:47:50Z","title":"Optimal Exploration for Model-Based RL in Nonlinear Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09210","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":"sha256:05f3efcb76bf7d843d6af40617ec4e297482e118f942cccdc5b8bcf05c298a92","target":"record","created_at":"2026-07-05T06:21:09Z","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":"92b62b371f6a928bffd5cd1bbd04dac302bf4bc2ae83da7ff6faec1a9a3e2239","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T15:47:50Z","title_canon_sha256":"546e5b9acfc4e3dddb09034f790636453e62b6770e1a3667f0c35ca393749469"},"schema_version":"1.0","source":{"id":"2306.09210","kind":"arxiv","version":1}},"canonical_sha256":"9c1911c959edf57db65b8116c30b56f088e2dca4e2e0d129e5f57babe2a15a1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c1911c959edf57db65b8116c30b56f088e2dca4e2e0d129e5f57babe2a15a1d","first_computed_at":"2026-07-05T06:21:09.764599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:09.764599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V0qaQFB22LGIhYuBB8mKWXvAepK8Zv+kFpYi8FFYEKVf3yeoGUdw2aonPH7MK7vJ1cbUgZCGt5MJ3uY5SfyUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:09.765011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f3efcb76bf7d843d6af40617ec4e297482e118f942cccdc5b8bcf05c298a92","sha256:afdd8c235ea8f24f871a76a9d2f093605be6b7c80a6bddecec547ac94ea766c1"],"state_sha256":"947b2dc54fdd459bf5d3d4ad5c9bd5f0d555cede58ab0cb04749dd7a80c600a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0TAuvSV4cehqVaPLDRBG1/W3ouutsFCihKslwvETg4Yy9+6+5MnKLksizcNorI/etR/3XFqSScnK8sobiM1BBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:16:37.708915Z","bundle_sha256":"9318639ed7c6450cf594e9d947d05661d32ed3a226e82d9d2a9a43b086ebe304"}}