{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:CBGFVY2UPKWL7OU5G56JUYU7H3","short_pith_number":"pith:CBGFVY2U","canonical_record":{"source":{"id":"1506.00685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-06-01T21:43:01Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"73b8b43e070adbd133066430015740333172b6f9342cd82f6d172eae43885066","abstract_canon_sha256":"cfc94fb762f5fbf9a94aa65cb886da9089d55e8a1f6422a577ba7c78df4771e1"},"schema_version":"1.0"},"canonical_sha256":"104c5ae3547aacbfba9d377c9a629f3ef7e3356f84043ff625d7b2cd5c418b22","source":{"kind":"arxiv","id":"1506.00685","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.00685","created_at":"2026-05-18T00:39:48Z"},{"alias_kind":"arxiv_version","alias_value":"1506.00685v1","created_at":"2026-05-18T00:39:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.00685","created_at":"2026-05-18T00:39:48Z"},{"alias_kind":"pith_short_12","alias_value":"CBGFVY2UPKWL","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"CBGFVY2UPKWL7OU5","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"CBGFVY2U","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:CBGFVY2UPKWL7OU5G56JUYU7H3","target":"record","payload":{"canonical_record":{"source":{"id":"1506.00685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-06-01T21:43:01Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"73b8b43e070adbd133066430015740333172b6f9342cd82f6d172eae43885066","abstract_canon_sha256":"cfc94fb762f5fbf9a94aa65cb886da9089d55e8a1f6422a577ba7c78df4771e1"},"schema_version":"1.0"},"canonical_sha256":"104c5ae3547aacbfba9d377c9a629f3ef7e3356f84043ff625d7b2cd5c418b22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:48.216851Z","signature_b64":"rIpHKDCQT/VtG8OK/Mr9R9pyn7ELj7HclfTe/zho/TiQOE7JEK9CfybhF1kqTlKNWNJW1JPAuwlfFv5l3DL8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"104c5ae3547aacbfba9d377c9a629f3ef7e3356f84043ff625d7b2cd5c418b22","last_reissued_at":"2026-05-18T00:39:48.216174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:48.216174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.00685","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":"2026-05-18T00:39:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6R89ogTBxqqpvrweQXcgEnpYBTvHPlzdkUas0iipLcTXnLMQp2/DlHBaGNPrxHXfBuE+sTs67P01FCr3aa78CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T17:21:23.255087Z"},"content_sha256":"b52edb1ef1d3da5faac5fb0b3e03dbe5f1478a4224df5e9bdb537ca95fcf6a4b","schema_version":"1.0","event_id":"sha256:b52edb1ef1d3da5faac5fb0b3e03dbe5f1478a4224df5e9bdb537ca95fcf6a4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:CBGFVY2UPKWL7OU5G56JUYU7H3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-based reinforcement learning for infinite-horizon approximate optimal tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.SY","authors_text":"Lindsey Andrews, Patrick Walters, Rushikesh Kamalapurkar, Warren E. Dixon","submitted_at":"2015-06-01T21:43:01Z","abstract_excerpt":"This paper provides an approximate online adaptive solution to the infinite-horizon optimal tracking problem for control-affine continuous-time nonlinear systems with unknown drift dynamics. Model-based reinforcement learning is used to relax the persistence of excitation condition. Model-based reinforcement learning is implemented using a concurrent learning-based system identifier to simulate experience by evaluating the Bellman error over unexplored areas of the state space. Tracking of the desired trajectory and convergence of the developed policy to a neighborhood of the optimal policy ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.00685","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":""},"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":"2026-05-18T00:39:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xeRVXO6KoaMP9ZU+rnF34NUfTQjAVaC7DNmUZNX2hfF98Meb4z8EC40NioHRFU1sY6pDe/lvTnj6xa7+GP/QCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T17:21:23.255861Z"},"content_sha256":"c07455556c2cd15c80b4cf3094a755a1b1215c5d986eb03cd8b3cd17ee8b8c8c","schema_version":"1.0","event_id":"sha256:c07455556c2cd15c80b4cf3094a755a1b1215c5d986eb03cd8b3cd17ee8b8c8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/bundle.json","state_url":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/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":"2026-06-11T17:21:23Z","links":{"resolver":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3","bundle":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/bundle.json","state":"https://pith.science/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBGFVY2UPKWL7OU5G56JUYU7H3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:CBGFVY2UPKWL7OU5G56JUYU7H3","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":"cfc94fb762f5fbf9a94aa65cb886da9089d55e8a1f6422a577ba7c78df4771e1","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-06-01T21:43:01Z","title_canon_sha256":"73b8b43e070adbd133066430015740333172b6f9342cd82f6d172eae43885066"},"schema_version":"1.0","source":{"id":"1506.00685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.00685","created_at":"2026-05-18T00:39:48Z"},{"alias_kind":"arxiv_version","alias_value":"1506.00685v1","created_at":"2026-05-18T00:39:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.00685","created_at":"2026-05-18T00:39:48Z"},{"alias_kind":"pith_short_12","alias_value":"CBGFVY2UPKWL","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"CBGFVY2UPKWL7OU5","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"CBGFVY2U","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:c07455556c2cd15c80b4cf3094a755a1b1215c5d986eb03cd8b3cd17ee8b8c8c","target":"graph","created_at":"2026-05-18T00:39:48Z","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"},"paper":{"abstract_excerpt":"This paper provides an approximate online adaptive solution to the infinite-horizon optimal tracking problem for control-affine continuous-time nonlinear systems with unknown drift dynamics. Model-based reinforcement learning is used to relax the persistence of excitation condition. Model-based reinforcement learning is implemented using a concurrent learning-based system identifier to simulate experience by evaluating the Bellman error over unexplored areas of the state space. Tracking of the desired trajectory and convergence of the developed policy to a neighborhood of the optimal policy ar","authors_text":"Lindsey Andrews, Patrick Walters, Rushikesh Kamalapurkar, Warren E. Dixon","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-06-01T21:43:01Z","title":"Model-based reinforcement learning for infinite-horizon approximate optimal tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.00685","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:b52edb1ef1d3da5faac5fb0b3e03dbe5f1478a4224df5e9bdb537ca95fcf6a4b","target":"record","created_at":"2026-05-18T00:39:48Z","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":"cfc94fb762f5fbf9a94aa65cb886da9089d55e8a1f6422a577ba7c78df4771e1","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-06-01T21:43:01Z","title_canon_sha256":"73b8b43e070adbd133066430015740333172b6f9342cd82f6d172eae43885066"},"schema_version":"1.0","source":{"id":"1506.00685","kind":"arxiv","version":1}},"canonical_sha256":"104c5ae3547aacbfba9d377c9a629f3ef7e3356f84043ff625d7b2cd5c418b22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"104c5ae3547aacbfba9d377c9a629f3ef7e3356f84043ff625d7b2cd5c418b22","first_computed_at":"2026-05-18T00:39:48.216174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:48.216174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rIpHKDCQT/VtG8OK/Mr9R9pyn7ELj7HclfTe/zho/TiQOE7JEK9CfybhF1kqTlKNWNJW1JPAuwlfFv5l3DL8BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:48.216851Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.00685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b52edb1ef1d3da5faac5fb0b3e03dbe5f1478a4224df5e9bdb537ca95fcf6a4b","sha256:c07455556c2cd15c80b4cf3094a755a1b1215c5d986eb03cd8b3cd17ee8b8c8c"],"state_sha256":"a9f6d6c3d8e31f954cbb2a47900aa7ba8b98fce8f6f89c5437ddb73528ef4dce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U6jDuEyfWgbshXfBF2d+v4+trimou6Vj9PLdbqoaCW0UtnsPmebD9QLUHp2sqNKXO9CwfysgilwbuhU/Ki71Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T17:21:23.260531Z","bundle_sha256":"e6d0b04f136af17988321645e0f607da1a1d49ab11f94df59227fc326f4605cb"}}