{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KHVJTXHUZ7URGEABOLSMGUADCP","short_pith_number":"pith:KHVJTXHU","canonical_record":{"source":{"id":"1902.04696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-13T01:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"bcf698a5fa97443093cd75e1ca9047a8f73236b50e7d1b65474dafd2ec6404c1","abstract_canon_sha256":"2730be5a3f912bd1482399c3f41d494a0a0416aa03f952e717b05d95c4deded4"},"schema_version":"1.0"},"canonical_sha256":"51ea99dcf4cfe913100172e4c3500313d52e5603398ff96320f20266452c0378","source":{"kind":"arxiv","id":"1902.04696","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04696","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04696v1","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04696","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"KHVJTXHUZ7UR","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KHVJTXHUZ7URGEAB","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KHVJTXHU","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KHVJTXHUZ7URGEABOLSMGUADCP","target":"record","payload":{"canonical_record":{"source":{"id":"1902.04696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-13T01:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"bcf698a5fa97443093cd75e1ca9047a8f73236b50e7d1b65474dafd2ec6404c1","abstract_canon_sha256":"2730be5a3f912bd1482399c3f41d494a0a0416aa03f952e717b05d95c4deded4"},"schema_version":"1.0"},"canonical_sha256":"51ea99dcf4cfe913100172e4c3500313d52e5603398ff96320f20266452c0378","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:06.257901Z","signature_b64":"YxGuZ2LDr5N5zZZ9/gVNYR3obwufXWzcJp0CoNlC4gno7aKr11iSdBaBtswW98e+XX8BvVCc+jkpqW5qYC3FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51ea99dcf4cfe913100172e4c3500313d52e5603398ff96320f20266452c0378","last_reissued_at":"2026-05-17T23:54:06.257473Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:06.257473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.04696","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":"2026-05-17T23:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlotlRYLR01rc8SLH9b9VHOpLAT13fs6AEhTsFYqN6iJZ1Ly2gF/jB6hfGWGGwUckQZNLWt7oWvsF7wix/YYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:08:31.331283Z"},"content_sha256":"39fd2ebe3420557d960af66659bee33d75ca391f83d801c6d06ac921dfc7d841","schema_version":"1.0","event_id":"sha256:39fd2ebe3420557d960af66659bee33d75ca391f83d801c6d06ac921dfc7d841"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KHVJTXHUZ7URGEABOLSMGUADCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Approximate Models in Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Lenjani","submitted_at":"2019-02-13T01:33:27Z","abstract_excerpt":"Trajectory following is one of the complicated control problems when its dynamics are nonlinear, stochastic and include a large number of parameters. The problem has significant difficulties including a large number of trials required for data collection and a massive volume of computations required to find a closed-loop controller for high dimensional and stochastic domains. For solving this type of problem, if we have an appropriate reward function and dynamics model; finding an optimal control policy is possible by using model-based reinforcement learning and optimal control algorithms. How"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04696","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":"2026-05-17T23:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9WrRWqkA3zCSfRNpaIQEev+y9I5Pa+tC4BeNEPgNhwj9UhtSXL1VqN83bwgh31VQXoUbHQzjJ2cl54nylvnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T11:08:31.331653Z"},"content_sha256":"0240c08f5204cc891d9c9f3f17f65c500b693a389aa21c77cc9cb2de986abdb4","schema_version":"1.0","event_id":"sha256:0240c08f5204cc891d9c9f3f17f65c500b693a389aa21c77cc9cb2de986abdb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/bundle.json","state_url":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHVJTXHUZ7URGEABOLSMGUADCP/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":"2026-05-28T11:08:31Z","links":{"resolver":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP","bundle":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/bundle.json","state":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHVJTXHUZ7URGEABOLSMGUADCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KHVJTXHUZ7URGEABOLSMGUADCP","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":"2730be5a3f912bd1482399c3f41d494a0a0416aa03f952e717b05d95c4deded4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-13T01:33:27Z","title_canon_sha256":"bcf698a5fa97443093cd75e1ca9047a8f73236b50e7d1b65474dafd2ec6404c1"},"schema_version":"1.0","source":{"id":"1902.04696","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04696","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04696v1","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04696","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"KHVJTXHUZ7UR","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KHVJTXHUZ7URGEAB","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KHVJTXHU","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:0240c08f5204cc891d9c9f3f17f65c500b693a389aa21c77cc9cb2de986abdb4","target":"graph","created_at":"2026-05-17T23:54:06Z","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":"Trajectory following is one of the complicated control problems when its dynamics are nonlinear, stochastic and include a large number of parameters. The problem has significant difficulties including a large number of trials required for data collection and a massive volume of computations required to find a closed-loop controller for high dimensional and stochastic domains. For solving this type of problem, if we have an appropriate reward function and dynamics model; finding an optimal control policy is possible by using model-based reinforcement learning and optimal control algorithms. How","authors_text":"Ali Lenjani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-13T01:33:27Z","title":"Using Approximate Models in Robot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04696","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":"sha256:39fd2ebe3420557d960af66659bee33d75ca391f83d801c6d06ac921dfc7d841","target":"record","created_at":"2026-05-17T23:54:06Z","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":"2730be5a3f912bd1482399c3f41d494a0a0416aa03f952e717b05d95c4deded4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-13T01:33:27Z","title_canon_sha256":"bcf698a5fa97443093cd75e1ca9047a8f73236b50e7d1b65474dafd2ec6404c1"},"schema_version":"1.0","source":{"id":"1902.04696","kind":"arxiv","version":1}},"canonical_sha256":"51ea99dcf4cfe913100172e4c3500313d52e5603398ff96320f20266452c0378","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51ea99dcf4cfe913100172e4c3500313d52e5603398ff96320f20266452c0378","first_computed_at":"2026-05-17T23:54:06.257473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:06.257473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YxGuZ2LDr5N5zZZ9/gVNYR3obwufXWzcJp0CoNlC4gno7aKr11iSdBaBtswW98e+XX8BvVCc+jkpqW5qYC3FBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:06.257901Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.04696","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39fd2ebe3420557d960af66659bee33d75ca391f83d801c6d06ac921dfc7d841","sha256:0240c08f5204cc891d9c9f3f17f65c500b693a389aa21c77cc9cb2de986abdb4"],"state_sha256":"9c93eff85a6893f81bd561cbf88957a94861a6c0ed9ac18e50e34f85b609f94b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cbyf/SxCu3XpwZB53iLIHRI1QcBHeTBbwuXQp//jthcgPz7LZgSO6Zm4vTK5x2G8TVYJFADhzVpwFBt1sI9BBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T11:08:31.333575Z","bundle_sha256":"819a039de115ed14286e976f2fe566ef0df12ec49633395f535e6734159eb725"}}