{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:REEQYT6APOHXYKSMI5TN5SIDAN","short_pith_number":"pith:REEQYT6A","canonical_record":{"source":{"id":"2012.06656","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"a0fc0655735cfe70617d927e46764af242f20ff32061fae561c4466ae2b88eda","abstract_canon_sha256":"16520aae4b698da8f06aa5c36b4b36b95f8ce3902dfec32af424f83d64dfdbf6"},"schema_version":"1.0"},"canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","source":{"kind":"arxiv","id":"2012.06656","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.06656","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2012.06656v2","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06656","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"REEQYT6APOHX","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"REEQYT6APOHXYKSM","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"REEQYT6A","created_at":"2026-07-05T03:22:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:REEQYT6APOHXYKSMI5TN5SIDAN","target":"record","payload":{"canonical_record":{"source":{"id":"2012.06656","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"a0fc0655735cfe70617d927e46764af242f20ff32061fae561c4466ae2b88eda","abstract_canon_sha256":"16520aae4b698da8f06aa5c36b4b36b95f8ce3902dfec32af424f83d64dfdbf6"},"schema_version":"1.0"},"canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:20.432328Z","signature_b64":"dSTMNiuKO9QiN4f9hHT9QiTJjNh5aach1zFVU5cuK/kCzmy7QC4V8Lh2vcjdPiU3mAelcnZmAIG/MEoOtNg5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","last_reissued_at":"2026-07-05T03:22:20.431953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:20.431953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.06656","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":"2026-07-05T03:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JL2lgIpS4Rk2yfYZO+2m04GTRNNdiDgt1FhAe2L0vAOtoMkL5R905sJuc+BM3RuV4MFSLVh+Y2JCduLY5VUZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:03:14.659691Z"},"content_sha256":"ac3619aeb3a405e080605817de7e2fc75b294cff480bd3c06bdb65250d9ed2cd","schema_version":"1.0","event_id":"sha256:ac3619aeb3a405e080605817de7e2fc75b294cff480bd3c06bdb65250d9ed2cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:REEQYT6APOHXYKSMI5TN5SIDAN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Bassel Mabsout, Kate Saenko, Renato Mancuso, Siddharth Mysore","submitted_at":"2020-12-11T21:50:27Z","abstract_excerpt":"We focus on the problem of reliably training Reinforcement Learning (RL) models (agents) for stable low-level control in embedded systems and test our methods on a high-performance, custom-built quadrotor platform. A common but often under-studied problem in developing RL agents for continuous control is that the control policies developed are not always smooth. This lack of smoothness can be a major problem when learning controllers %intended for deployment on real hardware as it can result in control instability and hardware failure. Issues of noisy control are further accentuated when train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06656","kind":"arxiv","version":2},"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/2012.06656/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":"2026-07-05T03:22:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dXCchlnV+Sib3nSQ5WGPqll9jWS/Hd06siL3A+uGDKNgbnMTLg5OSEIYH8lL1J4EsVSJa3QGvC9UFQqHTalOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:03:14.660625Z"},"content_sha256":"0ff16794b576fc43d42af634c7a3e24cbbd42ca456c97fc5f90aa38edd9f98f3","schema_version":"1.0","event_id":"sha256:0ff16794b576fc43d42af634c7a3e24cbbd42ca456c97fc5f90aa38edd9f98f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/bundle.json","state_url":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REEQYT6APOHXYKSMI5TN5SIDAN/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":"2026-08-05T08:03:14Z","links":{"resolver":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN","bundle":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/bundle.json","state":"https://pith.science/pith/REEQYT6APOHXYKSMI5TN5SIDAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REEQYT6APOHXYKSMI5TN5SIDAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:REEQYT6APOHXYKSMI5TN5SIDAN","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":"16520aae4b698da8f06aa5c36b4b36b95f8ce3902dfec32af424f83d64dfdbf6","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","title_canon_sha256":"a0fc0655735cfe70617d927e46764af242f20ff32061fae561c4466ae2b88eda"},"schema_version":"1.0","source":{"id":"2012.06656","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.06656","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2012.06656v2","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06656","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"REEQYT6APOHX","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"REEQYT6APOHXYKSM","created_at":"2026-07-05T03:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"REEQYT6A","created_at":"2026-07-05T03:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:0ff16794b576fc43d42af634c7a3e24cbbd42ca456c97fc5f90aa38edd9f98f3","target":"graph","created_at":"2026-07-05T03:22:20Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.06656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We focus on the problem of reliably training Reinforcement Learning (RL) models (agents) for stable low-level control in embedded systems and test our methods on a high-performance, custom-built quadrotor platform. A common but often under-studied problem in developing RL agents for continuous control is that the control policies developed are not always smooth. This lack of smoothness can be a major problem when learning controllers %intended for deployment on real hardware as it can result in control instability and hardware failure. Issues of noisy control are further accentuated when train","authors_text":"Bassel Mabsout, Kate Saenko, Renato Mancuso, Siddharth Mysore","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","title":"How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06656","kind":"arxiv","version":2},"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:ac3619aeb3a405e080605817de7e2fc75b294cff480bd3c06bdb65250d9ed2cd","target":"record","created_at":"2026-07-05T03:22:20Z","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":"16520aae4b698da8f06aa5c36b4b36b95f8ce3902dfec32af424f83d64dfdbf6","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-11T21:50:27Z","title_canon_sha256":"a0fc0655735cfe70617d927e46764af242f20ff32061fae561c4466ae2b88eda"},"schema_version":"1.0","source":{"id":"2012.06656","kind":"arxiv","version":2}},"canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89090c4fc07b8f7c2a4c4766dec903035d498cc84e5d07c34f9d4894d6c5a098","first_computed_at":"2026-07-05T03:22:20.431953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:20.431953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dSTMNiuKO9QiN4f9hHT9QiTJjNh5aach1zFVU5cuK/kCzmy7QC4V8Lh2vcjdPiU3mAelcnZmAIG/MEoOtNg5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:20.432328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.06656","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac3619aeb3a405e080605817de7e2fc75b294cff480bd3c06bdb65250d9ed2cd","sha256:0ff16794b576fc43d42af634c7a3e24cbbd42ca456c97fc5f90aa38edd9f98f3"],"state_sha256":"1220cc3c9e15dd59a4d322d1c860b39c727896f8b22cd5cf3f020cdd163939de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5isYDULcPhiscb/9U1oXzt/FAsTLyggM9D4vFtWrzSEiF1lDDZ4tHyr6Tq+Iz92LapSYA0VRaIYJ4i32v3sNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:03:14.668491Z","bundle_sha256":"2ed77360dff1ed7d94b77a1b8ab49eb9cb07fb7703c175c2bd557f4d65a51ca5"}}