{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6D3OLVER4YSNZROB7XIHZBKCFN","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":"4ed1ff8544754e628a3c878788ffbed0bde85af9275700f096731593ac7731d9","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-11T22:03:18Z","title_canon_sha256":"3f91eebc03829b47e3175abf4452d9cd1c72a6046bf230c1d40d5f8406df64dd"},"schema_version":"1.0","source":{"id":"2205.05787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05787","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05787v1","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05787","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"6D3OLVER4YSN","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"6D3OLVER4YSNZROB","created_at":"2026-07-05T04:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"6D3OLVER","created_at":"2026-07-05T04:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:707de1fc2ac539489e57db03aecefe055a0c89bdc43698a88b6ae5830877eaf0","target":"graph","created_at":"2026-07-05T04:22:41Z","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/2205.05787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bridging model-based safety and model-free reinforcement learning (RL) for dynamic robots is appealing since model-based methods are able to provide formal safety guarantees, while RL-based methods are able to exploit the robot agility by learning from the full-order system dynamics. However, current approaches to tackle this problem are mostly restricted to simple systems. In this paper, we propose a new method to combine model-based safety with model-free reinforcement learning by explicitly finding a low-dimensional model of the system controlled by a RL policy and applying stability and sa","authors_text":"Akshay Thirugnanam, Jun Zeng, Koushil Sreenath, Zhongyu Li","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-11T22:03:18Z","title":"Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05787","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":"sha256:7dd5497d73912b02f80132f7bf5358926e49ab9daad4a41b890cbe5a95e8ce21","target":"record","created_at":"2026-07-05T04:22:41Z","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":"4ed1ff8544754e628a3c878788ffbed0bde85af9275700f096731593ac7731d9","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-05-11T22:03:18Z","title_canon_sha256":"3f91eebc03829b47e3175abf4452d9cd1c72a6046bf230c1d40d5f8406df64dd"},"schema_version":"1.0","source":{"id":"2205.05787","kind":"arxiv","version":1}},"canonical_sha256":"f0f6e5d491e624dcc5c1fdd07c85422b5a6d852b0239f01206760967b6f5473b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0f6e5d491e624dcc5c1fdd07c85422b5a6d852b0239f01206760967b6f5473b","first_computed_at":"2026-07-05T04:22:41.833300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:41.833300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FLJi4jnQdwTIhVuFBzuLfikg6kdVactXEEgFoBl5fwcCoP+A3ta4CDIbrBQjknVhMCIgMIYSJp/JHOgtbVH0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:41.833722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dd5497d73912b02f80132f7bf5358926e49ab9daad4a41b890cbe5a95e8ce21","sha256:707de1fc2ac539489e57db03aecefe055a0c89bdc43698a88b6ae5830877eaf0"],"state_sha256":"74e24e1295cf54eb13dba598bd553db7331ba0500ccee6353c1a4ce78f08ed8a"}