{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4MCCMGFO5LQX7QQZVB737RVPGY","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":"d524fae40de3911617501cc4d78c9be2d8101223b16693832f708c804f284830","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T23:55:15Z","title_canon_sha256":"441fded9b6c9b07b04ea76f6df2be6887a1930b077af32f3af176b487fc2417b"},"schema_version":"1.0","source":{"id":"2605.12561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12561","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12561v1","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12561","created_at":"2026-05-18T03:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"4MCCMGFO5LQX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"4MCCMGFO5LQX7QQZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"4MCCMGFO","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:5f19d5616c10788239ca62eac67bad89657cc083d7beea85fcc42281babedf3f","target":"graph","created_at":"2026-05-18T03:10:01Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"On an inverted pendulum, cart-pole, and planar quadrotor, the learned policy achieves 1.91×, 1.45×, and 3.51× higher mean inter-sample interval (MSI) than a Lyapunov-triggered baseline; a fixed LQR controller at the same average rate is unstable on all three plants, showing that adaptive timing, not a lower average rate, makes sparsity safe."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The approach assumes a known equilibrium point where CARE-based LQR backups and Lyapunov certificates are well-defined, allowing the RTA to provide strictly stronger safety guarantees than expectation-based methods."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Learned policies with runtime Lyapunov shields achieve substantially higher communication intervals than baselines while maintaining stability on inverted pendulum, cart-pole, and quadrotor systems."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single RL policy learns both control actions and sparse timing decisions while a Lyapunov run-time assurance shield enforces stability via LQR overrides."}],"snapshot_sha256":"1c56a1bce8c46f358765398c6867bf6a22cdbc346d6e410efcf732e5fc9d31ae"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Safe reinforcement learning (RL) typically asks $\\textit{what}$ an agent should do. We ask $\\textit{when}$ it needs to act, and show that a single policy can jointly learn control inputs and communication-efficient timing decisions under a pointwise Lyapunov safety shield. We focus on stabilization around a known equilibrium, where CARE-based LQR backups, Lyapunov certificates, and classical Lyapunov-STC are well defined, enabling clean comparison against analytical baselines. A run-time assurance (RTA) layer overrides the policy via a one-step-ahead Lyapunov prediction and a precomputed LQR b","authors_text":"Adam Haroon, Cody Fleming, Erick J. Rodr\\'iguez-Seda, Tristan Schuler","cross_cats":["cs.RO"],"headline":"A single RL policy learns both control actions and sparse timing decisions while a Lyapunov run-time assurance shield enforces stability via LQR overrides.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T23:55:15Z","title":"Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance"},"references":{"count":31,"internal_anchors":2,"resolved_work":31,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A. Abels, D. Roijers, T. Lenaerts, A. Nowé, and D. Steckelmacher. Dynamic weights in multi-objective deep reinforcement learning. InInternational Conference on Machine Learning, pages 11–20. PMLR, 201","work_id":"a099ba9b-0c0a-474e-83c6-97c4ca689983","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"J. Achiam, D. Held, A. Tamar, and P. Abbeel. Constrained policy optimization. InInternational Conference on Machine Learning, pages 22–31. PMLR, 2017","work_id":"7fdc9762-60da-432e-bc31-8b4b4df1d8be","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"S. Aggarwal, D. Maity, and T. Ba¸ sar. Interq: A dqn framework for optimal intermittent control. IEEE Control Systems Letters, 2025","work_id":"baa7daaf-d36b-494e-b330-45fa25673810","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"M. Alshiekh, R. Bloem, R. Ehlers, B. Könighofer, S. Niekum, and U. Topcu. Safe reinforcement learning via shielding. InProceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018","work_id":"b22ca70f-4c39-4e2c-b237-a18a9ff40fe2","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Altman.Constrained Markov Decision Processes","work_id":"201db9f5-e923-4c71-8b35-465badee3afc","year":2021}],"snapshot_sha256":"178017d36ff07c71762999f698794874f1070cb5f9d883d861cf4b8ba0811ad1"},"source":{"id":"2605.12561","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:39:20.796514Z","id":"372e4dac-007a-41bf-bbdf-85f2f9e24c73","model_set":{"reader":"grok-4.3"},"one_line_summary":"Learned policies with runtime Lyapunov shields achieve substantially higher communication intervals than baselines while maintaining stability on inverted pendulum, cart-pole, and quadrotor systems.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single RL policy learns both control actions and sparse timing decisions while a Lyapunov run-time assurance shield enforces stability via LQR overrides.","strongest_claim":"On an inverted pendulum, cart-pole, and planar quadrotor, the learned policy achieves 1.91×, 1.45×, and 3.51× higher mean inter-sample interval (MSI) than a Lyapunov-triggered baseline; a fixed LQR controller at the same average rate is unstable on all three plants, showing that adaptive timing, not a lower average rate, makes sparsity safe.","weakest_assumption":"The approach assumes a known equilibrium point where CARE-based LQR backups and Lyapunov certificates are well-defined, allowing the RTA to provide strictly stronger safety guarantees than expectation-based methods."}},"verdict_id":"372e4dac-007a-41bf-bbdf-85f2f9e24c73"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dc4e63bef316505c22eaee55f09687528964e68d28a1c151836115bf5f196ef9","target":"record","created_at":"2026-05-18T03:10:01Z","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":"d524fae40de3911617501cc4d78c9be2d8101223b16693832f708c804f284830","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T23:55:15Z","title_canon_sha256":"441fded9b6c9b07b04ea76f6df2be6887a1930b077af32f3af176b487fc2417b"},"schema_version":"1.0","source":{"id":"2605.12561","kind":"arxiv","version":1}},"canonical_sha256":"e3042618aeeae17fc219a87fbfc6af36284ed772a4b249bbd9f183c6fb2f23aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3042618aeeae17fc219a87fbfc6af36284ed772a4b249bbd9f183c6fb2f23aa","first_computed_at":"2026-05-18T03:10:01.975671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:01.975671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HNlP9K3TR0ao1Rxlb0ZJxdEU/wE86h+bTGcXdTCBlMG1n3YAysauHoHFXPs2YfOOrZLvwpHP6raQnOUu/yaQBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:01.976427Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc4e63bef316505c22eaee55f09687528964e68d28a1c151836115bf5f196ef9","sha256:5f19d5616c10788239ca62eac67bad89657cc083d7beea85fcc42281babedf3f"],"state_sha256":"9627196b19d7146c77e813db4968a14654792ceceaee93fb5198528885d61098"}