{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CTEE5WIV4DPQKKE7ZKB4BGJVUC","short_pith_number":"pith:CTEE5WIV","schema_version":"1.0","canonical_sha256":"14c84ed915e0df05289fca83c09935a0a691acc4c22167e687b31f8c5d216985","source":{"kind":"arxiv","id":"2505.07594","version":1},"attestation_state":"computed","paper":{"title":"Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Amon Lahr, Andreas Krause, Johannes K\\\"ohler, Manish Prajapat, Melanie N. Zeilinger","submitted_at":"2025-05-12T14:20:20Z","abstract_excerpt":"Gaussian Process (GP) regression is shown to be effective for learning unknown dynamics, enabling efficient and safety-aware control strategies across diverse applications. However, existing GP-based model predictive control (GP-MPC) methods either rely on approximations, thus lacking guarantees, or are overly conservative, which limits their practical utility. To close this gap, we present a sampling-based framework that efficiently propagates the model's epistemic uncertainty while avoiding conservatism. We establish a novel sample complexity result that enables the construction of a reachab"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.07594","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-05-12T14:20:20Z","cross_cats_sorted":["cs.LG","cs.SY","math.OC"],"title_canon_sha256":"a3013bfff8dd6ae1cd89c398c1f0dc5480a2897633f7f12fb31f42c93c62ac30","abstract_canon_sha256":"ba6a841ed809ad0a6f05fa3ad8664aea2453ad80ef6cd4cd2d36d0f0a561141b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:50.187893Z","signature_b64":"8y1z4F+vYZFc0tBAsV03mgoQbvM1Ol8wc+InpJdK28f0Ufb9Ouh6e30DmZIhFeLgrgB1HXAANFgIa6yCDvqyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c84ed915e0df05289fca83c09935a0a691acc4c22167e687b31f8c5d216985","last_reissued_at":"2026-07-05T11:01:50.187416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:50.187416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Amon Lahr, Andreas Krause, Johannes K\\\"ohler, Manish Prajapat, Melanie N. Zeilinger","submitted_at":"2025-05-12T14:20:20Z","abstract_excerpt":"Gaussian Process (GP) regression is shown to be effective for learning unknown dynamics, enabling efficient and safety-aware control strategies across diverse applications. However, existing GP-based model predictive control (GP-MPC) methods either rely on approximations, thus lacking guarantees, or are overly conservative, which limits their practical utility. To close this gap, we present a sampling-based framework that efficiently propagates the model's epistemic uncertainty while avoiding conservatism. We establish a novel sample complexity result that enables the construction of a reachab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07594","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.07594/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.07594","created_at":"2026-07-05T11:01:50.187478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07594v1","created_at":"2026-07-05T11:01:50.187478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07594","created_at":"2026-07-05T11:01:50.187478+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTEE5WIV4DPQ","created_at":"2026-07-05T11:01:50.187478+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTEE5WIV4DPQKKE7","created_at":"2026-07-05T11:01:50.187478+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTEE5WIV","created_at":"2026-07-05T11:01:50.187478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19469","citing_title":"Sampling-Based Safe Reinforcement Learning","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02098","citing_title":"A robust and adaptive MPC formulation for Gaussian process models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC","json":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC.json","graph_json":"https://pith.science/api/pith-number/CTEE5WIV4DPQKKE7ZKB4BGJVUC/graph.json","events_json":"https://pith.science/api/pith-number/CTEE5WIV4DPQKKE7ZKB4BGJVUC/events.json","paper":"https://pith.science/paper/CTEE5WIV"},"agent_actions":{"view_html":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC","download_json":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC.json","view_paper":"https://pith.science/paper/CTEE5WIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07594&json=true","fetch_graph":"https://pith.science/api/pith-number/CTEE5WIV4DPQKKE7ZKB4BGJVUC/graph.json","fetch_events":"https://pith.science/api/pith-number/CTEE5WIV4DPQKKE7ZKB4BGJVUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC/action/storage_attestation","attest_author":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC/action/author_attestation","sign_citation":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC/action/citation_signature","submit_replication":"https://pith.science/pith/CTEE5WIV4DPQKKE7ZKB4BGJVUC/action/replication_record"}},"created_at":"2026-07-05T11:01:50.187478+00:00","updated_at":"2026-07-05T11:01:50.187478+00:00"}