{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4VVS3OKMMTTNADTEMWQOYIWE2L","short_pith_number":"pith:4VVS3OKM","schema_version":"1.0","canonical_sha256":"e56b2db94c64e6d00e6465a0ec22c4d2f1c6841205e2bed5050bbe2edd9deb00","source":{"kind":"arxiv","id":"2206.01341","version":1},"attestation_state":"computed","paper":{"title":"Equipping Black-Box Policies with Model-Based Advice for Stable Nonlinear Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Guannan Qu, Ruixiao Yang, Steven Low, Tongxin Li, Yiheng Lin","submitted_at":"2022-06-02T23:51:30Z","abstract_excerpt":"Machine-learned black-box policies are ubiquitous for nonlinear control problems. Meanwhile, crude model information is often available for these problems from, e.g., linear approximations of nonlinear dynamics. We study the problem of equipping a black-box control policy with model-based advice for nonlinear control on a single trajectory. We first show a general negative result that a naive convex combination of a black-box policy and a linear model-based policy can lead to instability, even if the two policies are both stabilizing. We then propose an adaptive $\\lambda$-confident policy, wit"},"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":"2206.01341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T23:51:30Z","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"fab1d1a6dc6225dc5443e60151c5de9593d9004d37de5d6e7db45173ccb3c21b","abstract_canon_sha256":"95108594700b4248c590e1a25549763b3c044b1d1be229d27e8eac0b21b8179a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:46.464253Z","signature_b64":"iNLv2Flxbgpw6Gd+yX/2W5AH+SCzdpNOlxDwlUJRX9HEcYTildOZfgryrLoS261yI63S/tjMcLwYE8BETy4FCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e56b2db94c64e6d00e6465a0ec22c4d2f1c6841205e2bed5050bbe2edd9deb00","last_reissued_at":"2026-07-05T04:28:46.463714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:46.463714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equipping Black-Box Policies with Model-Based Advice for Stable Nonlinear Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Guannan Qu, Ruixiao Yang, Steven Low, Tongxin Li, Yiheng Lin","submitted_at":"2022-06-02T23:51:30Z","abstract_excerpt":"Machine-learned black-box policies are ubiquitous for nonlinear control problems. Meanwhile, crude model information is often available for these problems from, e.g., linear approximations of nonlinear dynamics. We study the problem of equipping a black-box control policy with model-based advice for nonlinear control on a single trajectory. We first show a general negative result that a naive convex combination of a black-box policy and a linear model-based policy can lead to instability, even if the two policies are both stabilizing. We then propose an adaptive $\\lambda$-confident policy, wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01341","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/2206.01341/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":"2206.01341","created_at":"2026-07-05T04:28:46.463782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01341v1","created_at":"2026-07-05T04:28:46.463782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01341","created_at":"2026-07-05T04:28:46.463782+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VVS3OKMMTTN","created_at":"2026-07-05T04:28:46.463782+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VVS3OKMMTTNADTE","created_at":"2026-07-05T04:28:46.463782+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VVS3OKM","created_at":"2026-07-05T04:28:46.463782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13224","citing_title":"Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L","json":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L.json","graph_json":"https://pith.science/api/pith-number/4VVS3OKMMTTNADTEMWQOYIWE2L/graph.json","events_json":"https://pith.science/api/pith-number/4VVS3OKMMTTNADTEMWQOYIWE2L/events.json","paper":"https://pith.science/paper/4VVS3OKM"},"agent_actions":{"view_html":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L","download_json":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L.json","view_paper":"https://pith.science/paper/4VVS3OKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01341&json=true","fetch_graph":"https://pith.science/api/pith-number/4VVS3OKMMTTNADTEMWQOYIWE2L/graph.json","fetch_events":"https://pith.science/api/pith-number/4VVS3OKMMTTNADTEMWQOYIWE2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L/action/storage_attestation","attest_author":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L/action/author_attestation","sign_citation":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L/action/citation_signature","submit_replication":"https://pith.science/pith/4VVS3OKMMTTNADTEMWQOYIWE2L/action/replication_record"}},"created_at":"2026-07-05T04:28:46.463782+00:00","updated_at":"2026-07-05T04:28:46.463782+00:00"}