{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LIH2QFNU7VGAANCKFHQFMFZMX4","short_pith_number":"pith:LIH2QFNU","schema_version":"1.0","canonical_sha256":"5a0fa815b4fd4c00344a29e056172cbf34fcd12f13dc86aca9274007f9193bf5","source":{"kind":"arxiv","id":"2605.16170","version":1},"attestation_state":"computed","paper":{"title":"BAPR: Bayesian amnesic piecewise-robust reinforcement learning for non-stationary continuous control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Liang Zheng, Yifan Zhang","submitted_at":"2026-05-15T16:49:05Z","abstract_excerpt":"Real-world control systems frequently operate under \\emph{piecewise stationary} conditions, where dynamics remain stable for extended periods before undergoing abrupt regime changes. Standard robust RL methods face a fundamental dilemma: a globally conservative policy wastes performance during stable periods, while a locally adaptive policy risks catastrophic failure when the regime changes undetected.\n  We propose \\textbf{BAPR} (Bayesian Amnesic Piecewise-Robust SAC), which unifies Bayesian Online Change Detection (BOCD) with robust ensemble RL. The BAPR operator -- a convex combination of mo"},"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":"2605.16170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T16:49:05Z","cross_cats_sorted":[],"title_canon_sha256":"7f39477979e5aa1a7989fa084c670ec847a70923a36fff270e4ba214a5941620","abstract_canon_sha256":"bf69b975ffa1df1770dbcf65835b192e2650b14b8c4201649bb9376c613addf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:55.994471Z","signature_b64":"EXu14fi7HEk6c2JSaE8XFuO82llzsHL7oyhMl3eWT7bh5SiBPgQIZm3gKKKethx03bkgy5By39Y2nSXE2rCsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a0fa815b4fd4c00344a29e056172cbf34fcd12f13dc86aca9274007f9193bf5","last_reissued_at":"2026-05-20T00:01:55.993792Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:55.993792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAPR: Bayesian amnesic piecewise-robust reinforcement learning for non-stationary continuous control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Liang Zheng, Yifan Zhang","submitted_at":"2026-05-15T16:49:05Z","abstract_excerpt":"Real-world control systems frequently operate under \\emph{piecewise stationary} conditions, where dynamics remain stable for extended periods before undergoing abrupt regime changes. Standard robust RL methods face a fundamental dilemma: a globally conservative policy wastes performance during stable periods, while a locally adaptive policy risks catastrophic failure when the regime changes undetected.\n  We propose \\textbf{BAPR} (Bayesian Amnesic Piecewise-Robust SAC), which unifies Bayesian Online Change Detection (BOCD) with robust ensemble RL. The BAPR operator -- a convex combination of mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16170","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/2605.16170/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T17:52:14.792626Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:31.030935Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T17:31:45.988784Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.429015Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"08c9c947a3216b5fb922d9da1358476c726f24b0f9f0a10418f98ede5f80e08c"},"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":"2605.16170","created_at":"2026-05-20T00:01:55.993900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16170v1","created_at":"2026-05-20T00:01:55.993900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16170","created_at":"2026-05-20T00:01:55.993900+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIH2QFNU7VGA","created_at":"2026-05-20T00:01:55.993900+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIH2QFNU7VGAANCK","created_at":"2026-05-20T00:01:55.993900+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIH2QFNU","created_at":"2026-05-20T00:01:55.993900+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4","json":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4.json","graph_json":"https://pith.science/api/pith-number/LIH2QFNU7VGAANCKFHQFMFZMX4/graph.json","events_json":"https://pith.science/api/pith-number/LIH2QFNU7VGAANCKFHQFMFZMX4/events.json","paper":"https://pith.science/paper/LIH2QFNU"},"agent_actions":{"view_html":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4","download_json":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4.json","view_paper":"https://pith.science/paper/LIH2QFNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16170&json=true","fetch_graph":"https://pith.science/api/pith-number/LIH2QFNU7VGAANCKFHQFMFZMX4/graph.json","fetch_events":"https://pith.science/api/pith-number/LIH2QFNU7VGAANCKFHQFMFZMX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4/action/storage_attestation","attest_author":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4/action/author_attestation","sign_citation":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4/action/citation_signature","submit_replication":"https://pith.science/pith/LIH2QFNU7VGAANCKFHQFMFZMX4/action/replication_record"}},"created_at":"2026-05-20T00:01:55.993900+00:00","updated_at":"2026-05-20T00:01:55.993900+00:00"}