{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QG2TZZCRKGLAPG4G2K4LBJLPKP","short_pith_number":"pith:QG2TZZCR","schema_version":"1.0","canonical_sha256":"81b53ce4515196079b86d2b8b0a56f53e733e37f30788226cd5380133059f07e","source":{"kind":"arxiv","id":"2409.05898","version":2},"attestation_state":"computed","paper":{"title":"Simplex-enabled Safe Continual Learning Machine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hongpeng Cao, Lui Sha, Marco Caccamo, Yanbing Mao, Yihao Cai","submitted_at":"2024-09-05T16:03:00Z","abstract_excerpt":"This paper proposes the SeC-Learning Machine: Simplex-enabled safe continual learning for safety-critical autonomous systems. The SeC-learning machine is built on Simplex logic (that is, ``using simplicity to control complexity'') and physics-regulated deep reinforcement learning (Phy-DRL). The SeC-learning machine thus constitutes HP (high performance)-Student, HA (high assurance)-Teacher, and Coordinator. Specifically, the HP-Student is a pre-trained high-performance but not fully verified Phy-DRL, continuing to learn in a real plant to tune the action policy to be safe. In contrast, the HA-"},"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":"2409.05898","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-05T16:03:00Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"3fcd45f9e16e600b0b078a9a65532d34f793119dcccd471b54698cf4f8d8ec28","abstract_canon_sha256":"d34b6648bd2e6dc3bca752120093cbbeda20adcfafff5c55c2eb543757121e20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:21.123044Z","signature_b64":"FGAxLTsEujxhgJwPsHzmHWf2/whS7iK2ODcL+76xQCndn6xe6gscmFxKJIOjPaJO/Ihosu76G15oVcehLJDuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b53ce4515196079b86d2b8b0a56f53e733e37f30788226cd5380133059f07e","last_reissued_at":"2026-07-05T09:16:21.122511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:21.122511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simplex-enabled Safe Continual Learning Machine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hongpeng Cao, Lui Sha, Marco Caccamo, Yanbing Mao, Yihao Cai","submitted_at":"2024-09-05T16:03:00Z","abstract_excerpt":"This paper proposes the SeC-Learning Machine: Simplex-enabled safe continual learning for safety-critical autonomous systems. The SeC-learning machine is built on Simplex logic (that is, ``using simplicity to control complexity'') and physics-regulated deep reinforcement learning (Phy-DRL). The SeC-learning machine thus constitutes HP (high performance)-Student, HA (high assurance)-Teacher, and Coordinator. Specifically, the HP-Student is a pre-trained high-performance but not fully verified Phy-DRL, continuing to learn in a real plant to tune the action policy to be safe. In contrast, the HA-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05898","kind":"arxiv","version":2},"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/2409.05898/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":"2409.05898","created_at":"2026-07-05T09:16:21.122582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.05898v2","created_at":"2026-07-05T09:16:21.122582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05898","created_at":"2026-07-05T09:16:21.122582+00:00"},{"alias_kind":"pith_short_12","alias_value":"QG2TZZCRKGLA","created_at":"2026-07-05T09:16:21.122582+00:00"},{"alias_kind":"pith_short_16","alias_value":"QG2TZZCRKGLAPG4G","created_at":"2026-07-05T09:16:21.122582+00:00"},{"alias_kind":"pith_short_8","alias_value":"QG2TZZCR","created_at":"2026-07-05T09:16:21.122582+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":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP","json":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP.json","graph_json":"https://pith.science/api/pith-number/QG2TZZCRKGLAPG4G2K4LBJLPKP/graph.json","events_json":"https://pith.science/api/pith-number/QG2TZZCRKGLAPG4G2K4LBJLPKP/events.json","paper":"https://pith.science/paper/QG2TZZCR"},"agent_actions":{"view_html":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP","download_json":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP.json","view_paper":"https://pith.science/paper/QG2TZZCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.05898&json=true","fetch_graph":"https://pith.science/api/pith-number/QG2TZZCRKGLAPG4G2K4LBJLPKP/graph.json","fetch_events":"https://pith.science/api/pith-number/QG2TZZCRKGLAPG4G2K4LBJLPKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP/action/storage_attestation","attest_author":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP/action/author_attestation","sign_citation":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP/action/citation_signature","submit_replication":"https://pith.science/pith/QG2TZZCRKGLAPG4G2K4LBJLPKP/action/replication_record"}},"created_at":"2026-07-05T09:16:21.122582+00:00","updated_at":"2026-07-05T09:16:21.122582+00:00"}