{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MXGFJ5J5W2RMFUAYBCWSM4OAZL","short_pith_number":"pith:MXGFJ5J5","schema_version":"1.0","canonical_sha256":"65cc54f53db6a2c2d01808ad2671c0cafd58b43e07db5257c7a157787ad31ed7","source":{"kind":"arxiv","id":"2310.08602","version":3},"attestation_state":"computed","paper":{"title":"Safe Deep Policy Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Guanya Shi, John Dolan, Tairan He, Wenli Xiao","submitted_at":"2023-10-08T00:32:59Z","abstract_excerpt":"A critical goal of autonomy and artificial intelligence is enabling autonomous robots to rapidly adapt in dynamic and uncertain environments. Classic adaptive control and safe control provide stability and safety guarantees but are limited to specific system classes. In contrast, policy adaptation based on reinforcement learning (RL) offers versatility and generalizability but presents safety and robustness challenges. We propose SafeDPA, a novel RL and control framework that simultaneously tackles the problems of policy adaptation and safe reinforcement learning. SafeDPA jointly learns adapti"},"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":"2310.08602","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-08T00:32:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"64c829df0983da253c062343e67498e0625913f60e9b0ad12880e031884d682f","abstract_canon_sha256":"b4b6d8d0133420d937b14f8c7a80c4fcbc13d8a42f507d4167be3ae55b420607"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:45.419847Z","signature_b64":"ok4l0BuxE8MfmNPx8PBRXGEXWqy9007ty2WFITGJOaJKzrtHT1edtcaEZAqsrb0cgWUdtXzSJ/wHNRbtrx/TDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65cc54f53db6a2c2d01808ad2671c0cafd58b43e07db5257c7a157787ad31ed7","last_reissued_at":"2026-07-05T08:12:45.419385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:45.419385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Deep Policy Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Guanya Shi, John Dolan, Tairan He, Wenli Xiao","submitted_at":"2023-10-08T00:32:59Z","abstract_excerpt":"A critical goal of autonomy and artificial intelligence is enabling autonomous robots to rapidly adapt in dynamic and uncertain environments. Classic adaptive control and safe control provide stability and safety guarantees but are limited to specific system classes. In contrast, policy adaptation based on reinforcement learning (RL) offers versatility and generalizability but presents safety and robustness challenges. We propose SafeDPA, a novel RL and control framework that simultaneously tackles the problems of policy adaptation and safe reinforcement learning. SafeDPA jointly learns adapti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08602","kind":"arxiv","version":3},"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/2310.08602/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":"2310.08602","created_at":"2026-07-05T08:12:45.419436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08602v3","created_at":"2026-07-05T08:12:45.419436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08602","created_at":"2026-07-05T08:12:45.419436+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXGFJ5J5W2RM","created_at":"2026-07-05T08:12:45.419436+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXGFJ5J5W2RMFUAY","created_at":"2026-07-05T08:12:45.419436+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXGFJ5J5","created_at":"2026-07-05T08:12:45.419436+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/MXGFJ5J5W2RMFUAYBCWSM4OAZL","json":"https://pith.science/pith/MXGFJ5J5W2RMFUAYBCWSM4OAZL.json","graph_json":"https://pith.science/api/pith-number/MXGFJ5J5W2RMFUAYBCWSM4OAZL/graph.json","events_json":"https://pith.science/api/pith-number/MXGFJ5J5W2RMFUAYBCWSM4OAZL/events.json","paper":"https://pith.science/paper/MXGFJ5J5"},"agent_actions":{"view_html":"https://pith.science/pith/MXGFJ5J5W2RMFUAYBCWSM4OAZL","download_json":"https://pith.science/pith/MXGFJ5J5W2RMFUAYBCWSM4OAZL.json","view_paper":"https://pith.science/paper/MXGFJ5J5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08602&json=true","fetch_graph":"https://pith.science/api/pith-number/MXGFJ5J5W2RMFUAYBCWSM4OAZL/graph.json","fetch_events":"https://pith.science/api/pith-number/MXGFJ5J5W2RMFUAYBCWSM4OAZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXGFJ5J5W2RMFUAYBCWSM4OAZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXGFJ5J5W2RMFUAYBCWSM4OAZL/action/storage_attestation","attest_author":"https://pith.science/pith/MXGFJ5J5W2RMFUAYBCWSM4OAZL/action/author_attestation","sign_citation":"https://pith.science/pith/MXGFJ5J5W2RMFUAYBCWSM4OAZL/action/citation_signature","submit_replication":"https://pith.science/pith/MXGFJ5J5W2RMFUAYBCWSM4OAZL/action/replication_record"}},"created_at":"2026-07-05T08:12:45.419436+00:00","updated_at":"2026-07-05T08:12:45.419436+00:00"}