{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DPITD4FPCLLHYYTNXJ5FIL3GAA","short_pith_number":"pith:DPITD4FP","schema_version":"1.0","canonical_sha256":"1bd131f0af12d67c626dba7a542f660029ae215c3ad99a10ae0eb1a0723e1616","source":{"kind":"arxiv","id":"2410.07359","version":1},"attestation_state":"computed","paper":{"title":"Learning-Based Shielding for Safe Autonomy under Unknown Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Morteza Lahijanian, Robert Reed","submitted_at":"2024-10-07T16:10:15Z","abstract_excerpt":"Shielding is a common method used to guarantee the safety of a system under a black-box controller, such as a neural network controller from deep reinforcement learning (DRL), with simpler, verified controllers. Existing shielding methods rely on formal verification through Markov Decision Processes (MDPs), assuming either known or finite-state models, which limits their applicability to DRL settings with unknown, continuous-state systems. This paper addresses these limitations by proposing a data-driven shielding methodology that guarantees safety for unknown systems under black-box controlle"},"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":"2410.07359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2024-10-07T16:10:15Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"228508e3641014a9e1e91e713090904c30a5bfb5e3b0860876387600cdd69827","abstract_canon_sha256":"96dc781ee8919c6a240e25ffdf4970bb8a31a19dd071a776e7a57978a95e66be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:35.122127Z","signature_b64":"X2gVTQ2iwnEzovkMDApnLyDdcyiT4FRLpgy8DCKl2wKI/j9LQYdv4sF0roMgwS41nSm6B1hA4JeJylK9gMYwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd131f0af12d67c626dba7a542f660029ae215c3ad99a10ae0eb1a0723e1616","last_reissued_at":"2026-07-05T09:18:35.121579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:35.121579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning-Based Shielding for Safe Autonomy under Unknown Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Morteza Lahijanian, Robert Reed","submitted_at":"2024-10-07T16:10:15Z","abstract_excerpt":"Shielding is a common method used to guarantee the safety of a system under a black-box controller, such as a neural network controller from deep reinforcement learning (DRL), with simpler, verified controllers. Existing shielding methods rely on formal verification through Markov Decision Processes (MDPs), assuming either known or finite-state models, which limits their applicability to DRL settings with unknown, continuous-state systems. This paper addresses these limitations by proposing a data-driven shielding methodology that guarantees safety for unknown systems under black-box controlle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07359","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/2410.07359/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":"2410.07359","created_at":"2026-07-05T09:18:35.121637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07359v1","created_at":"2026-07-05T09:18:35.121637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07359","created_at":"2026-07-05T09:18:35.121637+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPITD4FPCLLH","created_at":"2026-07-05T09:18:35.121637+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPITD4FPCLLHYYTN","created_at":"2026-07-05T09:18:35.121637+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPITD4FP","created_at":"2026-07-05T09:18:35.121637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17703","citing_title":"Piecewise Control Barrier Functions for Stochastic Systems","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA","json":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA.json","graph_json":"https://pith.science/api/pith-number/DPITD4FPCLLHYYTNXJ5FIL3GAA/graph.json","events_json":"https://pith.science/api/pith-number/DPITD4FPCLLHYYTNXJ5FIL3GAA/events.json","paper":"https://pith.science/paper/DPITD4FP"},"agent_actions":{"view_html":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA","download_json":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA.json","view_paper":"https://pith.science/paper/DPITD4FP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07359&json=true","fetch_graph":"https://pith.science/api/pith-number/DPITD4FPCLLHYYTNXJ5FIL3GAA/graph.json","fetch_events":"https://pith.science/api/pith-number/DPITD4FPCLLHYYTNXJ5FIL3GAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA/action/storage_attestation","attest_author":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA/action/author_attestation","sign_citation":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA/action/citation_signature","submit_replication":"https://pith.science/pith/DPITD4FPCLLHYYTNXJ5FIL3GAA/action/replication_record"}},"created_at":"2026-07-05T09:18:35.121637+00:00","updated_at":"2026-07-05T09:18:35.121637+00:00"}