{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P54VRD2A6UTZ5PIQ55IEV46JXY","short_pith_number":"pith:P54VRD2A","schema_version":"1.0","canonical_sha256":"7f79588f40f5279ebd10ef504af3c9be3972f2844cd706eafa57260c0c12baed","source":{"kind":"arxiv","id":"2403.18539","version":2},"attestation_state":"computed","paper":{"title":"Safe and Robust Reinforcement Learning: Principles and Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Raul Santos-Rodriguez, Taku Yamagata","submitted_at":"2024-03-27T13:14:29Z","abstract_excerpt":"Reinforcement Learning (RL) has shown remarkable success in solving relatively complex tasks, yet the deployment of RL systems in real-world scenarios poses significant challenges related to safety and robustness. This paper aims to identify and further understand those challenges thorough the exploration of the main dimensions of the safe and robust RL landscape, encompassing algorithmic, ethical, and practical considerations. We conduct a comprehensive review of methodologies and open problems that summarizes the efforts in recent years to address the inherent risks associated with RL applic"},"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":"2403.18539","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T13:14:29Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"7d2e2106c6fe67537e4654e93740bd08a92277bc8babbeac59895057b16aeac2","abstract_canon_sha256":"20e443d7141923a22fd0427ba80a08b01d53e7a11d3f55a905f915d480cccb6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:26.077740Z","signature_b64":"VzfQOlZLMxBxb2+62ehP8osqW5J4m12I+jf64PwrSQZKyOrtJXawMzA07fWBHhwQygQl4nLJlhAtS+lCm5onAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f79588f40f5279ebd10ef504af3c9be3972f2844cd706eafa57260c0c12baed","last_reissued_at":"2026-07-05T08:02:26.077125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:26.077125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe and Robust Reinforcement Learning: Principles and Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Raul Santos-Rodriguez, Taku Yamagata","submitted_at":"2024-03-27T13:14:29Z","abstract_excerpt":"Reinforcement Learning (RL) has shown remarkable success in solving relatively complex tasks, yet the deployment of RL systems in real-world scenarios poses significant challenges related to safety and robustness. This paper aims to identify and further understand those challenges thorough the exploration of the main dimensions of the safe and robust RL landscape, encompassing algorithmic, ethical, and practical considerations. We conduct a comprehensive review of methodologies and open problems that summarizes the efforts in recent years to address the inherent risks associated with RL applic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18539","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/2403.18539/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":"2403.18539","created_at":"2026-07-05T08:02:26.077282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18539v2","created_at":"2026-07-05T08:02:26.077282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18539","created_at":"2026-07-05T08:02:26.077282+00:00"},{"alias_kind":"pith_short_12","alias_value":"P54VRD2A6UTZ","created_at":"2026-07-05T08:02:26.077282+00:00"},{"alias_kind":"pith_short_16","alias_value":"P54VRD2A6UTZ5PIQ","created_at":"2026-07-05T08:02:26.077282+00:00"},{"alias_kind":"pith_short_8","alias_value":"P54VRD2A","created_at":"2026-07-05T08:02:26.077282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24345","citing_title":"Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY","json":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY.json","graph_json":"https://pith.science/api/pith-number/P54VRD2A6UTZ5PIQ55IEV46JXY/graph.json","events_json":"https://pith.science/api/pith-number/P54VRD2A6UTZ5PIQ55IEV46JXY/events.json","paper":"https://pith.science/paper/P54VRD2A"},"agent_actions":{"view_html":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY","download_json":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY.json","view_paper":"https://pith.science/paper/P54VRD2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18539&json=true","fetch_graph":"https://pith.science/api/pith-number/P54VRD2A6UTZ5PIQ55IEV46JXY/graph.json","fetch_events":"https://pith.science/api/pith-number/P54VRD2A6UTZ5PIQ55IEV46JXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY/action/storage_attestation","attest_author":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY/action/author_attestation","sign_citation":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY/action/citation_signature","submit_replication":"https://pith.science/pith/P54VRD2A6UTZ5PIQ55IEV46JXY/action/replication_record"}},"created_at":"2026-07-05T08:02:26.077282+00:00","updated_at":"2026-07-05T08:02:26.077282+00:00"}