{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7ZVER5GZEL7JJBLJUQMRVPQHCK","short_pith_number":"pith:7ZVER5GZ","schema_version":"1.0","canonical_sha256":"fe6a48f4d922fe948569a4191abe0712a495032b12dd52be977b3b98462868a6","source":{"kind":"arxiv","id":"2412.19311","version":1},"attestation_state":"computed","paper":{"title":"xSRL: Safety-Aware Explainable Reinforcement Learning -- Safety as a Product of Explainability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Md Asifur Rahman, Risal Shahriar Shefin, Sarra Alqahtani, Thai Le","submitted_at":"2024-12-26T18:19:04Z","abstract_excerpt":"Reinforcement learning (RL) has shown great promise in simulated environments, such as games, where failures have minimal consequences. However, the deployment of RL agents in real-world systems such as autonomous vehicles, robotics, UAVs, and medical devices demands a higher level of safety and transparency, particularly when facing adversarial threats. Safe RL algorithms have been developed to address these concerns by optimizing both task performance and safety constraints. However, errors are inevitable, and when they occur, it is essential that the RL agents can also explain their actions"},"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":"2412.19311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-26T18:19:04Z","cross_cats_sorted":["cs.HC","cs.LG","cs.MA"],"title_canon_sha256":"01d7695ad25955aefa15511a7fe6920cf9e2476aef8264e503965b3e1d3862eb","abstract_canon_sha256":"61947b668c8a5ebd919d7ead657bb5d72be30133f9d85f1e5bb45610481074f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:33.768540Z","signature_b64":"mRC28B8rCBbrRdLzdVYKX33dnMuV5Z5+1mX/mjZ+tUirwneYXgyeTXXhwWR7z9ocZ3wPZEARKGCUPbmVezQoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe6a48f4d922fe948569a4191abe0712a495032b12dd52be977b3b98462868a6","last_reissued_at":"2026-07-05T09:54:33.767927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:33.767927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"xSRL: Safety-Aware Explainable Reinforcement Learning -- Safety as a Product of Explainability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Md Asifur Rahman, Risal Shahriar Shefin, Sarra Alqahtani, Thai Le","submitted_at":"2024-12-26T18:19:04Z","abstract_excerpt":"Reinforcement learning (RL) has shown great promise in simulated environments, such as games, where failures have minimal consequences. However, the deployment of RL agents in real-world systems such as autonomous vehicles, robotics, UAVs, and medical devices demands a higher level of safety and transparency, particularly when facing adversarial threats. Safe RL algorithms have been developed to address these concerns by optimizing both task performance and safety constraints. However, errors are inevitable, and when they occur, it is essential that the RL agents can also explain their actions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19311","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/2412.19311/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":"2412.19311","created_at":"2026-07-05T09:54:33.768010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19311v1","created_at":"2026-07-05T09:54:33.768010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19311","created_at":"2026-07-05T09:54:33.768010+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZVER5GZEL7J","created_at":"2026-07-05T09:54:33.768010+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZVER5GZEL7JJBLJ","created_at":"2026-07-05T09:54:33.768010+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZVER5GZ","created_at":"2026-07-05T09:54:33.768010+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/7ZVER5GZEL7JJBLJUQMRVPQHCK","json":"https://pith.science/pith/7ZVER5GZEL7JJBLJUQMRVPQHCK.json","graph_json":"https://pith.science/api/pith-number/7ZVER5GZEL7JJBLJUQMRVPQHCK/graph.json","events_json":"https://pith.science/api/pith-number/7ZVER5GZEL7JJBLJUQMRVPQHCK/events.json","paper":"https://pith.science/paper/7ZVER5GZ"},"agent_actions":{"view_html":"https://pith.science/pith/7ZVER5GZEL7JJBLJUQMRVPQHCK","download_json":"https://pith.science/pith/7ZVER5GZEL7JJBLJUQMRVPQHCK.json","view_paper":"https://pith.science/paper/7ZVER5GZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19311&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZVER5GZEL7JJBLJUQMRVPQHCK/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZVER5GZEL7JJBLJUQMRVPQHCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZVER5GZEL7JJBLJUQMRVPQHCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZVER5GZEL7JJBLJUQMRVPQHCK/action/storage_attestation","attest_author":"https://pith.science/pith/7ZVER5GZEL7JJBLJUQMRVPQHCK/action/author_attestation","sign_citation":"https://pith.science/pith/7ZVER5GZEL7JJBLJUQMRVPQHCK/action/citation_signature","submit_replication":"https://pith.science/pith/7ZVER5GZEL7JJBLJUQMRVPQHCK/action/replication_record"}},"created_at":"2026-07-05T09:54:33.768010+00:00","updated_at":"2026-07-05T09:54:33.768010+00:00"}