{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KWILOZRSQDIOVTXI5SGXPZBY4Z","short_pith_number":"pith:KWILOZRS","schema_version":"1.0","canonical_sha256":"5590b7663280d0eacee8ec8d77e438e6770eb9db1e3c90a385c01d78bf0e30e5","source":{"kind":"arxiv","id":"2507.06111","version":1},"attestation_state":"computed","paper":{"title":"Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Hsiu-Chin Lin, Joelle Pineau, Maxime Wabartha, Mohamad H. Danesh, Stanley Wu","submitted_at":"2025-07-08T15:51:57Z","abstract_excerpt":"Deploying reinforcement learning (RL) policies in real-world involves significant challenges, including distribution shifts, safety concerns, and the impracticality of direct interactions during policy refinement. Existing methods, such as domain randomization (DR) and off-dynamics RL, enhance policy robustness by direct interaction with the target domain, an inherently unsafe practice. We propose Uncertainty-Aware RL (UARL), a novel framework that prioritizes safety during training by addressing Out-Of-Distribution (OOD) detection and policy adaptation without requiring direct interactions in"},"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":"2507.06111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-08T15:51:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5132b4ef923741c429f73aedd51fd89303b33b9367baefcdb82d1c07649e379b","abstract_canon_sha256":"b16a908b89f1a54393ac3d80b53fe6e664696fdccf0b7d41bc51ff21663ec243"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:41.365986Z","signature_b64":"vqBvbn5n9pS/aTCd0b/dhcINwLbLAlIM9kCDXI9evhg+77PpOCZZeOdGkrGmgf4rcI+uzOKU2wFIOGT/YRulCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5590b7663280d0eacee8ec8d77e438e6770eb9db1e3c90a385c01d78bf0e30e5","last_reissued_at":"2026-07-05T11:33:41.365540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:41.365540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Domain Randomization via Uncertainty-Aware Out-of-Distribution Detection and Policy Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Hsiu-Chin Lin, Joelle Pineau, Maxime Wabartha, Mohamad H. Danesh, Stanley Wu","submitted_at":"2025-07-08T15:51:57Z","abstract_excerpt":"Deploying reinforcement learning (RL) policies in real-world involves significant challenges, including distribution shifts, safety concerns, and the impracticality of direct interactions during policy refinement. Existing methods, such as domain randomization (DR) and off-dynamics RL, enhance policy robustness by direct interaction with the target domain, an inherently unsafe practice. We propose Uncertainty-Aware RL (UARL), a novel framework that prioritizes safety during training by addressing Out-Of-Distribution (OOD) detection and policy adaptation without requiring direct interactions in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06111","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/2507.06111/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":"2507.06111","created_at":"2026-07-05T11:33:41.365596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06111v1","created_at":"2026-07-05T11:33:41.365596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06111","created_at":"2026-07-05T11:33:41.365596+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWILOZRSQDIO","created_at":"2026-07-05T11:33:41.365596+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWILOZRSQDIOVTXI","created_at":"2026-07-05T11:33:41.365596+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWILOZRS","created_at":"2026-07-05T11:33:41.365596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00350","citing_title":"Drift Q-Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08780","citing_title":"Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal Locomotion","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z","json":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z.json","graph_json":"https://pith.science/api/pith-number/KWILOZRSQDIOVTXI5SGXPZBY4Z/graph.json","events_json":"https://pith.science/api/pith-number/KWILOZRSQDIOVTXI5SGXPZBY4Z/events.json","paper":"https://pith.science/paper/KWILOZRS"},"agent_actions":{"view_html":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z","download_json":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z.json","view_paper":"https://pith.science/paper/KWILOZRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06111&json=true","fetch_graph":"https://pith.science/api/pith-number/KWILOZRSQDIOVTXI5SGXPZBY4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/KWILOZRSQDIOVTXI5SGXPZBY4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z/action/storage_attestation","attest_author":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z/action/author_attestation","sign_citation":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z/action/citation_signature","submit_replication":"https://pith.science/pith/KWILOZRSQDIOVTXI5SGXPZBY4Z/action/replication_record"}},"created_at":"2026-07-05T11:33:41.365596+00:00","updated_at":"2026-07-05T11:33:41.365596+00:00"}