{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3JMJWM3KAJFBQQ7J5W2GXZ6NCI","short_pith_number":"pith:3JMJWM3K","schema_version":"1.0","canonical_sha256":"da589b336a024a1843e9edb46be7cd121e38c83bece0db7b9565c3b238544982","source":{"kind":"arxiv","id":"2404.07099","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christian Schroeder de Witt, Jakob Foerster, Kai Sandbrink, Linas Nasvytis, Tim Franzmeyer","submitted_at":"2024-04-10T15:39:49Z","abstract_excerpt":"While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environments remains a significant concern. In this paper, we study the problem of out-of-distribution (OOD) detection in RL, which focuses on identifying situations at test time that RL agents have not encountered in their training environments. We first propose a clarification of terminology for OOD detection in RL, which aligns it with the literature from other machine learning domains. We then present new benchmark scena"},"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":"2404.07099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-10T15:39:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61b542263ff7810f615f2fe1f9c79826d64b67ee1e10552233cde5a439852e89","abstract_canon_sha256":"059f3bc78243870f9ec173b8c6c7dc5261e36ccd4665ff877b119c9857c3d6ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:35.233685Z","signature_b64":"JYcXjJNuJg3FeeidrilfacSpR7HyrHeeEBGlnN6elnQNvIemVASU/6ITautxVj4uL00yKdVgrsTkda+29gkhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da589b336a024a1843e9edb46be7cd121e38c83bece0db7b9565c3b238544982","last_reissued_at":"2026-07-05T08:06:35.233175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:35.233175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christian Schroeder de Witt, Jakob Foerster, Kai Sandbrink, Linas Nasvytis, Tim Franzmeyer","submitted_at":"2024-04-10T15:39:49Z","abstract_excerpt":"While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environments remains a significant concern. In this paper, we study the problem of out-of-distribution (OOD) detection in RL, which focuses on identifying situations at test time that RL agents have not encountered in their training environments. We first propose a clarification of terminology for OOD detection in RL, which aligns it with the literature from other machine learning domains. We then present new benchmark scena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07099","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/2404.07099/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":"2404.07099","created_at":"2026-07-05T08:06:35.233234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07099v1","created_at":"2026-07-05T08:06:35.233234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07099","created_at":"2026-07-05T08:06:35.233234+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JMJWM3KAJFB","created_at":"2026-07-05T08:06:35.233234+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JMJWM3KAJFBQQ7J","created_at":"2026-07-05T08:06:35.233234+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JMJWM3K","created_at":"2026-07-05T08:06:35.233234+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11474","citing_title":"Mahalanobis-Guided Latent OOD Detection for Hybrid ES-DRL Control in Time-Varying Systems","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27411","citing_title":"Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI","json":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI.json","graph_json":"https://pith.science/api/pith-number/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/graph.json","events_json":"https://pith.science/api/pith-number/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/events.json","paper":"https://pith.science/paper/3JMJWM3K"},"agent_actions":{"view_html":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI","download_json":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI.json","view_paper":"https://pith.science/paper/3JMJWM3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07099&json=true","fetch_graph":"https://pith.science/api/pith-number/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/graph.json","fetch_events":"https://pith.science/api/pith-number/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/action/storage_attestation","attest_author":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/action/author_attestation","sign_citation":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/action/citation_signature","submit_replication":"https://pith.science/pith/3JMJWM3KAJFBQQ7J5W2GXZ6NCI/action/replication_record"}},"created_at":"2026-07-05T08:06:35.233234+00:00","updated_at":"2026-07-05T08:06:35.233234+00:00"}