{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MS6TQZPBQCEPD5XVWR725C2WKQ","short_pith_number":"pith:MS6TQZPB","schema_version":"1.0","canonical_sha256":"64bd3865e18088f1f6f5b47fae8b56541742ca20cabd97ea8c40c68a24edaf1f","source":{"kind":"arxiv","id":"2606.03521","version":1},"attestation_state":"computed","paper":{"title":"Post-Hoc Robustness for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Anwar, Siegfried Mercelis, Siemen Herremans","submitted_at":"2026-06-02T11:43:13Z","abstract_excerpt":"To improve the real-world applicability of reinforcement learning (RL), the field of adversarially robust RL studies how to train agents under adversarial environment perturbations. In this setting, a protagonist agent optimizes a policy under environmental perturbations from an adversary, resulting in a zero-sum Markov game. When adversarially robust RL is combined with model-based RL, the adversary can target a learned transition model instead of the training environment. Extending this idea, this work introduces post-hoc robustification of deep RL agents at inference time. By using the lear"},"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":"2606.03521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T11:43:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"feff7af8956fe49cd3d894e52e86b8f64c526d191e33fc118edae223a2780952","abstract_canon_sha256":"b5758c1e1eea0c3fcb4df2d13d3cf9fe11b11b10cd1b144a65fe6649e5aa140d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:59.899853Z","signature_b64":"PDfjRee/nHhwbqlJMbg51Hx45tIOGgtR5r0B7YAlwe3bTYfUTJ6easgw71uRU7JXHBe55vkmp87nlmvmnJ7WAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64bd3865e18088f1f6f5b47fae8b56541742ca20cabd97ea8c40c68a24edaf1f","last_reissued_at":"2026-06-03T01:05:59.899487Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:59.899487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Post-Hoc Robustness for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Anwar, Siegfried Mercelis, Siemen Herremans","submitted_at":"2026-06-02T11:43:13Z","abstract_excerpt":"To improve the real-world applicability of reinforcement learning (RL), the field of adversarially robust RL studies how to train agents under adversarial environment perturbations. In this setting, a protagonist agent optimizes a policy under environmental perturbations from an adversary, resulting in a zero-sum Markov game. When adversarially robust RL is combined with model-based RL, the adversary can target a learned transition model instead of the training environment. Extending this idea, this work introduces post-hoc robustification of deep RL agents at inference time. By using the lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03521","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/2606.03521/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":"2606.03521","created_at":"2026-06-03T01:05:59.899541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03521v1","created_at":"2026-06-03T01:05:59.899541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03521","created_at":"2026-06-03T01:05:59.899541+00:00"},{"alias_kind":"pith_short_12","alias_value":"MS6TQZPBQCEP","created_at":"2026-06-03T01:05:59.899541+00:00"},{"alias_kind":"pith_short_16","alias_value":"MS6TQZPBQCEPD5XV","created_at":"2026-06-03T01:05:59.899541+00:00"},{"alias_kind":"pith_short_8","alias_value":"MS6TQZPB","created_at":"2026-06-03T01:05:59.899541+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/MS6TQZPBQCEPD5XVWR725C2WKQ","json":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ.json","graph_json":"https://pith.science/api/pith-number/MS6TQZPBQCEPD5XVWR725C2WKQ/graph.json","events_json":"https://pith.science/api/pith-number/MS6TQZPBQCEPD5XVWR725C2WKQ/events.json","paper":"https://pith.science/paper/MS6TQZPB"},"agent_actions":{"view_html":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ","download_json":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ.json","view_paper":"https://pith.science/paper/MS6TQZPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03521&json=true","fetch_graph":"https://pith.science/api/pith-number/MS6TQZPBQCEPD5XVWR725C2WKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MS6TQZPBQCEPD5XVWR725C2WKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/action/storage_attestation","attest_author":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/action/author_attestation","sign_citation":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/action/citation_signature","submit_replication":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/action/replication_record"}},"created_at":"2026-06-03T01:05:59.899541+00:00","updated_at":"2026-06-03T01:05:59.899541+00:00"}