{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MS6TQZPBQCEPD5XVWR725C2WKQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b5758c1e1eea0c3fcb4df2d13d3cf9fe11b11b10cd1b144a65fe6649e5aa140d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T11:43:13Z","title_canon_sha256":"feff7af8956fe49cd3d894e52e86b8f64c526d191e33fc118edae223a2780952"},"schema_version":"1.0","source":{"id":"2606.03521","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03521","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03521v1","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03521","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"MS6TQZPBQCEP","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"MS6TQZPBQCEPD5XV","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"MS6TQZPB","created_at":"2026-06-03T01:05:59Z"}],"graph_snapshots":[{"event_id":"sha256:8de5438b7c9a070bbdef49a8fc0fd62f7bc349fa74004ac77ea1fbb8cc5d752d","target":"graph","created_at":"2026-06-03T01:05:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.03521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ali Anwar, Siegfried Mercelis, Siemen Herremans","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T11:43:13Z","title":"Post-Hoc Robustness for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03521","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b622304170b530413cc788976ca0a01b71f4f49ce54f96174c27dffd9ecdccb6","target":"record","created_at":"2026-06-03T01:05:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b5758c1e1eea0c3fcb4df2d13d3cf9fe11b11b10cd1b144a65fe6649e5aa140d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T11:43:13Z","title_canon_sha256":"feff7af8956fe49cd3d894e52e86b8f64c526d191e33fc118edae223a2780952"},"schema_version":"1.0","source":{"id":"2606.03521","kind":"arxiv","version":1}},"canonical_sha256":"64bd3865e18088f1f6f5b47fae8b56541742ca20cabd97ea8c40c68a24edaf1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64bd3865e18088f1f6f5b47fae8b56541742ca20cabd97ea8c40c68a24edaf1f","first_computed_at":"2026-06-03T01:05:59.899487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:59.899487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PDfjRee/nHhwbqlJMbg51Hx45tIOGgtR5r0B7YAlwe3bTYfUTJ6easgw71uRU7JXHBe55vkmp87nlmvmnJ7WAA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:59.899853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03521","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b622304170b530413cc788976ca0a01b71f4f49ce54f96174c27dffd9ecdccb6","sha256:8de5438b7c9a070bbdef49a8fc0fd62f7bc349fa74004ac77ea1fbb8cc5d752d"],"state_sha256":"d37833ed78705b639117632c47fa7d18095d0ad4264259c89aa43d594a13681c"}