{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MS6TQZPBQCEPD5XVWR725C2WKQ","short_pith_number":"pith:MS6TQZPB","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"},"canonical_sha256":"64bd3865e18088f1f6f5b47fae8b56541742ca20cabd97ea8c40c68a24edaf1f","source":{"kind":"arxiv","id":"2606.03521","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MS6TQZPBQCEPD5XVWR725C2WKQ","target":"record","payload":{"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"},"canonical_sha256":"64bd3865e18088f1f6f5b47fae8b56541742ca20cabd97ea8c40c68a24edaf1f","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"},"source_kind":"arxiv","source_id":"2606.03521","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqtBp2REV+waiNYOhgxEzF+D4WY3RiWcvCJ5067S8Ix3U7EyZZH/kWSjc4X3M/c4EKsHB7SLZzmK8QBHiCE1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T03:38:14.802056Z"},"content_sha256":"b622304170b530413cc788976ca0a01b71f4f49ce54f96174c27dffd9ecdccb6","schema_version":"1.0","event_id":"sha256:b622304170b530413cc788976ca0a01b71f4f49ce54f96174c27dffd9ecdccb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MS6TQZPBQCEPD5XVWR725C2WKQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZLZJkV1Wb7qCaj/CpljI2SQuJtFD420QkmenUjKDoPswpwbfY8sOg0D6dCD2nAnmrbri3GmJYy5Zna7bk+3/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T03:38:14.802710Z"},"content_sha256":"8de5438b7c9a070bbdef49a8fc0fd62f7bc349fa74004ac77ea1fbb8cc5d752d","schema_version":"1.0","event_id":"sha256:8de5438b7c9a070bbdef49a8fc0fd62f7bc349fa74004ac77ea1fbb8cc5d752d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/bundle.json","state_url":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T03:38:14Z","links":{"resolver":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ","bundle":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/bundle.json","state":"https://pith.science/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MS6TQZPBQCEPD5XVWR725C2WKQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d0LTheHM2R7WjWngjouun10kjKaaxRqpf+hnvR0s2yHaOYOGVNjV9l9m/7CcJxO8ZAVRMKsxDHjH7BTXN1dIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T03:38:14.806074Z","bundle_sha256":"522a85b955806332aa1f28e92263d775f32e76e50b6a834a9a702d059276580c"}}