{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5WE5E65ATXUTIODUNR3IB7AKIL","short_pith_number":"pith:5WE5E65A","canonical_record":{"source":{"id":"2406.09976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T12:37:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"274cd9978ea2f5e623396cdf88382e5bfe0a8f86bcdb4e19fdc7323bf1cae555","abstract_canon_sha256":"41d04bab55ff3eacd1a90d6fc5178d2530d3698634794ec250325f61451bdeef"},"schema_version":"1.0"},"canonical_sha256":"ed89d27ba09de93438746c7680fc0a42c6fba9100db808b043fc9e0cc942c3d6","source":{"kind":"arxiv","id":"2406.09976","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09976","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09976v2","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09976","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"5WE5E65ATXUT","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"5WE5E65ATXUTIODU","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"5WE5E65A","created_at":"2026-07-05T08:38:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5WE5E65ATXUTIODUNR3IB7AKIL","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T12:37:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"274cd9978ea2f5e623396cdf88382e5bfe0a8f86bcdb4e19fdc7323bf1cae555","abstract_canon_sha256":"41d04bab55ff3eacd1a90d6fc5178d2530d3698634794ec250325f61451bdeef"},"schema_version":"1.0"},"canonical_sha256":"ed89d27ba09de93438746c7680fc0a42c6fba9100db808b043fc9e0cc942c3d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:38.664741Z","signature_b64":"AHptIEUcveUnUTmwPYunUEQkZE1Qx8BSS5YkIz1FdCfwn87A7JJXmwpziRx7o/fspV4Qynf75M2A882Xf/q9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed89d27ba09de93438746c7680fc0a42c6fba9100db808b043fc9e0cc942c3d6","last_reissued_at":"2026-07-05T08:38:38.664113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:38.664113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09976","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:38:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20wf+nuOFj6rx/NbCc6S8lf7xf0Z+boB+XNqt9aT6tJxBmkwmI8pjTiZgVg8oTcntReg74y8XxgiEs5Pg/w5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:48:24.407582Z"},"content_sha256":"e1b387729941eecc87c66ac317af3b89812dc939d0ee560e7dd1f3c9f9e6439c","schema_version":"1.0","event_id":"sha256:e1b387729941eecc87c66ac317af3b89812dc939d0ee560e7dd1f3c9f9e6439c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5WE5E65ATXUTIODUNR3IB7AKIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","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":"2024-06-14T12:37:08Z","abstract_excerpt":"Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09976","kind":"arxiv","version":2},"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/2406.09976/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":"2026-07-05T08:38:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mm/T+yDE9qxu7MaPtzjmIt8yHcXCrtbFrM2Dapsz6XBtC9J9wmO1Z2tbD7AOUft9svWQEXxohQ060hXBM56cAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:48:24.408683Z"},"content_sha256":"1cda08eb8915722cc7bfe6668c206019c248c12e22cf0cb18b32d6c85ca75360","schema_version":"1.0","event_id":"sha256:1cda08eb8915722cc7bfe6668c206019c248c12e22cf0cb18b32d6c85ca75360"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/bundle.json","state_url":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WE5E65ATXUTIODUNR3IB7AKIL/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":"2026-08-07T19:48:24Z","links":{"resolver":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL","bundle":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/bundle.json","state":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WE5E65ATXUTIODUNR3IB7AKIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5WE5E65ATXUTIODUNR3IB7AKIL","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":"41d04bab55ff3eacd1a90d6fc5178d2530d3698634794ec250325f61451bdeef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T12:37:08Z","title_canon_sha256":"274cd9978ea2f5e623396cdf88382e5bfe0a8f86bcdb4e19fdc7323bf1cae555"},"schema_version":"1.0","source":{"id":"2406.09976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09976","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09976v2","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09976","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"5WE5E65ATXUT","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"5WE5E65ATXUTIODU","created_at":"2026-07-05T08:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"5WE5E65A","created_at":"2026-07-05T08:38:38Z"}],"graph_snapshots":[{"event_id":"sha256:1cda08eb8915722cc7bfe6668c206019c248c12e22cf0cb18b32d6c85ca75360","target":"graph","created_at":"2026-07-05T08:38:38Z","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/2406.09976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an a","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":"2024-06-14T12:37:08Z","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09976","kind":"arxiv","version":2},"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:e1b387729941eecc87c66ac317af3b89812dc939d0ee560e7dd1f3c9f9e6439c","target":"record","created_at":"2026-07-05T08:38:38Z","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":"41d04bab55ff3eacd1a90d6fc5178d2530d3698634794ec250325f61451bdeef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T12:37:08Z","title_canon_sha256":"274cd9978ea2f5e623396cdf88382e5bfe0a8f86bcdb4e19fdc7323bf1cae555"},"schema_version":"1.0","source":{"id":"2406.09976","kind":"arxiv","version":2}},"canonical_sha256":"ed89d27ba09de93438746c7680fc0a42c6fba9100db808b043fc9e0cc942c3d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed89d27ba09de93438746c7680fc0a42c6fba9100db808b043fc9e0cc942c3d6","first_computed_at":"2026-07-05T08:38:38.664113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:38.664113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AHptIEUcveUnUTmwPYunUEQkZE1Qx8BSS5YkIz1FdCfwn87A7JJXmwpziRx7o/fspV4Qynf75M2A882Xf/q9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:38.664741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1b387729941eecc87c66ac317af3b89812dc939d0ee560e7dd1f3c9f9e6439c","sha256:1cda08eb8915722cc7bfe6668c206019c248c12e22cf0cb18b32d6c85ca75360"],"state_sha256":"20182d9206a65a68a7aa77e59da691cd0e133ad30c0def1655c5f7c4bbd393cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5T9Pn9JBZ1PNemGmpL0+zzeYmTy71mpyACRNlpUfzprYTYgfjji6btNhYCoW9C2z7fKIvyV3H4TPE1Ih0OWkDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:48:24.416108Z","bundle_sha256":"cfde06157438cea2457cd0a69cda96d4ae5f3650d3d1d05dcd74c2dd9a4517aa"}}