{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Q3OMKDBF5UCMXSAHGGCI52EWXI","short_pith_number":"pith:Q3OMKDBF","canonical_record":{"source":{"id":"1811.06512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T18:18:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b7e4fcba72f1e6f9f757648d66277322289c139c81d6380748ccdd4b04003462","abstract_canon_sha256":"9d7385cd99e895d9072692b25a4c0f7f3d06bccb6752dfe41f11254e4544ec22"},"schema_version":"1.0"},"canonical_sha256":"86dcc50c25ed04cbc80731848ee896ba1e307362aa28f3ac2aa7725f3d25a635","source":{"kind":"arxiv","id":"1811.06512","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.06512","created_at":"2026-05-18T00:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"1811.06512v1","created_at":"2026-05-18T00:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06512","created_at":"2026-05-18T00:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"Q3OMKDBF5UCM","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q3OMKDBF5UCMXSAH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q3OMKDBF","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Q3OMKDBF5UCMXSAHGGCI52EWXI","target":"record","payload":{"canonical_record":{"source":{"id":"1811.06512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T18:18:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b7e4fcba72f1e6f9f757648d66277322289c139c81d6380748ccdd4b04003462","abstract_canon_sha256":"9d7385cd99e895d9072692b25a4c0f7f3d06bccb6752dfe41f11254e4544ec22"},"schema_version":"1.0"},"canonical_sha256":"86dcc50c25ed04cbc80731848ee896ba1e307362aa28f3ac2aa7725f3d25a635","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:37.562420Z","signature_b64":"rY08l+dz8WkY3hFghqNI/IfugEion58C6vhTDE2yF8XI/sGbKv11YAEvH9Tz26pH/9C2djQEksBJQ804059nBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86dcc50c25ed04cbc80731848ee896ba1e307362aa28f3ac2aa7725f3d25a635","last_reissued_at":"2026-05-18T00:00:37.561906Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:37.561906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.06512","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":"2026-05-18T00:00:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XRrXmsEFne9+etsiW29z32+mRPN9PUsZ5DxNmaUJMFPhT7MEPw+lQN7xMGEbPGmFFughVDgfvg8iGqDRazIKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:35:25.040972Z"},"content_sha256":"2741cfedb24f44c741e4bf143ec30d42039c41422900dcd5f70b5b27b2a479ca","schema_version":"1.0","event_id":"sha256:2741cfedb24f44c741e4bf143ec30d42039c41422900dcd5f70b5b27b2a479ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Q3OMKDBF5UCMXSAHGGCI52EWXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tight Bayesian Ambiguity Sets for Robust MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marek Petrik, Reazul Hasan Russel","submitted_at":"2018-11-15T18:18:39Z","abstract_excerpt":"Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution is determined by its ambiguity set. Existing methods construct ambiguity sets that lead to impractically conservative solutions. In this paper, we propose RSVF, which achieves less conservative solutions with the same worst-case guarantees by 1) leveraging a Bayesian prior, 2) optimizi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06512","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":""},"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":"2026-05-18T00:00:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PmY8u5MWtP1lKTPPjYHxg6oSl+ZpFwzGQUuYUJC1DlYq+I3ozqbFFupz7JYLPa6x9Vn4aWftWAFmwglgrSP8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T11:35:25.041327Z"},"content_sha256":"d1e96ed2c40e4f77d27f46a17fd91a480d2d0f1ab1c94a699aae480da80d29a9","schema_version":"1.0","event_id":"sha256:d1e96ed2c40e4f77d27f46a17fd91a480d2d0f1ab1c94a699aae480da80d29a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3OMKDBF5UCMXSAHGGCI52EWXI/bundle.json","state_url":"https://pith.science/pith/Q3OMKDBF5UCMXSAHGGCI52EWXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3OMKDBF5UCMXSAHGGCI52EWXI/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":"2026-06-28T11:35:25Z","links":{"resolver":"https://pith.science/pith/Q3OMKDBF5UCMXSAHGGCI52EWXI","bundle":"https://pith.science/pith/Q3OMKDBF5UCMXSAHGGCI52EWXI/bundle.json","state":"https://pith.science/pith/Q3OMKDBF5UCMXSAHGGCI52EWXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3OMKDBF5UCMXSAHGGCI52EWXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Q3OMKDBF5UCMXSAHGGCI52EWXI","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":"9d7385cd99e895d9072692b25a4c0f7f3d06bccb6752dfe41f11254e4544ec22","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T18:18:39Z","title_canon_sha256":"b7e4fcba72f1e6f9f757648d66277322289c139c81d6380748ccdd4b04003462"},"schema_version":"1.0","source":{"id":"1811.06512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.06512","created_at":"2026-05-18T00:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"1811.06512v1","created_at":"2026-05-18T00:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06512","created_at":"2026-05-18T00:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"Q3OMKDBF5UCM","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q3OMKDBF5UCMXSAH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q3OMKDBF","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:d1e96ed2c40e4f77d27f46a17fd91a480d2d0f1ab1c94a699aae480da80d29a9","target":"graph","created_at":"2026-05-18T00:00:37Z","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"},"paper":{"abstract_excerpt":"Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution is determined by its ambiguity set. Existing methods construct ambiguity sets that lead to impractically conservative solutions. In this paper, we propose RSVF, which achieves less conservative solutions with the same worst-case guarantees by 1) leveraging a Bayesian prior, 2) optimizi","authors_text":"Marek Petrik, Reazul Hasan Russel","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T18:18:39Z","title":"Tight Bayesian Ambiguity Sets for Robust MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06512","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":"sha256:2741cfedb24f44c741e4bf143ec30d42039c41422900dcd5f70b5b27b2a479ca","target":"record","created_at":"2026-05-18T00:00:37Z","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":"9d7385cd99e895d9072692b25a4c0f7f3d06bccb6752dfe41f11254e4544ec22","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-15T18:18:39Z","title_canon_sha256":"b7e4fcba72f1e6f9f757648d66277322289c139c81d6380748ccdd4b04003462"},"schema_version":"1.0","source":{"id":"1811.06512","kind":"arxiv","version":1}},"canonical_sha256":"86dcc50c25ed04cbc80731848ee896ba1e307362aa28f3ac2aa7725f3d25a635","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86dcc50c25ed04cbc80731848ee896ba1e307362aa28f3ac2aa7725f3d25a635","first_computed_at":"2026-05-18T00:00:37.561906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:37.561906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rY08l+dz8WkY3hFghqNI/IfugEion58C6vhTDE2yF8XI/sGbKv11YAEvH9Tz26pH/9C2djQEksBJQ804059nBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:37.562420Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.06512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2741cfedb24f44c741e4bf143ec30d42039c41422900dcd5f70b5b27b2a479ca","sha256:d1e96ed2c40e4f77d27f46a17fd91a480d2d0f1ab1c94a699aae480da80d29a9"],"state_sha256":"e662bdaf977d0162e95fef6876f91baff32a06fb831b33442ac4ded813dbdc81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zjeAUdrMnwXl5IoBHDbgftRrybZcKs4MYtDufODMVNDr99gD27/vbCQnMRNauzotira2hGimys+q8skcNuHoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T11:35:25.043205Z","bundle_sha256":"6bb2dd2a397d7486ed358514cd1c54043cff271486b3e3589cccaf84649998de"}}