{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XCU4LJQGNHHCUE2R4IH3I3IMKM","short_pith_number":"pith:XCU4LJQG","canonical_record":{"source":{"id":"2301.01045","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-03T11:06:30Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"f0a3a28fcbbdfc7fdd2876fe326cea079c934d1bcd5f7b93717e4cdbed95ed3a","abstract_canon_sha256":"c3e3e31f9e8ee5f5d9110cc8c0141cada3141850447091004c4925ccf262ceec"},"schema_version":"1.0"},"canonical_sha256":"b8a9c5a60669ce2a1351e20fb46d0c533158f96b5e94c8b2bf70fde2dea068d0","source":{"kind":"arxiv","id":"2301.01045","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.01045","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"arxiv_version","alias_value":"2301.01045v2","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01045","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"pith_short_12","alias_value":"XCU4LJQGNHHC","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"pith_short_16","alias_value":"XCU4LJQGNHHCUE2R","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"pith_short_8","alias_value":"XCU4LJQG","created_at":"2026-07-05T05:30:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XCU4LJQGNHHCUE2R4IH3I3IMKM","target":"record","payload":{"canonical_record":{"source":{"id":"2301.01045","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-03T11:06:30Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"f0a3a28fcbbdfc7fdd2876fe326cea079c934d1bcd5f7b93717e4cdbed95ed3a","abstract_canon_sha256":"c3e3e31f9e8ee5f5d9110cc8c0141cada3141850447091004c4925ccf262ceec"},"schema_version":"1.0"},"canonical_sha256":"b8a9c5a60669ce2a1351e20fb46d0c533158f96b5e94c8b2bf70fde2dea068d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:34.248963Z","signature_b64":"JyalhPtjVZPySlFKt/jkUl37RxFFvVfZ7qZGdiVOrDlm5K41rJvbVSNGC+I0BRfmqayTBjvMYkDf7+AeKKM2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8a9c5a60669ce2a1351e20fb46d0c533158f96b5e94c8b2bf70fde2dea068d0","last_reissued_at":"2026-07-05T05:30:34.248547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:34.248547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.01045","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":"2026-07-05T05:30:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TpFqJL0z2n95eafCx+0RuGsAYJwNIGrKm3N650prIPdfvLOtY7QsS9PDuI569Ll3XUu/AjdsF387T26jGaR/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:31:16.588958Z"},"content_sha256":"3ffd05b80298bb93ecccf2de0cb60fb0325ae4e74c91d194894bacd6ac47676d","schema_version":"1.0","event_id":"sha256:3ffd05b80298bb93ecccf2de0cb60fb0325ae4e74c91d194894bacd6ac47676d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XCU4LJQGNHHCUE2R4IH3I3IMKM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-Averse MDPs under Reward Ambiguity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Chin Pang Ho, Haolin Ruan, Zhi Chen","submitted_at":"2023-01-03T11:06:30Z","abstract_excerpt":"We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity. The proposed model optimizes the weighted average of mean and percentile performances, and it covers the distributionally robust MDPs and the distributionally robust chance-constrained MDPs (both under reward ambiguity) as special cases. By considering that the unknown reward distribution lies in a Wasserstein ambiguity set, we derive the tractable reformulation for our model. In particular, we show that that the return-risk model can also account for risk from uncertain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01045","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/2301.01045/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":"2026-07-05T05:30:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7N6js13QI2e0jyUgWfrWIHoWP00zii7+0FXQ3UMJ+QOhpPsbDig0dRH/+jxowc1EY/UqmwPxuA3oUrVjW3ytCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:31:16.589464Z"},"content_sha256":"c92c46df135088a8a534b173c1f1126aef266b0f5e12176bab9271478a4e4ffa","schema_version":"1.0","event_id":"sha256:c92c46df135088a8a534b173c1f1126aef266b0f5e12176bab9271478a4e4ffa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/bundle.json","state_url":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/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":"2026-08-17T12:31:16Z","links":{"resolver":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM","bundle":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/bundle.json","state":"https://pith.science/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCU4LJQGNHHCUE2R4IH3I3IMKM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XCU4LJQGNHHCUE2R4IH3I3IMKM","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":"c3e3e31f9e8ee5f5d9110cc8c0141cada3141850447091004c4925ccf262ceec","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-03T11:06:30Z","title_canon_sha256":"f0a3a28fcbbdfc7fdd2876fe326cea079c934d1bcd5f7b93717e4cdbed95ed3a"},"schema_version":"1.0","source":{"id":"2301.01045","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.01045","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"arxiv_version","alias_value":"2301.01045v2","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01045","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"pith_short_12","alias_value":"XCU4LJQGNHHC","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"pith_short_16","alias_value":"XCU4LJQGNHHCUE2R","created_at":"2026-07-05T05:30:34Z"},{"alias_kind":"pith_short_8","alias_value":"XCU4LJQG","created_at":"2026-07-05T05:30:34Z"}],"graph_snapshots":[{"event_id":"sha256:c92c46df135088a8a534b173c1f1126aef266b0f5e12176bab9271478a4e4ffa","target":"graph","created_at":"2026-07-05T05:30:34Z","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/2301.01045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a distributionally robust return-risk model for Markov decision processes (MDPs) under risk and reward ambiguity. The proposed model optimizes the weighted average of mean and percentile performances, and it covers the distributionally robust MDPs and the distributionally robust chance-constrained MDPs (both under reward ambiguity) as special cases. By considering that the unknown reward distribution lies in a Wasserstein ambiguity set, we derive the tractable reformulation for our model. In particular, we show that that the return-risk model can also account for risk from uncertain","authors_text":"Chin Pang Ho, Haolin Ruan, Zhi Chen","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-03T11:06:30Z","title":"Risk-Averse MDPs under Reward Ambiguity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01045","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":"sha256:3ffd05b80298bb93ecccf2de0cb60fb0325ae4e74c91d194894bacd6ac47676d","target":"record","created_at":"2026-07-05T05:30:34Z","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":"c3e3e31f9e8ee5f5d9110cc8c0141cada3141850447091004c4925ccf262ceec","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-03T11:06:30Z","title_canon_sha256":"f0a3a28fcbbdfc7fdd2876fe326cea079c934d1bcd5f7b93717e4cdbed95ed3a"},"schema_version":"1.0","source":{"id":"2301.01045","kind":"arxiv","version":2}},"canonical_sha256":"b8a9c5a60669ce2a1351e20fb46d0c533158f96b5e94c8b2bf70fde2dea068d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8a9c5a60669ce2a1351e20fb46d0c533158f96b5e94c8b2bf70fde2dea068d0","first_computed_at":"2026-07-05T05:30:34.248547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:34.248547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JyalhPtjVZPySlFKt/jkUl37RxFFvVfZ7qZGdiVOrDlm5K41rJvbVSNGC+I0BRfmqayTBjvMYkDf7+AeKKM2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:34.248963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.01045","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ffd05b80298bb93ecccf2de0cb60fb0325ae4e74c91d194894bacd6ac47676d","sha256:c92c46df135088a8a534b173c1f1126aef266b0f5e12176bab9271478a4e4ffa"],"state_sha256":"45fe3ac62b84585b7a6223f1eb776b3ac03ae565a977f66cbad5d681e4971cd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZCMEPrG0rmXBFbm4Uo3NTxOqivtEN6KsjRGsB3GJbbqVu71GYiDJesiG3AKytFbw5QlViqpcj5mLF5Z+zswBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:31:16.593841Z","bundle_sha256":"d2a070a42e7f4b502e5a054344cf29f87285f2aa14aaf9fce0463c46e8fddf8f"}}