{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C67GIGIU4BOORCCHOT6XIENKVI","short_pith_number":"pith:C67GIGIU","canonical_record":{"source":{"id":"2405.01718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T20:28:49Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"41c7d07a76fc29e79668ecfa7db3a30830f75a9b14f29277ba9fbea0e6ca7e61","abstract_canon_sha256":"2d81e04223ca70046b2f0f798c45a027cd1a0fac7749b2c25f3191f75dafe4cd"},"schema_version":"1.0"},"canonical_sha256":"17be641914e05ce8884774fd7411aaaa1df67ae78f8059f8f0f683c54f3df9dd","source":{"kind":"arxiv","id":"2405.01718","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01718","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01718v1","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01718","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"C67GIGIU4BOO","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"C67GIGIU4BOORCCH","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"C67GIGIU","created_at":"2026-07-05T08:15:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C67GIGIU4BOORCCHOT6XIENKVI","target":"record","payload":{"canonical_record":{"source":{"id":"2405.01718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T20:28:49Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"41c7d07a76fc29e79668ecfa7db3a30830f75a9b14f29277ba9fbea0e6ca7e61","abstract_canon_sha256":"2d81e04223ca70046b2f0f798c45a027cd1a0fac7749b2c25f3191f75dafe4cd"},"schema_version":"1.0"},"canonical_sha256":"17be641914e05ce8884774fd7411aaaa1df67ae78f8059f8f0f683c54f3df9dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:01.166836Z","signature_b64":"Y7tNgQ59XBTD8y/t+1nTEhci/EJgXYwa9y4sfgyDp2sqWIYyW0GhEaE9wCSAe3z1r/DnvfHv/CWgvU160h9SAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17be641914e05ce8884774fd7411aaaa1df67ae78f8059f8f0f683c54f3df9dd","last_reissued_at":"2026-07-05T08:15:01.166431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:01.166431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.01718","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":"2026-07-05T08:15:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"df0bA86QHNRpEuqqJvXtiFCt2JPeTtVar6iN4LWlfhI+DELkKy5yRfEj088bmj0Kl2RPspLFgAxwT+/2LpYTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T07:57:10.773909Z"},"content_sha256":"4fd766d85a1270a0e11fb29daa184bac37648e10e88c821d072cb0df1cbc5534","schema_version":"1.0","event_id":"sha256:4fd766d85a1270a0e11fb29daa184bac37648e10e88c821d072cb0df1cbc5534"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C67GIGIU4BOORCCHOT6XIENKVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Risk-Sensitive Reinforcement Learning with Conditional Value-at-Risk","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lifeng Lai, Xinyi Ni","submitted_at":"2024-05-02T20:28:49Z","abstract_excerpt":"Robust Markov Decision Processes (RMDPs) have received significant research interest, offering an alternative to standard Markov Decision Processes (MDPs) that often assume fixed transition probabilities. RMDPs address this by optimizing for the worst-case scenarios within ambiguity sets. While earlier studies on RMDPs have largely centered on risk-neutral reinforcement learning (RL), with the goal of minimizing expected total discounted costs, in this paper, we analyze the robustness of CVaR-based risk-sensitive RL under RMDP. Firstly, we consider predetermined ambiguity sets. Based on the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01718","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/2405.01718/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":"2026-07-05T08:15:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSQZSwy4H+XUeXrLNQnMq32k7AYW7W6R74Exrw/xcXybSLsFTZ2lrhZPYh+zuNmIDIWoW892fu6YwrX6jx4ZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T07:57:10.774287Z"},"content_sha256":"56c2c1aa9b13f11b0609c8005e0fc4bc079507529c524af89b2d6cf3837a7cb9","schema_version":"1.0","event_id":"sha256:56c2c1aa9b13f11b0609c8005e0fc4bc079507529c524af89b2d6cf3837a7cb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C67GIGIU4BOORCCHOT6XIENKVI/bundle.json","state_url":"https://pith.science/pith/C67GIGIU4BOORCCHOT6XIENKVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C67GIGIU4BOORCCHOT6XIENKVI/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":"2026-07-20T07:57:10Z","links":{"resolver":"https://pith.science/pith/C67GIGIU4BOORCCHOT6XIENKVI","bundle":"https://pith.science/pith/C67GIGIU4BOORCCHOT6XIENKVI/bundle.json","state":"https://pith.science/pith/C67GIGIU4BOORCCHOT6XIENKVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C67GIGIU4BOORCCHOT6XIENKVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C67GIGIU4BOORCCHOT6XIENKVI","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":"2d81e04223ca70046b2f0f798c45a027cd1a0fac7749b2c25f3191f75dafe4cd","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T20:28:49Z","title_canon_sha256":"41c7d07a76fc29e79668ecfa7db3a30830f75a9b14f29277ba9fbea0e6ca7e61"},"schema_version":"1.0","source":{"id":"2405.01718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01718","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01718v1","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01718","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"C67GIGIU4BOO","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"C67GIGIU4BOORCCH","created_at":"2026-07-05T08:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"C67GIGIU","created_at":"2026-07-05T08:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:56c2c1aa9b13f11b0609c8005e0fc4bc079507529c524af89b2d6cf3837a7cb9","target":"graph","created_at":"2026-07-05T08:15:01Z","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/2405.01718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust Markov Decision Processes (RMDPs) have received significant research interest, offering an alternative to standard Markov Decision Processes (MDPs) that often assume fixed transition probabilities. RMDPs address this by optimizing for the worst-case scenarios within ambiguity sets. While earlier studies on RMDPs have largely centered on risk-neutral reinforcement learning (RL), with the goal of minimizing expected total discounted costs, in this paper, we analyze the robustness of CVaR-based risk-sensitive RL under RMDP. Firstly, we consider predetermined ambiguity sets. Based on the co","authors_text":"Lifeng Lai, Xinyi Ni","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T20:28:49Z","title":"Robust Risk-Sensitive Reinforcement Learning with Conditional Value-at-Risk"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01718","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":"sha256:4fd766d85a1270a0e11fb29daa184bac37648e10e88c821d072cb0df1cbc5534","target":"record","created_at":"2026-07-05T08:15:01Z","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":"2d81e04223ca70046b2f0f798c45a027cd1a0fac7749b2c25f3191f75dafe4cd","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T20:28:49Z","title_canon_sha256":"41c7d07a76fc29e79668ecfa7db3a30830f75a9b14f29277ba9fbea0e6ca7e61"},"schema_version":"1.0","source":{"id":"2405.01718","kind":"arxiv","version":1}},"canonical_sha256":"17be641914e05ce8884774fd7411aaaa1df67ae78f8059f8f0f683c54f3df9dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17be641914e05ce8884774fd7411aaaa1df67ae78f8059f8f0f683c54f3df9dd","first_computed_at":"2026-07-05T08:15:01.166431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:01.166431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y7tNgQ59XBTD8y/t+1nTEhci/EJgXYwa9y4sfgyDp2sqWIYyW0GhEaE9wCSAe3z1r/DnvfHv/CWgvU160h9SAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:01.166836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fd766d85a1270a0e11fb29daa184bac37648e10e88c821d072cb0df1cbc5534","sha256:56c2c1aa9b13f11b0609c8005e0fc4bc079507529c524af89b2d6cf3837a7cb9"],"state_sha256":"db99fe729424c9b53184221dd72eef70f0bac645af7867929d8241a3f05f1b32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VIPpxw/7eyiAUyaTV/YSl02abf9bH6nPU3rbcID2KwI/GGYK1mGaWuYcWqdNcrFgUbs9tUpRNd0V0v5t3YDRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T07:57:10.776866Z","bundle_sha256":"b8c4d8b50541174881c9c4430e04e403ca8c6a0880f88ff294508dc47562d787"}}