{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M2DBXXGPPF5V242HCB7U3WZB5R","short_pith_number":"pith:M2DBXXGP","schema_version":"1.0","canonical_sha256":"66861bdccf797b5d7347107f4ddb21ec6cbb243a24e100d644115d8f5f8073c3","source":{"kind":"arxiv","id":"2602.03778","version":2},"attestation_state":"computed","paper":{"title":"Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aneri Muni, Erick Delage, Esther Derman, Pierre-Luc Bacon, Vincent Taboga","submitted_at":"2026-02-03T17:39:45Z","abstract_excerpt":"Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-critical applications to prevent rare, yet catastrophic events. Unlike risk-neutral objectives, the static CVaR of the return depends on entire trajectories without admitting a recursive Bellman decomposition in the underlying Markov decision process. A classical resolution relies on state augmentation with a continuous variable. However, unless restricted to a specialized class of admissible value functions, this formulation induces sparse rewards and degenerate fixed points. In this work, we propose a n"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.03778","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T17:39:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7572e5d9008452a2a8f1afa9f93f9f3058d7bc41291a8124e18bfbfb3118d7bd","abstract_canon_sha256":"92c6b0c1842cd9ded137031d1591c9659b92efe63f3f158c016224d166a03fc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:46.436628Z","signature_b64":"4Y48Jn380pHG8WLtPPXwqRCGZOKQwW3HfzYuHLWTWwHiLalwS8qOGFbCqpLJcP9pWfzZYNp83Gh8gVgi6sGiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66861bdccf797b5d7347107f4ddb21ec6cbb243a24e100d644115d8f5f8073c3","last_reissued_at":"2026-07-01T01:17:46.436092Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:46.436092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aneri Muni, Erick Delage, Esther Derman, Pierre-Luc Bacon, Vincent Taboga","submitted_at":"2026-02-03T17:39:45Z","abstract_excerpt":"Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-critical applications to prevent rare, yet catastrophic events. Unlike risk-neutral objectives, the static CVaR of the return depends on entire trajectories without admitting a recursive Bellman decomposition in the underlying Markov decision process. A classical resolution relies on state augmentation with a continuous variable. However, unless restricted to a specialized class of admissible value functions, this formulation induces sparse rewards and degenerate fixed points. In this work, we propose a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03778","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/2602.03778/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.03778","created_at":"2026-07-01T01:17:46.436159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.03778v2","created_at":"2026-07-01T01:17:46.436159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03778","created_at":"2026-07-01T01:17:46.436159+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2DBXXGPPF5V","created_at":"2026-07-01T01:17:46.436159+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2DBXXGPPF5V242H","created_at":"2026-07-01T01:17:46.436159+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2DBXXGP","created_at":"2026-07-01T01:17:46.436159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.04795","citing_title":"Sample Complexity for Markov Decision Processes and Stochastic Optimal Control with Static Risk Measures","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R","json":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R.json","graph_json":"https://pith.science/api/pith-number/M2DBXXGPPF5V242HCB7U3WZB5R/graph.json","events_json":"https://pith.science/api/pith-number/M2DBXXGPPF5V242HCB7U3WZB5R/events.json","paper":"https://pith.science/paper/M2DBXXGP"},"agent_actions":{"view_html":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R","download_json":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R.json","view_paper":"https://pith.science/paper/M2DBXXGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.03778&json=true","fetch_graph":"https://pith.science/api/pith-number/M2DBXXGPPF5V242HCB7U3WZB5R/graph.json","fetch_events":"https://pith.science/api/pith-number/M2DBXXGPPF5V242HCB7U3WZB5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R/action/storage_attestation","attest_author":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R/action/author_attestation","sign_citation":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R/action/citation_signature","submit_replication":"https://pith.science/pith/M2DBXXGPPF5V242HCB7U3WZB5R/action/replication_record"}},"created_at":"2026-07-01T01:17:46.436159+00:00","updated_at":"2026-07-01T01:17:46.436159+00:00"}