{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QXY2NOMKLBHWFCKV47IW7MAHRU","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":"779429d53e0737ae822d373854b581f07de410bd4d09b05c42c752e4300563d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T18:33:46Z","title_canon_sha256":"c14cec7aa740b4e2fa90ca8fc378a6c47cf4ae4de1c3ef90ae86fec00304d660"},"schema_version":"1.0","source":{"id":"2601.22100","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.22100","created_at":"2026-06-23T00:11:48Z"},{"alias_kind":"arxiv_version","alias_value":"2601.22100v3","created_at":"2026-06-23T00:11:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22100","created_at":"2026-06-23T00:11:48Z"},{"alias_kind":"pith_short_12","alias_value":"QXY2NOMKLBHW","created_at":"2026-06-23T00:11:48Z"},{"alias_kind":"pith_short_16","alias_value":"QXY2NOMKLBHWFCKV","created_at":"2026-06-23T00:11:48Z"},{"alias_kind":"pith_short_8","alias_value":"QXY2NOMK","created_at":"2026-06-23T00:11:48Z"}],"graph_snapshots":[{"event_id":"sha256:0e991700528de2334f46a1bc4c515dd81d71c41c06ee4472299e0612e7bd8aab","target":"graph","created_at":"2026-06-23T00:11:48Z","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/2601.22100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimizing Conditional Value-at-risk (CVaR) using policy gradient (a.k.a CVaR-PG) faces significant challenges of sample inefficiency. This inefficiency stems from the fact that it focuses on tail-end performance and overlooks many sampled trajectories. We address this problem by augmenting CVaR with an expected quantile term. Quantile optimization admits a dynamic programming formulation that leverages all sampled data, thus improves sample efficiency. This does not alter the CVaR objective since CVaR corresponds to the expectation of quantile over the tail. Empirical results in domains with ","authors_text":"Erick Delage, Yudong Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T18:33:46Z","title":"Boosting CVaR Policy Optimization with Quantile Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22100","kind":"arxiv","version":3},"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":"sha256:92cf67f6d063629b55bfdb3d401730529f198349de4c7e8382af4b71037acf86","target":"record","created_at":"2026-06-23T00:11:48Z","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":"779429d53e0737ae822d373854b581f07de410bd4d09b05c42c752e4300563d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T18:33:46Z","title_canon_sha256":"c14cec7aa740b4e2fa90ca8fc378a6c47cf4ae4de1c3ef90ae86fec00304d660"},"schema_version":"1.0","source":{"id":"2601.22100","kind":"arxiv","version":3}},"canonical_sha256":"85f1a6b98a584f628955e7d16fb0078d253848af0c3ff541dc4cf7a0923e86f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85f1a6b98a584f628955e7d16fb0078d253848af0c3ff541dc4cf7a0923e86f4","first_computed_at":"2026-06-23T00:11:48.733488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T00:11:48.733488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G2ha7dzgKLUQBcRoBXYho2NYmcWbwH+YB3YV2n9Nogc2o2o6sC5yaRvWrIcvXyBGM3kQPYpGXhGAlDiCts+zDg==","signature_status":"signed_v1","signed_at":"2026-06-23T00:11:48.734027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.22100","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92cf67f6d063629b55bfdb3d401730529f198349de4c7e8382af4b71037acf86","sha256:0e991700528de2334f46a1bc4c515dd81d71c41c06ee4472299e0612e7bd8aab"],"state_sha256":"9dab5f9d991c1d1c8c63e02a2e0409d46e631da5f39a45ad74db6bebd37fb504"}