{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QXY2NOMKLBHWFCKV47IW7MAHRU","short_pith_number":"pith:QXY2NOMK","canonical_record":{"source":{"id":"2601.22100","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T18:33:46Z","cross_cats_sorted":[],"title_canon_sha256":"c14cec7aa740b4e2fa90ca8fc378a6c47cf4ae4de1c3ef90ae86fec00304d660","abstract_canon_sha256":"779429d53e0737ae822d373854b581f07de410bd4d09b05c42c752e4300563d8"},"schema_version":"1.0"},"canonical_sha256":"85f1a6b98a584f628955e7d16fb0078d253848af0c3ff541dc4cf7a0923e86f4","source":{"kind":"arxiv","id":"2601.22100","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QXY2NOMKLBHWFCKV47IW7MAHRU","target":"record","payload":{"canonical_record":{"source":{"id":"2601.22100","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-29T18:33:46Z","cross_cats_sorted":[],"title_canon_sha256":"c14cec7aa740b4e2fa90ca8fc378a6c47cf4ae4de1c3ef90ae86fec00304d660","abstract_canon_sha256":"779429d53e0737ae822d373854b581f07de410bd4d09b05c42c752e4300563d8"},"schema_version":"1.0"},"canonical_sha256":"85f1a6b98a584f628955e7d16fb0078d253848af0c3ff541dc4cf7a0923e86f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:48.734027Z","signature_b64":"G2ha7dzgKLUQBcRoBXYho2NYmcWbwH+YB3YV2n9Nogc2o2o6sC5yaRvWrIcvXyBGM3kQPYpGXhGAlDiCts+zDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85f1a6b98a584f628955e7d16fb0078d253848af0c3ff541dc4cf7a0923e86f4","last_reissued_at":"2026-06-23T00:11:48.733488Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:48.733488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.22100","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T00:11:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jeKHwF8gh1Ig11/cyEGxOKrfqrqxNA+WtL13NLdsGicEkkVMr18CdjyrYGIbYyOHVKVKQmfOo+5oPBRFvPdmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T05:20:04.824642Z"},"content_sha256":"92cf67f6d063629b55bfdb3d401730529f198349de4c7e8382af4b71037acf86","schema_version":"1.0","event_id":"sha256:92cf67f6d063629b55bfdb3d401730529f198349de4c7e8382af4b71037acf86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QXY2NOMKLBHWFCKV47IW7MAHRU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting CVaR Policy Optimization with Quantile Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erick Delage, Yudong Luo","submitted_at":"2026-01-29T18:33:46Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22100","kind":"arxiv","version":3},"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/2601.22100/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":"2026-06-23T00:11:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cX92tust9wB1wJuYEPzSb+Y5nqOzo65CcUo7yVlLOZj3NzDbyxXd/fh5D1+/aOWgF2DWdiUHoyKzaNBVtsAVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T05:20:04.825017Z"},"content_sha256":"0e991700528de2334f46a1bc4c515dd81d71c41c06ee4472299e0612e7bd8aab","schema_version":"1.0","event_id":"sha256:0e991700528de2334f46a1bc4c515dd81d71c41c06ee4472299e0612e7bd8aab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXY2NOMKLBHWFCKV47IW7MAHRU/bundle.json","state_url":"https://pith.science/pith/QXY2NOMKLBHWFCKV47IW7MAHRU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXY2NOMKLBHWFCKV47IW7MAHRU/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":"2026-07-19T05:20:04Z","links":{"resolver":"https://pith.science/pith/QXY2NOMKLBHWFCKV47IW7MAHRU","bundle":"https://pith.science/pith/QXY2NOMKLBHWFCKV47IW7MAHRU/bundle.json","state":"https://pith.science/pith/QXY2NOMKLBHWFCKV47IW7MAHRU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXY2NOMKLBHWFCKV47IW7MAHRU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iflzbIcQNj2cTsMkIZaRI00FrGLIbJC4nlUdahjLqj68q//xDTOsk5cTWRzndZW+RcXOSxEsANFu/i01S5KmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T05:20:04.827296Z","bundle_sha256":"53d05eddf02cf470960a29c1f15d1f4c2973175849d97891daa6faec2ba9c510"}}