{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DTIPUABL5HZKQB64AONEX2ZNMD","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":"645c4c9125ec940d896bb34253c3394a9840b7ac090839d99a83252c03853e73","cross_cats_sorted":["cs.DS","cs.LG","math.PR","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-02-15T23:19:07Z","title_canon_sha256":"a2f38f85992abe3f58be3e00c84de6ddb115c1f77f812c52e24087e609e76218"},"schema_version":"1.0","source":{"id":"2602.14342","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.14342","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.14342v2","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14342","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"DTIPUABL5HZK","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"DTIPUABL5HZKQB64","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"DTIPUABL","created_at":"2026-05-20T00:00:34Z"}],"graph_snapshots":[{"event_id":"sha256:f917dfff4e188716ae93bbc86e918915887c395041d602569fa3ad2e69bda992","target":"graph","created_at":"2026-05-20T00:00:34Z","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/2602.14342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that high-accuracy guarantees for log-concave sampling -- that is, iteration and query complexities which scale as $\\mathrm{poly}\\log(1/\\delta)$, where $\\delta$ is the desired target accuracy -- are achievable using stochastic gradients with subexponential tails. Notably, this exhibits a separation with the problem of convex optimization, where stochasticity (even additive Gaussian noise) in the gradient oracle incurs $\\mathrm{poly}(1/\\delta)$ queries. We also give an information-theoretic argument that light-tailed stochastic gradients are necessary for high accuracy: for example, in ","authors_text":"Alexander Rakhlin, Constantinos Daskalakis, Fan Chen, Sinho Chewi","cross_cats":["cs.DS","cs.LG","math.PR","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-02-15T23:19:07Z","title":"High-accuracy log-concave sampling with stochastic queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14342","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":"sha256:77b59dee4c2afbe927fda5df5983a74b952ca688ed5dd261cf7305a3548c27d3","target":"record","created_at":"2026-05-20T00:00:34Z","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":"645c4c9125ec940d896bb34253c3394a9840b7ac090839d99a83252c03853e73","cross_cats_sorted":["cs.DS","cs.LG","math.PR","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-02-15T23:19:07Z","title_canon_sha256":"a2f38f85992abe3f58be3e00c84de6ddb115c1f77f812c52e24087e609e76218"},"schema_version":"1.0","source":{"id":"2602.14342","kind":"arxiv","version":2}},"canonical_sha256":"1cd0fa002be9f2a807dc039a4beb2d60ec6437c0814fc9639b2e09f862f70be9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cd0fa002be9f2a807dc039a4beb2d60ec6437c0814fc9639b2e09f862f70be9","first_computed_at":"2026-05-20T00:00:34.583147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:34.583147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z4atYRC8cizoxljN9OtlnMbHgCXmSSsPfeYUGm7Hj5Njdo1444Zk/yidVibXJ4kS18en8udBkmlfnW+vrNFnAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:34.583857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.14342","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77b59dee4c2afbe927fda5df5983a74b952ca688ed5dd261cf7305a3548c27d3","sha256:f917dfff4e188716ae93bbc86e918915887c395041d602569fa3ad2e69bda992"],"state_sha256":"2d5819842dd82023a6fbe40b18273e5d77302ca908213e300b4c419ac9c31534"}