{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IFUVXOJ7SJILUK2J3WCXT7O7U4","short_pith_number":"pith:IFUVXOJ7","schema_version":"1.0","canonical_sha256":"41695bb93f9250ba2b49dd8579fddfa723e7b5aadb78b21f512976822650b012","source":{"kind":"arxiv","id":"2605.30573","version":1},"attestation_state":"computed","paper":{"title":"Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abolfazl Hashemi, Behzad Sharif, M. Berk Sahin","submitted_at":"2026-05-28T21:07:14Z","abstract_excerpt":"Sampling from high-dimensional, non-log-concave distributions with unnormalized densities remains a fundamental challenge in machine learning, particularly in black-box settings where gradient information is inaccessible or computationally prohibitive. While Langevin dynamics provides a principled framework for sampling when gradients are accessible, its extension to the black-box settings suffers from high variance and lacks non-asymptotic convergence guarantees for non-log-concave sampling. To address these limitations, we propose a variance-reduced zeroth-order Langevin sampling method. Our"},"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":"2605.30573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T21:07:14Z","cross_cats_sorted":[],"title_canon_sha256":"363dad0646c0c1bfe381f8ff09d14723ab7521d6c1b2bfa8a673303ee9eec699","abstract_canon_sha256":"d789a8dc742e7ef23f5a5333c0effbe03d734b5d062e562077eadb343e71cd7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:01.801207Z","signature_b64":"ajHC3fZFWDyL5hm42sq0VcVYvr/gM8pDlkj+FGrOgHHKm1we7dGT07G/xSeckJTFIRHLn5Hj3MfSyJbeU3M7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41695bb93f9250ba2b49dd8579fddfa723e7b5aadb78b21f512976822650b012","last_reissued_at":"2026-06-01T01:03:01.800129Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:01.800129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abolfazl Hashemi, Behzad Sharif, M. Berk Sahin","submitted_at":"2026-05-28T21:07:14Z","abstract_excerpt":"Sampling from high-dimensional, non-log-concave distributions with unnormalized densities remains a fundamental challenge in machine learning, particularly in black-box settings where gradient information is inaccessible or computationally prohibitive. While Langevin dynamics provides a principled framework for sampling when gradients are accessible, its extension to the black-box settings suffers from high variance and lacks non-asymptotic convergence guarantees for non-log-concave sampling. To address these limitations, we propose a variance-reduced zeroth-order Langevin sampling method. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30573","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/2605.30573/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":"2605.30573","created_at":"2026-06-01T01:03:01.800250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30573v1","created_at":"2026-06-01T01:03:01.800250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30573","created_at":"2026-06-01T01:03:01.800250+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFUVXOJ7SJIL","created_at":"2026-06-01T01:03:01.800250+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFUVXOJ7SJILUK2J","created_at":"2026-06-01T01:03:01.800250+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFUVXOJ7","created_at":"2026-06-01T01:03:01.800250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4","json":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4.json","graph_json":"https://pith.science/api/pith-number/IFUVXOJ7SJILUK2J3WCXT7O7U4/graph.json","events_json":"https://pith.science/api/pith-number/IFUVXOJ7SJILUK2J3WCXT7O7U4/events.json","paper":"https://pith.science/paper/IFUVXOJ7"},"agent_actions":{"view_html":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4","download_json":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4.json","view_paper":"https://pith.science/paper/IFUVXOJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30573&json=true","fetch_graph":"https://pith.science/api/pith-number/IFUVXOJ7SJILUK2J3WCXT7O7U4/graph.json","fetch_events":"https://pith.science/api/pith-number/IFUVXOJ7SJILUK2J3WCXT7O7U4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4/action/storage_attestation","attest_author":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4/action/author_attestation","sign_citation":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4/action/citation_signature","submit_replication":"https://pith.science/pith/IFUVXOJ7SJILUK2J3WCXT7O7U4/action/replication_record"}},"created_at":"2026-06-01T01:03:01.800250+00:00","updated_at":"2026-06-01T01:03:01.800250+00:00"}