{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DL6WGVJEWPQA37ZCKVISMBGNBF","short_pith_number":"pith:DL6WGVJE","schema_version":"1.0","canonical_sha256":"1afd635524b3e00dff2255512604cd094f1679ee0e4d75da56cf40ba07ac7d31","source":{"kind":"arxiv","id":"2605.18035","version":1},"attestation_state":"computed","paper":{"title":"New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"2) ((1) Harbin Institute of Technology, (2) Mohamed bin Zayed University of Artificial Intelligence, 3), (3) Jilin University), Bin Gu (2, Huan Xiong (1, William de Vazelhes (2), Xinzhe Yuan (1)","submitted_at":"2026-05-18T08:24:18Z","abstract_excerpt":"Hard-thresholding is an important type of algorithm in machine learning that is used to solve $\\ell_0$ constrained optimization problems. However, the true gradient of the objective function can be difficult to access in certain scenarios, which normally can be approximated by zeroth-order (ZO) methods. The SZOHT algorithm is the only algorithm tackling $\\ell_0$ sparsity constraints with ZO gradients so far. Unfortunately, SZOHT has a notable limitation on the number of random directions % in ZO gradients due to the inherent conflict between the deviation of ZO gradients and the expansivity of"},"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":"2605.18035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T08:24:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aeea752e6243baf20fd5c6a38f518a5bceb18cb9ec78d6570ff4200ee2a1314c","abstract_canon_sha256":"1ab5984850f2535c3b170e9bc2a953f59874f202033411f9b0704583745bd1b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:12.468487Z","signature_b64":"UjDkSC6R0GNxfKnDIwhLPAaVTc2Hp4IEHIE99esnYb5nXdxyQuS17hClOzsv8Euy3FDLjWBYKM1bTVCLFQgYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1afd635524b3e00dff2255512604cd094f1679ee0e4d75da56cf40ba07ac7d31","last_reissued_at":"2026-05-20T00:05:12.467674Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:12.467674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"2) ((1) Harbin Institute of Technology, (2) Mohamed bin Zayed University of Artificial Intelligence, 3), (3) Jilin University), Bin Gu (2, Huan Xiong (1, William de Vazelhes (2), Xinzhe Yuan (1)","submitted_at":"2026-05-18T08:24:18Z","abstract_excerpt":"Hard-thresholding is an important type of algorithm in machine learning that is used to solve $\\ell_0$ constrained optimization problems. However, the true gradient of the objective function can be difficult to access in certain scenarios, which normally can be approximated by zeroth-order (ZO) methods. The SZOHT algorithm is the only algorithm tackling $\\ell_0$ sparsity constraints with ZO gradients so far. Unfortunately, SZOHT has a notable limitation on the number of random directions % in ZO gradients due to the inherent conflict between the deviation of ZO gradients and the expansivity of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18035","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/2605.18035/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.503761Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"02a6a3c80a4017df4a86165f4ee909601f018d7ccf3c360dfce6a97a63adead0"},"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":"2605.18035","created_at":"2026-05-20T00:05:12.467797+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18035v1","created_at":"2026-05-20T00:05:12.467797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18035","created_at":"2026-05-20T00:05:12.467797+00:00"},{"alias_kind":"pith_short_12","alias_value":"DL6WGVJEWPQA","created_at":"2026-05-20T00:05:12.467797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DL6WGVJEWPQA37ZC","created_at":"2026-05-20T00:05:12.467797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DL6WGVJE","created_at":"2026-05-20T00:05:12.467797+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/DL6WGVJEWPQA37ZCKVISMBGNBF","json":"https://pith.science/pith/DL6WGVJEWPQA37ZCKVISMBGNBF.json","graph_json":"https://pith.science/api/pith-number/DL6WGVJEWPQA37ZCKVISMBGNBF/graph.json","events_json":"https://pith.science/api/pith-number/DL6WGVJEWPQA37ZCKVISMBGNBF/events.json","paper":"https://pith.science/paper/DL6WGVJE"},"agent_actions":{"view_html":"https://pith.science/pith/DL6WGVJEWPQA37ZCKVISMBGNBF","download_json":"https://pith.science/pith/DL6WGVJEWPQA37ZCKVISMBGNBF.json","view_paper":"https://pith.science/paper/DL6WGVJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18035&json=true","fetch_graph":"https://pith.science/api/pith-number/DL6WGVJEWPQA37ZCKVISMBGNBF/graph.json","fetch_events":"https://pith.science/api/pith-number/DL6WGVJEWPQA37ZCKVISMBGNBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DL6WGVJEWPQA37ZCKVISMBGNBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DL6WGVJEWPQA37ZCKVISMBGNBF/action/storage_attestation","attest_author":"https://pith.science/pith/DL6WGVJEWPQA37ZCKVISMBGNBF/action/author_attestation","sign_citation":"https://pith.science/pith/DL6WGVJEWPQA37ZCKVISMBGNBF/action/citation_signature","submit_replication":"https://pith.science/pith/DL6WGVJEWPQA37ZCKVISMBGNBF/action/replication_record"}},"created_at":"2026-05-20T00:05:12.467797+00:00","updated_at":"2026-05-20T00:05:12.467797+00:00"}