{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5QRKEETWHYT2ARPHNHPY74YPEG","short_pith_number":"pith:5QRKEETW","schema_version":"1.0","canonical_sha256":"ec22a212763e27a045e769df8ff30f21898076a9ebdae032d1da828c61519603","source":{"kind":"arxiv","id":"2606.27685","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Contamination Meets Hard Thresholding: An Iterative Algorithm with Signal Adaptivity and Minimax Optimality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hanming Yang, Shixiang Liu","submitted_at":"2026-06-26T03:30:25Z","abstract_excerpt":"Pervasive data contamination -- stemming from measurement errors, outliers, or adversarial corruption -- has motivated the development of robust statistical methods. In this context, we propose a two-stage Adversarial Contamination-resistant Iterative Hard Thresholding (AC-IHT) algorithm for high-dimensional regression with contamination. Our nonconvex algorithm achieves minimax near-optimal (up to logarithmic terms) estimation by iteratively updating the coefficient vector and the contamination vector with different thresholding scales. We further demonstrate that our AC-IHT estimator is sign"},"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":"2606.27685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-26T03:30:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"29c4dc03bd54bb6c19d1f1bad42d60431e579b8e0e7e30336da5bddad8cf0542","abstract_canon_sha256":"8cafa8668025fe0163438b66df52e7b0b27ce5a2b8ddf057f2ca29c3be95bc3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:45.325188Z","signature_b64":"QOiPZWvY5aLoT5zbjIPG/Og+D2pvm86+353inXvERc0JDTCJdrmtWjUMopx1p+bzPrFtMKdjAuFdUHX+UD8vCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec22a212763e27a045e769df8ff30f21898076a9ebdae032d1da828c61519603","last_reissued_at":"2026-06-29T01:14:45.324655Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:45.324655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Contamination Meets Hard Thresholding: An Iterative Algorithm with Signal Adaptivity and Minimax Optimality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hanming Yang, Shixiang Liu","submitted_at":"2026-06-26T03:30:25Z","abstract_excerpt":"Pervasive data contamination -- stemming from measurement errors, outliers, or adversarial corruption -- has motivated the development of robust statistical methods. In this context, we propose a two-stage Adversarial Contamination-resistant Iterative Hard Thresholding (AC-IHT) algorithm for high-dimensional regression with contamination. Our nonconvex algorithm achieves minimax near-optimal (up to logarithmic terms) estimation by iteratively updating the coefficient vector and the contamination vector with different thresholding scales. We further demonstrate that our AC-IHT estimator is sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27685","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/2606.27685/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":"2606.27685","created_at":"2026-06-29T01:14:45.324705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27685v1","created_at":"2026-06-29T01:14:45.324705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27685","created_at":"2026-06-29T01:14:45.324705+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QRKEETWHYT2","created_at":"2026-06-29T01:14:45.324705+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QRKEETWHYT2ARPH","created_at":"2026-06-29T01:14:45.324705+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QRKEETW","created_at":"2026-06-29T01:14:45.324705+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/5QRKEETWHYT2ARPHNHPY74YPEG","json":"https://pith.science/pith/5QRKEETWHYT2ARPHNHPY74YPEG.json","graph_json":"https://pith.science/api/pith-number/5QRKEETWHYT2ARPHNHPY74YPEG/graph.json","events_json":"https://pith.science/api/pith-number/5QRKEETWHYT2ARPHNHPY74YPEG/events.json","paper":"https://pith.science/paper/5QRKEETW"},"agent_actions":{"view_html":"https://pith.science/pith/5QRKEETWHYT2ARPHNHPY74YPEG","download_json":"https://pith.science/pith/5QRKEETWHYT2ARPHNHPY74YPEG.json","view_paper":"https://pith.science/paper/5QRKEETW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27685&json=true","fetch_graph":"https://pith.science/api/pith-number/5QRKEETWHYT2ARPHNHPY74YPEG/graph.json","fetch_events":"https://pith.science/api/pith-number/5QRKEETWHYT2ARPHNHPY74YPEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QRKEETWHYT2ARPHNHPY74YPEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QRKEETWHYT2ARPHNHPY74YPEG/action/storage_attestation","attest_author":"https://pith.science/pith/5QRKEETWHYT2ARPHNHPY74YPEG/action/author_attestation","sign_citation":"https://pith.science/pith/5QRKEETWHYT2ARPHNHPY74YPEG/action/citation_signature","submit_replication":"https://pith.science/pith/5QRKEETWHYT2ARPHNHPY74YPEG/action/replication_record"}},"created_at":"2026-06-29T01:14:45.324705+00:00","updated_at":"2026-06-29T01:14:45.324705+00:00"}