{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KP3GJ4CRWE6XHIO632RSL3KV5T","short_pith_number":"pith:KP3GJ4CR","schema_version":"1.0","canonical_sha256":"53f664f051b13d73a1dedea325ed55ecdd0c4e069f778d44431ef749362020bb","source":{"kind":"arxiv","id":"2602.21132","version":2},"attestation_state":"computed","paper":{"title":"Robust and Sparse Generalized Linear Models for High-Dimensional Data via Maximum Mean Discrepancy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Lulu Kang, Xiaoning Kang","submitted_at":"2026-02-24T17:28:12Z","abstract_excerpt":"High-dimensional datasets are frequently subject to contamination by outliers and heavy-tailed noise, which can severely bias standard regularized estimators like the Lasso. While Maximum Mean Discrepancy (MMD) has recently been introduced as a ``universal'' framework for robust regression, its application to high-dimensional Generalized Linear Models (GLMs) remains largely unexplored, particularly regarding variable selection. In this paper, we propose a penalized MMD framework for robust estimation and feature selection in GLMs. We introduce an $\\ell_1$-penalized MMD objective and develop tw"},"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":"2602.21132","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2026-02-24T17:28:12Z","cross_cats_sorted":[],"title_canon_sha256":"22f4b5ab17ae132f69498ea915bc23a7deb9a0116e8adc8abee4bde91a6744d7","abstract_canon_sha256":"92ecbe39afeb6849ee13b2daf98ec1d2c488ff1f062cb5ab09087308a273c13b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:09.199773Z","signature_b64":"QEs9wVnAeUzUi9Uj7ySSwkkOaRlYw2ppiIN647xsoUYLSoIsXJ3KUb1QhNa+sjj7pMugLLSbnJmGzv3hNMEqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53f664f051b13d73a1dedea325ed55ecdd0c4e069f778d44431ef749362020bb","last_reissued_at":"2026-06-08T01:05:09.198669Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:09.198669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust and Sparse Generalized Linear Models for High-Dimensional Data via Maximum Mean Discrepancy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Lulu Kang, Xiaoning Kang","submitted_at":"2026-02-24T17:28:12Z","abstract_excerpt":"High-dimensional datasets are frequently subject to contamination by outliers and heavy-tailed noise, which can severely bias standard regularized estimators like the Lasso. While Maximum Mean Discrepancy (MMD) has recently been introduced as a ``universal'' framework for robust regression, its application to high-dimensional Generalized Linear Models (GLMs) remains largely unexplored, particularly regarding variable selection. In this paper, we propose a penalized MMD framework for robust estimation and feature selection in GLMs. We introduce an $\\ell_1$-penalized MMD objective and develop tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.21132","kind":"arxiv","version":2},"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/2602.21132/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":"2602.21132","created_at":"2026-06-08T01:05:09.198831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.21132v2","created_at":"2026-06-08T01:05:09.198831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.21132","created_at":"2026-06-08T01:05:09.198831+00:00"},{"alias_kind":"pith_short_12","alias_value":"KP3GJ4CRWE6X","created_at":"2026-06-08T01:05:09.198831+00:00"},{"alias_kind":"pith_short_16","alias_value":"KP3GJ4CRWE6XHIO6","created_at":"2026-06-08T01:05:09.198831+00:00"},{"alias_kind":"pith_short_8","alias_value":"KP3GJ4CR","created_at":"2026-06-08T01:05:09.198831+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/KP3GJ4CRWE6XHIO632RSL3KV5T","json":"https://pith.science/pith/KP3GJ4CRWE6XHIO632RSL3KV5T.json","graph_json":"https://pith.science/api/pith-number/KP3GJ4CRWE6XHIO632RSL3KV5T/graph.json","events_json":"https://pith.science/api/pith-number/KP3GJ4CRWE6XHIO632RSL3KV5T/events.json","paper":"https://pith.science/paper/KP3GJ4CR"},"agent_actions":{"view_html":"https://pith.science/pith/KP3GJ4CRWE6XHIO632RSL3KV5T","download_json":"https://pith.science/pith/KP3GJ4CRWE6XHIO632RSL3KV5T.json","view_paper":"https://pith.science/paper/KP3GJ4CR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.21132&json=true","fetch_graph":"https://pith.science/api/pith-number/KP3GJ4CRWE6XHIO632RSL3KV5T/graph.json","fetch_events":"https://pith.science/api/pith-number/KP3GJ4CRWE6XHIO632RSL3KV5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KP3GJ4CRWE6XHIO632RSL3KV5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KP3GJ4CRWE6XHIO632RSL3KV5T/action/storage_attestation","attest_author":"https://pith.science/pith/KP3GJ4CRWE6XHIO632RSL3KV5T/action/author_attestation","sign_citation":"https://pith.science/pith/KP3GJ4CRWE6XHIO632RSL3KV5T/action/citation_signature","submit_replication":"https://pith.science/pith/KP3GJ4CRWE6XHIO632RSL3KV5T/action/replication_record"}},"created_at":"2026-06-08T01:05:09.198831+00:00","updated_at":"2026-06-08T01:05:09.198831+00:00"}