{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IWYBQFQ4UNKHQ5PYLMB6OK6TWG","short_pith_number":"pith:IWYBQFQ4","schema_version":"1.0","canonical_sha256":"45b018161ca3547875f85b03e72bd3b193c18097ba626ee5aa33c6f62ceaf76d","source":{"kind":"arxiv","id":"2509.08155","version":1},"attestation_state":"computed","paper":{"title":"Contributions to Robust and Efficient Methods for Analysis of High Dimensional Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC","physics.data-an","stat.TH"],"primary_cat":"math.ST","authors_text":"Kai Yang","submitted_at":"2025-09-09T21:30:01Z","abstract_excerpt":"A ubiquitous feature of data of our era is their extra-large sizes and dimensions. Analyzing such high-dimensional data poses significant challenges, since the feature dimension is often much larger than the sample size. This thesis introduces robust and computationally efficient methods to address several common challenges associated with high-dimensional data. In my first manuscript, I propose a coherent approach to variable screening that accommodates nonlinear associations. I develop a novel variable screening method that transcends traditional linear assumptions by leveraging mutual infor"},"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":"2509.08155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.ST","submitted_at":"2025-09-09T21:30:01Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.OC","physics.data-an","stat.TH"],"title_canon_sha256":"d9d2a0288295ca8621668c06cb43c4f121fdfac49517db6305e580435be42f62","abstract_canon_sha256":"0d94ad3a52421ffcee6f7d7f0082ac68a434fcdbf709c1b69b2f6652c2f845fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:23.935629Z","signature_b64":"eKnbXVDcvkdhGa0ZYAH6r26rZTZILWBzavSHiRXXOnclpeTI6IDt5ho+E3lxODFpmPL09NpHtG5CLLCqRiyABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45b018161ca3547875f85b03e72bd3b193c18097ba626ee5aa33c6f62ceaf76d","last_reissued_at":"2026-07-05T12:08:23.935100Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:23.935100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contributions to Robust and Efficient Methods for Analysis of High Dimensional Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.OC","physics.data-an","stat.TH"],"primary_cat":"math.ST","authors_text":"Kai Yang","submitted_at":"2025-09-09T21:30:01Z","abstract_excerpt":"A ubiquitous feature of data of our era is their extra-large sizes and dimensions. Analyzing such high-dimensional data poses significant challenges, since the feature dimension is often much larger than the sample size. This thesis introduces robust and computationally efficient methods to address several common challenges associated with high-dimensional data. In my first manuscript, I propose a coherent approach to variable screening that accommodates nonlinear associations. I develop a novel variable screening method that transcends traditional linear assumptions by leveraging mutual infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08155","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/2509.08155/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":"2509.08155","created_at":"2026-07-05T12:08:23.935163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08155v1","created_at":"2026-07-05T12:08:23.935163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08155","created_at":"2026-07-05T12:08:23.935163+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWYBQFQ4UNKH","created_at":"2026-07-05T12:08:23.935163+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWYBQFQ4UNKHQ5PY","created_at":"2026-07-05T12:08:23.935163+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWYBQFQ4","created_at":"2026-07-05T12:08:23.935163+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/IWYBQFQ4UNKHQ5PYLMB6OK6TWG","json":"https://pith.science/pith/IWYBQFQ4UNKHQ5PYLMB6OK6TWG.json","graph_json":"https://pith.science/api/pith-number/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/graph.json","events_json":"https://pith.science/api/pith-number/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/events.json","paper":"https://pith.science/paper/IWYBQFQ4"},"agent_actions":{"view_html":"https://pith.science/pith/IWYBQFQ4UNKHQ5PYLMB6OK6TWG","download_json":"https://pith.science/pith/IWYBQFQ4UNKHQ5PYLMB6OK6TWG.json","view_paper":"https://pith.science/paper/IWYBQFQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08155&json=true","fetch_graph":"https://pith.science/api/pith-number/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/graph.json","fetch_events":"https://pith.science/api/pith-number/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/action/storage_attestation","attest_author":"https://pith.science/pith/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/action/author_attestation","sign_citation":"https://pith.science/pith/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/action/citation_signature","submit_replication":"https://pith.science/pith/IWYBQFQ4UNKHQ5PYLMB6OK6TWG/action/replication_record"}},"created_at":"2026-07-05T12:08:23.935163+00:00","updated_at":"2026-07-05T12:08:23.935163+00:00"}