{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6SV4BX3O2G2STI66DWUJGUR7UM","short_pith_number":"pith:6SV4BX3O","schema_version":"1.0","canonical_sha256":"f4abc0df6ed1b529a3de1da893523fa33d3ca7e8b1f7db23849752aa0d8eeea3","source":{"kind":"arxiv","id":"2312.00130","version":2},"attestation_state":"computed","paper":{"title":"Sparse Data-Driven Random Projection in Regression for High-Dimensional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ME","authors_text":"Laura Vana-G\\\"ur, Peter Filzmoser, Roman Parzer","submitted_at":"2023-11-30T19:00:05Z","abstract_excerpt":"We examine the linear regression problem in a challenging high-dimensional setting with correlated predictors where the vector of coefficients can vary from sparse to dense. In this setting, we propose a combination of probabilistic variable screening with random projection tools as a viable approach. More specifically, we introduce a new data-driven random projection tailored to the problem at hand and derive a theoretical bound on the gain in expected prediction error over conventional random projections. The variables to enter the projection are screened by accounting for predictor correlat"},"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":"2312.00130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-11-30T19:00:05Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"5591ea9396254ef175e7fa5f437b6dc5df96c1626412f91ae9c0da2bc39484d4","abstract_canon_sha256":"659172d6115580c587e7d3255b57d9e1d627de8213525340c5555433644fc622"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:22.576112Z","signature_b64":"Q4XPVznKTVfl/w0uzCq47TRmxwcnKUKNhk1Xq9S8qvnlZViPyERUqD8eeKzCokcRVKHFpXS5TINkwISgwhbXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4abc0df6ed1b529a3de1da893523fa33d3ca7e8b1f7db23849752aa0d8eeea3","last_reissued_at":"2026-07-05T11:01:22.575635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:22.575635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Data-Driven Random Projection in Regression for High-Dimensional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"stat.ME","authors_text":"Laura Vana-G\\\"ur, Peter Filzmoser, Roman Parzer","submitted_at":"2023-11-30T19:00:05Z","abstract_excerpt":"We examine the linear regression problem in a challenging high-dimensional setting with correlated predictors where the vector of coefficients can vary from sparse to dense. In this setting, we propose a combination of probabilistic variable screening with random projection tools as a viable approach. More specifically, we introduce a new data-driven random projection tailored to the problem at hand and derive a theoretical bound on the gain in expected prediction error over conventional random projections. The variables to enter the projection are screened by accounting for predictor correlat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00130","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/2312.00130/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":"2312.00130","created_at":"2026-07-05T11:01:22.575684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00130v2","created_at":"2026-07-05T11:01:22.575684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00130","created_at":"2026-07-05T11:01:22.575684+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SV4BX3O2G2S","created_at":"2026-07-05T11:01:22.575684+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SV4BX3O2G2STI66","created_at":"2026-07-05T11:01:22.575684+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SV4BX3O","created_at":"2026-07-05T11:01:22.575684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17808","citing_title":"spar: Sparse Projected Averaged Regression in R","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM","json":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM.json","graph_json":"https://pith.science/api/pith-number/6SV4BX3O2G2STI66DWUJGUR7UM/graph.json","events_json":"https://pith.science/api/pith-number/6SV4BX3O2G2STI66DWUJGUR7UM/events.json","paper":"https://pith.science/paper/6SV4BX3O"},"agent_actions":{"view_html":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM","download_json":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM.json","view_paper":"https://pith.science/paper/6SV4BX3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00130&json=true","fetch_graph":"https://pith.science/api/pith-number/6SV4BX3O2G2STI66DWUJGUR7UM/graph.json","fetch_events":"https://pith.science/api/pith-number/6SV4BX3O2G2STI66DWUJGUR7UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM/action/storage_attestation","attest_author":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM/action/author_attestation","sign_citation":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM/action/citation_signature","submit_replication":"https://pith.science/pith/6SV4BX3O2G2STI66DWUJGUR7UM/action/replication_record"}},"created_at":"2026-07-05T11:01:22.575684+00:00","updated_at":"2026-07-05T11:01:22.575684+00:00"}