{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:PXEVL43X4FW7QVPUEPNLN723ES","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"01aa91e22e056be725c36d26f4bf9ec1a8a69e741072931a94ad381962025e6c","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2012-09-26T11:52:44Z","title_canon_sha256":"a006546147373f87e42b9b7b8546f89c89e0008e02730f50a7f68d2582819623"},"schema_version":"1.0","source":{"id":"1209.5908","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1209.5908","created_at":"2026-05-18T02:29:32Z"},{"alias_kind":"arxiv_version","alias_value":"1209.5908v1","created_at":"2026-05-18T02:29:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1209.5908","created_at":"2026-05-18T02:29:32Z"},{"alias_kind":"pith_short_12","alias_value":"PXEVL43X4FW7","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"PXEVL43X4FW7QVPU","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"PXEVL43X","created_at":"2026-05-18T12:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:11d79df381cd3615d253242ae0495d61744fa6d2c799e77f32b089f4ec10a0cd","target":"graph","created_at":"2026-05-18T02:29:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We consider estimation in a high-dimensional linear model with strongly correlated variables. We propose to cluster the variables first and do subsequent sparse estimation such as the Lasso for cluster-representatives or the group Lasso based on the structure from the clusters. Regarding the first step, we present a novel and bottom-up agglomerative clustering algorithm based on canonical correlations, and we show that it finds an optimal solution and is statistically consistent. We also present some theoretical arguments that canonical correlation based clustering leads to a better-posed comp","authors_text":"Cun-Hui Zhang, Peter B\\\"uhlmann, Philipp R\\\"utimann, Sara van de Geer","cross_cats":["math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2012-09-26T11:52:44Z","title":"Correlated variables in regression: clustering and sparse estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1209.5908","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cac1eccf7823df96207adaaeee3f0ce10a74b7cba6b0c2a17e321c9a8504e46c","target":"record","created_at":"2026-05-18T02:29:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"01aa91e22e056be725c36d26f4bf9ec1a8a69e741072931a94ad381962025e6c","cross_cats_sorted":["math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2012-09-26T11:52:44Z","title_canon_sha256":"a006546147373f87e42b9b7b8546f89c89e0008e02730f50a7f68d2582819623"},"schema_version":"1.0","source":{"id":"1209.5908","kind":"arxiv","version":1}},"canonical_sha256":"7dc955f377e16df855f423dab6ff5b24987720b3e380e82d742449eed17c867b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dc955f377e16df855f423dab6ff5b24987720b3e380e82d742449eed17c867b","first_computed_at":"2026-05-18T02:29:32.556289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:29:32.556289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ECI9Ok7GmmSs++dI4e3DyKXJNp3OZHmbrA7IT+Nw/0QHmSsjUGQ1fn7BpR9Cp5jTEl3sQAB1FvzRQ7fYoJgwDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:29:32.556717Z","signed_message":"canonical_sha256_bytes"},"source_id":"1209.5908","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cac1eccf7823df96207adaaeee3f0ce10a74b7cba6b0c2a17e321c9a8504e46c","sha256:11d79df381cd3615d253242ae0495d61744fa6d2c799e77f32b089f4ec10a0cd"],"state_sha256":"a2b94eda27228ce58a9f28028034e394e1c433db059fb5462fc971070f24ae1b"}