{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NKNOK2BMZWLKSNTHFGV7G5OUSY","short_pith_number":"pith:NKNOK2BM","schema_version":"1.0","canonical_sha256":"6a9ae5682ccd96a9366729abf375d4960633c8aadd9eac5163e720794f21e0ee","source":{"kind":"arxiv","id":"1805.06915","version":1},"attestation_state":"computed","paper":{"title":"A Note on Coding and Standardization of Categorical Variables in (Sparse) Group Lasso Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"stat.CO","authors_text":"Felicitas J. Detmer, Martin Slawski","submitted_at":"2018-05-17T18:21:58Z","abstract_excerpt":"Categorical regressor variables are usually handled by introducing a set of indicator variables, and imposing a linear constraint to ensure identifiability in the presence of an intercept, or equivalently, using one of various coding schemes. As proposed in Yuan and Lin [J. R. Statist. Soc. B, 68 (2006), 49-67], the group lasso is a natural and computationally convenient approach to perform variable selection in settings with categorical covariates. As pointed out by Simon and Tibshirani [Stat. Sin., 22 (2011), 983-1001], \"standardization\" by means of block-wise orthonormalization of column su"},"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":"1805.06915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.CO","submitted_at":"2018-05-17T18:21:58Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"6dae28293e5b2b5ba5645de87e4970d42e602b33bd718eb9c751786c322d22ab","abstract_canon_sha256":"282f3c89191effafb9ee91b320dd870442a7aafa78bc2b63000a9530695270cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:42.742878Z","signature_b64":"ub+VJYV2U8xfbGZ1lQvr9wsUC47EUUtJ3wIAO/nhLD9QnhrXt8b5ZbhsJFhW7fL4o+Y0ZrM8yhhYRl31IvRcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a9ae5682ccd96a9366729abf375d4960633c8aadd9eac5163e720794f21e0ee","last_reissued_at":"2026-05-18T00:15:42.742189Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:42.742189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Note on Coding and Standardization of Categorical Variables in (Sparse) Group Lasso Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"stat.CO","authors_text":"Felicitas J. Detmer, Martin Slawski","submitted_at":"2018-05-17T18:21:58Z","abstract_excerpt":"Categorical regressor variables are usually handled by introducing a set of indicator variables, and imposing a linear constraint to ensure identifiability in the presence of an intercept, or equivalently, using one of various coding schemes. As proposed in Yuan and Lin [J. R. Statist. Soc. B, 68 (2006), 49-67], the group lasso is a natural and computationally convenient approach to perform variable selection in settings with categorical covariates. As pointed out by Simon and Tibshirani [Stat. Sin., 22 (2011), 983-1001], \"standardization\" by means of block-wise orthonormalization of column su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06915","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":""},"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":"1805.06915","created_at":"2026-05-18T00:15:42.742288+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.06915v1","created_at":"2026-05-18T00:15:42.742288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06915","created_at":"2026-05-18T00:15:42.742288+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKNOK2BMZWLK","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKNOK2BMZWLKSNTH","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKNOK2BM","created_at":"2026-05-18T12:32:40.477152+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/NKNOK2BMZWLKSNTHFGV7G5OUSY","json":"https://pith.science/pith/NKNOK2BMZWLKSNTHFGV7G5OUSY.json","graph_json":"https://pith.science/api/pith-number/NKNOK2BMZWLKSNTHFGV7G5OUSY/graph.json","events_json":"https://pith.science/api/pith-number/NKNOK2BMZWLKSNTHFGV7G5OUSY/events.json","paper":"https://pith.science/paper/NKNOK2BM"},"agent_actions":{"view_html":"https://pith.science/pith/NKNOK2BMZWLKSNTHFGV7G5OUSY","download_json":"https://pith.science/pith/NKNOK2BMZWLKSNTHFGV7G5OUSY.json","view_paper":"https://pith.science/paper/NKNOK2BM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.06915&json=true","fetch_graph":"https://pith.science/api/pith-number/NKNOK2BMZWLKSNTHFGV7G5OUSY/graph.json","fetch_events":"https://pith.science/api/pith-number/NKNOK2BMZWLKSNTHFGV7G5OUSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKNOK2BMZWLKSNTHFGV7G5OUSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKNOK2BMZWLKSNTHFGV7G5OUSY/action/storage_attestation","attest_author":"https://pith.science/pith/NKNOK2BMZWLKSNTHFGV7G5OUSY/action/author_attestation","sign_citation":"https://pith.science/pith/NKNOK2BMZWLKSNTHFGV7G5OUSY/action/citation_signature","submit_replication":"https://pith.science/pith/NKNOK2BMZWLKSNTHFGV7G5OUSY/action/replication_record"}},"created_at":"2026-05-18T00:15:42.742288+00:00","updated_at":"2026-05-18T00:15:42.742288+00:00"}