{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:G64HMTXIKGXY4GGERYW5RPWV4O","short_pith_number":"pith:G64HMTXI","schema_version":"1.0","canonical_sha256":"37b8764ee851af8e18c48e2dd8bed5e3b9c81d77fcd87797c44a307ffe574310","source":{"kind":"arxiv","id":"2010.08529","version":2},"attestation_state":"computed","paper":{"title":"Feature Selection for Huge Data via Minipatch Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Genevera I. Allen, Tianyi Yao","submitted_at":"2020-10-16T17:41:08Z","abstract_excerpt":"Feature selection often leads to increased model interpretability, faster computation, and improved model performance by discarding irrelevant or redundant features. While feature selection is a well-studied problem with many widely-used techniques, there are typically two key challenges: i) many existing approaches become computationally intractable in huge-data settings with millions of observations and features; and ii) the statistical accuracy of selected features degrades in high-noise, high-correlation settings, thus hindering reliable model interpretation. We tackle these problems by pr"},"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":"2010.08529","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2020-10-16T17:41:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8bb5da03ce6d6bb9b3a58530ba6d321b96b6ed1235e7238580084a75d08ae2e0","abstract_canon_sha256":"66e576045be59732b451a829a51cd17b4f9170902b38004ee19b9e2b7b9c478f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:31.514820Z","signature_b64":"GrqhqVwyZx2mg23YuMmz82sJMguQLFz96NtvPC8lSGtJwEuESKHfxg1ZqzLm+CxPX7Pt6zEvy20T9gt1psfKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37b8764ee851af8e18c48e2dd8bed5e3b9c81d77fcd87797c44a307ffe574310","last_reissued_at":"2026-07-05T02:14:31.514428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:31.514428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Selection for Huge Data via Minipatch Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Genevera I. Allen, Tianyi Yao","submitted_at":"2020-10-16T17:41:08Z","abstract_excerpt":"Feature selection often leads to increased model interpretability, faster computation, and improved model performance by discarding irrelevant or redundant features. While feature selection is a well-studied problem with many widely-used techniques, there are typically two key challenges: i) many existing approaches become computationally intractable in huge-data settings with millions of observations and features; and ii) the statistical accuracy of selected features degrades in high-noise, high-correlation settings, thus hindering reliable model interpretation. We tackle these problems by pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08529","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/2010.08529/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":"2010.08529","created_at":"2026-07-05T02:14:31.514490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08529v2","created_at":"2026-07-05T02:14:31.514490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08529","created_at":"2026-07-05T02:14:31.514490+00:00"},{"alias_kind":"pith_short_12","alias_value":"G64HMTXIKGXY","created_at":"2026-07-05T02:14:31.514490+00:00"},{"alias_kind":"pith_short_16","alias_value":"G64HMTXIKGXY4GGE","created_at":"2026-07-05T02:14:31.514490+00:00"},{"alias_kind":"pith_short_8","alias_value":"G64HMTXI","created_at":"2026-07-05T02:14:31.514490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06661","citing_title":"iLOCO: Distribution-Free Inference for Feature Interactions","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O","json":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O.json","graph_json":"https://pith.science/api/pith-number/G64HMTXIKGXY4GGERYW5RPWV4O/graph.json","events_json":"https://pith.science/api/pith-number/G64HMTXIKGXY4GGERYW5RPWV4O/events.json","paper":"https://pith.science/paper/G64HMTXI"},"agent_actions":{"view_html":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O","download_json":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O.json","view_paper":"https://pith.science/paper/G64HMTXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08529&json=true","fetch_graph":"https://pith.science/api/pith-number/G64HMTXIKGXY4GGERYW5RPWV4O/graph.json","fetch_events":"https://pith.science/api/pith-number/G64HMTXIKGXY4GGERYW5RPWV4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O/action/storage_attestation","attest_author":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O/action/author_attestation","sign_citation":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O/action/citation_signature","submit_replication":"https://pith.science/pith/G64HMTXIKGXY4GGERYW5RPWV4O/action/replication_record"}},"created_at":"2026-07-05T02:14:31.514490+00:00","updated_at":"2026-07-05T02:14:31.514490+00:00"}