{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3R6BGYTTIF4HOQSADLZD4L6VE7","short_pith_number":"pith:3R6BGYTT","schema_version":"1.0","canonical_sha256":"dc7c13627341787742401af23e2fd527fe840e1d3021aaca55a08be6c9d97e04","source":{"kind":"arxiv","id":"2105.14647","version":1},"attestation_state":"computed","paper":{"title":"Orthogonal Subsampling for Big Data Linear Regression","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Hongquan Xu, Jake Elmstedt, Lin Wang, Weng Kee Wong","submitted_at":"2021-05-30T23:00:00Z","abstract_excerpt":"The dramatic growth of big datasets presents a new challenge to data storage and analysis. Data reduction, or subsampling, that extracts useful information from datasets is a crucial step in big data analysis. We propose an orthogonal subsampling (OSS) approach for big data with a focus on linear regression models. The approach is inspired by the fact that an orthogonal array of two levels provides the best experimental design for linear regression models in the sense that it minimizes the average variance of the estimated parameters and provides the best predictions. The merits of OSS are thr"},"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":"2105.14647","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ME","submitted_at":"2021-05-30T23:00:00Z","cross_cats_sorted":[],"title_canon_sha256":"7ad1085acad95346f334fc88a2b0544d238cd9875bd1166583965eba9f9e9520","abstract_canon_sha256":"17b1885d549e0deebcff69f7198c5c4ee4fc8372bcbff04892be7bc11a159858"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:39.744389Z","signature_b64":"YDnDelLo4nCLvJiX6aShoEx15NrBYcJ98iiOK13o4m9CdhLsLg3n5BELhkyKvpOAjw3AJzz2bA1W0IMH8in4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc7c13627341787742401af23e2fd527fe840e1d3021aaca55a08be6c9d97e04","last_reissued_at":"2026-07-05T02:44:39.743977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:39.743977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orthogonal Subsampling for Big Data Linear Regression","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Hongquan Xu, Jake Elmstedt, Lin Wang, Weng Kee Wong","submitted_at":"2021-05-30T23:00:00Z","abstract_excerpt":"The dramatic growth of big datasets presents a new challenge to data storage and analysis. Data reduction, or subsampling, that extracts useful information from datasets is a crucial step in big data analysis. We propose an orthogonal subsampling (OSS) approach for big data with a focus on linear regression models. The approach is inspired by the fact that an orthogonal array of two levels provides the best experimental design for linear regression models in the sense that it minimizes the average variance of the estimated parameters and provides the best predictions. The merits of OSS are thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14647","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/2105.14647/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":"2105.14647","created_at":"2026-07-05T02:44:39.744033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14647v1","created_at":"2026-07-05T02:44:39.744033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14647","created_at":"2026-07-05T02:44:39.744033+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R6BGYTTIF4H","created_at":"2026-07-05T02:44:39.744033+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R6BGYTTIF4HOQSA","created_at":"2026-07-05T02:44:39.744033+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R6BGYTT","created_at":"2026-07-05T02:44:39.744033+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/3R6BGYTTIF4HOQSADLZD4L6VE7","json":"https://pith.science/pith/3R6BGYTTIF4HOQSADLZD4L6VE7.json","graph_json":"https://pith.science/api/pith-number/3R6BGYTTIF4HOQSADLZD4L6VE7/graph.json","events_json":"https://pith.science/api/pith-number/3R6BGYTTIF4HOQSADLZD4L6VE7/events.json","paper":"https://pith.science/paper/3R6BGYTT"},"agent_actions":{"view_html":"https://pith.science/pith/3R6BGYTTIF4HOQSADLZD4L6VE7","download_json":"https://pith.science/pith/3R6BGYTTIF4HOQSADLZD4L6VE7.json","view_paper":"https://pith.science/paper/3R6BGYTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14647&json=true","fetch_graph":"https://pith.science/api/pith-number/3R6BGYTTIF4HOQSADLZD4L6VE7/graph.json","fetch_events":"https://pith.science/api/pith-number/3R6BGYTTIF4HOQSADLZD4L6VE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R6BGYTTIF4HOQSADLZD4L6VE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R6BGYTTIF4HOQSADLZD4L6VE7/action/storage_attestation","attest_author":"https://pith.science/pith/3R6BGYTTIF4HOQSADLZD4L6VE7/action/author_attestation","sign_citation":"https://pith.science/pith/3R6BGYTTIF4HOQSADLZD4L6VE7/action/citation_signature","submit_replication":"https://pith.science/pith/3R6BGYTTIF4HOQSADLZD4L6VE7/action/replication_record"}},"created_at":"2026-07-05T02:44:39.744033+00:00","updated_at":"2026-07-05T02:44:39.744033+00:00"}