{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:VCQIFTP4CSX23QSCPZXFD5GUWE","short_pith_number":"pith:VCQIFTP4","schema_version":"1.0","canonical_sha256":"a8a082cdfc14afadc2427e6e51f4d4b137d49f4dc80acf2aa8a6675afad5a941","source":{"kind":"arxiv","id":"1507.03285","version":1},"attestation_state":"computed","paper":{"title":"Scatter Matrix Concordance: A Diagnostic for Regressions on Subsets of Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Bryan Lewis, Michael J. Kane, Sekhar Tatikonda, Simon Urbanek","submitted_at":"2015-07-12T22:51:07Z","abstract_excerpt":"Linear regression models depend directly on the design matrix and its properties. Techniques that efficiently estimate model coefficients by partitioning rows of the design matrix are increasingly popular for large-scale problems because they fit well with modern parallel computing architectures. We propose a simple measure of {\\em concordance} between a design matrix and a subset of its rows that estimates how well a subset captures the variance-covariance structure of a larger data set. We illustrate the use of this measure in a heuristic method for selecting row partition sizes that balance"},"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":"1507.03285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-12T22:51:07Z","cross_cats_sorted":[],"title_canon_sha256":"3fa8bbfde7dd403316aa21dbd7c75de0ec3b24b43e99dfaa7e2dcb2bb398b7d3","abstract_canon_sha256":"08fd449071ee5e73e2db96cee654ea13747b91190e290afcd572e9b444611420"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:05.059053Z","signature_b64":"FrJaYuTBCSU2WxAHUldAE0OjlnbFdH3CEt/C+synkhkBJRKEOAboPDZodzr2BTXztFHBZew959pSvak+2SBKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8a082cdfc14afadc2427e6e51f4d4b137d49f4dc80acf2aa8a6675afad5a941","last_reissued_at":"2026-05-17T23:40:05.058341Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:05.058341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scatter Matrix Concordance: A Diagnostic for Regressions on Subsets of Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Bryan Lewis, Michael J. Kane, Sekhar Tatikonda, Simon Urbanek","submitted_at":"2015-07-12T22:51:07Z","abstract_excerpt":"Linear regression models depend directly on the design matrix and its properties. Techniques that efficiently estimate model coefficients by partitioning rows of the design matrix are increasingly popular for large-scale problems because they fit well with modern parallel computing architectures. We propose a simple measure of {\\em concordance} between a design matrix and a subset of its rows that estimates how well a subset captures the variance-covariance structure of a larger data set. We illustrate the use of this measure in a heuristic method for selecting row partition sizes that balance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.03285","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":"1507.03285","created_at":"2026-05-17T23:40:05.058466+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.03285v1","created_at":"2026-05-17T23:40:05.058466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.03285","created_at":"2026-05-17T23:40:05.058466+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCQIFTP4CSX2","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCQIFTP4CSX23QSC","created_at":"2026-05-18T12:29:44.643036+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCQIFTP4","created_at":"2026-05-18T12:29:44.643036+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/VCQIFTP4CSX23QSCPZXFD5GUWE","json":"https://pith.science/pith/VCQIFTP4CSX23QSCPZXFD5GUWE.json","graph_json":"https://pith.science/api/pith-number/VCQIFTP4CSX23QSCPZXFD5GUWE/graph.json","events_json":"https://pith.science/api/pith-number/VCQIFTP4CSX23QSCPZXFD5GUWE/events.json","paper":"https://pith.science/paper/VCQIFTP4"},"agent_actions":{"view_html":"https://pith.science/pith/VCQIFTP4CSX23QSCPZXFD5GUWE","download_json":"https://pith.science/pith/VCQIFTP4CSX23QSCPZXFD5GUWE.json","view_paper":"https://pith.science/paper/VCQIFTP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.03285&json=true","fetch_graph":"https://pith.science/api/pith-number/VCQIFTP4CSX23QSCPZXFD5GUWE/graph.json","fetch_events":"https://pith.science/api/pith-number/VCQIFTP4CSX23QSCPZXFD5GUWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCQIFTP4CSX23QSCPZXFD5GUWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCQIFTP4CSX23QSCPZXFD5GUWE/action/storage_attestation","attest_author":"https://pith.science/pith/VCQIFTP4CSX23QSCPZXFD5GUWE/action/author_attestation","sign_citation":"https://pith.science/pith/VCQIFTP4CSX23QSCPZXFD5GUWE/action/citation_signature","submit_replication":"https://pith.science/pith/VCQIFTP4CSX23QSCPZXFD5GUWE/action/replication_record"}},"created_at":"2026-05-17T23:40:05.058466+00:00","updated_at":"2026-05-17T23:40:05.058466+00:00"}