{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:W34DWCK7RIHJZ2W3TGN66MPYJM","short_pith_number":"pith:W34DWCK7","schema_version":"1.0","canonical_sha256":"b6f83b095f8a0e9ceadb999bef31f84b086ef0257d68937ffb14ba0c27a68dc0","source":{"kind":"arxiv","id":"1709.00640","version":1},"attestation_state":"computed","paper":{"title":"When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\\ell_2$-consistency and Neuroscience Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"Grace Wahba, Hao Henry Zhou, Sterling C. Johnson, Vamsi K. Ithapu, Vikas Singh, Yilin Zhang","submitted_at":"2017-09-02T22:17:31Z","abstract_excerpt":"Many studies in biomedical and health sciences involve small sample sizes due to logistic or financial constraints. Often, identifying weak (but scientifically interesting) associations between a set of predictors and a response necessitates pooling datasets from multiple diverse labs or groups. While there is a rich literature in statistical machine learning to address distributional shifts and inference in multi-site datasets, it is less clear ${\\it when}$ such pooling is guaranteed to help (and when it does not) -- independent of the inference algorithms we use. In this paper, we present a "},"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":"1709.00640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-09-02T22:17:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a92efbe74414ecfaf090538332559b9f023cfd30bc6a6a00afdad87bd6a6f2a8","abstract_canon_sha256":"eefbe37760d80f97826ba3d5d996fafddb255ab86c8fa11d3345162d760d8459"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:07.402181Z","signature_b64":"dN9ffUIS0ku8OgDng3GjdQBwdQ2xN2zFuXClz4RemMNUFEA+2V2RdtopkeFdmJZuWLDMSIYYfZz6zUGksIoTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6f83b095f8a0e9ceadb999bef31f84b086ef0257d68937ffb14ba0c27a68dc0","last_reissued_at":"2026-05-18T00:36:07.401489Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:07.401489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\\ell_2$-consistency and Neuroscience Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"stat.ME","authors_text":"Grace Wahba, Hao Henry Zhou, Sterling C. Johnson, Vamsi K. Ithapu, Vikas Singh, Yilin Zhang","submitted_at":"2017-09-02T22:17:31Z","abstract_excerpt":"Many studies in biomedical and health sciences involve small sample sizes due to logistic or financial constraints. Often, identifying weak (but scientifically interesting) associations between a set of predictors and a response necessitates pooling datasets from multiple diverse labs or groups. While there is a rich literature in statistical machine learning to address distributional shifts and inference in multi-site datasets, it is less clear ${\\it when}$ such pooling is guaranteed to help (and when it does not) -- independent of the inference algorithms we use. In this paper, we present a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00640","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":"1709.00640","created_at":"2026-05-18T00:36:07.401599+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.00640v1","created_at":"2026-05-18T00:36:07.401599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00640","created_at":"2026-05-18T00:36:07.401599+00:00"},{"alias_kind":"pith_short_12","alias_value":"W34DWCK7RIHJ","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"W34DWCK7RIHJZ2W3","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"W34DWCK7","created_at":"2026-05-18T12:31:49.984773+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/W34DWCK7RIHJZ2W3TGN66MPYJM","json":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM.json","graph_json":"https://pith.science/api/pith-number/W34DWCK7RIHJZ2W3TGN66MPYJM/graph.json","events_json":"https://pith.science/api/pith-number/W34DWCK7RIHJZ2W3TGN66MPYJM/events.json","paper":"https://pith.science/paper/W34DWCK7"},"agent_actions":{"view_html":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM","download_json":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM.json","view_paper":"https://pith.science/paper/W34DWCK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.00640&json=true","fetch_graph":"https://pith.science/api/pith-number/W34DWCK7RIHJZ2W3TGN66MPYJM/graph.json","fetch_events":"https://pith.science/api/pith-number/W34DWCK7RIHJZ2W3TGN66MPYJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/action/storage_attestation","attest_author":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/action/author_attestation","sign_citation":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/action/citation_signature","submit_replication":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/action/replication_record"}},"created_at":"2026-05-18T00:36:07.401599+00:00","updated_at":"2026-05-18T00:36:07.401599+00:00"}