{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:W34DWCK7RIHJZ2W3TGN66MPYJM","short_pith_number":"pith:W34DWCK7","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"},"canonical_sha256":"b6f83b095f8a0e9ceadb999bef31f84b086ef0257d68937ffb14ba0c27a68dc0","source":{"kind":"arxiv","id":"1709.00640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00640","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00640v1","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00640","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"W34DWCK7RIHJ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"W34DWCK7RIHJZ2W3","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"W34DWCK7","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:W34DWCK7RIHJZ2W3TGN66MPYJM","target":"record","payload":{"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"},"canonical_sha256":"b6f83b095f8a0e9ceadb999bef31f84b086ef0257d68937ffb14ba0c27a68dc0","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"},"source_kind":"arxiv","source_id":"1709.00640","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XqkY05VfzyuuDejRLVEsnNv9z5n9IQdovU0DefJ4/cJgPg6BIkwndsM9lkxoclavopnhR4gouIel06q6ddG0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T01:36:51.758233Z"},"content_sha256":"ff13c2407aaba6807a2fd945e0d3a5ef7b78aaee4df1717fc3625c1507a0c3a4","schema_version":"1.0","event_id":"sha256:ff13c2407aaba6807a2fd945e0d3a5ef7b78aaee4df1717fc3625c1507a0c3a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:W34DWCK7RIHJZ2W3TGN66MPYJM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GV81LRyOY+JZaHGcjgGrZqu06UaZmXWXWTnO5sP0Q8uWW9Kx1v9e4YDYqwGfiefESoamIUncEBVTm7iFGFtiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T01:36:51.758803Z"},"content_sha256":"da7c2906ba3f81efaca3f8a06ecfb84a460828247ff3bd75bd9431ef8db8a928","schema_version":"1.0","event_id":"sha256:da7c2906ba3f81efaca3f8a06ecfb84a460828247ff3bd75bd9431ef8db8a928"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/bundle.json","state_url":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T01:36:51Z","links":{"resolver":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM","bundle":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/bundle.json","state":"https://pith.science/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W34DWCK7RIHJZ2W3TGN66MPYJM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:W34DWCK7RIHJZ2W3TGN66MPYJM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eefbe37760d80f97826ba3d5d996fafddb255ab86c8fa11d3345162d760d8459","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-09-02T22:17:31Z","title_canon_sha256":"a92efbe74414ecfaf090538332559b9f023cfd30bc6a6a00afdad87bd6a6f2a8"},"schema_version":"1.0","source":{"id":"1709.00640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00640","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00640v1","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00640","created_at":"2026-05-18T00:36:07Z"},{"alias_kind":"pith_short_12","alias_value":"W34DWCK7RIHJ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"W34DWCK7RIHJZ2W3","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"W34DWCK7","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:da7c2906ba3f81efaca3f8a06ecfb84a460828247ff3bd75bd9431ef8db8a928","target":"graph","created_at":"2026-05-18T00:36:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Grace Wahba, Hao Henry Zhou, Sterling C. Johnson, Vamsi K. Ithapu, Vikas Singh, Yilin Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-09-02T22:17:31Z","title":"When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\\ell_2$-consistency and Neuroscience Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00640","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ff13c2407aaba6807a2fd945e0d3a5ef7b78aaee4df1717fc3625c1507a0c3a4","target":"record","created_at":"2026-05-18T00:36:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eefbe37760d80f97826ba3d5d996fafddb255ab86c8fa11d3345162d760d8459","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-09-02T22:17:31Z","title_canon_sha256":"a92efbe74414ecfaf090538332559b9f023cfd30bc6a6a00afdad87bd6a6f2a8"},"schema_version":"1.0","source":{"id":"1709.00640","kind":"arxiv","version":1}},"canonical_sha256":"b6f83b095f8a0e9ceadb999bef31f84b086ef0257d68937ffb14ba0c27a68dc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6f83b095f8a0e9ceadb999bef31f84b086ef0257d68937ffb14ba0c27a68dc0","first_computed_at":"2026-05-18T00:36:07.401489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:07.401489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dN9ffUIS0ku8OgDng3GjdQBwdQ2xN2zFuXClz4RemMNUFEA+2V2RdtopkeFdmJZuWLDMSIYYfZz6zUGksIoTAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:07.402181Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff13c2407aaba6807a2fd945e0d3a5ef7b78aaee4df1717fc3625c1507a0c3a4","sha256:da7c2906ba3f81efaca3f8a06ecfb84a460828247ff3bd75bd9431ef8db8a928"],"state_sha256":"891deb59471be954887bdef1d3959b0a257c9745704b2efd8e73f973b87f6b99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vxMjf97D3UTvaxpR0rRm7xgQ9PyBBM65JEHakIpM/a9Ulnc/Q1HQn7XBFnToJQYnIs9x0K/FZuTRqrNid16SBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T01:36:51.761697Z","bundle_sha256":"8edf48d5e0b781706cfeeb9baecf2713e4615a1f44700d57ea2dbe48a5d3485a"}}