{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LAWCFQMWZJ64K6FL6EE7BYVPO3","short_pith_number":"pith:LAWCFQMW","schema_version":"1.0","canonical_sha256":"582c22c196ca7dc578abf109f0e2af76f192397890b1425cb66c74e69e16ac0a","source":{"kind":"arxiv","id":"1905.07382","version":4},"attestation_state":"computed","paper":{"title":"Merging versus Ensembling in Multi-Study Prediction: Theoretical Insight from Random Effects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Giovanni Parmigiani, Prasad Patil, Zoe Guan","submitted_at":"2019-05-17T17:28:39Z","abstract_excerpt":"A critical decision point when training predictors using multiple studies is whether studies should be combined or treated separately. We compare two multi-study prediction approaches in the presence of potential heterogeneity in predictor-outcome relationships across datasets: 1) merging all of the datasets and training a single learner, and 2) multi-study ensembling, which involves training a separate learner on each dataset and combining the predictions resulting from each learner. For ridge regression, we show analytically and confirm via simulation that merging yields lower prediction err"},"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":"1905.07382","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-17T17:28:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d3899d81bd4bb1a0ec7864d3020ff81b0e9c3fec621ed5e9819904e267860269","abstract_canon_sha256":"89519decc731590762f573742df32ae744af3d9ca3232e30eafc0e458e0fe0ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:09.949730Z","signature_b64":"QEsnbAhN6N6nkREj5d9AO/RynipgKT4QLAmbiJyyG3kfKnlI4eb/oCK2M9PbdX/GNmjRs+Ff0fzsdoxjp17IDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"582c22c196ca7dc578abf109f0e2af76f192397890b1425cb66c74e69e16ac0a","last_reissued_at":"2026-07-05T09:48:09.949327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:09.949327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Merging versus Ensembling in Multi-Study Prediction: Theoretical Insight from Random Effects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Giovanni Parmigiani, Prasad Patil, Zoe Guan","submitted_at":"2019-05-17T17:28:39Z","abstract_excerpt":"A critical decision point when training predictors using multiple studies is whether studies should be combined or treated separately. We compare two multi-study prediction approaches in the presence of potential heterogeneity in predictor-outcome relationships across datasets: 1) merging all of the datasets and training a single learner, and 2) multi-study ensembling, which involves training a separate learner on each dataset and combining the predictions resulting from each learner. For ridge regression, we show analytically and confirm via simulation that merging yields lower prediction err"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07382","kind":"arxiv","version":4},"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/1905.07382/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":"1905.07382","created_at":"2026-07-05T09:48:09.949385+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07382v4","created_at":"2026-07-05T09:48:09.949385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07382","created_at":"2026-07-05T09:48:09.949385+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAWCFQMWZJ64","created_at":"2026-07-05T09:48:09.949385+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAWCFQMWZJ64K6FL","created_at":"2026-07-05T09:48:09.949385+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAWCFQMW","created_at":"2026-07-05T09:48:09.949385+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/LAWCFQMWZJ64K6FL6EE7BYVPO3","json":"https://pith.science/pith/LAWCFQMWZJ64K6FL6EE7BYVPO3.json","graph_json":"https://pith.science/api/pith-number/LAWCFQMWZJ64K6FL6EE7BYVPO3/graph.json","events_json":"https://pith.science/api/pith-number/LAWCFQMWZJ64K6FL6EE7BYVPO3/events.json","paper":"https://pith.science/paper/LAWCFQMW"},"agent_actions":{"view_html":"https://pith.science/pith/LAWCFQMWZJ64K6FL6EE7BYVPO3","download_json":"https://pith.science/pith/LAWCFQMWZJ64K6FL6EE7BYVPO3.json","view_paper":"https://pith.science/paper/LAWCFQMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07382&json=true","fetch_graph":"https://pith.science/api/pith-number/LAWCFQMWZJ64K6FL6EE7BYVPO3/graph.json","fetch_events":"https://pith.science/api/pith-number/LAWCFQMWZJ64K6FL6EE7BYVPO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAWCFQMWZJ64K6FL6EE7BYVPO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAWCFQMWZJ64K6FL6EE7BYVPO3/action/storage_attestation","attest_author":"https://pith.science/pith/LAWCFQMWZJ64K6FL6EE7BYVPO3/action/author_attestation","sign_citation":"https://pith.science/pith/LAWCFQMWZJ64K6FL6EE7BYVPO3/action/citation_signature","submit_replication":"https://pith.science/pith/LAWCFQMWZJ64K6FL6EE7BYVPO3/action/replication_record"}},"created_at":"2026-07-05T09:48:09.949385+00:00","updated_at":"2026-07-05T09:48:09.949385+00:00"}