{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VDB6MRWEMEKRHRFZWBCWZG4R3F","short_pith_number":"pith:VDB6MRWE","schema_version":"1.0","canonical_sha256":"a8c3e646c4611513c4b9b0456c9b91d95dd4c091a9fc659b5e39905e6791a00e","source":{"kind":"arxiv","id":"2410.19643","version":4},"attestation_state":"computed","paper":{"title":"Impact of Leakage on Data Harmonization in Machine Learning Pipelines in Class Imbalance Across Sites","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Artur Lichtenberg, Christian Jung, Federico Raimondo, Kaustubh R. Patil, Kersten Diers, Malte Kelm, Martin Reuter, Nicol\\'as Nieto, Simon B. Eickhoff","submitted_at":"2024-10-25T15:49:04Z","abstract_excerpt":"Machine learning (ML) models benefit from large datasets. Collecting data in biomedical domains is costly and challenging, hence, combining datasets has become a common practice. However, datasets obtained under different conditions could present undesired site-specific variability. Data harmonization methods aim to remove site-specific variance while retaining biologically relevant information. This study evaluates the effectiveness of popularly used ComBat-based methods for harmonizing data in scenarios where the class balance is not equal across sites. We find that these methods struggle wi"},"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":"2410.19643","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T15:49:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0fa6d5ec17817496ea6d3d355eb853a21a6684193f16c952155bfa6a08d15006","abstract_canon_sha256":"afba20282220cfaac649c05d76aec5b23e3f1501730f40ea3b662cd99e1b1f7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:16.037313Z","signature_b64":"8378YXQIYa7RWa2r7oar2u4VH13c+rMfEiBB6Bi5e5TKbTru72gr81z2qYrXQqDNSg1hUG6nUl4PdLfZrViWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8c3e646c4611513c4b9b0456c9b91d95dd4c091a9fc659b5e39905e6791a00e","last_reissued_at":"2026-07-05T11:07:16.036793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:16.036793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impact of Leakage on Data Harmonization in Machine Learning Pipelines in Class Imbalance Across Sites","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Artur Lichtenberg, Christian Jung, Federico Raimondo, Kaustubh R. Patil, Kersten Diers, Malte Kelm, Martin Reuter, Nicol\\'as Nieto, Simon B. Eickhoff","submitted_at":"2024-10-25T15:49:04Z","abstract_excerpt":"Machine learning (ML) models benefit from large datasets. Collecting data in biomedical domains is costly and challenging, hence, combining datasets has become a common practice. However, datasets obtained under different conditions could present undesired site-specific variability. Data harmonization methods aim to remove site-specific variance while retaining biologically relevant information. This study evaluates the effectiveness of popularly used ComBat-based methods for harmonizing data in scenarios where the class balance is not equal across sites. We find that these methods struggle wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19643","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/2410.19643/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":"2410.19643","created_at":"2026-07-05T11:07:16.036856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19643v4","created_at":"2026-07-05T11:07:16.036856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19643","created_at":"2026-07-05T11:07:16.036856+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDB6MRWEMEKR","created_at":"2026-07-05T11:07:16.036856+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDB6MRWEMEKRHRFZ","created_at":"2026-07-05T11:07:16.036856+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDB6MRWE","created_at":"2026-07-05T11:07:16.036856+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/VDB6MRWEMEKRHRFZWBCWZG4R3F","json":"https://pith.science/pith/VDB6MRWEMEKRHRFZWBCWZG4R3F.json","graph_json":"https://pith.science/api/pith-number/VDB6MRWEMEKRHRFZWBCWZG4R3F/graph.json","events_json":"https://pith.science/api/pith-number/VDB6MRWEMEKRHRFZWBCWZG4R3F/events.json","paper":"https://pith.science/paper/VDB6MRWE"},"agent_actions":{"view_html":"https://pith.science/pith/VDB6MRWEMEKRHRFZWBCWZG4R3F","download_json":"https://pith.science/pith/VDB6MRWEMEKRHRFZWBCWZG4R3F.json","view_paper":"https://pith.science/paper/VDB6MRWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19643&json=true","fetch_graph":"https://pith.science/api/pith-number/VDB6MRWEMEKRHRFZWBCWZG4R3F/graph.json","fetch_events":"https://pith.science/api/pith-number/VDB6MRWEMEKRHRFZWBCWZG4R3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDB6MRWEMEKRHRFZWBCWZG4R3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDB6MRWEMEKRHRFZWBCWZG4R3F/action/storage_attestation","attest_author":"https://pith.science/pith/VDB6MRWEMEKRHRFZWBCWZG4R3F/action/author_attestation","sign_citation":"https://pith.science/pith/VDB6MRWEMEKRHRFZWBCWZG4R3F/action/citation_signature","submit_replication":"https://pith.science/pith/VDB6MRWEMEKRHRFZWBCWZG4R3F/action/replication_record"}},"created_at":"2026-07-05T11:07:16.036856+00:00","updated_at":"2026-07-05T11:07:16.036856+00:00"}