{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VDB6MRWEMEKRHRFZWBCWZG4R3F","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":"afba20282220cfaac649c05d76aec5b23e3f1501730f40ea3b662cd99e1b1f7b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T15:49:04Z","title_canon_sha256":"0fa6d5ec17817496ea6d3d355eb853a21a6684193f16c952155bfa6a08d15006"},"schema_version":"1.0","source":{"id":"2410.19643","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.19643","created_at":"2026-07-05T11:07:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.19643v4","created_at":"2026-07-05T11:07:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19643","created_at":"2026-07-05T11:07:16Z"},{"alias_kind":"pith_short_12","alias_value":"VDB6MRWEMEKR","created_at":"2026-07-05T11:07:16Z"},{"alias_kind":"pith_short_16","alias_value":"VDB6MRWEMEKRHRFZ","created_at":"2026-07-05T11:07:16Z"},{"alias_kind":"pith_short_8","alias_value":"VDB6MRWE","created_at":"2026-07-05T11:07:16Z"}],"graph_snapshots":[{"event_id":"sha256:7a058639220636542ca51ce8cb384152438e43ff0d79ffbde081c33947ec155c","target":"graph","created_at":"2026-07-05T11:07:16Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.19643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Artur Lichtenberg, Christian Jung, Federico Raimondo, Kaustubh R. Patil, Kersten Diers, Malte Kelm, Martin Reuter, Nicol\\'as Nieto, Simon B. Eickhoff","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T15:49:04Z","title":"Impact of Leakage on Data Harmonization in Machine Learning Pipelines in Class Imbalance Across Sites"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19643","kind":"arxiv","version":4},"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:f5727709baf7167cb6ad9e5f1e946fc41a0c1f1536db86a7b3ceab9156d6d3db","target":"record","created_at":"2026-07-05T11:07:16Z","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":"afba20282220cfaac649c05d76aec5b23e3f1501730f40ea3b662cd99e1b1f7b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-25T15:49:04Z","title_canon_sha256":"0fa6d5ec17817496ea6d3d355eb853a21a6684193f16c952155bfa6a08d15006"},"schema_version":"1.0","source":{"id":"2410.19643","kind":"arxiv","version":4}},"canonical_sha256":"a8c3e646c4611513c4b9b0456c9b91d95dd4c091a9fc659b5e39905e6791a00e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8c3e646c4611513c4b9b0456c9b91d95dd4c091a9fc659b5e39905e6791a00e","first_computed_at":"2026-07-05T11:07:16.036793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:16.036793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8378YXQIYa7RWa2r7oar2u4VH13c+rMfEiBB6Bi5e5TKbTru72gr81z2qYrXQqDNSg1hUG6nUl4PdLfZrViWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:16.037313Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.19643","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5727709baf7167cb6ad9e5f1e946fc41a0c1f1536db86a7b3ceab9156d6d3db","sha256:7a058639220636542ca51ce8cb384152438e43ff0d79ffbde081c33947ec155c"],"state_sha256":"3af9dea176f9246ba53faa2884155cf1137c6e91a6b4ed32679c604e0cd886d6"}