{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PR6BO5Z4CMPGG2BQQYRFKA3TRV","short_pith_number":"pith:PR6BO5Z4","schema_version":"1.0","canonical_sha256":"7c7c17773c131e63683086225503738d521868e370c4b04d0016ce4b4227f8a4","source":{"kind":"arxiv","id":"1804.10764","version":1},"attestation_state":"computed","paper":{"title":"Detect, Quantify, and Incorporate Dataset Bias: A Neuroimaging Analysis on 12,207 Individuals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anna Rieckmann, Benjamin Gutierrez Becker, Christian Wachinger","submitted_at":"2018-04-28T09:11:34Z","abstract_excerpt":"Neuroimaging datasets keep growing in size to address increasingly complex medical questions. However, even the largest datasets today alone are too small for training complex models or for finding genome wide associations. A solution is to grow the sample size by merging data across several datasets. However, bias in datasets complicates this approach and includes additional sources of variation in the data instead. In this work, we combine 15 large neuroimaging datasets to study bias. First, we detect bias by demonstrating that scans can be correctly assigned to a dataset with 73.3% accuracy"},"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":"1804.10764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-28T09:11:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbaa2eb77f0467918df2726f2d7296ffb63c53e0e250ba246aeea0b032c6bf72","abstract_canon_sha256":"12ec6d1ceaea0f53af0f7b46d33768b79ecb651e3879ab33c509abbf10954471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:15.644632Z","signature_b64":"1RfKMXK0qygNSnxGv4mQo7Xi1NJwEVjrWcDIgEpAGUPysHAJaqA2MUPGyvHt8W4W+KRvDAWtlIBQEkAK5B9QBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c7c17773c131e63683086225503738d521868e370c4b04d0016ce4b4227f8a4","last_reissued_at":"2026-05-18T00:17:15.644208Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:15.644208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detect, Quantify, and Incorporate Dataset Bias: A Neuroimaging Analysis on 12,207 Individuals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anna Rieckmann, Benjamin Gutierrez Becker, Christian Wachinger","submitted_at":"2018-04-28T09:11:34Z","abstract_excerpt":"Neuroimaging datasets keep growing in size to address increasingly complex medical questions. However, even the largest datasets today alone are too small for training complex models or for finding genome wide associations. A solution is to grow the sample size by merging data across several datasets. However, bias in datasets complicates this approach and includes additional sources of variation in the data instead. In this work, we combine 15 large neuroimaging datasets to study bias. First, we detect bias by demonstrating that scans can be correctly assigned to a dataset with 73.3% accuracy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10764","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":"1804.10764","created_at":"2026-05-18T00:17:15.644258+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.10764v1","created_at":"2026-05-18T00:17:15.644258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10764","created_at":"2026-05-18T00:17:15.644258+00:00"},{"alias_kind":"pith_short_12","alias_value":"PR6BO5Z4CMPG","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PR6BO5Z4CMPGG2BQ","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PR6BO5Z4","created_at":"2026-05-18T12:32:46.962924+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/PR6BO5Z4CMPGG2BQQYRFKA3TRV","json":"https://pith.science/pith/PR6BO5Z4CMPGG2BQQYRFKA3TRV.json","graph_json":"https://pith.science/api/pith-number/PR6BO5Z4CMPGG2BQQYRFKA3TRV/graph.json","events_json":"https://pith.science/api/pith-number/PR6BO5Z4CMPGG2BQQYRFKA3TRV/events.json","paper":"https://pith.science/paper/PR6BO5Z4"},"agent_actions":{"view_html":"https://pith.science/pith/PR6BO5Z4CMPGG2BQQYRFKA3TRV","download_json":"https://pith.science/pith/PR6BO5Z4CMPGG2BQQYRFKA3TRV.json","view_paper":"https://pith.science/paper/PR6BO5Z4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.10764&json=true","fetch_graph":"https://pith.science/api/pith-number/PR6BO5Z4CMPGG2BQQYRFKA3TRV/graph.json","fetch_events":"https://pith.science/api/pith-number/PR6BO5Z4CMPGG2BQQYRFKA3TRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PR6BO5Z4CMPGG2BQQYRFKA3TRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PR6BO5Z4CMPGG2BQQYRFKA3TRV/action/storage_attestation","attest_author":"https://pith.science/pith/PR6BO5Z4CMPGG2BQQYRFKA3TRV/action/author_attestation","sign_citation":"https://pith.science/pith/PR6BO5Z4CMPGG2BQQYRFKA3TRV/action/citation_signature","submit_replication":"https://pith.science/pith/PR6BO5Z4CMPGG2BQQYRFKA3TRV/action/replication_record"}},"created_at":"2026-05-18T00:17:15.644258+00:00","updated_at":"2026-05-18T00:17:15.644258+00:00"}