{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TUNRE4CADU2OJLNDG6D5QANV3F","short_pith_number":"pith:TUNRE4CA","canonical_record":{"source":{"id":"1907.04102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-09T11:57:22Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"ac5e092bdd2941b128874a4a607771c8ab5cc7515c05432cff55e4b30df771ff","abstract_canon_sha256":"7f664eb40e0a72400a35f51ad52411c011d21063f46cbc8456a73d54778af300"},"schema_version":"1.0"},"canonical_sha256":"9d1b1270401d34e4ada33787d801b5d970eb48ddea6724f6b89afff14f63f096","source":{"kind":"arxiv","id":"1907.04102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04102","created_at":"2026-05-17T23:41:03Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04102v1","created_at":"2026-05-17T23:41:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04102","created_at":"2026-05-17T23:41:03Z"},{"alias_kind":"pith_short_12","alias_value":"TUNRE4CADU2O","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TUNRE4CADU2OJLND","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TUNRE4CA","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TUNRE4CADU2OJLNDG6D5QANV3F","target":"record","payload":{"canonical_record":{"source":{"id":"1907.04102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-09T11:57:22Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"ac5e092bdd2941b128874a4a607771c8ab5cc7515c05432cff55e4b30df771ff","abstract_canon_sha256":"7f664eb40e0a72400a35f51ad52411c011d21063f46cbc8456a73d54778af300"},"schema_version":"1.0"},"canonical_sha256":"9d1b1270401d34e4ada33787d801b5d970eb48ddea6724f6b89afff14f63f096","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:03.315332Z","signature_b64":"STIpTKjr3whWgotdE+TtcXtj3kkPI6jik9W3ihcfaAwXP8YWK/I2HW7tjqMahXoUkRQUxu4yCFFlGxtC8/owAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d1b1270401d34e4ada33787d801b5d970eb48ddea6724f6b89afff14f63f096","last_reissued_at":"2026-05-17T23:41:03.314649Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:03.314649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.04102","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":"2026-05-17T23:41:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4pQdeHNVs+qKlhJ2ynEAseaATMZWwc2ZZ2r3XKe43I7SRcy21BqJ4QatNnPlw+Zu0wvzj6gaGzpmdx4dYTP7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:24:36.483964Z"},"content_sha256":"a33d08d91a813a207b5d4456be656a54641a4129c0a89a49b452bfe38ab8050f","schema_version":"1.0","event_id":"sha256:a33d08d91a813a207b5d4456be656a54641a4129c0a89a49b452bfe38ab8050f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TUNRE4CADU2OJLNDG6D5QANV3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying Confounding Bias in Neuroimaging Datasets with Causal Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anna Rieckmann, Benjamin Gutierrez Becker, Christian Wachinger, Sebastian P\\\"olsterl","submitted_at":"2019-07-09T11:57:22Z","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 machine learning models. A potential solution is to increase sample size by pooling scans from several datasets. In this work, we combine 12,207 MRI scans from 15 studies and show that simple pooling is often ill-advised due to introducing various types of biases in the training data. First, we systematically define these biases. Second, we detect bias by experimentally showing that scans can be correctly assigned to the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04102","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":"2026-05-17T23:41:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXvXyBCK8HOa/T89x5v59P4mereEI2h2nB7KzmPJqzhXr8/r3nKYpZy33dcY6wX6fu5dkK++XHQFOk/7+tr1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T15:24:36.484698Z"},"content_sha256":"97129fe344e324d6c8ea1e1aceaecc9c720e1b1d3ea8802b6dca83a98c409a5f","schema_version":"1.0","event_id":"sha256:97129fe344e324d6c8ea1e1aceaecc9c720e1b1d3ea8802b6dca83a98c409a5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUNRE4CADU2OJLNDG6D5QANV3F/bundle.json","state_url":"https://pith.science/pith/TUNRE4CADU2OJLNDG6D5QANV3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUNRE4CADU2OJLNDG6D5QANV3F/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":"2026-05-29T15:24:36Z","links":{"resolver":"https://pith.science/pith/TUNRE4CADU2OJLNDG6D5QANV3F","bundle":"https://pith.science/pith/TUNRE4CADU2OJLNDG6D5QANV3F/bundle.json","state":"https://pith.science/pith/TUNRE4CADU2OJLNDG6D5QANV3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUNRE4CADU2OJLNDG6D5QANV3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TUNRE4CADU2OJLNDG6D5QANV3F","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":"7f664eb40e0a72400a35f51ad52411c011d21063f46cbc8456a73d54778af300","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-09T11:57:22Z","title_canon_sha256":"ac5e092bdd2941b128874a4a607771c8ab5cc7515c05432cff55e4b30df771ff"},"schema_version":"1.0","source":{"id":"1907.04102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04102","created_at":"2026-05-17T23:41:03Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04102v1","created_at":"2026-05-17T23:41:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04102","created_at":"2026-05-17T23:41:03Z"},{"alias_kind":"pith_short_12","alias_value":"TUNRE4CADU2O","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TUNRE4CADU2OJLND","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TUNRE4CA","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:97129fe344e324d6c8ea1e1aceaecc9c720e1b1d3ea8802b6dca83a98c409a5f","target":"graph","created_at":"2026-05-17T23:41:03Z","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":"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 machine learning models. A potential solution is to increase sample size by pooling scans from several datasets. In this work, we combine 12,207 MRI scans from 15 studies and show that simple pooling is often ill-advised due to introducing various types of biases in the training data. First, we systematically define these biases. Second, we detect bias by experimentally showing that scans can be correctly assigned to the","authors_text":"Anna Rieckmann, Benjamin Gutierrez Becker, Christian Wachinger, Sebastian P\\\"olsterl","cross_cats":["cs.CV","eess.IV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-09T11:57:22Z","title":"Quantifying Confounding Bias in Neuroimaging Datasets with Causal Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04102","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:a33d08d91a813a207b5d4456be656a54641a4129c0a89a49b452bfe38ab8050f","target":"record","created_at":"2026-05-17T23:41:03Z","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":"7f664eb40e0a72400a35f51ad52411c011d21063f46cbc8456a73d54778af300","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-09T11:57:22Z","title_canon_sha256":"ac5e092bdd2941b128874a4a607771c8ab5cc7515c05432cff55e4b30df771ff"},"schema_version":"1.0","source":{"id":"1907.04102","kind":"arxiv","version":1}},"canonical_sha256":"9d1b1270401d34e4ada33787d801b5d970eb48ddea6724f6b89afff14f63f096","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d1b1270401d34e4ada33787d801b5d970eb48ddea6724f6b89afff14f63f096","first_computed_at":"2026-05-17T23:41:03.314649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:03.314649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"STIpTKjr3whWgotdE+TtcXtj3kkPI6jik9W3ihcfaAwXP8YWK/I2HW7tjqMahXoUkRQUxu4yCFFlGxtC8/owAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:03.315332Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.04102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a33d08d91a813a207b5d4456be656a54641a4129c0a89a49b452bfe38ab8050f","sha256:97129fe344e324d6c8ea1e1aceaecc9c720e1b1d3ea8802b6dca83a98c409a5f"],"state_sha256":"e95095e398c5c976f702d56c3718a3076dbcdde9f0f5bef5223832fd7fb41cd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KiVXCgGMgT6BW0e1n/s2F6qB0tnfJYm2CBUgdNi9D1Pm/nwjqwD8W2c0R6+AFERQeaSKISs3G1tdiHbd9v9qCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T15:24:36.488381Z","bundle_sha256":"39e877711cf581d580b240e3c20cc1cdc9ee044998e9d0d27b77d7c2724aef8f"}}