{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:S2WT5GEOVCRJAN62M5PMR66CYR","short_pith_number":"pith:S2WT5GEO","canonical_record":{"source":{"id":"1912.07661","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T18:45:25Z","cross_cats_sorted":["eess.IV","q-bio.QM","stat.ML"],"title_canon_sha256":"3b169fd5a82c60169f4040c3ed18dd6df5a65d007c00e363b42442225dba9366","abstract_canon_sha256":"16484b7b777e2511197d57a4fd2269bfae6f1d8913de24b16fb8c13e19956cc7"},"schema_version":"1.0"},"canonical_sha256":"96ad3e988ea8a29037da675ec8fbc2c457a5f0beb532c6ef8faf1ceacbaa4559","source":{"kind":"arxiv","id":"1912.07661","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.07661","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"arxiv_version","alias_value":"1912.07661v2","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07661","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"pith_short_12","alias_value":"S2WT5GEOVCRJ","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"pith_short_16","alias_value":"S2WT5GEOVCRJAN62","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"pith_short_8","alias_value":"S2WT5GEO","created_at":"2026-07-05T00:53:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:S2WT5GEOVCRJAN62M5PMR66CYR","target":"record","payload":{"canonical_record":{"source":{"id":"1912.07661","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T18:45:25Z","cross_cats_sorted":["eess.IV","q-bio.QM","stat.ML"],"title_canon_sha256":"3b169fd5a82c60169f4040c3ed18dd6df5a65d007c00e363b42442225dba9366","abstract_canon_sha256":"16484b7b777e2511197d57a4fd2269bfae6f1d8913de24b16fb8c13e19956cc7"},"schema_version":"1.0"},"canonical_sha256":"96ad3e988ea8a29037da675ec8fbc2c457a5f0beb532c6ef8faf1ceacbaa4559","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:09.882752Z","signature_b64":"6Y9fsiLeIjjD0Z8ldjSpjSJ8nZ+Q/0udZtIGWqwvJ0XVKFZsSSeweFMZtOIpmCyjltGZYh2Il9jKpzhjREBWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96ad3e988ea8a29037da675ec8fbc2c457a5f0beb532c6ef8faf1ceacbaa4559","last_reissued_at":"2026-07-05T00:53:09.882312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:09.882312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.07661","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:53:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1foADPFJ+j4bQv1OLMEy9yKZisV9W1+efXropr4ha4sQxnw7jvPKD4EqR+x4or/xj2DwstqayXwlD/yVPkKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:55:13.347125Z"},"content_sha256":"ddbf2d2f2f9effff034bfe3ffd3e9af82fd971bdfd1d54d0589c0b0c0599e2a9","schema_version":"1.0","event_id":"sha256:ddbf2d2f2f9effff034bfe3ffd3e9af82fd971bdfd1d54d0589c0b0c0599e2a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:S2WT5GEOVCRJAN62M5PMR66CYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"It's easy to fool yourself: Case studies on identifying bias and confounding in bio-medical datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anton Geraschenko, Arunachalam Narayanaswamy, Brian Wainger, Christine Marques, James Hawrot, Joao Pereira, Lee Rubin, Marc Berndl, Michael Brenner, Nina Makhortova, Samuel Yang, Scott Lipnick, Subhashini Venugopalan","submitted_at":"2019-12-12T18:45:25Z","abstract_excerpt":"Confounding variables are a well known source of nuisance in biomedical studies. They present an even greater challenge when we combine them with black-box machine learning techniques that operate on raw data. This work presents two case studies. In one, we discovered biases arising from systematic errors in the data generation process. In the other, we found a spurious source of signal unrelated to the prediction task at hand. In both cases, our prediction models performed well but under careful examination hidden confounders and biases were revealed. These are cautionary tales on the limits "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07661","kind":"arxiv","version":2},"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/1912.07661/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:53:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmZKUElJEAUH4FssiaN3vnL2avc/oyQLMO9eY7DEGs+pFN3/SiA4jHfrIGHhDYH47D4eG7w8Y6N/45ih4cbsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:55:13.347873Z"},"content_sha256":"425ae2668bda8e8c6b202a800737d81769fe1bdc7319d420f86058f494b53a4e","schema_version":"1.0","event_id":"sha256:425ae2668bda8e8c6b202a800737d81769fe1bdc7319d420f86058f494b53a4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S2WT5GEOVCRJAN62M5PMR66CYR/bundle.json","state_url":"https://pith.science/pith/S2WT5GEOVCRJAN62M5PMR66CYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S2WT5GEOVCRJAN62M5PMR66CYR/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":"2026-07-07T05:55:13Z","links":{"resolver":"https://pith.science/pith/S2WT5GEOVCRJAN62M5PMR66CYR","bundle":"https://pith.science/pith/S2WT5GEOVCRJAN62M5PMR66CYR/bundle.json","state":"https://pith.science/pith/S2WT5GEOVCRJAN62M5PMR66CYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S2WT5GEOVCRJAN62M5PMR66CYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:S2WT5GEOVCRJAN62M5PMR66CYR","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":"16484b7b777e2511197d57a4fd2269bfae6f1d8913de24b16fb8c13e19956cc7","cross_cats_sorted":["eess.IV","q-bio.QM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T18:45:25Z","title_canon_sha256":"3b169fd5a82c60169f4040c3ed18dd6df5a65d007c00e363b42442225dba9366"},"schema_version":"1.0","source":{"id":"1912.07661","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.07661","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"arxiv_version","alias_value":"1912.07661v2","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.07661","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"pith_short_12","alias_value":"S2WT5GEOVCRJ","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"pith_short_16","alias_value":"S2WT5GEOVCRJAN62","created_at":"2026-07-05T00:53:09Z"},{"alias_kind":"pith_short_8","alias_value":"S2WT5GEO","created_at":"2026-07-05T00:53:09Z"}],"graph_snapshots":[{"event_id":"sha256:425ae2668bda8e8c6b202a800737d81769fe1bdc7319d420f86058f494b53a4e","target":"graph","created_at":"2026-07-05T00:53:09Z","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/1912.07661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Confounding variables are a well known source of nuisance in biomedical studies. They present an even greater challenge when we combine them with black-box machine learning techniques that operate on raw data. This work presents two case studies. In one, we discovered biases arising from systematic errors in the data generation process. In the other, we found a spurious source of signal unrelated to the prediction task at hand. In both cases, our prediction models performed well but under careful examination hidden confounders and biases were revealed. These are cautionary tales on the limits ","authors_text":"Anton Geraschenko, Arunachalam Narayanaswamy, Brian Wainger, Christine Marques, James Hawrot, Joao Pereira, Lee Rubin, Marc Berndl, Michael Brenner, Nina Makhortova, Samuel Yang, Scott Lipnick, Subhashini Venugopalan","cross_cats":["eess.IV","q-bio.QM","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T18:45:25Z","title":"It's easy to fool yourself: Case studies on identifying bias and confounding in bio-medical datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.07661","kind":"arxiv","version":2},"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:ddbf2d2f2f9effff034bfe3ffd3e9af82fd971bdfd1d54d0589c0b0c0599e2a9","target":"record","created_at":"2026-07-05T00:53:09Z","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":"16484b7b777e2511197d57a4fd2269bfae6f1d8913de24b16fb8c13e19956cc7","cross_cats_sorted":["eess.IV","q-bio.QM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T18:45:25Z","title_canon_sha256":"3b169fd5a82c60169f4040c3ed18dd6df5a65d007c00e363b42442225dba9366"},"schema_version":"1.0","source":{"id":"1912.07661","kind":"arxiv","version":2}},"canonical_sha256":"96ad3e988ea8a29037da675ec8fbc2c457a5f0beb532c6ef8faf1ceacbaa4559","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96ad3e988ea8a29037da675ec8fbc2c457a5f0beb532c6ef8faf1ceacbaa4559","first_computed_at":"2026-07-05T00:53:09.882312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:53:09.882312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Y9fsiLeIjjD0Z8ldjSpjSJ8nZ+Q/0udZtIGWqwvJ0XVKFZsSSeweFMZtOIpmCyjltGZYh2Il9jKpzhjREBWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:53:09.882752Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.07661","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddbf2d2f2f9effff034bfe3ffd3e9af82fd971bdfd1d54d0589c0b0c0599e2a9","sha256:425ae2668bda8e8c6b202a800737d81769fe1bdc7319d420f86058f494b53a4e"],"state_sha256":"8385bf43f45a9f60846df9309371a20776a2b6c6d61096f9d87a2d277c0faeab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6CjEwZNcDCBnmWUYRW6vUD02ER6CNRJKD2mZNxKNEoSjmuPoRmaDYilTwaskB5Q7oqvXbvDR75XAlkATuhxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:55:13.351119Z","bundle_sha256":"845f1e91156c0820b78614c4bf75bb00bf0ebe85956b289b247b8d722b664a68"}}