{"id":"W4200501894","doi":"10.21203/rs.3.rs-943804/v1","title":"Biased Data, Biased AI: Deep Networks Predict the Acquisition Site of TCGA Images","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University; McMaster University; University of Waterloo","funders":"","keywords":"Digital pathology; Computer science; Demographics; Artificial intelligence; Deep learning; Scope (computer science); Machine learning; Data science; Pattern recognition (psychology); Demography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004711492,0.000315307,0.0004304491,0.0004413236,0.0004310551,0.001014434,0.00453562,0.0004280093,0.0001400293],"category_scores_gemma":[0.00057501,0.0002591945,0.0001967182,0.001688972,0.0003829369,0.0007569661,0.01020278,0.002548651,0.00002646886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000385392,"about_ca_system_score_gemma":0.0009624101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009533852,"about_ca_topic_score_gemma":0.0002379063,"domain_scores_codex":[0.9927662,0.002027599,0.0005651779,0.001505169,0.002343608,0.0007922595],"domain_scores_gemma":[0.9906178,0.00137741,0.0002860477,0.006024673,0.001512894,0.0001812189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005028408,0.0009760747,0.01197753,0.005073972,0.0008915747,0.0006006107,0.005372237,0.5258849,0.005694402,0.0008120914,0.1103451,0.3318686],"study_design_scores_gemma":[0.0003755065,0.0002114625,0.01885846,0.001134275,0.00002581733,0.00001121129,0.0002132716,0.9736755,0.003360288,0.0007848332,0.001045843,0.0003034842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01113495,0.004315793,0.9778125,0.003144149,0.001228708,0.001427698,0.0003197585,0.0002463163,0.0003700864],"genre_scores_gemma":[0.9918871,0.001183222,0.004460567,0.0001674144,0.0009418799,0.0002430714,0.0009819929,0.00004637518,0.00008838312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9807522,"threshold_uncertainty_score":0.9999861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07956605645229957,"score_gpt":0.3862819758299171,"score_spread":0.3067159193776175,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}