{"id":"W4387435243","doi":"10.1007/978-3-031-45249-9_27","title":"Debiasing Counterfactuals in the Presence of Spurious Correlations","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Engineering and Physical Sciences Research Council","keywords":"Spurious relationship; Counterfactual thinking; Debiasing; Computer science; Artificial intelligence; Machine learning; Correlation; Population; Classifier (UML); Metric (unit); A priori and a posteriori; Pattern recognition (psychology); Mathematics; Psychology; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05941413,0.001294015,0.002729175,0.002955384,0.001288854,0.006557347,0.003077877,0.003899999,0.005968194],"category_scores_gemma":[0.3364973,0.001538457,0.001378286,0.002797412,0.007307266,0.01166211,0.006337411,0.006442753,0.0006719602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001492783,"about_ca_system_score_gemma":0.001763859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001027785,"about_ca_topic_score_gemma":0.0008929052,"domain_scores_codex":[0.9705718,0.02091037,0.001586082,0.002679012,0.003533879,0.0007190269],"domain_scores_gemma":[0.5196558,0.4322404,0.01671097,0.02614905,0.004131167,0.001112505],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007029661,0.0001004015,0.00656087,0.0003672338,0.0004057451,0.001048695,0.0009870356,0.0662714,0.0009336621,0.8285736,0.003478669,0.09056983],"study_design_scores_gemma":[0.00006544826,0.00006770321,0.0006208718,0.0001345419,0.00007399651,0.0003060941,0.0001131352,0.3078211,0.0009691635,0.6881788,0.001612712,0.00003648833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06297426,0.002902475,0.9195349,0.003822543,0.0004324217,0.0001011302,0.0001576974,0.0004821911,0.009592278],"genre_scores_gemma":[0.7972738,0.001265127,0.1947885,0.0008718096,0.0006792873,0.0001930239,0.0002353809,0.0002122595,0.004480869],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05941413,"threshold_uncertainty_score":0.3142157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04550542943998621,"score_gpt":0.3192125921469094,"score_spread":0.2737071627069232,"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."}}