{"id":"W4400438951","doi":"10.1007/978-3-031-63800-8_7","title":"Evaluating the Faithfulness of Causality in Saliency-Based Explanations of Deep Learning Models for Temporal Colour Constancy","year":2024,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Color perception and design","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada); University of British Columbia","funders":"","keywords":"Causality (physics); Artificial intelligence; Computer science; Natural language processing; Cognitive psychology; Psychology; Physics","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":[0.001612189,0.0004015618,0.0003689285,0.0004999864,0.0003129432,0.001314646,0.001094568,0.001156623,0.006887854],"category_scores_gemma":[0.01625476,0.0003894393,0.0005070152,0.0004015113,0.0008455757,0.003464465,0.001043618,0.002197739,0.0002674318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001025446,"about_ca_system_score_gemma":0.0005736923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002952508,"about_ca_topic_score_gemma":0.003768719,"domain_scores_codex":[0.9997434,0.000121984,0.00001538153,0.00004277649,0.00005121619,0.00002526925],"domain_scores_gemma":[0.9904971,0.008168253,0.0004120424,0.0003588199,0.0003326679,0.0002311822],"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":[0.0008609403,0.0002002532,0.008174039,0.00035174,0.0001739113,0.0002760957,0.0008396399,0.3878278,0.009292267,0.4707482,0.006232148,0.115023],"study_design_scores_gemma":[0.00002271751,0.00002910367,0.0007846273,0.00001280247,0.00001128005,0.00001966581,0.00004636034,0.7653326,0.0008152708,0.2326239,0.0002913511,0.00001030985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4493122,0.001021852,0.5280805,0.004947416,0.0003010562,0.00005284274,0.0004516641,0.0006837163,0.01514874],"genre_scores_gemma":[0.974843,0.0001813502,0.02335799,0.0000996437,0.00005757999,0.00001363797,0.0001442619,0.00006777054,0.001234781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006887854,"threshold_uncertainty_score":0.02304214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2211839654853968,"score_gpt":0.4321309570282689,"score_spread":0.2109469915428721,"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."}}