{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002524908,0.0001198206,0.0002291565,0.0007202905,0.0002095904,0.00006462363,0.0007648023,0.0001024175,0.0000452195],"category_scores_gemma":[0.00007188024,0.0001036494,0.0000515214,0.0003828605,0.0008748378,0.0006975931,0.000236557,0.0003245222,0.000006958292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008352011,"about_ca_system_score_gemma":0.0002672537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000596586,"about_ca_topic_score_gemma":0.0001335743,"domain_scores_codex":[0.9984889,0.00009084474,0.0008603515,0.0001592756,0.0002727822,0.0001278317],"domain_scores_gemma":[0.9975832,0.0007937274,0.000413597,0.0007331003,0.0004476123,0.00002873959],"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":[0.00002654505,0.00003165227,0.0001725006,0.00007944812,0.000007263819,7.310582e-8,0.0104776,0.02108335,0.000006506603,0.9117852,0.00003872748,0.05629113],"study_design_scores_gemma":[0.0004710968,0.0001460502,0.001439358,0.0002079913,0.00001408373,0.000002690945,0.0009341537,0.9697658,0.000004392894,0.0240221,0.00286127,0.0001310243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005982363,0.000776761,0.6597317,0.001054848,0.0005252361,0.002066054,0.0001337408,0.00006145173,0.3296679],"genre_scores_gemma":[0.9855024,0.00006382532,0.01341303,0.0001424688,0.000008494864,0.000149518,0.00008033206,0.000006812741,0.0006331124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.97952,"threshold_uncertainty_score":0.42267,"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."}}