{"id":"W4402905695","doi":"10.1167/jov.24.10.1463","title":"Deep learning models for lightness constancy can exploit both natural lighting cues and rendering artifacts.","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Visual perception and processing mechanisms","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Exploit; Rendering (computer graphics); Lightness; Computer science; Artificial intelligence; Color constancy; Computer vision; Natural (archaeology); Geology","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":[0.0008125698,0.001709032,0.0005524266,0.0004157196,0.0002494643,0.001081288,0.001671557,0.001116757,0.002075937],"category_scores_gemma":[0.002733682,0.0005994667,0.0009066163,0.0004590144,0.0005355271,0.001534591,0.000725483,0.002643986,0.0007563517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001224571,"about_ca_system_score_gemma":0.0007128036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01015877,"about_ca_topic_score_gemma":0.01571748,"domain_scores_codex":[0.9997802,0.00003446364,0.000007939778,0.00009430928,0.00003966464,0.00004337604],"domain_scores_gemma":[0.9994569,0.0002480577,0.00005999254,0.00009123445,0.0001071737,0.00003644698],"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":[0.0001305538,0.0001248646,0.002254357,0.0001046455,0.0001502622,0.00005964843,0.00006581558,0.8409164,0.01840013,0.002854399,0.003536261,0.1314026],"study_design_scores_gemma":[0.000004193848,0.0000197187,0.0002577506,0.000009359566,0.000009393349,0.000009562972,0.000004984314,0.9955881,0.002395071,0.001256245,0.0004401495,0.000005438217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1904673,0.001605798,0.7922667,0.001021228,0.0002409253,0.0001075313,0.0007434118,0.005973314,0.007573781],"genre_scores_gemma":[0.8315258,0.0006259478,0.1542684,0.0006411176,0.00008324984,0.000148267,0.001687756,0.0005484689,0.01047105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01015877,"threshold_uncertainty_score":0.0201993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06737809097833539,"score_gpt":0.3420867202260699,"score_spread":0.2747086292477345,"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."}}