{"id":"W2964100365","doi":"10.2352/issn.2169-2629.2018.26.350","title":"Rehabilitating the ColorChecker Dataset for Illuminant Estimation","year":2018,"lang":"en","type":"article","venue":"Color and Imaging Conference","topic":"Color Science and Applications","field":"Physics and Astronomy","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Engineering and Physical Sciences Research Council","keywords":"Standard illuminant; Benchmark (surveying); Ground truth; Set (abstract data type); Computer science; Range (aeronautics); Estimation; Artificial intelligence; Algorithm; Machine learning; Data mining; Geography","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":[0.004169825,0.002386559,0.001520626,0.003717265,0.001402731,0.00296599,0.004575367,0.002236675,0.004609655],"category_scores_gemma":[0.01106752,0.000624884,0.001723859,0.004499467,0.0008399688,0.002697145,0.002479443,0.002804145,0.007650202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002635193,"about_ca_system_score_gemma":0.001790627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02535913,"about_ca_topic_score_gemma":0.0565588,"domain_scores_codex":[0.9944645,0.000882641,0.0003305682,0.001357547,0.002600606,0.0003642389],"domain_scores_gemma":[0.9927272,0.001167489,0.0002835356,0.002112318,0.003479539,0.000230043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008163794,0.0006058462,0.01309235,0.001827823,0.0005043488,0.0001606583,0.0002243578,0.0261954,0.017012,0.005521487,0.7003897,0.2336497],"study_design_scores_gemma":[0.0004726074,0.0005591778,0.0401042,0.0004278559,0.0002605039,0.000797384,0.0006744007,0.2328159,0.1116432,0.01132995,0.6003937,0.0005211817],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.1366101,0.00867893,0.2812581,0.003459252,0.00456862,0.001368859,0.3512356,0.1590297,0.05379089],"genre_scores_gemma":[0.1313635,0.001003293,0.2137602,0.001421492,0.000260986,0.0007420496,0.6363491,0.006309335,0.008790046],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02535913,"threshold_uncertainty_score":0.05042303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01873737524303075,"score_gpt":0.3200496335953371,"score_spread":0.3013122583523063,"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."}}