{"id":"W2806245989","doi":"10.1002/sdtp.12154","title":"P‐31: A Statistical Paradigm for Assessment of Subjective Image Quality Results","year":2018,"lang":"en","type":"article","venue":"SID Symposium Digest of Technical Papers","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Qualcomm (Canada); York University","funders":"","keywords":"Codec; Computer science; Selection (genetic algorithm); Quality (philosophy); Image quality; Artificial intelligence; Machine learning; Image (mathematics); Data mining; Telecommunications","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":[0.002039179,0.0002046644,0.0005261098,0.00009966311,0.0001118384,0.0000527497,0.0008925594,0.0001399502,0.000005967088],"category_scores_gemma":[0.0008245539,0.0001772855,0.0001938693,0.0003498794,0.0007074619,0.000243957,0.0002380616,0.000184761,0.000003237455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001189221,"about_ca_system_score_gemma":0.0002762641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009657254,"about_ca_topic_score_gemma":0.00002062327,"domain_scores_codex":[0.9973853,0.000282227,0.0008491806,0.0005903699,0.0005045649,0.0003884203],"domain_scores_gemma":[0.9964753,0.001862994,0.0003609081,0.0008599008,0.0003054711,0.0001354168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002685699,0.0002302096,0.0001284964,0.00006128968,0.00002769336,0.000004506544,0.0001269809,0.000006101631,0.8764921,0.1217916,0.0004083434,0.0004540466],"study_design_scores_gemma":[0.006622194,0.007168518,0.2005388,0.0002630912,0.0001348003,0.00003476239,0.00007365314,0.0009706307,0.7490549,0.02839799,0.005605076,0.001135548],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007043374,0.00002709582,0.5219937,0.002424971,0.0004113034,0.0009054467,0.0002679645,0.0002244659,0.4667017],"genre_scores_gemma":[0.8132585,0.000007420706,0.1863803,0.0001156494,0.00006588906,0.00003207826,0.00001052139,0.0000124507,0.0001172413],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8062151,"threshold_uncertainty_score":0.7229491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03242513996299233,"score_gpt":0.3716313176160926,"score_spread":0.3392061776531002,"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."}}