{"id":"W4403153014","doi":"10.1002/jsid.2003","title":"Subjective assessment of visual fidelity: Comparison of forced‐choice methods","year":2024,"lang":"en","type":"article","venue":"Journal of the Society for Information Display","topic":"Color perception and design","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Fidelity; Two-alternative forced choice; Computer vision; Artificial intelligence; Cognitive psychology; Psychology; 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":[0.001746797,0.00008926253,0.0002812392,0.00007606959,0.00007273456,0.00003546037,0.0002002829,0.0001079348,0.0002000649],"category_scores_gemma":[0.0001240068,0.00005866515,0.001189368,0.0002628056,0.00007160848,0.0005027577,0.00003447963,0.0002653887,0.00000441472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001238354,"about_ca_system_score_gemma":0.0001455237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001412185,"about_ca_topic_score_gemma":0.000002246307,"domain_scores_codex":[0.9984564,0.0001202256,0.0009617792,0.00005034235,0.0002977272,0.0001135377],"domain_scores_gemma":[0.9979256,0.0006837372,0.0008258363,0.0001291425,0.0003969123,0.00003877033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0009712146,0.001170488,0.02077876,0.002298248,0.006380852,3.956573e-7,0.2400765,0.008518368,0.02106097,0.1129975,0.3621227,0.2236239],"study_design_scores_gemma":[0.004766544,0.002843387,0.4218351,0.0006057271,0.001414578,0.00007502708,0.0873393,0.2293672,0.006261072,0.003570192,0.2414248,0.000497087],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3026819,0.0002995701,0.6870161,0.0006137217,0.002749058,0.0005220343,0.00007632498,0.00001856306,0.006022759],"genre_scores_gemma":[0.9849127,0.00001046183,0.01444976,0.000236415,0.00009291319,0.00001078728,0.000006342044,0.000006654152,0.0002739721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6822308,"threshold_uncertainty_score":0.2392295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04805130254661202,"score_gpt":0.4934409230876151,"score_spread":0.4453896205410031,"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."}}