{"id":"W2517256444","doi":"10.5555/2981324.2981327","title":"A benchmark image set for evaluating stylization","year":2016,"lang":"en","type":"article","venue":"Non-Photorealistic Animation and Rendering","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Benchmark (surveying); Rendering (computer graphics); Computer science; Computer graphics; Set (abstract data type); Artificial intelligence; Graphics; Subject matter; Image (mathematics); Range (aeronautics); Computer vision; Computer graphics (images)","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":[0.00555926,0.001688041,0.001130025,0.004599416,0.001537083,0.003265433,0.002772131,0.001949609,0.006987542],"category_scores_gemma":[0.02652054,0.0005725567,0.001667797,0.002824048,0.001546361,0.002982304,0.002817879,0.002027122,0.003066322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001798726,"about_ca_system_score_gemma":0.00132368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005741538,"about_ca_topic_score_gemma":0.008806026,"domain_scores_codex":[0.9963577,0.0009939407,0.0004283403,0.0005582605,0.001451966,0.0002098606],"domain_scores_gemma":[0.9881756,0.003536146,0.0005129759,0.003677564,0.003592058,0.0005056383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002035351,0.002679912,0.009486076,0.003602955,0.0006521628,0.0005620659,0.0006765632,0.08950177,0.06005786,0.0285107,0.1488194,0.6534151],"study_design_scores_gemma":[0.0008211288,0.00283907,0.02730844,0.001115332,0.0004387197,0.003193182,0.001262208,0.5480416,0.2053245,0.0350234,0.1742533,0.0003791303],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3006194,0.01048722,0.5364056,0.003423042,0.002114786,0.008999256,0.04436238,0.02022454,0.07336367],"genre_scores_gemma":[0.4054355,0.002321136,0.4877643,0.001119155,0.0003183523,0.002799677,0.08797025,0.003071079,0.009200504],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006987542,"threshold_uncertainty_score":0.02940059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04077526988863166,"score_gpt":0.348756799635227,"score_spread":0.3079815297465953,"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."}}