{"id":"W3048658394","doi":"10.1093/iwcomp/iwaa017","title":"Benchmarking Human Performance in Semi-Automated Image Segmentation","year":2020,"lang":"en","type":"article","venue":"Interacting with Computers","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island; University of Saskatchewan","funders":"","keywords":"Computer science; Benchmarking; Segmentation; Artificial intelligence; Context (archaeology); Image segmentation; Identification (biology); Rigour; Focus (optics); Computer vision; Object (grammar); Image (mathematics); Markup language; Pattern recognition (psychology); Machine learning; Mathematics","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":[0.02133032,0.00138497,0.001137661,0.002058377,0.00115166,0.004314604,0.002928812,0.00292919,0.00370781],"category_scores_gemma":[0.07912071,0.0006665753,0.0008902552,0.001153868,0.002567478,0.002180163,0.003364559,0.001034432,0.002679292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111041,"about_ca_system_score_gemma":0.0006982213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002425397,"about_ca_topic_score_gemma":0.002613207,"domain_scores_codex":[0.9659802,0.02160209,0.001675363,0.005709815,0.004307796,0.0007246813],"domain_scores_gemma":[0.9002494,0.07078044,0.006166728,0.01060737,0.01112982,0.001066283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.007106921,0.001101044,0.0491063,0.008290699,0.002677119,0.0005546603,0.0123108,0.05923563,0.2079888,0.007066987,0.01408446,0.6304766],"study_design_scores_gemma":[0.0005612154,0.00498619,0.1703757,0.001333521,0.0009290645,0.001964681,0.005194721,0.4646666,0.2876038,0.02974344,0.0317289,0.0009122863],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6887218,0.007554892,0.2818912,0.0008883008,0.0005464772,0.001070838,0.001341981,0.005343956,0.01264052],"genre_scores_gemma":[0.9016317,0.0007925558,0.09238334,0.0003376066,0.0001163879,0.000458021,0.001513487,0.0005874052,0.002179573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02133032,"threshold_uncertainty_score":0.1128068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01827325276619219,"score_gpt":0.2853288004801154,"score_spread":0.2670555477139233,"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."}}