{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001289559,0.0001273041,0.0001239082,0.000125268,0.0001254615,0.0002394459,0.0003159334,0.00002552312,0.000009657994],"category_scores_gemma":[0.00002035712,0.0001184793,0.00003006969,0.0005007002,0.00001707816,0.001118606,0.0001138234,0.0001965354,0.00003256955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007226218,"about_ca_system_score_gemma":0.0000154506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002434621,"about_ca_topic_score_gemma":0.000008769535,"domain_scores_codex":[0.9989246,0.00006402765,0.0002614984,0.0003484237,0.0002027591,0.0001987328],"domain_scores_gemma":[0.9995043,0.00009138839,0.0001495035,0.00013319,0.00005251223,0.00006905834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000246038,0.0006389598,0.2365692,0.0006546253,0.0001974784,0.0005475738,0.06423219,0.109597,0.3165542,0.001237777,0.004347694,0.2651773],"study_design_scores_gemma":[0.0004521252,0.0003216057,0.02723384,0.0002451653,0.000002112069,0.0000283175,0.0001451248,0.9658168,0.005491588,0.000003445498,0.00009796547,0.0001619318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6758221,0.000001794119,0.3221612,0.0004218586,0.0005742437,0.0001041581,1.585909e-7,0.0005288488,0.0003856875],"genre_scores_gemma":[0.9754183,8.671372e-7,0.02398681,0.0004981691,0.00006818064,0.000007350109,0.000004903633,0.000008898267,0.000006505896],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8562197,"threshold_uncertainty_score":0.4831445,"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."}}