{"id":"W2804364191","doi":"10.22215/etd/2009-09134","title":"Learning a test Oracle towards automating image segmentation evaluation","year":2009,"lang":"en","type":"dissertation","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Oracle; Test (biology); Computer science; Information retrieval; Artificial intelligence; Art; Software engineering","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":[0.004912839,0.001459303,0.001630067,0.002277494,0.0005563131,0.003122177,0.00274347,0.002230373,0.005112235],"category_scores_gemma":[0.02271003,0.0006245265,0.0007208567,0.001629231,0.0009241456,0.00320395,0.002264991,0.002181344,0.005178418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001121046,"about_ca_system_score_gemma":0.00225109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005403368,"about_ca_topic_score_gemma":0.007710624,"domain_scores_codex":[0.9952464,0.001702987,0.0004145435,0.0009810285,0.001307684,0.0003474789],"domain_scores_gemma":[0.9873017,0.005647619,0.0006451567,0.002632396,0.003129117,0.0006439071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009752875,0.0004506466,0.006628366,0.0002571081,0.0001175063,0.0001657765,0.00008808463,0.02655171,0.03274552,0.0052889,0.01977895,0.9069521],"study_design_scores_gemma":[0.0000956434,0.0003283883,0.003400763,0.00005735909,0.00006487851,0.0002445108,0.0001039319,0.9256685,0.05258466,0.009983804,0.007432909,0.00003462105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04476565,0.001038616,0.9215381,0.0004703634,0.0001300068,0.0002552217,0.0006867074,0.02729215,0.003823251],"genre_scores_gemma":[0.4271478,0.0004990084,0.5577491,0.0006829195,0.0001699497,0.0002800927,0.005032427,0.001881422,0.00655728],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005403368,"threshold_uncertainty_score":0.0259819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0173279982315608,"score_gpt":0.3356658261627857,"score_spread":0.3183378279312249,"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."}}