{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001456923,0.000290119,0.0002386129,0.0002904491,0.0003586073,0.0007442517,0.0006295263,0.0002074707,0.0001705092],"category_scores_gemma":[0.001414311,0.0002856487,0.00008468302,0.0005314238,0.000009219607,0.00107845,0.00004479165,0.000546037,0.0003229725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001896368,"about_ca_system_score_gemma":0.0003545952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001904558,"about_ca_topic_score_gemma":0.0001163877,"domain_scores_codex":[0.9972659,0.0002991664,0.0004894175,0.0007001049,0.0009768315,0.0002685366],"domain_scores_gemma":[0.9981577,0.0001473465,0.0006116314,0.0005390315,0.0004656246,0.00007866586],"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":[0.000003375658,0.00005859145,0.0001342982,0.00005641229,0.000009081494,0.000001544203,0.001218973,0.0001750405,0.006435712,0.0008370651,0.0006447668,0.9904251],"study_design_scores_gemma":[0.0004023565,0.0002171808,0.0738238,0.0001297213,0.0000587783,0.000006381171,0.0008931184,0.917723,0.00414179,0.0008633373,0.001278413,0.0004621013],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04394516,0.0004612921,0.5299001,0.002096384,0.001474698,0.001933155,0.00001035899,0.003996579,0.4161823],"genre_scores_gemma":[0.574372,0.00009731388,0.3809175,0.0002496869,0.0003634846,0.0002486331,0.01404992,0.00007888367,0.02962253],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9899631,"threshold_uncertainty_score":0.9999596,"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."}}