{"id":"W2559780085","doi":"","title":"Proceedings of the 3rd International Workshop on Evaluation Methods for Machine Learning","year":2008,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","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":[0.001957364,0.0002573316,0.0002388828,0.0003385376,0.0004424189,0.0002052828,0.002008601,0.0001016163,0.0003178372],"category_scores_gemma":[0.003869328,0.0002087067,0.0001889853,0.0003894634,0.0001139597,0.0005664131,0.0003684933,0.0008217776,0.00004148905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002155995,"about_ca_system_score_gemma":0.0001374033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008332481,"about_ca_topic_score_gemma":0.00001278016,"domain_scores_codex":[0.9972736,0.000221694,0.0005316294,0.0005973644,0.00107728,0.0002984338],"domain_scores_gemma":[0.9969671,0.0006719397,0.0005564182,0.0002321614,0.001500581,0.00007183039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002670628,0.0002474378,0.01055676,0.00001733422,0.0001499766,0.000002989922,0.003351978,0.04081494,0.01997617,0.6765471,0.0002088112,0.2478595],"study_design_scores_gemma":[0.0003809972,0.0002110262,0.001362655,0.0001366114,0.00001088845,0.00001945616,0.000193349,0.9548531,0.01857785,0.01161255,0.01242497,0.00021653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1027378,0.0001375224,0.7568947,0.02400377,0.003805419,0.001473783,0.00001787248,0.0004025825,0.1105266],"genre_scores_gemma":[0.9642351,0.00007072191,0.03086393,0.0003544164,0.000183846,0.0001109658,0.00002764564,0.00002537425,0.004127973],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9140382,"threshold_uncertainty_score":0.8510811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1414765380481503,"score_gpt":0.4130435025122038,"score_spread":0.2715669644640536,"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."}}