{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05922967,0.00199923,0.004555145,0.002273677,0.00117001,0.009221082,0.00335492,0.002689671,0.02002244],"category_scores_gemma":[0.09996296,0.001176294,0.001815615,0.001128365,0.0021427,0.008137869,0.00375765,0.005200961,0.005006608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002328056,"about_ca_system_score_gemma":0.003424344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003209013,"about_ca_topic_score_gemma":0.004032744,"domain_scores_codex":[0.9682794,0.02159791,0.002475848,0.002086103,0.004958651,0.0006020774],"domain_scores_gemma":[0.917958,0.05122224,0.001369654,0.01091976,0.01672795,0.001802369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001109671,0.0006282267,0.004968311,0.0008867329,0.0006025389,0.00009906272,0.0008293226,0.00890338,0.002084905,0.06557404,0.1020823,0.8122315],"study_design_scores_gemma":[0.0005666451,0.0006382741,0.009605031,0.001682798,0.000841755,0.0005568597,0.0007731951,0.297805,0.008130832,0.390386,0.2888188,0.0001947321],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.007552689,0.01640016,0.9526222,0.004679707,0.004788499,0.000563713,0.0006764311,0.001614325,0.01110225],"genre_scores_gemma":[0.1050229,0.005971047,0.8484313,0.001503385,0.003613178,0.001394417,0.004305589,0.002316966,0.02744134],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.05922967,"threshold_uncertainty_score":0.3132402,"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."}}