{"id":"W2922025696","doi":"","title":"Multitask Metric Learning: Theory and Algorithm","year":2019,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Boosting (machine learning); Generalization; Multi-task learning; Stability (learning theory); Metric (unit); Benchmark (surveying); Algorithm; Artificial intelligence; Machine learning; Learning to rank; Task (project management); Mathematics; Ranking (information retrieval)","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":[0.006009907,0.001687618,0.002089428,0.001668473,0.0007922057,0.002360484,0.00269302,0.002513707,0.002708115],"category_scores_gemma":[0.02306684,0.0007874003,0.001087687,0.003067087,0.002464815,0.003891692,0.004801105,0.004009623,0.001294089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002180883,"about_ca_system_score_gemma":0.001687382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002493673,"about_ca_topic_score_gemma":0.001568654,"domain_scores_codex":[0.9966695,0.001731445,0.0001986193,0.0006264633,0.0006130293,0.0001609272],"domain_scores_gemma":[0.9899733,0.007329929,0.0005212786,0.000882451,0.001004658,0.0002883472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001060441,0.0001421546,0.001490565,0.000628032,0.0001487753,0.0001641553,0.0002328728,0.3068748,0.001006313,0.4301027,0.01489037,0.2442131],"study_design_scores_gemma":[0.00001219525,0.00004504894,0.0001451284,0.00002728994,0.000009618054,0.0000677656,0.00002047387,0.7503044,0.0002086645,0.2456894,0.003452902,0.0000170345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001286284,0.001385705,0.9956246,0.0005090599,0.00005788836,0.00003662268,0.00004332942,0.0001172698,0.0009392342],"genre_scores_gemma":[0.2149128,0.005152517,0.7714204,0.0008864141,0.001004632,0.001061217,0.0006766842,0.0003234989,0.004561754],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006009907,"threshold_uncertainty_score":0.03178382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05850819405852739,"score_gpt":0.3255875308177551,"score_spread":0.2670793367592277,"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."}}