{"id":"W2040852548","doi":"10.1007/s10994-007-5043-5","title":"A notion of task relatedness yielding provable multiple-task learning guarantees","year":2008,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generalization; Multi-task learning; Computer science; Task (project management); Artificial intelligence; Similarity (geometry); Machine learning; Point (geometry); Domain (mathematical analysis); Variety (cybernetics); Theoretical computer science; Mathematics","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":[0.0009342417,0.0003404049,0.0004827071,0.0003560024,0.0009195814,0.0000977481,0.0007863823,0.0001618163,0.00004000752],"category_scores_gemma":[0.001192423,0.0003204628,0.0001877897,0.000895884,0.00009808132,0.0005885282,0.0003863711,0.001527329,0.00007131031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005040608,"about_ca_system_score_gemma":0.00007679407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000850002,"about_ca_topic_score_gemma":0.00001337496,"domain_scores_codex":[0.9970704,0.0004870683,0.000581018,0.0006990426,0.0005698424,0.0005926701],"domain_scores_gemma":[0.9983854,0.0004102279,0.0004785217,0.0004520465,0.0001518019,0.0001219931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007993837,0.0002903795,0.3822595,0.0002241046,0.0001355094,0.0002538717,0.01375176,0.4649151,0.03089488,0.002020499,0.0001494264,0.105025],"study_design_scores_gemma":[0.0009857407,0.0003508611,0.009582072,0.0001634652,0.00001519524,0.0002156543,0.00009759334,0.9761927,0.001442779,0.00009566322,0.0104294,0.0004288401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5518563,0.0007758206,0.4411004,0.0004991053,0.0004786489,0.0002590209,0.000001719363,0.001077449,0.003951583],"genre_scores_gemma":[0.977063,0.00008185967,0.01861227,0.00005511349,0.0001318206,0.00001523727,0.00002373519,0.00004572585,0.003971269],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5112776,"threshold_uncertainty_score":0.9999247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01261317721952781,"score_gpt":0.2234001724758154,"score_spread":0.2107869952562876,"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."}}