{"id":"W4315815891","doi":"10.1109/icicml57342.2022.10009760","title":"Estimator performance for shallow and deep models","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Estimator; Computer science; Recommender system; Propensity score matching; Ranking (information retrieval); Artificial intelligence; Machine learning; Statistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005444422,0.0002329165,0.000237914,0.0002430084,0.0007787279,0.0008006949,0.000713317,0.00003964875,0.00007299379],"category_scores_gemma":[0.00001361042,0.0002101247,0.00005334217,0.0001264076,0.0000468059,0.0008273887,0.0009580807,0.0004553393,0.000002241785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005219267,"about_ca_system_score_gemma":0.00006015935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002617357,"about_ca_topic_score_gemma":0.000003155481,"domain_scores_codex":[0.9983035,0.00009981562,0.0003109784,0.0006231805,0.0004299287,0.0002325777],"domain_scores_gemma":[0.9992248,0.00006744909,0.0002341137,0.000178608,0.000196832,0.0000981617],"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":[0.00006945299,0.0001262134,0.000576689,0.0001168813,0.00002785167,0.00001280258,0.001021502,0.001288923,0.00041778,0.07237668,0.0007818382,0.9231834],"study_design_scores_gemma":[0.0005007873,0.0007079443,0.0003323992,0.00007781887,0.000004356677,0.0001074769,0.00004300682,0.9782282,0.00006156607,0.004814672,0.01487951,0.000242271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00543401,0.0003254027,0.9877346,0.002896574,0.0003337605,0.0002636029,0.000008699174,0.0002783396,0.00272497],"genre_scores_gemma":[0.8543957,0.0001355958,0.1438174,0.0007079444,0.00007464815,0.000133322,0.0000344453,0.00002109213,0.0006798938],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9769393,"threshold_uncertainty_score":0.8568637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03202464806830251,"score_gpt":0.2968203899372381,"score_spread":0.2647957418689356,"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."}}