{"id":"W6901695316","doi":"10.60692/rxvb0-q5858","title":"Synbols: Probing Learning Algorithms with Synthetic Datasets","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Benchmark (surveying); Code (set theory); Synthetic data; Source code; Key (lock); Pattern recognition (psychology)","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":[0.009154476,0.002985251,0.001129176,0.003653683,0.001126115,0.002043587,0.005112905,0.002353326,0.009783396],"category_scores_gemma":[0.04723696,0.001006129,0.001551172,0.004943264,0.001165882,0.002999009,0.002008374,0.002975898,0.004513774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001882148,"about_ca_system_score_gemma":0.002178004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00700499,"about_ca_topic_score_gemma":0.01115719,"domain_scores_codex":[0.9940646,0.00268851,0.0006262064,0.0008651254,0.001378224,0.0003774599],"domain_scores_gemma":[0.9740935,0.01419833,0.0007845238,0.006135974,0.004157586,0.000630073],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001925035,0.001889144,0.00715842,0.001816785,0.0006833407,0.0002485961,0.0003030966,0.114307,0.003972203,0.008871489,0.7567097,0.1021151],"study_design_scores_gemma":[0.002980113,0.001332991,0.006510084,0.0002622851,0.0001769997,0.0003697758,0.0003741801,0.8614359,0.01935131,0.01983916,0.08720624,0.0001609309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2538184,0.002591917,0.2113697,0.004693468,0.004247278,0.004238053,0.3080325,0.1803981,0.03061054],"genre_scores_gemma":[0.245987,0.0005590577,0.312715,0.001643096,0.0002923148,0.004466777,0.4154852,0.012608,0.00624352],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009783396,"threshold_uncertainty_score":0.04841411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03454430125556018,"score_gpt":0.2162257387580032,"score_spread":0.181681437502443,"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."}}