{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003267752,0.0001587447,0.0001669977,0.0001129653,0.0002235772,0.0005963417,0.0005471865,0.000051182,0.000005893006],"category_scores_gemma":[0.00005305983,0.0001196931,0.00002742589,0.0003944798,0.00001838206,0.001867561,0.0001531154,0.0002071564,0.001079288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004020502,"about_ca_system_score_gemma":0.00004016861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004172447,"about_ca_topic_score_gemma":3.347383e-8,"domain_scores_codex":[0.9986799,0.0001168348,0.0003731924,0.0002621341,0.0003507214,0.0002171881],"domain_scores_gemma":[0.9989796,0.00001135277,0.0003127668,0.0004783277,0.00007781562,0.0001401743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002076051,0.00001550501,0.1695719,0.003502505,0.0002524461,0.00007665086,0.6418285,0.02902044,0.00003553138,0.02069274,0.001736562,0.1330597],"study_design_scores_gemma":[0.0008289178,0.0001908941,0.009411919,0.0002486801,0.00002169701,0.0001356388,0.006701043,0.9679465,0.0002836507,6.76921e-7,0.01380797,0.0004223908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007792855,0.000002300901,0.9882182,0.0007377252,0.00008743985,0.0002513806,0.00005095729,0.0008509263,0.002008244],"genre_scores_gemma":[0.9897789,7.985109e-8,0.009700921,0.0002491518,0.00004963357,0.0000359772,0.0001549758,0.000007720546,0.00002264343],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.981986,"threshold_uncertainty_score":0.9996985,"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."}}