{"id":"W2481236656","doi":"10.1109/swste.2016.23","title":"A Preliminary Survey on Domain-Specific Languages for Machine Learning in Big Data","year":2016,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Big data; Computer science; Domain (mathematical analysis); Data science; Domain-specific language; Software; Domain analysis; Machine learning; Artificial intelligence; Visualization; Data modeling; Software engineering; Data mining; Software development; Programming language; Software construction","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":[0.01493296,0.0001078505,0.0001748636,0.0003812508,0.0001236603,0.0002758254,0.001904433,0.0000291726,0.000275796],"category_scores_gemma":[0.003873526,0.00005595383,0.00003320383,0.0006260333,0.00005393199,0.0001870308,0.001165397,0.00006561065,0.0005318364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002402267,"about_ca_system_score_gemma":0.00002084168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002695715,"about_ca_topic_score_gemma":0.001355312,"domain_scores_codex":[0.9971967,0.0003351066,0.0004190043,0.001037773,0.0007369697,0.000274471],"domain_scores_gemma":[0.9914784,0.006205874,0.0001079161,0.002073155,0.00007288254,0.00006172189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001557756,0.000068768,0.02471335,0.000001396618,0.000003898261,0.000007402818,0.00008480176,0.00003996881,0.00008172775,0.001271877,0.2530291,0.720542],"study_design_scores_gemma":[0.0007670235,0.0001613171,0.2605135,0.00003230711,0.000001263503,9.999453e-7,0.0003542871,0.002268831,0.00004798603,0.001875229,0.7338325,0.0001448404],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3880135,0.0004458764,0.5826721,0.006770884,0.002912714,0.0008750584,0.001359987,0.0002583797,0.01669161],"genre_scores_gemma":[0.9556491,0.00002014809,0.005187706,0.0002045873,0.0001571246,0.000008660944,0.0002812761,0.00001302213,0.03847842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7203971,"threshold_uncertainty_score":0.6835858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3488895636320767,"score_gpt":0.412870069686725,"score_spread":0.06398050605464828,"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."}}