{"id":"W4391785473","doi":"10.1007/s00778-024-00835-2","title":"Assisted design of data science pipelines","year":2024,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Berlin Center for Machine Learning; Banting and Best Diabetes Centre, University of Toronto; Technische Universität Berlin","keywords":"Pipeline transport; Computer science; Data science; Engineering; Mechanical engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004119814,0.00005250777,0.00006370874,0.0001374601,0.0002629682,0.0005952428,0.003438677,0.00001325736,0.00001493749],"category_scores_gemma":[0.0003015534,0.00002885096,0.00001734875,0.0007848564,0.0001490871,0.001431426,0.0004341691,0.0002472027,0.00004027018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001607108,"about_ca_system_score_gemma":0.0003597856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007981723,"about_ca_topic_score_gemma":4.790203e-7,"domain_scores_codex":[0.9989538,0.0001363516,0.0001943482,0.0001992007,0.0003838095,0.0001325106],"domain_scores_gemma":[0.9986504,0.0002050954,0.00008977019,0.0009136459,0.00009133512,0.0000497529],"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":[0.000006751747,0.00003288495,0.0001343249,0.00001698667,0.0000147498,0.00001755013,0.0005671554,0.0008319439,0.03005883,0.0408041,0.01254104,0.9149737],"study_design_scores_gemma":[0.00005696119,0.00003392768,0.004316045,0.00005879582,0.0000106392,0.0005171837,0.00002426067,0.9723957,0.000577574,0.002592524,0.01935729,0.0000591675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006856071,0.0008634182,0.9917012,0.005618825,0.0004951906,0.00003366468,0.000003287732,0.00005681476,0.0005420106],"genre_scores_gemma":[0.8905144,0.0001873426,0.1086662,0.0000932461,0.0002602001,7.117844e-7,0.000003178742,0.000005283742,0.0002693949],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9715637,"threshold_uncertainty_score":0.6389975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1634969110956813,"score_gpt":0.3746252582239727,"score_spread":0.2111283471282914,"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."}}