{"id":"W4413943427","doi":"10.14778/3742728.3742754","title":"CatDB: Data-Catalog-Guided, LLM-Based Generation of Data-Centric ML Pipelines","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Pipeline transport; Computer science; Environmental science","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":[0.0009724876,0.0001416655,0.0001982261,0.0001691955,0.0001238954,0.0001021595,0.004521489,0.00004703688,0.000005222705],"category_scores_gemma":[0.0005165258,0.0001019236,0.00003860113,0.0007505009,0.00006301809,0.0007788903,0.001899682,0.0001273214,0.000006308883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004373011,"about_ca_system_score_gemma":0.0001504682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002517831,"about_ca_topic_score_gemma":0.00001286109,"domain_scores_codex":[0.9982977,0.00002262156,0.0004922063,0.0005959546,0.0004117323,0.0001797687],"domain_scores_gemma":[0.9976485,0.00006451469,0.0004535436,0.001523611,0.0002728242,0.00003701296],"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":[0.00005769252,0.001495334,0.04013199,0.001189345,0.0002026242,6.73699e-7,0.0004949994,0.001059934,0.186931,0.1913219,0.3883801,0.1887344],"study_design_scores_gemma":[0.001038184,0.00006313557,0.004800881,0.0001629161,0.0001132545,0.000004536686,0.00005136023,0.7891405,0.1381947,0.000968196,0.06522674,0.000235712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1220797,0.003764219,0.7787744,0.06870809,0.004006774,0.003967969,0.001461255,0.0008087559,0.0164288],"genre_scores_gemma":[0.9618042,0.00006762869,0.03668521,0.0003480705,0.0001070819,0.00002026982,0.0005647264,0.000008437706,0.0003943401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8397245,"threshold_uncertainty_score":0.8402126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1042295938021906,"score_gpt":0.3298866644214558,"score_spread":0.2256570706192652,"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."}}