{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005143492,0.003028408,0.001745546,0.003751466,0.001572708,0.005097552,0.007734261,0.002080505,0.01326801],"category_scores_gemma":[0.02840506,0.002379526,0.002907293,0.003372438,0.002344875,0.006832651,0.009485458,0.003963036,0.01404396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002528256,"about_ca_system_score_gemma":0.005487538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008105272,"about_ca_topic_score_gemma":0.007960838,"domain_scores_codex":[0.9946148,0.0007794347,0.00064276,0.001795972,0.001861344,0.0003056835],"domain_scores_gemma":[0.9855899,0.003834132,0.0007009025,0.006356738,0.002966067,0.0005522491],"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":[0.001594085,0.0004784999,0.008973233,0.002030432,0.0004562234,0.0006196785,0.001680054,0.03556427,0.02783486,0.02301971,0.4640426,0.4337065],"study_design_scores_gemma":[0.0006355573,0.0003409077,0.002883626,0.0002696527,0.0001494141,0.0005131859,0.0004633189,0.5628453,0.1202934,0.04704397,0.2642062,0.0003554621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.005317667,0.000460662,0.371142,0.0004405525,0.0002161692,0.0003155965,0.01120617,0.6073793,0.003521889],"genre_scores_gemma":[0.06842161,0.0004063107,0.7577076,0.001284891,0.00009736888,0.001240976,0.09384237,0.07128597,0.005712932],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01326801,"threshold_uncertainty_score":0.04438585,"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."}}