{"id":"W4413458163","doi":"10.1109/icdew67478.2025.00018","title":"LLM + Vector Data: Coupling of Large Language Models with Vector Data Management for Enhancing Data Science","year":2025,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Vector (molecular biology); Coupling (piping); Data modeling; Data mining; Database; Engineering; Biology","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":[0.006606678,0.001117489,0.001128874,0.001385116,0.0007491572,0.004959524,0.002790221,0.001438739,0.006369221],"category_scores_gemma":[0.02131266,0.0009174144,0.001873455,0.002062427,0.001667097,0.01120508,0.006741959,0.004686042,0.003898732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001810202,"about_ca_system_score_gemma":0.002567028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005005689,"about_ca_topic_score_gemma":0.007596496,"domain_scores_codex":[0.9954547,0.002269452,0.0003711777,0.000849226,0.0008550585,0.0002003886],"domain_scores_gemma":[0.9906508,0.004465155,0.0003849112,0.003168756,0.0009097646,0.000420653],"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":[0.000434585,0.0004338541,0.00386819,0.0005056764,0.0002915696,0.0002706693,0.001352269,0.1159946,0.009093191,0.2585739,0.07169275,0.5374888],"study_design_scores_gemma":[0.00003745835,0.0000755064,0.0003076849,0.00005675959,0.00003060438,0.00006641611,0.0001322945,0.7619957,0.0041866,0.1930685,0.03998667,0.00005583167],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004601193,0.0006947286,0.983493,0.002361952,0.0002578527,0.0001001954,0.0006881796,0.006144717,0.001658132],"genre_scores_gemma":[0.1472135,0.001412191,0.8360848,0.001688457,0.0005633073,0.0005476461,0.004496216,0.001986388,0.006007408],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006606678,"threshold_uncertainty_score":0.03493989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06124829965169441,"score_gpt":0.3325158929792142,"score_spread":0.2712675933275198,"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."}}