{"id":"W4416037522","doi":"10.18653/v1/2025.emnlp-industry.33","title":"QuackIR: Retrieval in DuckDB and Other Relational Database Management Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Relational database; Data retrieval; Entity–relationship model; Database design; Information system; Data management; Relational database management system; Relational model","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001126151,0.0003200799,0.0003985455,0.0004587844,0.0002209998,0.0001894689,0.0003509944,0.0001085324,0.00007393015],"category_scores_gemma":[0.00006105259,0.0003004353,0.0000477268,0.001170244,0.0001614744,0.001229149,0.001096177,0.0002494296,0.00007014222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001562928,"about_ca_system_score_gemma":0.0001257251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000406086,"about_ca_topic_score_gemma":0.0001485055,"domain_scores_codex":[0.996946,0.0002215457,0.0008739321,0.001038438,0.0004566443,0.0004634899],"domain_scores_gemma":[0.9983204,0.0001875514,0.0001667949,0.001127263,0.00007827084,0.0001197289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006335375,0.00008035448,0.003992658,0.0005904652,0.00005969911,0.00006607946,0.0002274091,0.0003328717,0.00004921619,0.9894953,0.002009944,0.003032602],"study_design_scores_gemma":[0.002385548,0.00007125695,0.006272299,0.002662899,0.00004173303,0.00003981495,0.00147198,0.159096,0.0001255112,0.001325313,0.8257806,0.000727033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002676495,0.008967184,0.9410186,0.0007430005,0.002083575,0.0009529862,0.0001704635,0.00008032845,0.04330732],"genre_scores_gemma":[0.4781123,0.003521744,0.3073555,0.003282396,0.0005947138,0.0001803403,0.0001513068,0.0000942681,0.2067075],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.98817,"threshold_uncertainty_score":0.9999448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0240072976872973,"score_gpt":0.2777318631896082,"score_spread":0.2537245655023109,"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."}}