{"id":"W4414266787","doi":"10.14778/3750601.3750638","title":"SQL:Trek Automated Index Design at Airbnb","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Air Canada","funders":"","keywords":"Index (typography); Scalability; Index selection; False positive paradox; Selection (genetic algorithm); Database index; Compiler; Relational database","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":[0.000394382,0.0001534274,0.0001631711,0.0001441887,0.0001651807,0.0001657026,0.001996736,0.00003588725,0.00001188326],"category_scores_gemma":[0.00004769432,0.000107206,0.0000785027,0.0007392616,0.00005698923,0.0004879938,0.002072374,0.00008212798,0.00002724657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000112671,"about_ca_system_score_gemma":0.00002792988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002275244,"about_ca_topic_score_gemma":9.749665e-7,"domain_scores_codex":[0.9987481,0.00000896589,0.0002561718,0.0003463214,0.0003616899,0.0002788085],"domain_scores_gemma":[0.9993742,0.00003474438,0.0001654653,0.0002831784,0.0001017843,0.00004068915],"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":[0.00007201033,0.0005130765,0.0104181,0.000424935,0.0004078845,0.000004529574,0.001098593,0.0004207401,0.02465963,0.306394,0.5821592,0.07342727],"study_design_scores_gemma":[0.002529655,0.0002070808,0.02239292,0.0004769096,0.0001163021,0.00001007625,0.0002032425,0.5147537,0.3541705,0.03187958,0.07259785,0.0006622144],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09391152,0.001406291,0.4947748,0.04851554,0.007466677,0.008349009,0.00004230532,0.007322901,0.3382109],"genre_scores_gemma":[0.9498861,0.00005203732,0.0358341,0.0009390598,0.00004267291,0.0001057965,0.000001906359,0.00001340432,0.01312489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8559746,"threshold_uncertainty_score":0.4371735,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01118379359232271,"score_gpt":0.2298920848846669,"score_spread":0.2187082912923442,"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."}}