{"id":"W4416942877","doi":"10.1109/bigdata66926.2025.11402455","title":"Relation-Stratified Sampling for Shapley Values Estimation in Relational Databases","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Tuple; Estimator; Joins; Sampling (signal processing); RSS; Relational database; Variance (accounting); Stratification (seeds); Sample (material)","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":[0.008103428,0.001008905,0.001452778,0.001627874,0.0008022586,0.002530666,0.00230879,0.0009776922,0.002674325],"category_scores_gemma":[0.03772074,0.0007076508,0.0009935764,0.002040032,0.001320639,0.003546696,0.002018771,0.002045274,0.000449417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001841066,"about_ca_system_score_gemma":0.002079757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003046368,"about_ca_topic_score_gemma":0.00317752,"domain_scores_codex":[0.9951366,0.002578677,0.0002093553,0.0008863593,0.0009629678,0.0002261724],"domain_scores_gemma":[0.9858083,0.01002807,0.0007620252,0.002050477,0.001064295,0.000287024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003309778,0.0001733898,0.007099337,0.0001827574,0.0002028771,0.00008799328,0.0004000395,0.5709029,0.003479585,0.2529249,0.002563035,0.1616522],"study_design_scores_gemma":[0.00001722286,0.00003750663,0.000321359,0.000014097,0.00001176179,0.00002318497,0.00002638669,0.9041534,0.0009365262,0.09372383,0.0007206301,0.00001400148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0101911,0.0001452559,0.9885104,0.00007179326,0.00001569636,0.00007622264,0.00008775699,0.00026564,0.0006360713],"genre_scores_gemma":[0.4825645,0.0002928642,0.5147828,0.0001825909,0.0000843823,0.000433383,0.0006321194,0.0001674411,0.0008598958],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008103428,"threshold_uncertainty_score":0.04285556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08141308089082669,"score_gpt":0.3521301432663022,"score_spread":0.2707170623754754,"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."}}