{"id":"W4364321947","doi":"10.1109/tkde.2023.3265840","title":"Summarizing Provenance of Aggregate Query Results in Relational Databases","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Automatic summarization; Provenance; Relevance (law); Information retrieval; Aggregate (composite); Tuple; Database; Relational database; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.002972038,0.0001025552,0.0001655074,0.0007302236,0.00008519148,0.00006449085,0.0005324023,0.00002595639,0.00001010859],"category_scores_gemma":[0.0005047426,0.00009083989,0.00002633513,0.001669499,0.00003578534,0.0005894852,0.00004976313,0.0001380888,0.00009206784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001649136,"about_ca_system_score_gemma":0.00003689759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005083986,"about_ca_topic_score_gemma":0.0001587601,"domain_scores_codex":[0.9982318,0.00004000316,0.0005269842,0.0006411324,0.0003722214,0.0001878784],"domain_scores_gemma":[0.9972905,0.001302286,0.00007811301,0.001220171,0.00005518596,0.00005374824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001552404,0.0003311239,0.000622593,0.0001574635,0.00005588122,0.00003864399,0.001345221,0.4333804,0.002158559,0.002369641,0.03289721,0.526488],"study_design_scores_gemma":[0.0005569366,0.00002370448,0.005235308,0.0002913018,0.00001047672,0.000002812297,0.0001509481,0.9329841,0.001351673,0.0001260979,0.05909461,0.0001720428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0880845,0.0004345808,0.9037813,0.0003098214,0.002382926,0.0002866936,0.003201352,0.0002169804,0.001301875],"genre_scores_gemma":[0.9954752,0.0001073092,0.00284008,0.000006288383,0.00003636917,0.00000734361,0.0001964895,0.000009685254,0.001321248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9073907,"threshold_uncertainty_score":0.3704343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1898363623171656,"score_gpt":0.3749400823753054,"score_spread":0.1851037200581397,"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."}}