{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01036355,0.0008406009,0.001360267,0.0045019,0.001383115,0.005259961,0.001530291,0.0009662607,0.001036484],"category_scores_gemma":[0.04527548,0.0007035053,0.001128011,0.005777353,0.000870644,0.006497458,0.002452001,0.0009759914,0.00060832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001320437,"about_ca_system_score_gemma":0.001876932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005544251,"about_ca_topic_score_gemma":0.00571418,"domain_scores_codex":[0.9866882,0.004338421,0.001827137,0.001232055,0.00558721,0.0003269399],"domain_scores_gemma":[0.9681078,0.01544236,0.002490663,0.007473533,0.006072892,0.0004129405],"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":[0.001627549,0.0003822295,0.01476774,0.001443513,0.0004697236,0.0007645767,0.005535067,0.2042108,0.02926923,0.08202478,0.0156546,0.6438502],"study_design_scores_gemma":[0.0001671705,0.0004785417,0.003513084,0.0002314434,0.0003651304,0.0004943447,0.001289608,0.7829089,0.05208127,0.1290282,0.02928352,0.0001588557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05120457,0.001608748,0.93796,0.0005314231,0.00007713012,0.0003227595,0.001605067,0.005282791,0.00140745],"genre_scores_gemma":[0.335195,0.001259207,0.6561652,0.0001689046,0.0001208315,0.000273256,0.004903672,0.00066946,0.001244492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01036355,"threshold_uncertainty_score":0.05480832,"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."}}