{"id":"W3215670116","doi":"10.1109/icde53745.2022.00169","title":"Efficiently Transforming Tables for Joinability","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Disk formatting; Computer science; Row; Transformation (genetics); Set (abstract data type); Representation (politics); State (computer science); Table (database); Theoretical computer science; Join (topology); Data mining; Data transformation; Algorithm; Programming language; Information retrieval; Data warehouse; Mathematics","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":[0.003262127,0.001527636,0.001302233,0.002710196,0.001531411,0.004932967,0.002308927,0.001333423,0.01224732],"category_scores_gemma":[0.01710197,0.001003703,0.003118007,0.003846665,0.001349275,0.006899237,0.005281261,0.002699794,0.004971365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009361597,"about_ca_system_score_gemma":0.00214583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001561625,"about_ca_topic_score_gemma":0.001582478,"domain_scores_codex":[0.9946989,0.0007993802,0.0006921445,0.001096892,0.002321237,0.0003913928],"domain_scores_gemma":[0.9889469,0.004734127,0.0005880517,0.003936573,0.001570561,0.0002239022],"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":[0.0004148507,0.0002473306,0.003439648,0.0006716592,0.0001247472,0.0004362832,0.001113568,0.04286817,0.02897048,0.09857428,0.03348641,0.7896526],"study_design_scores_gemma":[0.0001626487,0.0002842199,0.001301294,0.0001700415,0.0001413713,0.000870318,0.000970847,0.4923368,0.08543643,0.3067186,0.1114919,0.0001155208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009542082,0.0001819033,0.9751027,0.000260889,0.00009391592,0.0003084202,0.001053529,0.01077121,0.00268534],"genre_scores_gemma":[0.08417935,0.0002416002,0.9061486,0.0001322434,0.0000855075,0.0002470938,0.004740347,0.002179675,0.002045664],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01224732,"threshold_uncertainty_score":0.0409714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.335103052832682,"score_gpt":0.4249302990745663,"score_spread":0.08982724624188426,"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."}}