{"id":"W2427822648","doi":"10.1109/icde.2016.7498319","title":"DataXFormer: A robust transformation discovery system","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Transformation (genetics); Data transformation; Representation (politics); External Data Representation; Knowledge base; Information retrieval; Base (topology); World Wide Web; Data mining; Theoretical computer science; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002701367,0.00006887154,0.0001215243,0.0001184461,0.00008227745,0.0003717908,0.0006170991,0.00002399604,0.0004849851],"category_scores_gemma":[0.0002369782,0.00003019055,0.00005331533,0.0002305538,0.00003736019,0.004149607,0.0001056094,0.00001958262,0.002968214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000388401,"about_ca_system_score_gemma":0.00001615121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005091473,"about_ca_topic_score_gemma":0.0001250609,"domain_scores_codex":[0.9982138,0.00008922201,0.0004594417,0.0002426479,0.0008402826,0.0001546585],"domain_scores_gemma":[0.9988818,0.0003011689,0.00008642875,0.0006299283,0.0000488276,0.00005191504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002006219,0.00002274254,0.0001178106,0.00001617523,0.00001035248,0.000001589989,0.0001626216,0.00001353488,0.0001811385,0.783845,0.06957199,0.146037],"study_design_scores_gemma":[0.0007722301,0.00005322631,0.002222907,0.00007301682,0.00001500369,0.000006993277,0.00829381,0.0009839215,0.001177853,0.007760935,0.9784109,0.0002292028],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007657728,0.000005328338,0.8764841,0.003448039,0.0002737723,0.0001468644,0.0001575209,0.00007201974,0.1117546],"genre_scores_gemma":[0.9765282,0.00001162829,0.0007825337,0.0003032623,0.00003952019,0.00001083903,0.00001729176,0.000003279113,0.02230351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9688704,"threshold_uncertainty_score":0.9978081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2087469238632512,"score_gpt":0.3724310305524388,"score_spread":0.1636841066891875,"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."}}