{"id":"W4410636879","doi":"10.1145/3701716.3715600","title":"WebTableX: Efficiently Discovering Web Table Transformations Through Sampling","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science; Table (database); Information retrieval; Sampling (signal processing); Data mining; World Wide Web; Data science","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":[0.001773284,0.001449888,0.001150373,0.003147641,0.0007448501,0.002438304,0.002370385,0.001003504,0.00285139],"category_scores_gemma":[0.009907882,0.0006210044,0.001638159,0.003859297,0.0005729625,0.003105049,0.002015122,0.001209942,0.002214261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000634816,"about_ca_system_score_gemma":0.002145231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007048674,"about_ca_topic_score_gemma":0.0161723,"domain_scores_codex":[0.9980072,0.0003290423,0.0001866517,0.0006662178,0.0006838728,0.0001270528],"domain_scores_gemma":[0.9951969,0.002476272,0.0003330068,0.001363905,0.0004555211,0.0001744238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009490824,0.0006356273,0.05696341,0.001377331,0.000628003,0.0006897396,0.001150948,0.06930581,0.027026,0.01013641,0.08679461,0.744343],"study_design_scores_gemma":[0.0002037088,0.0001505831,0.007055853,0.00006251966,0.00008484107,0.0006035346,0.0006070099,0.92983,0.01947022,0.01892684,0.02294966,0.00005520156],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1080292,0.001871824,0.779433,0.0008013234,0.0002384041,0.0008979575,0.03552028,0.07057532,0.002632665],"genre_scores_gemma":[0.1830432,0.000389984,0.7391594,0.000198041,0.00009739192,0.0005343561,0.07344598,0.001355633,0.001776029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007048674,"threshold_uncertainty_score":0.01401526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1778719289962122,"score_gpt":0.4464159695996306,"score_spread":0.2685440406034184,"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."}}