{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002009155,0.0001062262,0.0001891165,0.0001970521,0.0003776953,0.0007662756,0.0007667771,0.00003462841,0.001175267],"category_scores_gemma":[0.000506338,0.0000774933,0.00007694197,0.001500839,0.0000537144,0.001483166,0.0002487131,0.00008698896,0.0005707903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003719319,"about_ca_system_score_gemma":0.00008808673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001942397,"about_ca_topic_score_gemma":0.000439902,"domain_scores_codex":[0.9980252,0.00006636091,0.0005925387,0.0003468296,0.0006864193,0.0002826593],"domain_scores_gemma":[0.9986449,0.0005440603,0.0000644907,0.0006235166,0.00008404889,0.00003891533],"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":[0.00001141186,0.000102379,0.0001548702,0.00002725766,0.00002729666,6.707829e-7,0.0007873287,0.009342011,0.0003589886,0.8697158,0.09821982,0.02125214],"study_design_scores_gemma":[0.0002977008,0.00001002995,0.0002628995,0.00002988274,0.00001407484,3.416549e-7,0.004524763,0.008319943,0.0006766559,0.04653419,0.9392161,0.0001134395],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005411648,0.00006511313,0.6145096,0.002424521,0.0003961115,0.0001599577,0.0000583065,0.0000690158,0.3769057],"genre_scores_gemma":[0.8926026,0.0001060269,0.01670698,0.004036129,0.00004108319,0.00003801196,0.00004745225,0.000008195582,0.08641353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8871909,"threshold_uncertainty_score":0.9997378,"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."}}