{"id":"W4404988426","doi":"10.14778/3749646.3749657","title":"TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations","year":2025,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Table (database); Class (philosophy); Computer science; Programming language; Natural language processing; Theoretical computer science; Artificial intelligence; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.001452211,0.0002707491,0.0004626949,0.0002834445,0.0003878936,0.0002944377,0.003320588,0.0002453949,0.00002622098],"category_scores_gemma":[0.0006134996,0.000178579,0.0003274747,0.0006769834,0.0000908163,0.0003161339,0.002158087,0.0004431106,0.000006519331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001196411,"about_ca_system_score_gemma":0.0001293732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009800927,"about_ca_topic_score_gemma":0.00003123651,"domain_scores_codex":[0.9972925,0.000007665031,0.0008740259,0.0006501473,0.0007746479,0.0004010238],"domain_scores_gemma":[0.997761,0.0001785981,0.0006476376,0.00072056,0.0006405422,0.00005167447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007023745,0.001196012,0.0004875678,0.00144596,0.0003869353,2.299046e-7,0.01104185,0.01306438,0.01227691,0.6974289,0.2082241,0.05437686],"study_design_scores_gemma":[0.001586558,0.0000331223,0.0001099145,0.0005973117,0.0002042071,0.00000269647,0.01263489,0.4488056,0.08868796,0.3105322,0.1362453,0.0005602099],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0804909,0.003700745,0.7906835,0.03810385,0.002114235,0.01572897,0.02462595,0.001022831,0.04352902],"genre_scores_gemma":[0.9483646,0.0002995013,0.0420296,0.0003833017,0.00006541371,0.002264424,0.00008020388,0.00002424962,0.006488776],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8678736,"threshold_uncertainty_score":0.7282241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2077244150039675,"score_gpt":0.3823279855500974,"score_spread":0.17460357054613,"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."}}