{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005158285,0.001707316,0.0009623235,0.00222984,0.0009113707,0.004930559,0.003020629,0.001047159,0.00721316],"category_scores_gemma":[0.02480926,0.001082044,0.003200411,0.002496639,0.001349347,0.007124696,0.004568659,0.003307354,0.004424698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001471956,"about_ca_system_score_gemma":0.003549373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006084635,"about_ca_topic_score_gemma":0.0105211,"domain_scores_codex":[0.9959084,0.001460658,0.000472894,0.0008760854,0.001097097,0.0001849562],"domain_scores_gemma":[0.986997,0.007038435,0.0007308892,0.00407854,0.0009604462,0.0001946559],"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":[0.0007702241,0.0005031665,0.008139218,0.001507578,0.0004142469,0.0005701444,0.002018146,0.1112685,0.01492755,0.1280454,0.09813705,0.6336988],"study_design_scores_gemma":[0.0001305167,0.0001079036,0.0005635382,0.0001908525,0.00007644325,0.0002234068,0.0002718546,0.7664211,0.01820511,0.1308421,0.08287568,0.00009149112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004908435,0.0003395845,0.9202427,0.0004554856,0.0001106509,0.0002245696,0.003951949,0.06835503,0.001411561],"genre_scores_gemma":[0.07378691,0.0004594796,0.8981178,0.0005523128,0.0000835646,0.0006059938,0.01520021,0.008956855,0.002236887],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00721316,"threshold_uncertainty_score":0.02727997,"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."}}