{"id":"W4393183687","doi":"10.1145/3639279","title":"DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transformer; Computer science; Engineering; Electrical engineering; Voltage","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001020412,0.0001410283,0.0001770954,0.00007531972,0.00007403425,0.0001305876,0.006777298,0.00003344394,0.000005912318],"category_scores_gemma":[0.00003270242,0.0001083073,0.00006895718,0.0002364509,0.00002739451,0.001814663,0.002141988,0.0001039159,0.000001051985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000309453,"about_ca_system_score_gemma":0.00001259022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005040476,"about_ca_topic_score_gemma":0.000002233174,"domain_scores_codex":[0.998341,0.000006780432,0.0002984295,0.0006866871,0.0004056437,0.0002615245],"domain_scores_gemma":[0.9978883,0.00003836085,0.00008842078,0.00188624,0.00005954535,0.00003919055],"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":[0.00006730713,0.0006777084,0.0004567385,0.008183014,0.0005037949,0.000002951273,0.01043204,0.001083869,0.0191301,0.7719576,0.02803653,0.1594683],"study_design_scores_gemma":[0.0004619313,0.00009157027,0.00006154757,0.00037819,0.00008968128,8.198775e-7,0.001028081,0.9256535,0.008482542,0.05390392,0.009634013,0.0002142011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1769517,0.0003968514,0.8154009,0.003943454,0.0002164728,0.00121592,0.0003027914,0.0001863628,0.001385517],"genre_scores_gemma":[0.8571216,0.00003576341,0.1424001,0.0001222814,0.00003108404,0.00002959426,0.00003553982,0.00001719983,0.0002067466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9245696,"threshold_uncertainty_score":0.9985965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1034483500304466,"score_gpt":0.3135535429041299,"score_spread":0.2101051928736833,"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."}}