{"id":"W4385571965","doi":"10.18653/v1/2023.findings-acl.604","title":"AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Metadata; Computer science; Field (mathematics); Metadata repository; Table (database); Information retrieval; Dimension (graph theory); Data element; Data type; Data mining; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"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":[0.008955189,0.0001721034,0.0005775664,0.0008742458,0.0001858862,0.0004891625,0.003534442,0.0000667496,0.00443495],"category_scores_gemma":[0.003754933,0.0001263963,0.0001040317,0.006250065,0.00009430674,0.002487107,0.004888348,0.0001117152,0.0005836242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003274726,"about_ca_system_score_gemma":0.00006908165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001404768,"about_ca_topic_score_gemma":0.004751602,"domain_scores_codex":[0.9959547,0.0003076579,0.000991989,0.001113769,0.001287351,0.0003445699],"domain_scores_gemma":[0.9926267,0.002621325,0.0002972131,0.004199003,0.0001096121,0.0001461551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001599627,0.0001337809,0.0003731694,0.00001068798,0.0006778303,0.000005518345,0.0000534947,0.0001486246,0.0001235411,0.004263618,0.992954,0.001239777],"study_design_scores_gemma":[0.0006508278,0.0000461522,0.000473937,0.00001123001,0.0008605787,5.35326e-7,0.003803075,0.2313729,0.0003227446,0.003184681,0.7589609,0.0003124161],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0008263984,0.0003339156,0.7549451,0.002273993,0.0003573049,0.000340826,0.2386753,0.000115742,0.002131432],"genre_scores_gemma":[0.2314285,0.0002100172,0.05582472,0.003280187,0.00008687309,0.00003361598,0.6337357,0.00004745294,0.07535296],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.6991204,"threshold_uncertainty_score":0.9964752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6644636814897413,"score_gpt":0.5129623906594967,"score_spread":0.1515012908302447,"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."}}