{"id":"W3083318759","doi":"10.1109/tvcg.2020.3030462","title":"Table Scraps: An Actionable Framework for Multi-Table Data Wrangling From An Artifact Study of Computational Journalism","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Parallels; Artifact (error); Table (database); Context (archaeology); Journalism; Data science; Data mining; Artificial intelligence; Engineering; Political science; Geography","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002586627,0.0003902487,0.0006563434,0.0008437465,0.0008592704,0.00185018,0.001875613,0.000250455,0.00009465697],"category_scores_gemma":[0.0001158427,0.0003737386,0.0001184933,0.001400983,0.0001065945,0.001042402,0.0001356727,0.0005704467,0.000005562316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002499409,"about_ca_system_score_gemma":0.0001661739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004557741,"about_ca_topic_score_gemma":0.0002562437,"domain_scores_codex":[0.9940979,0.0005642506,0.001341858,0.002078038,0.001631553,0.0002863853],"domain_scores_gemma":[0.9948496,0.001024332,0.0008129464,0.002066923,0.0009466119,0.0002995937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002735588,0.005671774,0.0004779487,0.00009527514,0.000543943,0.000007693627,0.006808789,0.9373552,0.000007302363,0.02224233,0.002261997,0.02425423],"study_design_scores_gemma":[0.001023478,0.0004532747,0.0006221256,0.0001162548,0.0001626871,0.000002120733,0.001691364,0.9630963,0.00004566245,0.03126283,0.001171328,0.0003525291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0603614,0.00003595899,0.9334564,0.00008919436,0.003122028,0.0009320468,0.0018572,0.0001413812,0.000004360351],"genre_scores_gemma":[0.9169392,0.00003760952,0.08034808,0.0005127044,0.0003324465,0.00004467221,0.001681066,0.00005320025,0.00005104377],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8565778,"threshold_uncertainty_score":0.9998714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.335592819321051,"score_gpt":0.4663434896748334,"score_spread":0.1307506703537824,"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."}}