{"id":"W4287671863","doi":"10.48550/arxiv.2009.02373","title":"Table Scraps: An Actionable Framework for Multi-Table Data Wrangling\\n From An Artifact Study of Computational Journalism","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Parallels; Table (database); Artifact (error); Context (archaeology); Journalism; Data science; Task (project management); Code (set theory); Set (abstract data type); Data mining; Artificial intelligence; Engineering; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01758476,0.001615673,0.00127078,0.009004744,0.004890513,0.01329045,0.007423368,0.002895495,0.01350324],"category_scores_gemma":[0.03418557,0.002218197,0.005943962,0.007219959,0.01199147,0.02130309,0.01324455,0.005936402,0.004145572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002760855,"about_ca_system_score_gemma":0.005407472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009889049,"about_ca_topic_score_gemma":0.01738993,"domain_scores_codex":[0.9863272,0.006331207,0.001732059,0.002312998,0.002581533,0.0007150219],"domain_scores_gemma":[0.9669126,0.01350398,0.002302305,0.01379761,0.001956393,0.001527134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005612411,0.00005837831,0.00176647,0.0003421594,0.00004033857,0.0003560075,0.00767391,0.004121855,0.001312928,0.8994254,0.01018724,0.07465933],"study_design_scores_gemma":[0.00003469138,0.00007509863,0.0007680794,0.0004776053,0.00005746453,0.0006446789,0.003354793,0.04201536,0.003775829,0.6224579,0.3262019,0.0001367088],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001787933,0.0001797892,0.9878044,0.0008425401,0.00009703237,0.0002568082,0.0005971251,0.004312439,0.004121857],"genre_scores_gemma":[0.02420448,0.000206227,0.9690911,0.0002557181,0.00007846425,0.0004636379,0.001128998,0.001206283,0.003365066],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01758476,"threshold_uncertainty_score":0.09299821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2921002124729303,"score_gpt":0.3206074615157642,"score_spread":0.02850724904283392,"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."}}