{"id":"W2996118209","doi":"10.1109/visual.2019.8933542","title":"Uncovering Data Landscapes through Data Reconnaissance and Task Wrangling","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data science; Computer science; Task (project management); Domain (mathematical analysis); Visualization; Set (abstract data type); Data visualization; Data mining; Systems engineering; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0002705489,0.0000749898,0.0001024937,0.00003089641,0.0000512167,0.0003079584,0.002264957,0.00002217113,0.0000462438],"category_scores_gemma":[0.00008383377,0.00006353333,0.000005581144,0.0002327097,0.00001254983,0.002977574,0.002934725,0.00004771591,0.00009726991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004659286,"about_ca_system_score_gemma":0.00004142622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004922354,"about_ca_topic_score_gemma":0.00005655317,"domain_scores_codex":[0.9990528,0.00001706216,0.0001347483,0.0005271637,0.0001346389,0.0001336007],"domain_scores_gemma":[0.9974753,0.00005530931,0.00004465479,0.002366242,0.00002134112,0.00003716612],"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":[0.00001515419,0.0001856458,0.04555943,0.0003565308,0.0001818444,0.00003540106,0.00178685,0.001466733,0.0009848734,0.6343236,0.1496749,0.1654291],"study_design_scores_gemma":[0.0001953056,0.000009412099,0.0001409751,0.00002536114,0.000003210061,0.00000558924,0.00004338612,0.7336282,0.00006341393,0.001017316,0.2647475,0.0001203593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00329235,0.0003452455,0.9810169,0.000848337,0.0002786024,0.00008139607,0.0001363839,0.0001588091,0.01384197],"genre_scores_gemma":[0.7879972,0.001150145,0.2012945,0.004121409,0.0003006567,0.000001134888,0.001818985,0.00002613102,0.003289879],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7847048,"threshold_uncertainty_score":0.4208891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08160704378035767,"score_gpt":0.330723064920984,"score_spread":0.2491160211406264,"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."}}