{"id":"W4226018502","doi":"10.1145/3545995","title":"EDAssistant: Supporting Exploratory Data Analysis in Computational Notebooks with In Situ Code Search and Recommendation","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Interactive Intelligent Systems","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Computer science; Context (archaeology); Code (set theory); Exploratory search; Data science; Visualization; Information retrieval; Human–computer interaction; World Wide Web; Data mining; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0008953789,0.0001522791,0.0002611823,0.001143639,0.0002531726,0.0002154799,0.0008752872,0.00002786391,0.00008652769],"category_scores_gemma":[0.00003031795,0.0001539722,0.00003705051,0.001460136,0.00003501715,0.0008611544,0.0001311405,0.0004013612,0.000007740463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003343443,"about_ca_system_score_gemma":0.0001144924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003864893,"about_ca_topic_score_gemma":0.001666927,"domain_scores_codex":[0.9977072,0.0004784999,0.0005706521,0.0006333485,0.0003970102,0.0002132567],"domain_scores_gemma":[0.9985015,0.0004668957,0.0001637057,0.0006969901,0.0001009932,0.00006995307],"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":[0.0002554835,0.001161304,0.006582632,0.00006896084,0.0006706651,0.00008564277,0.01393215,0.9362845,0.0002066711,0.00355038,0.00008006488,0.03712152],"study_design_scores_gemma":[0.0003340055,0.0001413723,0.000749231,0.00005458123,0.00004043035,0.00002144884,0.01099143,0.9858273,0.0004808774,0.00009642581,0.001058246,0.000204629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01602767,0.00001409957,0.982518,0.0005349778,0.0001760456,0.0002642795,0.000240983,0.00004255397,0.0001813515],"genre_scores_gemma":[0.996805,0.00001069781,0.002433361,0.0001258992,0.000008206877,0.00007358089,0.0004276088,0.00001166249,0.0001040416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9807773,"threshold_uncertainty_score":0.6278806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08697835265267972,"score_gpt":0.3651222442131325,"score_spread":0.2781438915604528,"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."}}