{"id":"W4366549844","doi":"10.1145/3544548.3581271","title":"Dirty Data in the Newsroom: Comparing Data Preparation in Journalism and Data Science","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Workflow; Computer science; Data science; Context (archaeology); Big data; Thematic analysis; Data modeling; Journalism; Information retrieval; Data mining; Qualitative research; Database; Sociology","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":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005052545,0.00006807409,0.00009634408,0.0002330245,0.0001435492,0.001110021,0.01222533,0.00001571707,0.000004377908],"category_scores_gemma":[0.0004629507,0.00004712407,0.000002527801,0.002350712,0.00009674258,0.007395223,0.0121923,0.0001061219,0.0000237314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001152268,"about_ca_system_score_gemma":0.0001585426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003200302,"about_ca_topic_score_gemma":0.002129214,"domain_scores_codex":[0.9983006,0.00008823253,0.0002607108,0.0007065995,0.000439796,0.0002040718],"domain_scores_gemma":[0.994655,0.0001124096,0.00006115321,0.005101187,0.00002306548,0.00004723903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001405119,0.0004123193,0.1524978,0.00007395767,0.00002065354,0.0001246652,0.008159131,0.001706018,0.0005443488,0.3884037,0.3993128,0.04873063],"study_design_scores_gemma":[0.0001478144,0.000004613953,0.02349321,0.00001628609,0.000001855948,0.000008015878,0.0001957122,0.9607756,0.000005612631,0.0004191628,0.01486563,0.00006649817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07656182,0.0002629969,0.892414,0.01793861,0.0006949437,0.0006868335,0.0004686209,0.0003586342,0.01061358],"genre_scores_gemma":[0.9891247,0.000298279,0.00736207,0.0008566653,0.00005089048,0.000001069337,0.002142719,0.000004340849,0.0001593114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9590696,"threshold_uncertainty_score":0.9999269,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2672447097259812,"score_gpt":0.4532393490338437,"score_spread":0.1859946393078625,"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."}}