{"id":"W4400375525","doi":"10.48550/arxiv.2407.02611","title":"Co-Designing Unstructured Text Data Visualization Systems","year":2024,"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":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Unstructured data; Computer science; Visualization; Data visualization; Information visualization; Data science; Data mining; Big data","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004028745,0.0003228214,0.0003288185,0.0004346769,0.0001545954,0.0009517257,0.003859711,0.0002782755,0.00002831477],"category_scores_gemma":[0.00005594935,0.0003583657,0.00008488194,0.001058381,0.0000761089,0.0006007297,0.004221988,0.0004201261,0.0003000287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001547267,"about_ca_system_score_gemma":0.0003413876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008995603,"about_ca_topic_score_gemma":0.00001068932,"domain_scores_codex":[0.9974968,0.000200842,0.0002989643,0.001537528,0.0001781175,0.0002876924],"domain_scores_gemma":[0.9967547,0.00006772119,0.0002722833,0.002585441,0.000158921,0.0001609064],"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":[0.000004019109,0.00003419856,0.0002129271,0.0003395315,0.0001415101,0.0002123845,0.0001778023,0.1042593,0.00005503243,0.8794203,0.01484267,0.0003003025],"study_design_scores_gemma":[0.0001653161,0.00001379824,0.00002100998,0.0002248303,0.000104311,0.000007131504,0.0001003454,0.978326,0.00007320575,0.01355397,0.007011627,0.0003984785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001370739,0.0001944768,0.9930134,0.00004426513,0.001449329,0.0002563818,0.0002658803,0.0006196745,0.002785848],"genre_scores_gemma":[0.9937583,0.0002065969,0.001012512,0.0001034686,0.0001716472,4.191374e-7,0.001568646,0.00003490828,0.003143561],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9923875,"threshold_uncertainty_score":0.9998868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1273281141633771,"score_gpt":0.2607642495659284,"score_spread":0.1334361354025513,"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."}}