{"id":"W4403813921","doi":"10.48550/arxiv.2409.19747","title":"Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directions","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Centre International de Recherche sur le Cancer","keywords":"Natural (archaeology); State (computer science); Computer science; Visualization; Human–computer interaction; Data science; Geology; Programming language; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0001113568,0.0001187608,0.0001233127,0.0001323563,0.00009963615,0.00008501779,0.0004146256,0.00006650436,0.000002622111],"category_scores_gemma":[0.00002070337,0.0001012282,0.00008667483,0.0002958628,0.00004697231,0.0001383516,0.0007502697,0.000149064,0.00000350446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003274471,"about_ca_system_score_gemma":0.000072809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006951703,"about_ca_topic_score_gemma":0.0001607121,"domain_scores_codex":[0.9992682,0.00006174729,0.0001163014,0.000407327,0.00005350371,0.00009289385],"domain_scores_gemma":[0.9992541,0.00003301613,0.0001162375,0.0004423544,0.0001206923,0.00003359765],"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":[0.00000362178,0.00005487332,0.00001887454,0.0003122647,0.0001196128,0.000006078808,0.002738011,0.006388719,0.0001505873,0.9741451,0.001962097,0.01410021],"study_design_scores_gemma":[0.0001198647,0.00001320347,0.0001329555,0.00005454831,0.00006398684,0.000001476832,0.0001904478,0.9677147,0.000203688,0.01482383,0.01653736,0.0001439353],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0684532,0.02553442,0.8918766,0.003772992,0.005924773,0.001295044,0.0005321389,0.0005206722,0.002090171],"genre_scores_gemma":[0.9832214,0.01039551,0.0007972406,0.0001126943,0.0002470309,0.000002082166,0.0001101846,0.00001501105,0.005098832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.961326,"threshold_uncertainty_score":0.4127968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06189839220070732,"score_gpt":0.2383711742443884,"score_spread":0.1764727820436811,"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."}}