{"id":"W4402683795","doi":"10.18653/v1/2024.findings-acl.619","title":"ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning","year":2024,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Comprehension; Chart; Artificial intelligence; Natural language processing; Programming language; Mathematics; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000918292,0.002178905,0.0009167211,0.001383971,0.0004444407,0.001404098,0.002672376,0.00133204,0.03632444],"category_scores_gemma":[0.008627644,0.0008654403,0.0005349335,0.0005694529,0.0003286441,0.002443788,0.001477816,0.001436024,0.009650769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008647145,"about_ca_system_score_gemma":0.001402952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004974522,"about_ca_topic_score_gemma":0.005294793,"domain_scores_codex":[0.9988721,0.0001638977,0.00009164888,0.0004627987,0.0002803193,0.0001291931],"domain_scores_gemma":[0.9969255,0.001386044,0.0001601307,0.0005642136,0.0007039345,0.0002602142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002699788,0.0009255632,0.00424138,0.0004433102,0.00008989035,0.0002327923,0.0003485966,0.008493636,0.05246802,0.001270978,0.07436087,0.8544252],"study_design_scores_gemma":[0.001070663,0.0009199422,0.009812337,0.0001092603,0.0001690127,0.0002870674,0.0001994671,0.6263422,0.2981093,0.004147009,0.05859849,0.0002352891],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.05238613,0.0003767767,0.3269433,0.0002233411,0.000404915,0.0005229096,0.003078553,0.6090794,0.006984686],"genre_scores_gemma":[0.4592792,0.0002409548,0.4746951,0.0004309575,0.0001715465,0.001049526,0.01025634,0.03263855,0.0212377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03632444,"threshold_uncertainty_score":0.1215174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02018435208255513,"score_gpt":0.2567453480779363,"score_spread":0.2365609959953811,"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."}}