{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002278915,0.00009290978,0.00009963253,0.00009941683,0.0001878703,0.0003503209,0.0001117859,0.00003726187,0.000006639941],"category_scores_gemma":[0.0000196164,0.00007890449,0.0000387901,0.0001188343,0.00001381402,0.0004661495,0.0000824122,0.00009818457,0.00001674025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002357786,"about_ca_system_score_gemma":0.00001712108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002427707,"about_ca_topic_score_gemma":8.979077e-7,"domain_scores_codex":[0.999235,0.00001944705,0.0001488657,0.0003153452,0.0001055686,0.0001757215],"domain_scores_gemma":[0.9996896,0.00006573953,0.00002877092,0.000125973,0.00004313946,0.0000468236],"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":[0.000001799649,0.000001835437,0.0001942296,0.00007841906,0.000009943505,0.000003477516,0.0007085031,0.00002976245,0.009976747,0.8972799,0.0001145328,0.09160087],"study_design_scores_gemma":[0.0001478247,0.00008035486,0.0005234306,0.000381313,0.0000046112,0.0001351409,0.0002176685,0.7177195,0.005404504,0.001486969,0.2737131,0.0001856225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.103115,0.0003699882,0.8929,0.0002611274,0.001348711,0.0001381485,4.813469e-7,0.0004274216,0.001439168],"genre_scores_gemma":[0.9393187,0.00001016895,0.05636735,0.00005598353,0.000288589,0.00001383021,0.000001481974,0.00001204868,0.003931828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8957929,"threshold_uncertainty_score":0.3378153,"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."}}