{"id":"W6910356136","doi":"10.48448/hpst-xq06","title":"ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Chart; Pipeline (software); Comprehension; Scope (computer science); Set (abstract data type); Range (aeronautics); Visual reasoning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001417993,0.002875335,0.0007210267,0.001659025,0.0005106876,0.001698429,0.003408448,0.002028661,0.00896641],"category_scores_gemma":[0.00909658,0.0004802091,0.001448815,0.001195817,0.0006065305,0.003168496,0.001596856,0.003210578,0.007383275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001911734,"about_ca_system_score_gemma":0.003172101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02306309,"about_ca_topic_score_gemma":0.03544218,"domain_scores_codex":[0.9986849,0.000226498,0.0001059934,0.0006241319,0.0002143011,0.0001441772],"domain_scores_gemma":[0.9978334,0.0007300213,0.0001265261,0.0006617992,0.0004729828,0.0001752416],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001274387,0.001308295,0.01195922,0.001353729,0.0002001523,0.0003652391,0.0003924091,0.04843919,0.02282779,0.003763676,0.3051204,0.6029957],"study_design_scores_gemma":[0.0004501376,0.0006504029,0.009593124,0.000177714,0.0001334353,0.0002219012,0.0003170217,0.7991881,0.07284379,0.008789395,0.1074567,0.0001783431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.149629,0.003686043,0.2393688,0.001759477,0.001236414,0.001807949,0.108027,0.4748957,0.01958973],"genre_scores_gemma":[0.3355269,0.0009278847,0.3652033,0.001194987,0.0001618,0.001695483,0.2783852,0.004663075,0.01224142],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02306309,"threshold_uncertainty_score":0.04585773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02709560434493346,"score_gpt":0.3081338421366798,"score_spread":0.2810382377917463,"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."}}