{"id":"W4400434413","doi":"10.48550/arxiv.2407.04172","title":"ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Educational Games and Gamification","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Chart; Computer science; Psychology; 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":[0.001453637,0.002068053,0.0007217189,0.001418856,0.0003748221,0.002037663,0.004314926,0.00153047,0.01328205],"category_scores_gemma":[0.0115206,0.0006668421,0.001628401,0.0009002755,0.0008133406,0.003472447,0.002534139,0.003495937,0.00515089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001335118,"about_ca_system_score_gemma":0.001933805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00967307,"about_ca_topic_score_gemma":0.01609737,"domain_scores_codex":[0.999176,0.0002063274,0.00005715501,0.0003277165,0.0001497708,0.00008307666],"domain_scores_gemma":[0.997772,0.001169324,0.00007837563,0.0006040695,0.0002648456,0.0001112214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0011869,0.000982039,0.006583545,0.00116441,0.0002074375,0.0003197056,0.0005006637,0.1902263,0.01231567,0.02506122,0.1645571,0.596895],"study_design_scores_gemma":[0.0001883449,0.0001080752,0.0006857976,0.00006716745,0.00002461014,0.00004515951,0.0000539684,0.9458897,0.007639777,0.02577319,0.01949394,0.00003029461],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03720098,0.0008986347,0.6166071,0.0009303654,0.0004575817,0.0008359819,0.01202854,0.3208154,0.01022539],"genre_scores_gemma":[0.2482842,0.0005227884,0.7032684,0.0007942927,0.00007627355,0.001594796,0.03229019,0.006758881,0.006410192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01328205,"threshold_uncertainty_score":0.04443294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08952285437443963,"score_gpt":0.270634373807959,"score_spread":0.1811115194335194,"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."}}