{"id":"W4285255856","doi":"10.18653/v1/2022.findings-acl.177","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":246,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Question answering; Benchmark (surveying); Vocabulary; Chart; Visual reasoning; Artificial intelligence; Qualitative reasoning; Variety (cybernetics); Natural language processing; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009637872,0.0001143519,0.0001790518,0.0001072114,0.000702091,0.0001280358,0.0003711482,0.00003795848,0.000009585857],"category_scores_gemma":[0.002997548,0.0001033033,0.00007964962,0.0003287639,0.00002624723,0.00008537086,0.0002956899,0.0001196317,6.028991e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002114411,"about_ca_system_score_gemma":0.0001075054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005535547,"about_ca_topic_score_gemma":0.000002138611,"domain_scores_codex":[0.9985949,0.00006930058,0.0003031181,0.0002863162,0.0005523568,0.000193947],"domain_scores_gemma":[0.9980562,0.0007296404,0.0004786123,0.0001129161,0.0005785397,0.00004413391],"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":[0.00006087657,0.0001368999,0.03254679,0.00006951487,0.0001055286,6.297278e-7,0.0006027553,0.0430487,0.00004593078,0.9187155,0.004246948,0.0004199284],"study_design_scores_gemma":[0.001052248,0.0003359713,0.02319528,0.00004834739,0.0000535307,0.000004370799,0.00007413731,0.9250005,0.0001007976,0.01729109,0.03261926,0.0002244444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05123135,0.00009587705,0.9426915,0.001399376,0.001643258,0.001154533,0.001105033,0.0001417116,0.0005373669],"genre_scores_gemma":[0.9738755,0.000003107136,0.02454177,0.0003412899,0.0001978087,0.00007569358,0.000436613,0.00001489408,0.0005133916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9226441,"threshold_uncertainty_score":0.5399987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00984609113906177,"score_gpt":0.2772540827683285,"score_spread":0.2674079916292668,"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."}}