{"id":"W2963202404","doi":"","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Plot (graphics); Visual reasoning; Artificial intelligence; Task (project management); Intersection (aeronautics); Bar chart; Scatter plot; Bounding overwatch; Minimum bounding box; Natural language processing; Smoothness; Baseline (sea); Machine learning; Line (geometry); Image (mathematics); Mathematics","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":[0.000887662,0.002859113,0.0008636091,0.00413312,0.000972986,0.002063973,0.003536033,0.003981805,0.05281039],"category_scores_gemma":[0.009019935,0.0006298453,0.001817731,0.003233308,0.0008155882,0.003155672,0.002465477,0.002173652,0.02749192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002067883,"about_ca_system_score_gemma":0.001280613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02321013,"about_ca_topic_score_gemma":0.04934249,"domain_scores_codex":[0.9985121,0.0003153567,0.0001631056,0.0004886497,0.0004116543,0.0001092068],"domain_scores_gemma":[0.9968162,0.001543822,0.000179866,0.0006713833,0.0005897286,0.0001989086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000449345,0.0002777582,0.002923449,0.003242444,0.0001158704,0.0009652507,0.0005255375,0.004305814,0.004877331,0.00543032,0.9136586,0.0632283],"study_design_scores_gemma":[0.0004486044,0.0001859416,0.0108782,0.0008809539,0.00008508272,0.001377722,0.001109469,0.0424518,0.007539399,0.01567934,0.9192148,0.0001486458],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02027204,0.003567093,0.02773508,0.001529988,0.0005371179,0.0009825759,0.8837571,0.03978894,0.02183005],"genre_scores_gemma":[0.03110679,0.0005694341,0.04995626,0.0005693065,0.0000579706,0.0008408542,0.9091921,0.001631282,0.006075907],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05281039,"threshold_uncertainty_score":0.1766683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07102971897405239,"score_gpt":0.4403949223429446,"score_spread":0.3693652033688922,"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."}}