{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003457318,0.0001869429,0.0001551756,0.0001765211,0.001476495,0.001558258,0.002304506,0.00007969995,0.0002313067],"category_scores_gemma":[0.001860901,0.0001970988,0.00007019724,0.00009035876,0.00009781904,0.001314464,0.0002846577,0.0004397226,0.0002058216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005351559,"about_ca_system_score_gemma":0.0001124493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007007679,"about_ca_topic_score_gemma":0.00004433479,"domain_scores_codex":[0.9981803,0.0001201604,0.0002857967,0.0007332156,0.0004147912,0.0002657225],"domain_scores_gemma":[0.9975749,0.0002649681,0.0004320012,0.001098222,0.0004843697,0.0001455671],"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":[0.0001057529,0.0005289077,0.04216962,0.00001534549,0.0001772226,0.00002241521,0.002304567,0.02182831,0.008557227,0.8562774,0.005655949,0.06235727],"study_design_scores_gemma":[0.0005948783,0.0001579013,0.1140107,0.00004030804,0.000009454819,0.000008252257,0.0001149297,0.8674757,0.0003806553,0.003798467,0.0131649,0.0002438993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2190443,0.00000939625,0.6907077,0.03950058,0.001396963,0.001287121,0.0009371951,0.0008671492,0.04624958],"genre_scores_gemma":[0.9740696,0.000006276371,0.02035116,0.0001987272,0.0002062851,0.0002615113,0.003135849,0.00002047948,0.001750124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8524789,"threshold_uncertainty_score":0.9998235,"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."}}