{"id":"W4366549398","doi":"10.1145/3544548.3581113","title":"ChartDetective: Easy and Accurate Interactive Data Extraction from Complex Vector Charts","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Agence Nationale de la Recherche","keywords":"Computer science; Raster data; Data mining; Raster graphics; Data extraction; Interface (matter); Artificial intelligence; Pattern recognition (psychology)","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":[0.0001534201,0.00009556911,0.0001080054,0.0001022546,0.0001033402,0.0003221865,0.0006254684,0.0000281059,0.0001968944],"category_scores_gemma":[0.000101466,0.0000859999,0.00001340237,0.0004172237,0.00002576637,0.001804337,0.0008079615,0.00007690318,0.0004797514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001455399,"about_ca_system_score_gemma":0.00002130584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001039279,"about_ca_topic_score_gemma":0.00004411067,"domain_scores_codex":[0.9990478,0.00005266257,0.0001423031,0.0004526502,0.000160464,0.0001441513],"domain_scores_gemma":[0.9989803,0.0001537566,0.00007280016,0.0006614404,0.00005285906,0.00007883165],"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":[0.0001019623,0.0005442437,0.002847885,0.00007377206,0.0005612853,0.0002008113,0.006441897,0.00012737,0.08996151,0.1421815,0.331661,0.4252968],"study_design_scores_gemma":[0.000202949,0.00002090168,0.03356245,0.00001075409,0.000005933731,0.000003637515,0.0001422948,0.9234557,0.001172779,0.0006256418,0.04065892,0.000138056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01334445,0.00001942079,0.9799753,0.002181695,0.0006413686,0.0001780848,0.0004234088,0.0007961876,0.002440113],"genre_scores_gemma":[0.9934635,0.00008479081,0.00345569,0.0006981835,0.0001260879,0.000004687596,0.0009183662,0.00001057113,0.001238148],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.980119,"threshold_uncertainty_score":0.6166394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1290413302430225,"score_gpt":0.3909459923106922,"score_spread":0.2619046620676697,"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."}}