{"id":"W4379374334","doi":"10.21428/594757db.0b1f96f6","title":"ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Automatic summarization; Benchmark (surveying); Chart; Metadata; Data mining; Information retrieval; Artificial intelligence; Natural language processing; World Wide Web","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002888613,0.0002629937,0.0005138688,0.0002281845,0.00009206001,0.0001966932,0.0006779053,0.0002125437,0.0000102315],"category_scores_gemma":[0.00008098452,0.0002576773,0.0001116423,0.0001482072,0.00007145425,0.0002083971,0.001793624,0.00018315,0.000003291434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003512884,"about_ca_system_score_gemma":0.0001403955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001191965,"about_ca_topic_score_gemma":0.00008996211,"domain_scores_codex":[0.998099,0.00004686655,0.0005586313,0.0007169772,0.000304245,0.000274311],"domain_scores_gemma":[0.9982939,0.0003305445,0.0001831778,0.0008274879,0.0002864867,0.00007835189],"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":[0.00004735907,0.000326045,0.05940831,0.02068533,0.001284153,0.00006424824,0.01511385,0.02205106,0.00136335,0.373466,0.01380945,0.4923808],"study_design_scores_gemma":[0.0001523522,0.00003608651,0.0101546,0.0003134303,0.00003256131,0.000003130906,0.00005824329,0.9749319,0.0005566425,0.0132509,0.0002216365,0.0002884991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04094979,0.0002226595,0.9552613,0.000814367,0.0009507727,0.001111781,0.0000400706,0.0003996782,0.0002496179],"genre_scores_gemma":[0.6849324,0.0003324326,0.3114377,0.0003098722,0.0002815584,0.0004916791,0.0005001868,0.00007229825,0.001641864],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9528809,"threshold_uncertainty_score":0.9999875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0721323320600067,"score_gpt":0.2976251434578269,"score_spread":0.2254928113978202,"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."}}