{"id":"W7067264059","doi":"","title":"Leveraging large language models for automated chart summarization","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Automatic summarization; Chart; Language model; Data modeling; Natural language","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":[0.0005491892,0.0005290093,0.000493974,0.000451349,0.001282693,0.0002946312,0.001273125,0.0003655645,0.00001769815],"category_scores_gemma":[0.0001308854,0.0006249222,0.0003223222,0.001063729,0.00001082061,0.00105113,0.0002365423,0.0005414737,0.00007114001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003265619,"about_ca_system_score_gemma":0.0001696632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009303811,"about_ca_topic_score_gemma":0.0001700009,"domain_scores_codex":[0.9968762,0.0001236652,0.0006803029,0.001166516,0.0005741184,0.0005791938],"domain_scores_gemma":[0.9973848,0.0003604547,0.0004570504,0.0009265276,0.0006978685,0.0001732787],"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":[0.00001862226,0.0001556585,7.542207e-7,0.0002232946,0.00009706613,0.000003684327,0.00004942278,0.003911546,0.003804593,0.9154045,0.00008380516,0.07624708],"study_design_scores_gemma":[0.0008812118,0.00003961152,0.0001455801,0.0002830268,0.00009174959,0.000003069421,0.0001102489,0.623551,0.008017663,0.3393183,0.02665262,0.0009058874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3443837,0.001788379,0.1629115,0.0009441939,0.01205433,0.0146472,0.01868612,0.01816096,0.4264235],"genre_scores_gemma":[0.9539004,0.0000480482,0.02244533,0.0006989431,0.00008651552,0.0008410211,0.010257,0.0001235774,0.01159915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6196395,"threshold_uncertainty_score":0.9996202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01864198829575992,"score_gpt":0.2706150358132903,"score_spread":0.2519730475175304,"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."}}