{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016556,0.000907948,0.0005664279,0.00118279,0.0007621163,0.002943248,0.001307379,0.0007952334,0.0039472],"category_scores_gemma":[0.009592214,0.0004944486,0.001545933,0.0008116884,0.0006386763,0.003558995,0.001676791,0.001980572,0.002050826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001275492,"about_ca_system_score_gemma":0.002134667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008825663,"about_ca_topic_score_gemma":0.01720361,"domain_scores_codex":[0.9986482,0.0005198495,0.0001194193,0.0002943212,0.0003634007,0.00005473549],"domain_scores_gemma":[0.9957074,0.002756649,0.0003656542,0.0004445569,0.0006322458,0.00009334519],"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":[0.0003689745,0.0004911746,0.003327099,0.0008737874,0.0002173192,0.0007498821,0.002351086,0.3315802,0.02949173,0.05999096,0.03030848,0.5402492],"study_design_scores_gemma":[0.00003490894,0.00005814128,0.0002543923,0.00004158369,0.00005615777,0.00005215982,0.0002137339,0.9455397,0.0073779,0.02814934,0.01818921,0.00003278457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01419177,0.0001930959,0.9665904,0.0007554062,0.00009250487,0.0003105843,0.0009876055,0.01310893,0.003769674],"genre_scores_gemma":[0.1605489,0.0003603319,0.8300564,0.00029748,0.00006752159,0.000397818,0.003370877,0.001006526,0.003894267],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008825663,"threshold_uncertainty_score":0.01754856,"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."}}