{"id":"W4413390404","doi":"10.18260/1-2--55493","title":"Automating Structured Information Extraction from Images of Academic Transcripts Using Machine Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Information extraction; Extraction (chemistry); Artificial intelligence; Feature extraction; Machine learning; Information retrieval; Natural language processing; Chromatography; Chemistry","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":[],"consensus_categories":[],"category_scores_codex":[0.0003449029,0.0001201219,0.0001793098,0.0002753994,0.0002092509,0.0001881888,0.0003773812,0.00009005734,0.00003201364],"category_scores_gemma":[0.0001680115,0.0001102848,0.00004936355,0.0003889198,0.00002234638,0.00408294,0.00008924714,0.0002839001,0.000004307165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000408649,"about_ca_system_score_gemma":0.00008473891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001223044,"about_ca_topic_score_gemma":0.000001854081,"domain_scores_codex":[0.9987241,0.00004111345,0.0007348787,0.000112144,0.0002370343,0.0001507548],"domain_scores_gemma":[0.9990391,0.000101183,0.0005103519,0.0001715175,0.0001482041,0.00002961611],"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":[0.00001589046,0.0000393118,0.008738481,0.00140096,0.0001032571,6.34818e-7,0.02948587,0.03394901,0.1097251,0.07026858,0.0002624519,0.7460104],"study_design_scores_gemma":[0.0002305951,0.000006771386,0.001908836,0.0001647099,0.000009415491,0.000003226743,0.0002258003,0.930366,0.06179169,0.004951362,0.0002423331,0.00009919323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1200582,0.00009681302,0.8751178,0.00008031811,0.0002711589,0.00009152198,0.00000182208,0.0002559225,0.004026457],"genre_scores_gemma":[0.7765084,0.000008326478,0.2232398,0.0001560073,0.00001566709,0.0000010977,0.000009771395,0.000002658299,0.00005828367],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8964171,"threshold_uncertainty_score":0.4497285,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0145392872475217,"score_gpt":0.2821719971585983,"score_spread":0.2676327099110766,"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."}}