{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001141194,0.0009366544,0.000680154,0.007188494,0.0009686909,0.001883475,0.0007993215,0.0009736092,0.00575464],"category_scores_gemma":[0.006195068,0.0003893085,0.0008033185,0.004680187,0.0006885221,0.001483748,0.001313152,0.001245184,0.0068705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008409698,"about_ca_system_score_gemma":0.002344273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004649943,"about_ca_topic_score_gemma":0.009039959,"domain_scores_codex":[0.9990208,0.0001984237,0.00009290536,0.0002210969,0.0003290829,0.0001376626],"domain_scores_gemma":[0.9943914,0.002734567,0.0004540891,0.000413436,0.001861304,0.0001451988],"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":[0.0005541201,0.000140439,0.004505701,0.002796254,0.00007184542,0.001299193,0.002823856,0.002411467,0.191923,0.005671465,0.0538268,0.7339758],"study_design_scores_gemma":[0.0001490273,0.0004799108,0.07309737,0.001558849,0.000503644,0.003464315,0.01895762,0.1451977,0.3709683,0.0450094,0.340246,0.0003678362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1593155,0.004898123,0.7457758,0.003480183,0.001105673,0.002364688,0.03583021,0.01994069,0.02728911],"genre_scores_gemma":[0.219857,0.002307242,0.7422711,0.0003261198,0.0004148551,0.00102466,0.02408628,0.0009410307,0.008771596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007188494,"threshold_uncertainty_score":0.01925123,"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."}}