{"id":"W2098345386","doi":"10.1007/s10032-006-0020-2","title":"A survey of document image classification: problem statement, classifier architecture and performance evaluation","year":2006,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":174,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Xerox Foundation","keywords":"Computer science; Classifier (UML); Document classification; Contextual image classification; Artificial intelligence; Pattern recognition (psychology); Problem statement; Ambiguity; Information retrieval; Machine learning; Data mining; Image (mathematics)","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":[0.002610092,0.0002138797,0.0002987199,0.001076402,0.0001648205,0.0007244788,0.0003797886,0.00007766073,0.0003577771],"category_scores_gemma":[0.00005773034,0.0001759364,0.000141063,0.0006210809,0.00009395547,0.0009583492,0.000106911,0.0002526276,0.00001362313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001690418,"about_ca_system_score_gemma":0.00008876112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001638734,"about_ca_topic_score_gemma":0.0001310962,"domain_scores_codex":[0.9967981,0.00041323,0.0009287193,0.0004224125,0.001241011,0.0001965485],"domain_scores_gemma":[0.9970593,0.0001447507,0.0008287504,0.0001952438,0.00166441,0.000107586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001452085,0.0003145308,0.03312308,0.00002414911,0.001262804,0.00001128509,0.00022661,0.000110431,0.001262075,0.001153215,0.0009167804,0.9614499],"study_design_scores_gemma":[0.00273554,0.0007365838,0.8932781,0.0003155858,0.0006942907,0.0001237344,0.00007572821,0.02849116,0.01416995,0.05713075,0.001566541,0.000682054],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7562963,0.0002298146,0.2370886,0.0025974,0.0002655585,0.0005007182,0.00006072151,0.00007015313,0.002890733],"genre_scores_gemma":[0.9795442,0.0009252122,0.01871325,0.000162928,0.0001051626,0.00005317228,0.0002841387,0.000009714541,0.0002022721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9607678,"threshold_uncertainty_score":0.7174479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02727027337698614,"score_gpt":0.3066844968063903,"score_spread":0.2794142234294041,"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."}}