{"id":"W2119306545","doi":"10.1109/icdar.2005.32","title":"A statistical learning approach to document image analysis","year":2005,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Document layout analysis; Heuristic; Artificial intelligence; Field (mathematics); Segmentation; Image segmentation; Classifier (UML); Software; Statistical learning; Machine learning; Statistical analysis; Variety (cybernetics); Image (mathematics); Pattern recognition (psychology); Data mining","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":[0.0003389385,0.0000955176,0.0001576909,0.0002992857,0.00007176233,0.0002706416,0.000421165,0.00002988416,0.0003750396],"category_scores_gemma":[0.00004977534,0.00008322408,0.00006698209,0.000901696,0.00001783528,0.0003685785,0.0002039711,0.0001152175,0.0005735373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005380891,"about_ca_system_score_gemma":0.00001730131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003462598,"about_ca_topic_score_gemma":0.000008174728,"domain_scores_codex":[0.9988708,0.00007641422,0.0001921096,0.0003662415,0.0002627131,0.0002316714],"domain_scores_gemma":[0.9993957,0.00005608251,0.00002878823,0.0002869135,0.00007286,0.0001596526],"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":[0.000004638602,0.0002603259,0.0004429728,0.000009821781,0.0002147592,0.000008943807,0.0009929182,0.0008127075,0.0009546813,0.2413952,0.01264236,0.7422607],"study_design_scores_gemma":[0.0006400966,0.0004338203,0.007339064,0.00001373749,0.0002739225,0.00003786463,0.0001863344,0.833349,0.0474421,0.0126182,0.09632444,0.001341437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007855088,0.000004178989,0.9212212,0.0007246056,0.000007660626,0.0001178694,9.661555e-7,0.0005738319,0.07656419],"genre_scores_gemma":[0.3161065,0.000001787108,0.6819397,0.0005217774,0.00002136037,0.00003570136,0.000005462387,0.000003550454,0.001364218],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8325363,"threshold_uncertainty_score":0.7371853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01128092482742816,"score_gpt":0.2770110766983321,"score_spread":0.265730151870904,"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."}}