{"id":"W2029526043","doi":"10.1007/s10032-011-0156-6","title":"Error handling approach using characterization and correction steps for handwritten document analysis","year":2011,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"H2020 European Research Council","keywords":"Computer science; Phrase; Word (group theory); Artificial intelligence; Speech recognition; Natural language processing; Sentence; Intelligent word recognition; Posterior probability; Handwriting; Error detection and correction; Pattern recognition (psychology); Intelligent character recognition; Algorithm; Bayesian probability; Linguistics","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":[0.001059966,0.001268454,0.0009462765,0.002360905,0.001209289,0.001967752,0.001956165,0.001215949,0.003562727],"category_scores_gemma":[0.00404064,0.0004621053,0.0007936436,0.001586485,0.000497625,0.001422121,0.001056272,0.001469327,0.001855957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004157799,"about_ca_system_score_gemma":0.00164772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003365255,"about_ca_topic_score_gemma":0.003691753,"domain_scores_codex":[0.9980622,0.0001914694,0.0002427384,0.0004471308,0.0008780605,0.0001783726],"domain_scores_gemma":[0.9938923,0.001053882,0.0006247776,0.001138812,0.003137865,0.0001524291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004528705,0.0001842681,0.002805465,0.0002311035,0.0000897837,0.0005049007,0.0003408489,0.006173949,0.1459751,0.001331105,0.002516446,0.8393942],"study_design_scores_gemma":[0.00003861161,0.0004374812,0.006944356,0.00007415518,0.0002562047,0.002508249,0.0003915681,0.3777846,0.5923817,0.002021918,0.01704947,0.0001116653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03099354,0.0003213792,0.9625005,0.00008550163,0.0001220391,0.000106034,0.00007939541,0.005038024,0.0007534914],"genre_scores_gemma":[0.1979662,0.0003159639,0.7935607,0.0001129427,0.00005719319,0.00009659734,0.0005279938,0.0006746944,0.006687758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003562727,"threshold_uncertainty_score":0.01191849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04020382215980793,"score_gpt":0.2903658157744112,"score_spread":0.2501619936146032,"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."}}