{"id":"W4386919255","doi":"10.1007/978-3-031-43849-3_28","title":"Detection of Redacted Text in Legal Documents","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Computer science; Redaction; Optical character recognition; Artificial intelligence; Discriminator; Segmentation; Character (mathematics); Grayscale; Task (project management); Pattern recognition (psychology); Image (mathematics); Natural language processing; Detector; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001054007,0.0003980152,0.0005308073,0.002209295,0.00009082896,0.0002963619,0.002384204,0.000379371,0.00001658462],"category_scores_gemma":[0.0001612856,0.0003982655,0.0001201048,0.001571143,0.0004174118,0.0009360622,0.001060395,0.0008167293,0.00005343385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003413496,"about_ca_system_score_gemma":0.0003492032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001603273,"about_ca_topic_score_gemma":0.0004243623,"domain_scores_codex":[0.9964708,0.0000533164,0.0007418029,0.001225839,0.0009740727,0.0005341353],"domain_scores_gemma":[0.9978777,0.0003523562,0.0003677827,0.001020691,0.0002772381,0.0001042746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006366131,0.00002884099,0.00003507355,0.00004317679,0.000006842232,0.00008871326,0.0002212444,0.0005120905,0.003351016,0.004162415,0.00001087309,0.9915333],"study_design_scores_gemma":[0.0009317832,0.0007289239,0.001584632,0.002287075,0.00001356725,0.0001514824,5.113486e-7,0.2295424,0.2293874,0.5319121,0.00182559,0.001634546],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004484316,0.00006180276,0.9939151,0.0002239655,0.001047436,0.0004540709,0.000006162853,0.0003962167,0.003446794],"genre_scores_gemma":[0.7895716,0.0001206116,0.2082795,0.0004939013,0.0002400458,0.00004330434,0.000008742227,0.00006832039,0.001173922],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9898988,"threshold_uncertainty_score":0.9998469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01566223343905755,"score_gpt":0.2573974911616965,"score_spread":0.2417352577226389,"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."}}