{"id":"W3202466114","doi":"10.1007/978-3-030-86549-8_9","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Parsing; Digitization; Set (abstract data type); Reuse; Reusability; Extensibility; Artificial intelligence; Software engineering; World Wide Web; Programming language; Software; Computer vision","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001510231,0.0006307516,0.0009142048,0.001940384,0.0003830936,0.00147832,0.002923448,0.0003814556,0.0001368249],"category_scores_gemma":[0.0002615103,0.0006277391,0.0005568049,0.001946705,0.0004104681,0.0007330102,0.001004126,0.0008670398,0.00002595358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004225165,"about_ca_system_score_gemma":0.0006102682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002436213,"about_ca_topic_score_gemma":0.0001481594,"domain_scores_codex":[0.9952019,0.00009837569,0.00073349,0.00210199,0.001057972,0.0008062756],"domain_scores_gemma":[0.996054,0.0009777276,0.0004360068,0.001498382,0.0008107848,0.0002230939],"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":[0.00001346952,0.00005917499,0.00006019714,0.0001050224,0.000172829,0.0001714749,0.0004491071,0.03678847,0.000420873,0.0124018,0.0000249033,0.9493327],"study_design_scores_gemma":[0.000475787,0.0002919855,0.00005608227,0.0003075694,0.0001618205,0.00002069615,5.423796e-7,0.9143375,0.01386668,0.06526912,0.004122955,0.001089273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003157362,0.0002687473,0.9955791,0.0008361756,0.0004458376,0.0006642013,0.000008845686,0.0004772286,0.00168825],"genre_scores_gemma":[0.03996862,0.00004218427,0.9570712,0.001676924,0.0002333529,0.00008731497,0.00007309002,0.00004684932,0.0008004188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9482434,"threshold_uncertainty_score":0.9996174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01471688984861719,"score_gpt":0.2596056761146642,"score_spread":0.244888786266047,"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."}}