{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005303078,0.002415864,0.001155407,0.002031591,0.0005453949,0.002254385,0.004194463,0.001368666,0.05179321],"category_scores_gemma":[0.001564563,0.001597944,0.001958009,0.001922513,0.000365533,0.002445733,0.002502595,0.002888298,0.03088249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007592624,"about_ca_system_score_gemma":0.001110183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005506082,"about_ca_topic_score_gemma":0.0131451,"domain_scores_codex":[0.9995421,0.00004071268,0.00003248425,0.0001252742,0.0001989234,0.00006050318],"domain_scores_gemma":[0.9995221,0.0001449014,0.00003020793,0.0001177912,0.0001413172,0.00004364156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003297573,0.0001823633,0.0006187082,0.000842015,0.0002205163,0.0002405537,0.0001248215,0.0228739,0.03382825,0.009039584,0.2081282,0.7235714],"study_design_scores_gemma":[0.0001343047,0.0001119635,0.0009822068,0.0001593249,0.00009546763,0.0004742215,0.00007756676,0.7421936,0.0771511,0.02812077,0.1503566,0.0001428536],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001441674,0.0003559276,0.7899616,0.00007737401,0.0001195006,0.0001004282,0.00459626,0.2003939,0.002953256],"genre_scores_gemma":[0.02416252,0.0007364649,0.9163175,0.000291989,0.00005115095,0.0004881806,0.0160335,0.02162668,0.02029198],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.05179321,"threshold_uncertainty_score":0.1732656,"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."}}