{"id":"W4378946015","doi":"10.48550/arxiv.2305.19181","title":"Table Detection for Visually Rich Document Images","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Mitacs","keywords":"Computer science; Information loss; Intersection (aeronautics); Artificial intelligence; Ground truth; Task (project management); Image (mathematics); Data mining; Table (database); Term (time); Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006535766,0.001421281,0.001092924,0.002959898,0.000338685,0.002151337,0.001725824,0.001361881,0.004212189],"category_scores_gemma":[0.003411328,0.0004121244,0.0008946656,0.001532718,0.0004386916,0.002934041,0.0008661398,0.001170943,0.003546568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008446633,"about_ca_system_score_gemma":0.0008419806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006739405,"about_ca_topic_score_gemma":0.01056843,"domain_scores_codex":[0.9992102,0.00006164707,0.00004372041,0.0003238731,0.000267614,0.00009289906],"domain_scores_gemma":[0.9985638,0.0004762381,0.0002228686,0.0003355542,0.0003249025,0.00007668595],"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":[0.0006607901,0.0001672362,0.004479587,0.0005213156,0.0001176962,0.0003874647,0.0001204819,0.07882423,0.04448022,0.002883947,0.0284253,0.8389316],"study_design_scores_gemma":[0.00001587215,0.00008663213,0.001921244,0.0000406953,0.00003540373,0.0003593085,0.00008656902,0.947529,0.04063265,0.003638476,0.005632268,0.00002192075],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1277016,0.003661132,0.8238318,0.0006506044,0.0004335357,0.0002980139,0.005578716,0.03035731,0.007487268],"genre_scores_gemma":[0.6143519,0.001443304,0.3582813,0.0003629821,0.0002216057,0.0001141258,0.01267242,0.0009042782,0.01164812],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006739405,"threshold_uncertainty_score":0.01409119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0660151355830532,"score_gpt":0.2256042815368107,"score_spread":0.1595891459537574,"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."}}