{"id":"W3203851352","doi":"10.1016/j.neucom.2022.09.094","title":"On cropped versus uncropped training sets in tabular structure detection","year":2022,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Gnowit (Canada); University of Ottawa","funders":"","keywords":"Table (database); Intersection (aeronautics); Set (abstract data type); Computer science; Artificial intelligence; Precision and recall; Training set; Data mining; Machine learning; Geography; Cartography","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":[0.003153356,0.0009950579,0.001237708,0.001899524,0.0007389681,0.001541356,0.001393802,0.001678505,0.004107601],"category_scores_gemma":[0.01385361,0.0003567099,0.0008047762,0.001115544,0.0006224446,0.001755379,0.00123851,0.0009335352,0.001851436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006289075,"about_ca_system_score_gemma":0.001065948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007827098,"about_ca_topic_score_gemma":0.0135374,"domain_scores_codex":[0.997687,0.0006577798,0.000167055,0.0004801981,0.0007228832,0.0002850723],"domain_scores_gemma":[0.9906427,0.006317051,0.0002749209,0.001164179,0.001371538,0.0002296145],"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":[0.002539743,0.0003150702,0.003983618,0.0003121453,0.0001606853,0.0002242032,0.0001110526,0.05352096,0.03337239,0.000848913,0.006126573,0.8984846],"study_design_scores_gemma":[0.00008874378,0.0004819372,0.00969413,0.00007533397,0.0001491303,0.0003635859,0.0002082529,0.9486189,0.03675197,0.001399402,0.002138799,0.0000297649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6804907,0.00498454,0.2909537,0.0007870515,0.0005657391,0.0003954723,0.00209448,0.006874297,0.01285398],"genre_scores_gemma":[0.7730541,0.0009859496,0.2142464,0.0003659794,0.0001274366,0.0001095629,0.004645745,0.000509633,0.005955294],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007827098,"threshold_uncertainty_score":0.01667672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0270636309194266,"score_gpt":0.2630589935034269,"score_spread":0.2359953625840003,"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."}}