{"id":"W2953662108","doi":"10.22260/isarc2019/0060","title":"Text Detection and Classification of Construction Documents","year":2019,"lang":"en","type":"article","venue":"Proceedings of the ... ISARC","topic":"BIM and Construction Integration","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Optical character recognition; Information retrieval; Set (abstract data type); Bounding overwatch; Task (project management); Minimum bounding box; Artificial intelligence; Class (philosophy); Character (mathematics); Document processing; Download; Deep learning; Document management system; Data set; Control (management); Natural language processing; Image (mathematics); World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005956345,0.00005626423,0.00007652248,0.00005533991,0.00002263222,0.00001242698,0.0000585389,0.00005156317,0.00002403859],"category_scores_gemma":[0.0000111922,0.00004452155,0.00002696806,0.0001330076,0.00006111545,0.0001967595,0.00001273884,0.00006828162,0.000005392239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000232162,"about_ca_system_score_gemma":0.000003658109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005793247,"about_ca_topic_score_gemma":0.00000134079,"domain_scores_codex":[0.9996162,0.000001669263,0.000154418,0.0000731547,0.0001005253,0.00005401322],"domain_scores_gemma":[0.999747,0.000006737682,0.0000881978,0.00004521615,0.0001003646,0.00001243759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001056071,0.000004011653,0.02588018,0.0001266882,0.00001592808,1.37016e-9,0.0001401122,0.00001323982,0.9149377,0.01232941,0.00006198362,0.04648017],"study_design_scores_gemma":[0.0004218843,0.00005188932,0.1131888,0.0001109223,0.00003618708,0.00002817924,0.001427971,0.01122424,0.865013,0.006678753,0.001688375,0.0001298051],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811736,0.00004092651,0.0001294814,0.00003665815,0.000378981,0.0001343362,0.000001500873,0.00003682373,0.01806763],"genre_scores_gemma":[0.9995047,0.00002783035,0.0003096168,0.000002906329,0.00002074695,0.000006108462,2.723497e-7,0.000006625838,0.0001212326],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0873086,"threshold_uncertainty_score":0.1815536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005978358122068816,"score_gpt":0.1911489674612615,"score_spread":0.1851706093391927,"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."}}