{"id":"W4411020509","doi":"10.1093/jcde/qwaf053","title":"Optimizing image format piping and instrumentation diagram recognition: Integrating symbol and text recognition with a single backbone architecture","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Design and Engineering","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"ASTER","funders":"Ministry of Science and ICT, South Korea; Ministry of Education, India; National Research Foundation; National Research Foundation of Korea; Ministry of Education","keywords":"Symbol (formal); Instrumentation (computer programming); Architecture; Piping; Diagram; Computer science; Engineering drawing; Artificial intelligence; Pattern recognition (psychology); Computer vision; Speech recognition; Natural language processing; Engineering; Mechanical engineering; Programming language; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0003557595,0.0001442794,0.0001916815,0.0004169052,0.0001112083,0.0003573245,0.00007544331,0.00004779268,0.000001819966],"category_scores_gemma":[0.00005809471,0.0001262053,0.00002593002,0.0002550323,0.00003544231,0.001000065,0.0000447761,0.0002216986,3.918282e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004091461,"about_ca_system_score_gemma":0.00004069978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001756457,"about_ca_topic_score_gemma":3.84868e-7,"domain_scores_codex":[0.9991594,0.00005177348,0.0003436001,0.0001507826,0.000164152,0.0001302873],"domain_scores_gemma":[0.9991323,0.0003426686,0.0001703902,0.00004262766,0.0002360599,0.00007600249],"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":[0.0000499816,0.00003745145,0.0000273132,0.0001873573,0.00008490986,0.00002018646,0.001389123,0.01095516,0.007951493,0.0003404462,0.00003473376,0.9789218],"study_design_scores_gemma":[0.001883914,0.0007737777,0.001073018,0.002937481,0.00008193043,0.002043938,0.0004167854,0.9394852,0.01572739,0.0350947,0.00004898679,0.000432887],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08463982,0.0002768726,0.9144261,0.0003161984,0.00005402397,0.000154243,0.000001460104,0.00006369349,0.0000675656],"genre_scores_gemma":[0.3937157,0.00007019542,0.6060966,0.00007639756,0.00002297435,0.000006622374,0.000003986891,0.000006020538,0.000001503174],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.978489,"threshold_uncertainty_score":0.5146501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01171334417516466,"score_gpt":0.2171274700654885,"score_spread":0.2054141258903238,"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."}}