{"id":"W4411127324","doi":"10.22399/ijcesen.2481","title":"INTELLIDOC - An Adaptive Transformer-Powered Pipeline For Intelligent Document Processing And Entity Extraction","year":2025,"lang":"en","type":"article","venue":"International Journal of Computational and Experimental Science and Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Transformer; Pipeline (software); Computer science; Artificial intelligence; Natural language processing; Engineering; Electrical engineering; Programming language","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":[0.0008882767,0.001267085,0.0008946616,0.00224335,0.000570618,0.001788095,0.002385949,0.0008481726,0.004456951],"category_scores_gemma":[0.002696526,0.0005489445,0.001020856,0.00215923,0.0005672002,0.003472471,0.001787393,0.00113785,0.006026257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001038346,"about_ca_system_score_gemma":0.002026949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007042459,"about_ca_topic_score_gemma":0.01279335,"domain_scores_codex":[0.9992773,0.00006454735,0.00005638474,0.0002650184,0.000252238,0.00008460655],"domain_scores_gemma":[0.9984208,0.0003866003,0.0001095317,0.0005326091,0.0004780218,0.00007245262],"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":[0.0004631852,0.0001722308,0.001835358,0.0004396918,0.0001070861,0.0002706409,0.0002912231,0.009104806,0.05588825,0.003271583,0.05426002,0.873896],"study_design_scores_gemma":[0.0001904336,0.0005217843,0.003529233,0.00008382615,0.0002042926,0.001392604,0.0003344784,0.6308545,0.2218711,0.0103645,0.130469,0.0001841984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01979173,0.001367539,0.8726218,0.0002840063,0.0001607448,0.0003478118,0.003029593,0.09801447,0.004382268],"genre_scores_gemma":[0.1123231,0.0006108403,0.8574222,0.0004139389,0.00009060492,0.0003072377,0.01518045,0.001943992,0.01170766],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007042459,"threshold_uncertainty_score":0.01490992,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0148744002419663,"score_gpt":0.3138410068152804,"score_spread":0.2989666065733141,"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."}}