{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003823606,0.00007676101,0.00008791578,0.0002289544,0.0001042213,0.0002289306,0.0002226846,0.00001729516,0.000001255929],"category_scores_gemma":[0.00002456206,0.00006872197,0.00001961734,0.0001078359,0.00005796707,0.001445987,0.00005463827,0.00006442986,7.540342e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009077285,"about_ca_system_score_gemma":0.0000895679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000721698,"about_ca_topic_score_gemma":6.282124e-7,"domain_scores_codex":[0.999163,0.000005450861,0.0002419437,0.000165554,0.0003262968,0.00009781122],"domain_scores_gemma":[0.9994564,0.00004643797,0.0000692324,0.00002980099,0.0003202916,0.00007780291],"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":[0.0002261767,0.0002061849,0.0002407214,0.00004806798,0.00007294369,0.000009993902,0.005500737,0.1103228,0.0562829,0.1196213,0.00002253869,0.7074457],"study_design_scores_gemma":[0.0003954652,0.000129151,0.0005579012,0.00009396793,0.000004623787,0.0001091375,0.0004791305,0.9700353,0.01995815,0.007755779,0.0003911473,0.00009020805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2201507,0.0006006329,0.7783687,0.0004228702,0.0003536117,0.00005965997,6.724925e-7,0.000008866473,0.00003426461],"genre_scores_gemma":[0.9265966,0.00003859088,0.0732073,0.00008627059,0.00005818334,0.000003500559,6.601357e-7,0.00000193319,0.000006958311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8597125,"threshold_uncertainty_score":0.28024,"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."}}