{"id":"W7147479603","doi":"10.1109/icaft66710.2025.11452853","title":"Unsupervised Key-Value Pair selection on Enterprise Documents through Generative type Transformer Framework","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Generative grammar; Transformer; Unsupervised learning; Automation; Generative model; Generalization","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003931225,0.0007675163,0.0007600421,0.0004753331,0.0007138231,0.0005302727,0.001379889,0.0005211724,0.0007789746],"category_scores_gemma":[0.0001413315,0.0007045475,0.0004404029,0.00430753,0.0001772392,0.00192013,0.0001939873,0.0009714093,0.0002594872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006328365,"about_ca_system_score_gemma":0.0004161497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001627803,"about_ca_topic_score_gemma":0.00004295725,"domain_scores_codex":[0.9952361,0.0004615468,0.0009861757,0.001649547,0.0007960307,0.0008706222],"domain_scores_gemma":[0.9976439,0.0002872467,0.0002123968,0.001197789,0.0005038362,0.0001548636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003729872,0.001296821,0.001656165,0.00009215813,0.001081912,0.00001623412,0.006626955,0.003456126,0.005815984,0.832734,0.01195965,0.134891],"study_design_scores_gemma":[0.001136258,0.001739227,0.0003669318,0.0009291036,0.0003517497,0.000004329956,0.0002337064,0.1876902,0.4231307,0.3331638,0.04991283,0.001341099],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003918611,0.0005768495,0.9591161,0.00427915,0.001025782,0.0009537116,0.000003641017,0.0007247095,0.02940145],"genre_scores_gemma":[0.5380042,0.001152179,0.4413683,0.008839259,0.0001480282,0.00009189223,0.000009311735,0.00003999428,0.01034683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5340856,"threshold_uncertainty_score":0.9995406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01417059786319918,"score_gpt":0.3244799686035344,"score_spread":0.3103093707403352,"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."}}