{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001463226,0.0006086511,0.0008859683,0.002772232,0.0006668695,0.002086539,0.001823241,0.0008311056,0.003195319],"category_scores_gemma":[0.0048495,0.0004548313,0.001447978,0.003154363,0.001117966,0.004272456,0.001804972,0.001309308,0.001899504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0010759,"about_ca_system_score_gemma":0.001789634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002850921,"about_ca_topic_score_gemma":0.00453124,"domain_scores_codex":[0.9985864,0.0003841064,0.00008693459,0.0004096216,0.0003962172,0.0001367852],"domain_scores_gemma":[0.9977773,0.001159816,0.0001746627,0.0004388365,0.0003577576,0.00009169793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005353802,0.0002376535,0.006187909,0.0003519413,0.0001332355,0.000908141,0.00112293,0.06658363,0.02787313,0.1290489,0.009571845,0.7574453],"study_design_scores_gemma":[0.00004783218,0.00008008008,0.001098056,0.00003511047,0.00007589613,0.0006666676,0.000259453,0.8510121,0.03558107,0.09600493,0.015084,0.00005488712],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01784548,0.000163785,0.9766912,0.0001678877,0.00002289732,0.0001275194,0.0003135726,0.002582136,0.002085584],"genre_scores_gemma":[0.4114788,0.0003171978,0.5779653,0.000176033,0.00005802345,0.0001857758,0.001852464,0.0006369555,0.007329345],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003195319,"threshold_uncertainty_score":0.01068938,"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."}}