{"id":"W4413677204","doi":"10.1016/j.ipm.2025.104335","title":"Class-Missing Semi-supervised document key information extraction via synergistic refinement estimation","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Vector Institute; Western University","funders":"Key Research and Development Projects of Shaanxi Province; National Natural Science Foundation of China","keywords":"Key (lock); Estimation; Class (philosophy); Computer science; Extraction (chemistry); Information retrieval; Artificial intelligence; Engineering; Chemistry; Chromatography; Computer security","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":[0.003582697,0.001654189,0.00226107,0.003037438,0.001026638,0.001956405,0.003174375,0.001658093,0.002128019],"category_scores_gemma":[0.01052346,0.0007093891,0.001640193,0.003180471,0.001294407,0.004535759,0.003160132,0.002545442,0.003691543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007875282,"about_ca_system_score_gemma":0.002083144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002715856,"about_ca_topic_score_gemma":0.005921555,"domain_scores_codex":[0.9962438,0.0007040888,0.0003258896,0.001329205,0.001124548,0.0002724349],"domain_scores_gemma":[0.9918424,0.002516018,0.0008418583,0.002634356,0.001973785,0.0001916554],"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":[0.0005367475,0.0001639556,0.002061137,0.000471742,0.0001310137,0.0001861192,0.0003305064,0.02284614,0.03352722,0.004283372,0.01701741,0.9184446],"study_design_scores_gemma":[0.00008880223,0.0001817348,0.002032684,0.00006527229,0.0001324226,0.0005868532,0.0002766198,0.9065031,0.05181937,0.02014248,0.01808201,0.00008859321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01300268,0.001036617,0.9759982,0.0002148868,0.00009720057,0.0001514965,0.0008228041,0.0076366,0.001039531],"genre_scores_gemma":[0.162121,0.0006284386,0.8242917,0.0002850273,0.0001766845,0.0002990354,0.006984365,0.0006561542,0.004557652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003582697,"threshold_uncertainty_score":0.01894736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005924988358388565,"score_gpt":0.2776531864921736,"score_spread":0.2717281981337851,"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."}}