{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0006592773,0.0002744588,0.0002197078,0.001097485,0.0005012413,0.001446439,0.0006468064,0.00009116117,0.00002035254],"category_scores_gemma":[0.00006663564,0.0002788583,0.00007750291,0.001389056,0.00003534571,0.01740475,0.0003307033,0.0001769604,0.0001270048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006611741,"about_ca_system_score_gemma":0.00008304726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001958758,"about_ca_topic_score_gemma":0.000002039166,"domain_scores_codex":[0.9975212,0.00004354945,0.001136796,0.0002449667,0.0007188179,0.0003346994],"domain_scores_gemma":[0.9982644,0.00003327908,0.0006657498,0.0006044683,0.0003625307,0.00006952801],"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":[0.000009897685,0.00002920091,0.000009039434,0.0005069859,0.00003627099,9.358071e-7,0.0005970945,0.01653807,0.00006595727,0.04277629,0.00112427,0.938306],"study_design_scores_gemma":[0.0005324678,0.00002678821,0.0005825903,0.0003829224,0.00007439005,0.000002811475,0.0002038286,0.8980135,0.002450161,0.02869154,0.06871055,0.0003284474],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002461651,0.00004869792,0.9618654,0.00180223,0.000227087,0.0005520314,8.535549e-7,0.0009263465,0.03433118],"genre_scores_gemma":[0.5949916,0.00004073573,0.4021963,0.001980494,0.00001672731,0.0002530565,0.0001491309,0.000007105069,0.0003648665],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9379776,"threshold_uncertainty_score":0.9999664,"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."}}