{"id":"W4401943123","doi":"10.1109/tkde.2024.3443928","title":"PLBR: A Semi-Supervised Document Key Information Extraction via Pseudo-Labeling Bias Rectification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Rectification; Key (lock); Artificial intelligence; Information extraction; Information retrieval; Pattern recognition (psychology)","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":[0.0003744375,0.0001855632,0.0001422144,0.000518357,0.0001438084,0.0003781598,0.0004311414,0.00008473045,0.00001046205],"category_scores_gemma":[0.0000124887,0.0001869891,0.00004757847,0.0007633236,0.00001148904,0.005178624,0.0000143933,0.0002900706,0.00009696974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001221244,"about_ca_system_score_gemma":0.00003582349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001900744,"about_ca_topic_score_gemma":0.00001414847,"domain_scores_codex":[0.9988718,0.00002450233,0.0003364946,0.0004115629,0.0001669641,0.0001886877],"domain_scores_gemma":[0.998861,0.0001514351,0.00003896094,0.0007999416,0.00006831213,0.00008031613],"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":[0.000006916057,0.00006700731,0.000001428722,0.0002252591,0.00009383534,0.000003715495,0.001375416,0.0242292,0.03289428,0.001153876,0.0003465964,0.9396025],"study_design_scores_gemma":[0.00009834542,0.00003315205,0.000009359777,0.000135574,0.00004175983,0.00002643992,0.000018366,0.9497723,0.03521675,0.0001363965,0.01430275,0.0002087841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001430706,0.0005329027,0.9958149,0.0001214777,0.0006520353,0.0001755331,0.00002013239,0.001137254,0.0001150656],"genre_scores_gemma":[0.8792195,0.0007122389,0.1197243,0.00002365776,0.00007130396,0.00007351507,0.00006424227,0.00002026597,0.00009099041],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9393937,"threshold_uncertainty_score":0.7625194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02764258680815602,"score_gpt":0.2946802442361714,"score_spread":0.2670376574280154,"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."}}