{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001915532,0.002001229,0.001815641,0.00247869,0.0008591077,0.001568534,0.002981522,0.001832763,0.003500603],"category_scores_gemma":[0.004824202,0.0007711573,0.001419627,0.002465807,0.0009163525,0.003529707,0.002440058,0.002570907,0.006194839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006259409,"about_ca_system_score_gemma":0.001695711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002444788,"about_ca_topic_score_gemma":0.004205001,"domain_scores_codex":[0.9970421,0.0005295197,0.0001882385,0.001129413,0.0009089159,0.0002018029],"domain_scores_gemma":[0.9973399,0.0006121995,0.0003127884,0.0007418186,0.000901045,0.00009217606],"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":[0.0004056147,0.0001422276,0.0006935879,0.000433892,0.00008440006,0.000130754,0.0001798412,0.01423313,0.05166625,0.003029179,0.01812801,0.9108731],"study_design_scores_gemma":[0.00012466,0.000292288,0.001538112,0.00006642726,0.000102093,0.000609313,0.0001921466,0.8560234,0.1006647,0.01236713,0.02789603,0.0001236957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009271326,0.001055728,0.9770454,0.0002468376,0.0001364098,0.0001605973,0.0006958573,0.01010413,0.00128381],"genre_scores_gemma":[0.09746048,0.0006994254,0.8852008,0.0004896267,0.0001786724,0.0003822497,0.006139171,0.0009431646,0.008506403],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003500603,"threshold_uncertainty_score":0.0117107,"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."}}