{"id":"W4416266029","doi":"10.1016/j.neunet.2025.108218","title":"Optimizing boundary dynamics for nested named entity recognition via semantic refinement and trimming","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Key Research and Development Program of China; Key Technologies Research and Development Program; Natural Science Foundation of Sichuan Province; National Natural Science Foundation of China","keywords":"Ambiguity; Trimming; Entity linking; Kernel (algebra); Construct (python library); Semantics (computer science); Boundary (topology); Semantic data model; Task (project management)","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":[0.0002359104,0.0001211009,0.000158551,0.00008185486,0.0002503656,0.0002293051,0.0002349066,0.00007802514,0.000001401671],"category_scores_gemma":[0.00002937255,0.0001252501,0.00005058779,0.0002228333,0.00002391533,0.0002704592,0.0001921018,0.000160704,4.789552e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006811973,"about_ca_system_score_gemma":0.00002265531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003339995,"about_ca_topic_score_gemma":0.0001176517,"domain_scores_codex":[0.9989715,0.0000446828,0.0002511652,0.0003680534,0.00009518089,0.0002694197],"domain_scores_gemma":[0.999425,0.0001336218,0.00007515995,0.0002576779,0.00006317698,0.00004535614],"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":[0.00002575343,0.00002595826,0.0007165654,0.00007914345,0.00002292859,0.000005992983,0.0001085343,0.02468713,0.00007963391,0.001621327,0.0001667726,0.9724603],"study_design_scores_gemma":[0.0004500498,0.00003347598,0.000333958,0.00007002516,0.00001912958,0.000006021555,0.0000117049,0.9964796,0.0000269685,0.002212687,0.0002387192,0.0001176668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07330114,0.0003819322,0.9236543,0.001126114,0.0009898912,0.0003129558,8.967928e-7,0.0001215793,0.0001112526],"genre_scores_gemma":[0.9086855,0.00003210443,0.09024314,0.0007270401,0.0001123296,0.00004056351,0.00002516404,0.00000844531,0.000125693],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9723426,"threshold_uncertainty_score":0.5107552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01768936287948043,"score_gpt":0.2488046597694865,"score_spread":0.2311152968900061,"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."}}