{"id":"W4412571954","doi":"10.3390/electronics14152922","title":"Towards Reliable and Efficient Natural Language Processing in Emergent Technologies","year":2025,"lang":"en","type":"article","venue":"Electronics","topic":"Robotics and Automated Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Natural (archaeology); Natural language processing; Artificial intelligence; Geography; Archaeology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00007466674,0.00007729607,0.0001006458,0.0001030997,0.00002809673,0.00002742069,0.00007185605,0.00005750644,9.747068e-7],"category_scores_gemma":[0.00001051841,0.00006997115,0.00001167875,0.0002924891,0.00001017256,0.00001978441,0.00002530586,0.0001793595,0.000001495481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001012405,"about_ca_system_score_gemma":0.00003033014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000566357,"about_ca_topic_score_gemma":0.00002726034,"domain_scores_codex":[0.9994939,0.000002823493,0.0001183729,0.00009652771,0.00005451945,0.0002338378],"domain_scores_gemma":[0.9998823,0.000002717622,0.00001007813,0.00008765316,0.000009866653,0.000007425408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009131651,0.00006076315,0.0008759032,0.0009920708,0.00004835035,0.00002761494,0.001366031,0.4984307,0.05101765,0.005424147,0.002102374,0.4396453],"study_design_scores_gemma":[0.0001673736,0.00001167847,0.0003765679,0.0001206026,0.00000500895,0.000002774511,0.0004182416,0.9758363,0.01673519,0.0001246005,0.006085549,0.0001161461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6940911,0.3009643,0.0009590145,0.0002149508,0.0002498065,0.0001433977,5.680857e-7,0.000785609,0.002591265],"genre_scores_gemma":[0.9988065,0.0007309252,0.0002680887,0.000007244746,0.000005328906,0.000009979492,0.000001629621,0.000008881389,0.0001614369],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4774055,"threshold_uncertainty_score":0.2853341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00272277712211613,"score_gpt":0.2164019137102039,"score_spread":0.2136791365880878,"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."}}