{"id":"W4411170507","doi":"10.1080/00295450.2025.2481358","title":"Natural Language Processing in the Nuclear Industry: Opportunities and Challenges","year":2025,"lang":"en","type":"article","venue":"Nuclear Technology","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Nuclear industry; Computer science; Nuclear engineering; Engineering","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":[0.00016422,0.00007564452,0.00009837811,0.0002574298,0.0000916686,0.00007250867,0.0007594227,0.000229786,0.000003373051],"category_scores_gemma":[0.00004038467,0.0000589609,0.00001039545,0.0002676744,0.0001114424,0.0001510805,0.0003389383,0.0005369304,0.000003442521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001659019,"about_ca_system_score_gemma":0.00002153637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001245861,"about_ca_topic_score_gemma":0.00001402048,"domain_scores_codex":[0.9993984,0.00003083072,0.0001028959,0.0002200717,0.00007455089,0.0001733067],"domain_scores_gemma":[0.9995735,0.00001625822,0.00002935819,0.0003544622,0.00001568547,0.00001075885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[9.120665e-7,0.000009774676,0.00003212148,0.00002042249,0.000001759001,0.00002773164,0.002748267,7.606669e-7,0.0001157219,0.4315153,0.00007133446,0.5654559],"study_design_scores_gemma":[0.001420229,0.0002056737,0.008769446,0.0005708401,0.00002281995,0.0004269282,0.1755778,0.3133811,0.0001501317,0.04679393,0.4518776,0.0008034385],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7373862,0.01712715,0.0003857732,0.2288442,0.0001620308,0.0001790587,3.750464e-7,0.0007711701,0.015144],"genre_scores_gemma":[0.9950815,0.0003032573,0.003341472,0.001173548,0.00001231852,0.000003549118,9.373911e-8,0.000005857907,0.00007836907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5646525,"threshold_uncertainty_score":0.2404356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04038123152615424,"score_gpt":0.2608355193112306,"score_spread":0.2204542877850763,"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."}}