{"id":"W6903410689","doi":"10.11575/prism/49038","title":"Domain-Specific Generative AI in Energy Engineering: A Case Study in Geothermal Energy","year":2025,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Energi Simulation","keywords":"Embedding; Classifier (UML); Leverage (statistics); Geothermal gradient; Efficient energy use; Pipeline (software); Pipeline transport; Domain (mathematical analysis)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001294569,0.0006205861,0.000342261,0.0006551235,0.0004618924,0.00117815,0.001027795,0.001418222,0.003246812],"category_scores_gemma":[0.004076494,0.0002033637,0.0009755721,0.001097924,0.0008395655,0.002203469,0.001005526,0.001209686,0.0009992103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001091149,"about_ca_system_score_gemma":0.0007416253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005495414,"about_ca_topic_score_gemma":0.0100323,"domain_scores_codex":[0.9991149,0.000514337,0.00004019149,0.0001582592,0.0001292533,0.0000430945],"domain_scores_gemma":[0.9964663,0.002924837,0.00008304596,0.00028751,0.0001856012,0.00005274094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003376806,0.0008134894,0.0149107,0.002121704,0.0001791837,0.003337699,0.003294557,0.4937935,0.01830064,0.07506508,0.01894968,0.3688961],"study_design_scores_gemma":[0.00006514094,0.0001701091,0.003817315,0.00009404426,0.00005358231,0.0009025671,0.001373436,0.8663964,0.01250021,0.05323635,0.06132879,0.00006197112],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3080309,0.004188228,0.6415496,0.005601829,0.0002439732,0.0006395846,0.002794952,0.005866732,0.0310842],"genre_scores_gemma":[0.7648643,0.001360173,0.2198403,0.0008295209,0.00008232162,0.0002347765,0.002782948,0.0003919494,0.009613837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005495414,"threshold_uncertainty_score":0.01092684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02401290110125443,"score_gpt":0.2881971874612048,"score_spread":0.2641842863599503,"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."}}