{"id":"W4290875536","doi":"10.1145/3534678.3539219","title":"Towards Reliable Detection of Dielectric Hotspots in Thermal Images of the Underground Distribution Network","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hydro-Québec","funders":"","keywords":"Hotspot (geology); Software deployment; Computer science; Truck; Segmentation; Visual inspection; Artificial intelligence; Image segmentation; Artificial neural network; Real-time computing; Data mining; Computer vision; Engineering; Geology; Automotive engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004898745,0.0001441269,0.0002252485,0.00006891524,0.0001426423,0.00003256134,0.0009988003,0.00005299552,0.00000701554],"category_scores_gemma":[0.0001460818,0.0001041817,0.00005516032,0.0007341937,0.0001197051,0.0003539282,0.0007532885,0.0002794457,3.382955e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000381963,"about_ca_system_score_gemma":0.00004909377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004584554,"about_ca_topic_score_gemma":0.00001150437,"domain_scores_codex":[0.9991076,0.00002291209,0.0002947322,0.0002086733,0.0001713095,0.0001947726],"domain_scores_gemma":[0.9992758,0.0001027401,0.0001870953,0.0003531069,0.00006251804,0.00001870733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008561578,0.0003843932,0.03589792,0.001363503,0.0001947391,6.164101e-7,0.003299907,0.001717292,0.8829494,0.01567191,0.001283117,0.05638104],"study_design_scores_gemma":[0.001052807,0.0007823692,0.2440165,0.001589286,0.000258235,0.00001491953,0.00425241,0.03168419,0.6975921,0.01774612,0.0003304654,0.0006806063],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959124,0.0006576661,0.0003072583,0.00002598719,0.0001957361,0.0002299456,0.0005554385,0.00003303123,0.002082568],"genre_scores_gemma":[0.9996914,0.0001174788,0.00006924231,0.000004629098,0.00002781741,0.00002931506,0.00001628801,0.00001289846,0.00003094973],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2081186,"threshold_uncertainty_score":0.4248405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02300611810598622,"score_gpt":0.2420399321642931,"score_spread":0.2190338140583069,"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."}}