{"id":"W4402244312","doi":"10.23977/jeeem.2024.070301","title":"Hierarchical Multi-granularity Joint Learning for Well-Overflow Detection","year":2024,"lang":"en","type":"article","venue":"Journal of Electrotechnology Electrical Engineering and Management","topic":"Seismic Imaging and Inversion Techniques","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Granularity; Joint (building); Computer science; Artificial intelligence; Machine learning; Data mining; Engineering; Programming language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004620157,0.0001227519,0.0001923594,0.0005964258,0.00008890106,0.00005375114,0.0001108184,0.0001067086,0.00001293547],"category_scores_gemma":[0.00008735969,0.0001017944,0.0000993119,0.000341524,0.00003146196,0.00009818363,0.00001143672,0.0007533088,0.000004052371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002451721,"about_ca_system_score_gemma":0.00001400673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002670807,"about_ca_topic_score_gemma":0.000001370798,"domain_scores_codex":[0.9991191,0.00002166878,0.0002524128,0.000174648,0.0001301129,0.0003020663],"domain_scores_gemma":[0.999711,0.00008045635,0.00005136808,0.00006268425,0.00002984289,0.00006464955],"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":[0.00009106375,0.00003284746,0.0001681013,0.0002969925,0.0002249147,0.0001205387,0.00002253484,0.006093368,0.005269672,0.002428237,0.00146126,0.9837905],"study_design_scores_gemma":[0.000307762,0.0009044349,0.0005246587,0.00006030674,0.00006250603,0.0003191684,0.000007427238,0.8827494,0.01281061,0.001576368,0.1005432,0.0001341161],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03121029,0.006143147,0.9601142,0.001494865,0.0003106629,0.0002272814,8.17337e-7,0.0003747909,0.0001238972],"genre_scores_gemma":[0.9796991,0.00245481,0.0174896,0.0001213928,0.00007834211,0.000003651659,0.000001988128,0.000007994839,0.0001430768],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9836563,"threshold_uncertainty_score":0.4151056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006946444814688191,"score_gpt":0.1987054122416469,"score_spread":0.1917589674269587,"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."}}