{"id":"W4384207605","doi":"10.1016/j.energy.2023.128406","title":"Knowledge sharing-based multi-block federated learning for few-shot oil layer identification","year":2023,"lang":"en","type":"article","venue":"Energy","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Generalization; Block (permutation group theory); Identification (biology); Computer science; Layer (electronics); Artificial intelligence; Interference (communication); Class (philosophy); Petroleum; Machine learning; Data mining; Channel (broadcasting); Geology; Mathematics; Telecommunications","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":[0.0003449785,0.0001130067,0.0001067085,0.00007644588,0.0003451044,0.0001789594,0.0004500789,0.00008344748,0.00001576897],"category_scores_gemma":[0.0002515416,0.0001151815,0.00006209797,0.0004994429,0.00001648289,0.0001020904,0.0001563351,0.00008461549,0.00009146926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002284989,"about_ca_system_score_gemma":0.00004731704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002722643,"about_ca_topic_score_gemma":0.00003999498,"domain_scores_codex":[0.9989678,0.0000380299,0.0001853022,0.000434387,0.00009134904,0.0002831667],"domain_scores_gemma":[0.9992999,0.000118398,0.0000810209,0.0002739828,0.0001683058,0.00005838966],"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":[0.00004454735,0.0004687922,0.002506534,0.0003840823,0.0001143251,0.00004602512,0.00180915,0.491408,0.3172682,0.05333947,0.02460638,0.1080045],"study_design_scores_gemma":[0.0002962359,0.00001341356,0.0004537374,0.00001596275,0.000001919507,0.000001306939,0.00001870081,0.7653546,0.06560453,0.000357923,0.1677511,0.0001306566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03829501,0.0001991903,0.9354687,0.005510075,0.001171024,0.0001021349,0.000002806696,0.002025536,0.01722549],"genre_scores_gemma":[0.9346594,0.000005485983,0.001278191,0.0001001799,0.0000817352,0.00008692417,0.00006608583,0.000005338331,0.06371666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9341906,"threshold_uncertainty_score":0.4696966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06030867008475405,"score_gpt":0.288971949616243,"score_spread":0.2286632795314889,"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."}}