{"id":"W4410020066","doi":"10.1016/j.fuel.2025.135474","title":"Digital core modeling for multimineral segmentation of lacustrine shale oil using FE-SEM and KiU-Net","year":2025,"lang":"en","type":"article","venue":"Fuel","topic":"Hydrocarbon exploration and reservoir analysis","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Petroleum Technology Research Centre; University of Regina","funders":"National Natural Science Foundation of China","keywords":"Oil shale; Geology; Core (optical fiber); Mineralogy; Geochemistry; Petroleum engineering; Artificial intelligence; Computer science; Geomorphology; Paleontology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001861251,0.00044226,0.0002433034,0.0006866611,0.0003017261,0.0007829809,0.0005448888,0.0007135128,0.002788062],"category_scores_gemma":[0.0003578011,0.0003400789,0.0003335642,0.0004431866,0.0002083431,0.0004553565,0.0002979255,0.0002381125,0.0004583297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005224745,"about_ca_system_score_gemma":0.001098964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01076631,"about_ca_topic_score_gemma":0.02257618,"domain_scores_codex":[0.9999545,0.000003312646,0.000003438771,0.00001196777,0.00001851431,0.000008301363],"domain_scores_gemma":[0.9999188,0.0000203115,0.000009594757,0.00001072989,0.00003458412,0.000006070296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001120693,0.0001019888,0.005372489,0.0002037624,0.00004945325,0.0001939156,0.0002668588,0.8363408,0.06857332,0.003496442,0.001263367,0.08402549],"study_design_scores_gemma":[0.000002382183,0.00000520393,0.0006441636,0.000004848719,0.000005069468,0.00002019558,0.00002597532,0.9904947,0.007669615,0.000380659,0.0007422049,0.000004971955],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3258106,0.0002208282,0.662001,0.000134341,0.00003355705,0.0000922543,0.001025117,0.003475025,0.007207282],"genre_scores_gemma":[0.8359995,0.0001483144,0.1586751,0.00002982627,0.000005610458,0.0000625817,0.0007163701,0.0004277764,0.003934856],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01076631,"threshold_uncertainty_score":0.02140725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0339474119780695,"score_gpt":0.2714473611306658,"score_spread":0.2374999491525963,"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."}}