{"id":"W4411551122","doi":"10.1109/jstars.2025.3582520","title":"SulfideNet: Deep Learning for Detection and Quantification of Iron Sulfides in Drill Core Scans","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geoscience BC","funders":"","keywords":"Drill; Core (optical fiber); Computer science; Geology; Metallurgy; Materials science","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":[0.0006175208,0.001268176,0.0004190956,0.0009933431,0.0002802682,0.0005230984,0.001285299,0.0007915039,0.002014227],"category_scores_gemma":[0.001267197,0.000383395,0.0004674526,0.0006241724,0.0003218886,0.000780966,0.0009568548,0.0006120749,0.001102501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007247409,"about_ca_system_score_gemma":0.001129433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01311787,"about_ca_topic_score_gemma":0.02391724,"domain_scores_codex":[0.9997599,0.00003104696,0.00001245702,0.0001016808,0.00005903281,0.00003588],"domain_scores_gemma":[0.9997769,0.00006642359,0.00002774654,0.00003008787,0.00007916211,0.0000197048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009127058,0.0004837332,0.02589068,0.0006016286,0.0003477335,0.0004882221,0.0002745785,0.2015267,0.04931618,0.003077525,0.07180478,0.6452755],"study_design_scores_gemma":[0.0000442761,0.0001235446,0.003747888,0.00004195513,0.00003179079,0.00009544204,0.00007562857,0.9691196,0.01772977,0.002245161,0.006724623,0.00002038783],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4710457,0.003176255,0.4502513,0.0009203014,0.0004628789,0.0003803392,0.01865773,0.04534769,0.009757838],"genre_scores_gemma":[0.7319938,0.0008500734,0.2183894,0.0006226493,0.00009473804,0.0003274682,0.0355436,0.0005724501,0.01160578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01311787,"threshold_uncertainty_score":0.02608305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02155607150010798,"score_gpt":0.240965080112758,"score_spread":0.21940900861265,"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."}}