{"id":"W4405529641","doi":"10.1016/j.powtec.2024.120558","title":"CG-SOLOv2: Enhanced instance segmentation for coal-gangue with novel feature extraction and fusion modules","year":2024,"lang":"en","type":"article","venue":"Powder Technology","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Lakes Environmental (Canada); University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; Austrian Institute of Technology","keywords":"Fusion; Segmentation; Artificial intelligence; Extraction (chemistry); Coal; Pattern recognition (psychology); Gangue; Feature (linguistics); Computer science; Feature extraction; Materials science; Engineering; Chemistry; Waste management; Chromatography; Metallurgy","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":[0.0000355238,0.0001054277,0.00009285692,0.0001746454,0.00006294176,0.00003715593,0.00004184519,0.0001608286,0.000003424411],"category_scores_gemma":[0.000009512962,0.000089674,0.00001113597,0.0001952487,0.00003405401,0.0001405325,0.00001036525,0.0001725547,0.000002217519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003725498,"about_ca_system_score_gemma":0.000006172434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002383903,"about_ca_topic_score_gemma":0.00002996113,"domain_scores_codex":[0.9995489,0.000001637365,0.00007448226,0.0001816597,0.00004808829,0.0001452574],"domain_scores_gemma":[0.9998505,0.00002032643,0.00001550675,0.00007693392,0.00002063637,0.00001612304],"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":[0.00001371562,0.000008557376,0.00004669929,0.0003008122,0.00002405478,0.000002722699,0.0002135186,0.001802262,0.9380119,0.001303855,0.0005328013,0.05773903],"study_design_scores_gemma":[0.0008848042,0.0001798634,0.0004374836,0.000548108,0.00005628922,0.0001525044,0.000822306,0.1006943,0.8812112,0.002580485,0.01199138,0.0004412497],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6736899,0.002056793,0.3221177,0.0006473538,0.0002090502,0.0001560556,0.00001295065,0.0008338209,0.0002763697],"genre_scores_gemma":[0.9846522,0.00009115448,0.01472502,0.00001640235,0.00005040832,0.00006374632,0.00001715412,0.00002661259,0.0003573464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3109623,"threshold_uncertainty_score":0.3656799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007763404491472767,"score_gpt":0.2433674987500667,"score_spread":0.2356040942585939,"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."}}