{"id":"W2038884454","doi":"10.1016/j.cageo.2015.04.008","title":"A new intelligent method for minerals segmentation in thin sections based on a novel incremental color clustering","year":2015,"lang":"en","type":"article","venue":"Computers & Geosciences","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Thin section; Segmentation; Cluster analysis; Geology; Petrography; Hue; Mineralogy; Thin film; Mineral; Mars Exploration Program; Artificial intelligence; Computer science; Pattern recognition (psychology); Materials science; Physics","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":[0.000473997,0.0001137784,0.0001199367,0.0002194332,0.0000771022,0.0001147697,0.0001565721,0.00003299549,0.000003118519],"category_scores_gemma":[0.00003178023,0.0001052611,0.0000318164,0.0003439697,0.00001675957,0.0001703882,0.00002157069,0.0000721568,0.000002575116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001542906,"about_ca_system_score_gemma":0.0000588452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003724997,"about_ca_topic_score_gemma":0.0002641817,"domain_scores_codex":[0.9992084,0.0000178988,0.0001908422,0.0002025283,0.0001701411,0.0002101958],"domain_scores_gemma":[0.9996638,0.0001081673,0.00003376409,0.00006991335,0.00002137929,0.0001029301],"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":[0.00001256166,0.00002258915,0.0001094234,0.00002523173,0.000003300965,4.864817e-7,0.001148551,0.971298,0.01631054,0.00003108253,0.00142557,0.009612673],"study_design_scores_gemma":[0.0005039788,0.0001363204,0.0001049156,0.00007926829,0.000004018432,0.000002980157,0.0003998326,0.9917038,0.005955107,0.000073893,0.0009084636,0.0001274153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09004159,0.00003404198,0.9081368,0.0001538768,0.0009940161,0.0002057357,0.000004356918,0.0000963928,0.0003331967],"genre_scores_gemma":[0.469036,7.04073e-7,0.5304797,0.0001872122,0.0001211817,0.00003050008,0.000007854924,0.000009747133,0.0001271158],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3789944,"threshold_uncertainty_score":0.4292421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06080255484459258,"score_gpt":0.3160816534234656,"score_spread":0.255279098578873,"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."}}