{"id":"W4221057764","doi":"10.1190/int-2021-0194.1","title":"Generating a labeled data set to train machine learning algorithms for lithologic classification of drill cuttings","year":2022,"lang":"en","type":"article","venue":"Interpretation","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Workflow; Convolutional neural network; Lithology; Artificial intelligence; Algorithm; Geology; Data set; Computer science; Set (abstract data type); Drill; Machine learning; Pattern recognition (psychology); Database; Petrology; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005210752,0.00008623315,0.0001211322,0.0001078228,0.000135743,0.00003055254,0.0002011919,0.00002575983,0.0000228817],"category_scores_gemma":[0.0002277624,0.00009211481,0.00002413627,0.0001815656,0.000007176154,0.0001308376,0.00006569175,0.000151172,0.000001879172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005592615,"about_ca_system_score_gemma":0.000009787465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001611755,"about_ca_topic_score_gemma":0.000008903326,"domain_scores_codex":[0.999252,0.00005170969,0.0002581734,0.0001961022,0.0001140767,0.0001279457],"domain_scores_gemma":[0.9996122,0.00008881706,0.00008123581,0.0001514968,0.00004050401,0.00002576879],"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":[0.00003089429,0.00001456022,0.000332292,0.0001408414,0.00002698797,7.574225e-7,0.008135639,0.6057895,0.2691566,0.00006233732,0.0007944359,0.1155152],"study_design_scores_gemma":[0.0001579941,0.00009128932,0.0001097317,0.00002732311,0.00001319697,0.000004719583,0.0005538131,0.9953399,0.001665038,0.0000597029,0.001878717,0.00009851923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6739986,0.0001647553,0.3247907,0.0001683342,0.0001821753,0.000217297,0.0001279969,0.0001785193,0.0001715859],"genre_scores_gemma":[0.9731507,0.000001785661,0.02574963,0.0000715963,0.00005558442,0.00008872927,0.0007134382,0.00002290488,0.0001456582],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3895505,"threshold_uncertainty_score":0.3756333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06237746096804688,"score_gpt":0.3144729504777315,"score_spread":0.2520954895096847,"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."}}