{"id":"W3197720659","doi":"10.1190/segam2021-3580872.1","title":"Pitfalls and insights from a machine learning contest on log facies classification","year":2021,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"CONTEST; Facies; Computer science; Artificial intelligence; Machine learning; Natural language processing; Geology; Philosophy; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06469243,0.001809264,0.002033997,0.004380377,0.003804904,0.00963292,0.003358102,0.003093826,0.002576027],"category_scores_gemma":[0.1358163,0.0007926377,0.001110702,0.004271531,0.004913077,0.008374548,0.006422495,0.006729195,0.002164425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003129633,"about_ca_system_score_gemma":0.00314398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009858152,"about_ca_topic_score_gemma":0.01335591,"domain_scores_codex":[0.9329504,0.03371361,0.004065253,0.007505891,0.01981923,0.001945538],"domain_scores_gemma":[0.8723814,0.08328607,0.004847608,0.01356139,0.02181309,0.004110507],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001564946,0.001124918,0.0767963,0.0008133117,0.0003571424,0.001233586,0.005877718,0.06252579,0.008743342,0.07962154,0.1346663,0.6266751],"study_design_scores_gemma":[0.0002382719,0.0007162464,0.0370036,0.0005948831,0.00008607667,0.001660142,0.006252953,0.589457,0.01396712,0.2697847,0.07983937,0.0003997926],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4056003,0.007143564,0.4417173,0.1016292,0.003048246,0.0005041515,0.002647135,0.006499198,0.03121079],"genre_scores_gemma":[0.8150235,0.0005367681,0.1706993,0.005027891,0.001314482,0.0002659215,0.001952517,0.001223756,0.003955791],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9353076,"threshold_uncertainty_score":0.3421304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03202404632800689,"score_gpt":0.2515952865697584,"score_spread":0.2195712402417515,"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."}}