{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006973654,0.0001118515,0.0001273418,0.00006873671,0.0001233739,0.0002198216,0.0003253341,0.00006050777,0.0000298239],"category_scores_gemma":[0.0001723803,0.00009717926,0.00002027251,0.0002122071,0.00004878089,0.0004160914,0.00017351,0.0001712669,0.00007474341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003123198,"about_ca_system_score_gemma":0.00003672582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004663114,"about_ca_topic_score_gemma":0.00004448665,"domain_scores_codex":[0.9989706,0.00010155,0.0001810558,0.0004543292,0.0001775066,0.0001149078],"domain_scores_gemma":[0.9990011,0.0002043151,0.00008507055,0.0005505501,0.0001015724,0.00005738694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003593823,0.0000685519,0.002588735,0.000004357728,0.00001088157,0.00001078138,0.0004930643,0.000003615548,0.1314176,0.8432935,0.0007527551,0.02135251],"study_design_scores_gemma":[0.0008340481,0.000224053,0.167713,0.0000855627,0.00001129103,0.00002343971,0.0004496934,0.3154615,0.3432423,0.03179536,0.1394478,0.000711897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0295026,0.0004402632,0.9552139,0.003246675,0.00009747082,0.0001223488,0.00001711966,0.0007924619,0.01056716],"genre_scores_gemma":[0.9404213,0.0001753306,0.05679575,0.0008278712,0.00001652327,0.00001751688,0.0001265248,0.000007004844,0.001612112],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9109188,"threshold_uncertainty_score":0.3962855,"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."}}