{"id":"W4414715898","doi":"10.30632/pjv66n5-2025a11","title":"Automatic Fracture Identifications From Image Logs With Machine-Learning Approaches: A Contest Summary","year":2025,"lang":"en","type":"article","venue":"Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Petrophysics; Fracture (geology); Consistency (knowledge bases); Feature (linguistics); Borehole; Identification (biology); Data set; Well logging; Scalability; Big data","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001137334,0.0001408809,0.000178284,0.0002383314,0.0005849873,0.0005010053,0.0004537026,0.00006150887,0.00001773662],"category_scores_gemma":[0.0001071389,0.00009225497,0.00008743985,0.0006161182,0.00007674898,0.002060361,0.00006954977,0.0004006394,0.000006806734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001440101,"about_ca_system_score_gemma":0.0001312369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004362641,"about_ca_topic_score_gemma":0.00001655048,"domain_scores_codex":[0.9983151,0.0003201844,0.0005283018,0.0001685544,0.0005453599,0.0001224983],"domain_scores_gemma":[0.997972,0.0001289222,0.0007323272,0.0003522892,0.0007626623,0.00005182778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004735059,0.001779982,0.004452662,0.0006260211,0.001268008,0.000011082,0.02063191,0.09438752,0.07638192,0.1627957,0.02365096,0.6135407],"study_design_scores_gemma":[0.0005923851,0.0001077838,0.008082172,0.0001217782,0.0001246476,0.00002666005,0.0006693365,0.9664642,0.00196457,0.01903358,0.002698097,0.0001148384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0850058,0.0004314393,0.908295,0.005175419,0.00009013517,0.0003866922,0.000004495669,0.0000758475,0.0005351306],"genre_scores_gemma":[0.9804456,0.0001693096,0.01876784,0.0001993003,0.00006073661,0.00006185446,0.00004347045,0.000007627811,0.0002442259],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8954399,"threshold_uncertainty_score":0.4831206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0315279243083011,"score_gpt":0.2638837746800949,"score_spread":0.2323558503717938,"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."}}