{"id":"W4411349578","doi":"10.1007/s00603-025-04659-6","title":"Tensile Fracture Propagation in Deep Coalbed Methane Layers Under Brazilian Test: A Quantitative Analysis Using Digital Rock Technology and Deep Learning-Based Image Segmentation","year":2025,"lang":"en","type":"article","venue":"Rock Mechanics and Rock Engineering","topic":"Rock Mechanics and Modeling","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Digital image analysis; Fracture (geology); Geology; Ultimate tensile strength; Coalbed methane; Segmentation; Geotechnical engineering; Digital image correlation; Digital image; Artificial intelligence; Image (mathematics); Image processing; Materials science; Engineering; Composite material; Computer science; Computer vision; Coal; Coal mining","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":[],"consensus_categories":[],"category_scores_codex":[0.0002025979,0.0003410087,0.0002446848,0.000904461,0.0003517295,0.0004168772,0.0004945681,0.0006597303,0.0014187],"category_scores_gemma":[0.0005142535,0.0002352327,0.0002934363,0.0005452426,0.0005397429,0.0004716215,0.0003077225,0.0003779921,0.0001622183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004286258,"about_ca_system_score_gemma":0.0003560626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01371571,"about_ca_topic_score_gemma":0.01814877,"domain_scores_codex":[0.9998964,0.000005279673,0.00000468061,0.00002199524,0.00004370231,0.00002786166],"domain_scores_gemma":[0.999754,0.00005362434,0.00003932133,0.00001793014,0.0001006684,0.00003445301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002166776,0.0009344107,0.2300818,0.0003663033,0.0001951266,0.002353943,0.0008561903,0.3387678,0.3267997,0.002528526,0.002758927,0.09219052],"study_design_scores_gemma":[0.00001909116,0.0001521736,0.2427233,0.00002633551,0.00005615285,0.0002199521,0.0004412524,0.7177951,0.03728203,0.0007079499,0.0005213558,0.00005534468],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945647,0.00005821494,0.004064486,0.0000412964,0.000007798742,0.000005794417,0.0003023006,0.0001199536,0.0008354703],"genre_scores_gemma":[0.9987137,0.00001885356,0.0007315972,0.000006491694,0.000001726663,0.000002723864,0.0001666909,0.00001179162,0.0003463081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01371571,"threshold_uncertainty_score":0.02727175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005815188152287604,"score_gpt":0.2279334542094618,"score_spread":0.2221182660571742,"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."}}