{"id":"W7093384034","doi":"","title":"SBAN: A Framework & Multi-Dimensional Dataset for Large Language Model Pre-Training and Software Code Mining","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Natural language; Malware; Code review; Software; Software construction; Software development; Source code; Bridging (networking); Software system; Software framework","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":[0.002149839,0.002346173,0.0008036413,0.003989716,0.001284297,0.00150567,0.003646607,0.00210033,0.004321819],"category_scores_gemma":[0.01139811,0.0006899396,0.001846808,0.003126178,0.0009867108,0.002534478,0.003746655,0.003339623,0.005517496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001638213,"about_ca_system_score_gemma":0.002828009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01519868,"about_ca_topic_score_gemma":0.03252389,"domain_scores_codex":[0.9979672,0.0005278716,0.0002333965,0.0005400526,0.0005528661,0.0001785861],"domain_scores_gemma":[0.9964858,0.001410806,0.0002855324,0.0009523811,0.0006132848,0.0002521497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000800312,0.001165665,0.02263607,0.001725723,0.0003510055,0.0007709602,0.0006754913,0.03899646,0.01042456,0.01577718,0.70219,0.2044866],"study_design_scores_gemma":[0.000641902,0.0005719674,0.01915261,0.0003722905,0.0001595954,0.001114801,0.0007838371,0.4539315,0.02283128,0.04983962,0.4502941,0.0003065645],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.05944107,0.001778325,0.2027586,0.002838939,0.000736033,0.001476042,0.6464142,0.07770333,0.006853503],"genre_scores_gemma":[0.04676986,0.0003467659,0.160253,0.0005435514,0.00008123941,0.001943804,0.7871404,0.001183994,0.001737439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01519868,"threshold_uncertainty_score":0.03022045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02567316331022167,"score_gpt":0.308321661100631,"score_spread":0.2826484977904093,"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."}}