{"id":"W4393940451","doi":"10.1007/s12243-024-01028-2","title":"Large language models and unsupervised feature learning: implications for log analysis","year":2024,"lang":"en","type":"article","venue":"Annals of Telecommunications","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Feature (linguistics); Unsupervised learning; Natural language processing; Artificial intelligence; Machine learning; Psychology; Cognitive psychology; Linguistics","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":[0.0005190787,0.00008818007,0.0001872357,0.0002466422,0.0002664883,0.00009990078,0.0007507902,0.00007361477,0.000003377956],"category_scores_gemma":[0.00006951616,0.00007554331,0.0001778807,0.001113147,0.00004756547,0.0004247439,0.0002254453,0.0001545033,0.000003618327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007555378,"about_ca_system_score_gemma":0.00005539519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003594103,"about_ca_topic_score_gemma":0.00005005873,"domain_scores_codex":[0.9992544,0.00005908097,0.0002114991,0.0002325203,0.00006892144,0.0001735848],"domain_scores_gemma":[0.9981806,0.0003705742,0.00006001879,0.001145385,0.0001975763,0.00004590171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001212492,0.0005341378,0.02471229,0.0006548774,0.001948911,6.774e-7,0.01971701,0.01189064,0.001124157,0.8269144,0.01457624,0.09791453],"study_design_scores_gemma":[0.0002062737,0.00008900365,0.04479834,0.0000589113,0.0002120477,0.000006050743,0.0004650759,0.8899473,0.0004550735,0.02843154,0.03503985,0.00029054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06013285,0.01071246,0.8885236,0.03855715,0.00005451684,0.0004199322,0.00009857742,0.0003972019,0.001103699],"genre_scores_gemma":[0.9766941,0.0009519875,0.02170608,0.0002118495,0.000018919,0.0001061034,0.00008159778,0.000007337306,0.0002220338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9165612,"threshold_uncertainty_score":0.3080567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05299772579082376,"score_gpt":0.3576383480537408,"score_spread":0.3046406222629171,"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."}}