{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009328551,0.0009936814,0.001924027,0.002152764,0.001149687,0.0040242,0.0027067,0.002071223,0.00331924],"category_scores_gemma":[0.09273037,0.0009637732,0.001468571,0.002242075,0.002634098,0.01159838,0.002406763,0.005555649,0.0008334443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001485036,"about_ca_system_score_gemma":0.002553943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005712236,"about_ca_topic_score_gemma":0.007397651,"domain_scores_codex":[0.9954901,0.002822592,0.0002311354,0.0007400422,0.0005264241,0.0001897012],"domain_scores_gemma":[0.8349159,0.1526375,0.00266342,0.00643911,0.002698715,0.0006452944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007563439,0.0008213896,0.01591101,0.0003918879,0.0004588423,0.0005822975,0.0008625556,0.3973749,0.002366061,0.3067867,0.01552058,0.2581674],"study_design_scores_gemma":[0.0000201509,0.0000195801,0.0007427578,0.00001435911,0.00001460522,0.00005529613,0.00004958226,0.6762179,0.0002291315,0.3220972,0.000516968,0.00002249714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02605252,0.0004916336,0.9665112,0.004106481,0.00007788237,0.00005082481,0.0005872977,0.0009078323,0.001214296],"genre_scores_gemma":[0.739949,0.001239718,0.2462563,0.001445995,0.001333089,0.0004596838,0.002417143,0.0005507238,0.006348172],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009328551,"threshold_uncertainty_score":0.04933465,"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."}}