SpikeLogBERT achieves 0.99997 parsing accuracy on HDFS logs while cutting estimated energy use by 62.6% versus standard neural models through spiking transformer computation and BERT distillation.
Drain: An online log parsing approach with fixed depth tree
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A survey that organizes LLM agent applications in NetOps and AIOps around autonomy hierarchies, workflow evaluation, and safety governance.
citing papers explorer
-
SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks
SpikeLogBERT achieves 0.99997 parsing accuracy on HDFS logs while cutting estimated energy use by 62.6% versus standard neural models through spiking transformer computation and BERT distillation.
-
Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety
A survey that organizes LLM agent applications in NetOps and AIOps around autonomy hierarchies, workflow evaluation, and safety governance.