mlsanityData to 14 Oct 2026

K4: Online Log Anomaly Detection Via Unsupervised Typicality Learning

arXiv 2507.20051 ↗First posted 26 Jul 2025cs.LG cs.CL cs.DCcited by 6

Not on the map. Why?

Abstract (arXiv)

Existing Log Anomaly Detection (LogAD) methods are often slow, dependent on error-prone parsing, and use unrealistic evaluation protocols. We introduce K4, an unsupervised and parser-independent framework for high-performance online detection. K4 transforms arbitrary log embeddings into compact four-dimensional descriptors (Precision, Recall, Density, Coverage) using efficient k-nearest neighbor (k-NN) statistics. These descriptors enable lightweight detectors to accurately score anomalies without retraining. Using a more realistic online evaluation protocol, K4 sets a new state-of-the-art (AUROC: 0.995-0.999), outperforming baselines by large margins while being orders of magnitude faster, with training under 4 seconds and inference as low as 4 μs.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 26 Jul 2025.

Builds on

14 of 35 references.

References · 14

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  3. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  4. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  5. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  6. 2016FastText.zip: Compressing text classification modelscited by 335
  7. 2021LogBERT: Log Anomaly Detection via BERTcited by 118
  8. 2020Density of States Estimation for Out-of-Distribution Detectioncited by 74
  9. 2020Loghub: A Large Collection of System Log Datasets for AI-driven Log Analyticscited by 70
  10. 2022Log-based Anomaly Detection with Deep Learning: How Far Are We?cited by 57
  11. 2024LogLLM: Log-based Anomaly Detection Using Large Language Modelscited by 22
  12. 2024Forte : Finding Outliers with Representation Typicality Estimationcited by 9
2 more
  1. 2024Large Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learningcited by 6
  2. 2024FastLogAD: Log Anomaly Detection with Mask-Guided Pseudo Anomaly Generation and Discriminationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Trust The Typicalcited by 3
  2. 2026Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separationcited by 3
  3. 2026Context Determines Optimal Architecture in Materials Segmentationcited by 1
  4. 2026Reliability-Gated Source Anchoring for Continual Test-Time Adaptationcited by 1
  5. 2026Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generationcited by 0
  6. 2026CausalGuard: Conformal Inference under Graph Uncertaintycited by 0