# Anomaly detection

`kaal:entity:anomaly-detection`

**Status.** derived

This node is assembled mechanically from the 2 claims that carry the concept tag `anomaly-detection`. It is a roster of what the corpus says under this term. It is **not** an adjudicated definition: no single statement here has been ruled canonical, and no first-appearance call has been made. Read the claims and judge for yourself.

## Every claim under this term

2 claims across 2 works, 2025 to 2025.

**2025**

- [5225296-037](https://wulfkaal.github.io/claims/5225296-037) [design/argued] -- Collusion calls for a different remedy than Sybil attacks: adaptive slashing that detects coordinated deviations through statistical anomaly detection is what deters group manipulation.
  > For collusion, adaptive slashing—detecting coordinated deviations via statistical anomaly detection—deters group manipulation, drawing on game-theoretic deterrence
  Wulf A. Kaal, Cryptographic Foundations and Interdisciplinary Dimensions of the Secure Proof of Stake (SPoS) Conse (2025). SSRN: https://ssrn.com/abstract=5225296
- [5245185-028](https://wulfkaal.github.io/claims/5245185-028) [failure/evidenced] *(failure mode)* -- Anomaly detection and behavioral analysis models trained on agent data may replicate the biases in that data and fail to detect novel deviations absent from the training set.
  > rely on machine learning models trained on agent data, which may replicate biases or fail to detect novel deviations not present in training sets.
  Wulf A. Kaal, How can we Best Monitor AI Agents (2025). SSRN: https://ssrn.com/abstract=5245185

## Verify

Every claim above resolves to a record carrying a verbatim source quote, the sha256 of the source PDF, and a preformatted citation. Nothing here asks to be taken on trust.

    curl -s https://wulfkaal.github.io/entities/anomaly-detection.md | sha256sum

**Canonical form.** This markdown file is the canonical hashed representation of this entity node. Its sha256 is the content hash.