cluster-embed-order-is-deterministic
IN premise
Beliefs are sorted by ID before embedding (`ids = sorted(beliefs.keys())`), making cluster assignments reproducible given the same random seed.
Summary
Cluster assignments will produce the same results every time as long as the random seed stays the same, because beliefs are always processed in a consistent alphabetical order before being fed to the clustering algorithm. This matters for reproducibility — rerunning the clustering won't silently shuffle beliefs between topics.
Dependents
These beliefs depend on this one:
- cluster-selection-is-deterministic-and-budget-exact — Cluster-based belief selection produces identical results given the same seed, returns exactly the requested budget count, and processes beliefs in sorted order — ensuring fully reproducible, precisely-sized belief subsets for derive prompt construction.
Details
| Source | entries/2026/05/08/reasons_lib-cluster.md |