list-negative-is-bounded-and-batch-scalable
OUT derived (depth 2)
The list-negative classification pipeline is both defensively bounded (two-stage keyword + LLM filtering with hallucination rejection and graceful malformed-output handling) and scalably partitioned (fixed batch size of ~50 candidates per LLM call), ensuring predictable resource usage and bounded LLM costs regardless of belief network size.
Summary
The classification pipeline for finding negative beliefs was designed to be both safe and cost-efficient — it filters candidates before sending them to an LLM, rejects hallucinated results, handles errors gracefully, and processes nodes in fixed batches of about 50 to keep LLM costs predictable regardless of how large the belief network grows. This claim is currently marked OUT, meaning one or both of its supporting facts (the defensive bounding or the batch size behavior) are no longer considered valid.
Justifications
SL — Defensive bounding prevents quality degradation; fixed batching prevents resource exhaustion — together they make classification safe at any scale.
Antecedents (all must be IN):
- list-negative-is-defensively-bounded — The negative belief listing pipeline applies defense-in-depth: keyword pre-filtering narrows candidates before LLM classification, hallucinated node IDs are discarded against the actual network, and malformed LLM output falls back gracefully to zero count rather than raising.
- list-negative-batches-at-50 — `list_negative` splits candidate nodes into batches of approximately 50 for LLM classification, verified by the test suite asserting exactly 3 LLM calls for 120 candidates.
Dependents
These beliefs depend on this one:
- llm-belief-operations-span-creation-and-classification — All LLM-driven belief operations — creation via derive (with safety, completeness, and resource efficiency) and classification via list-negative (with defensive bounding and batch scaling) — share consistent defensive patterns across the complete belief quality lifecycle.