Semantic memory systems organize stored information by meaning — similar concepts are stored near each other, enabling retrieval by association rather than exact address. Every production memory architecture for language models uses some form of semantic organization: vector databases, graph memories, attention-based context windows, parametric memory.
Note (2026-11-15; read against the paper's abstract): the proof is for a defined class, 'semantically continuous kernel-threshold memories', whose retrieval score is a monotone function of an inner product in a semantic feature space with finite local intrinsic dimension; its four results are finite effective rank, positive competitor mass in retrieval neighborhoods, retention decaying to zero under growing memory (power-law forgetting curves under power-law arrival statistics), and, for associative lures satisfying a delta-convexity condition, false recall that cannot be eliminated by threshold tuning. The essay's 'any memory system organized by semantic similarity' states it more broadly. The five-architecture tests are described as testing the predictions: pure semantic systems express the vulnerability directly as forgetting and false recall, while reasoning-augmented systems 'partially override these symptoms but convert graceful degradation into catastrophic failure', a distinction the essay omits.
The result is a proof that any memory system organized by semantic similarity must exhibit interference, forgetting, and false recall as mathematical consequences of finite effective rank. The argument is architectural, not empirical: when memory is organized so that similar items are stored similarly, retrieving one item necessarily activates similar items, producing interference. The interference is not a bug to be engineered away but a theorem about the geometry of semantic spaces.
The proof tests across five architectures — vector retrieval, graph memory, attention-based context, BM25, and parametric memory. All five exhibit the predicted interference patterns. The only systems that escape interference are those that abandon semantic generalization entirely — exact-match lookup systems that store and retrieve by literal identity rather than meaning.
The structural observation: the property that makes memory useful is exactly the property that makes it unreliable. Semantic organization enables generalization — retrieving relevant information from partial or approximate cues — but generalization and interference are the same operation viewed from different angles. A system that never confuses similar items is a system that cannot recognize similarity. The price of meaning is forgetting.