Cuemap

Structural Extraction : Emits deterministic cues for observable evidence such as dates, numbers, lists, source metadata, and surface entities.

Recency & Salience (Signal Dynamics) : Balances fresh data with salient, high-signal events prioritized by an adaptive impact scoring module.

Reinforcement (Access-based Learning) : Frequently accessed memories gain signal strength, remaining highly accessible even as they age.

Sparse Recall : Uses normalized lexical cues, structural facets, recency, salience, and bounded deterministic reranking.

As of v0.7.2, CueMap's default core path is deterministic and ontology-free. GloVe/Ollama cue generation, WordNet/POS expansion, semantic bridges, pattern completion, external lexicon graphs, context expansion/speculation endpoints, and autonomous consolidation have been removed from the default engine path. v0.7.2 bundles a qint8 all-MiniLM-L3-v2 vector layer for semantic reranking, intent classification, and query embeddings; the edge profile selects a q4 build of the same model. The encoder can still be disabled for constrained builds or deployments.

v0.7.2 also uses numeric per-project memory IDs everywhere. If callers need deterministic upsert/dedupe identity, pass source_key ; memory IDs remain compact runtime addresses.