' />
folklore GitHub
☰
ResearchWhitepaperGitHub Install
Chapter the Fourth & three-quarters — Provenance

anonymous retrieval is a poisoning surface.

Every other AI memory feeds your model unsigned text from nowhere. Folklore signs every record by a verified human, so a model can refuse what it can't trace.

RAG's open wound

5 → 97%

5 poisoned documents can hijack a retrieval system with a 97% attack success rate. The model has no way to tell trustworthy context from an injected lie.

PoisonedRAG, arXiv · Zou et al.

Folklore's answer

59% → 2%

Signed by a verified GitHub identity, with an auditable chain: who curated it, what they grounded on, when. Provenance ranking keeps only signed gold and drops unsigned poison — cutting flip-ASR from 58.9% to 2.4% (24.8×) on the displaced-poison matrix. Trust becomes a property the model can read.

measured · Haiku agent, Opus judge · BEIR SciFact

Chapter the Fifth — The Reckoning

each claim, on disk.

0
tests passing
0
BEIR SciFact NDCG@10
+43%
recall@1, peer-shared
11ms
median retrieval
~140ms
federation-hit P50
24.8×
poison flip-ASR cut · provenance rank
9.1×
fewer paid web trips · 200k queries
77%
fewer model-input tokens · transfer
84.1%
web correctly denied · graph holds answer
2.5%
false-deny rate · 0% on far-miss
90.2%
cooperative cache hit · 64 peers (vs 18% alone)
98.7%
stored-vector self-recall@5
Folklore CPU0.7522
E5-base0.7370
E5-large0.7230
SPLADE0.6990
ColBERT0.6710
BM250.6650

# Folklore leads the CPU / production-grade retrievers. The overall top score is InRanker-3b — 0.783, a 3 B-parameter GPU cross-encoder reranker (different weight class); it beats every CPU baseline here. Folklore claims the CPU lead, not the GPU crown.

CPU-only retrieval, full stack (hybrid + cross-encoder + graph PPR), on full BEIR SciFact. Baselines are published BEIR SciFact NDCG@10 (BM25, ColBERT, SPLADE, E5) — Folklore leads the production-grade pack; a 3B GPU reranker (InRanker) tops it at 0.783. Poison-defense is real displaced-poison retrieval (Haiku agent, Opus judge). Compounding & token figures are simulator-grade — the hundred-peer pilot is next.