Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

darwin-core iter 2 — reasoning-bank: scifact bm25 tie-breaker 0.0→0.05 Δ=+0.0024

ruv28ea21f6c8e7
diff --git a/v3/@claude-flow/cli/scripts/run-beir-hybrid.mjs b/v3/@claude-flow/cli/scripts/run-beir-hybrid.mjs
index 0919cc31d3..b16c9a9f50 100644
--- a/v3/@claude-flow/cli/scripts/run-beir-hybrid.mjs
+++ b/v3/@claude-flow/cli/scripts/run-beir-hybrid.mjs
@@ -50,7 +50,7 @@ const BASELINES_BY_DATASET = {
const DATASET_RRF_WEIGHTS = {
arguana: { dense: 1.0, bm25: 0.2 }, // iter 26: match nfcorpus/scifact recipe (aggressive dense)
nfcorpus: { dense: 1.0, bm25: 0.0 }, // iter 14: pure dense fusion (0.2→0.0) RRF with single system + minMax norm preserved
- scifact: { dense: 1.0, bm25: 0.0 }, // iter 20: test nfcorpus winner recipe on scifact (0.2→0.0 pure dense)
+ scifact: { dense: 1.0, bm25: 0.05 }, // darwin iter2: small bm25 tie-breaker on top of pure dense (0.0→0.05)
};
function detectDataset(path) {
const p = path.toLowerCase();