All configurations / retriever
BM25 top-5
- Configuration
- Lexical BM25 over the 5,183-abstract corpus, top five returned. No model. The Find floor.
- Source
- contestants.py L0_bm25
- Recorded runs
- 60 scored outputs · $0.00 measured model spend · runs on 2026-07-13
- Access
- open harness · standard tools
FIG. 01
By dimension
Scores /10 · Paired p-values are exploratory and unadjusted—Verify
Not yet tested.
—Ground
Not yet tested.
8.03Find
Baselinen=60 · recall@5 · $0.0000/task · 2026-07-13
precision@5 0.177
Run provenance
Report path: outputs/find/results.json
Task pack: scifact-retrieval-60
Run: find-60
—Extract
Not yet tested.
—Analyze
Not yet tested.
—Compute
Not yet tested.
—Synthesize
Not yet tested.
—Review
Not yet tested.
—Hypothesize
Not yet tested.