Automated README summary
Automatically summarized from the README on 28 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
SiftRank is a Go CLI that uses LLMs to rank prose, files, JSON, code, or any text-representable items by relevance to a prompt, breaking large collections into batches and combining relative orderings.
How it uses Jev
With --provider jev, SiftRank asks Jev to compare pairs of items within each batch; the returned probabilities are combined into an ordering and fed into SiftRank's normal ranking algorithm. Jev does not support reasoning effort or --relevance.
Primitives:choice
Technique worth stealing
Batch items randomly, ask for pairwise comparisons, and combine relative orderings across repeated trials with convergence checks.
Try it
go install github.com/noperator/siftrank/cmd/siftrank@latest, then run siftrank --provider jev --model jev-latest --file testdata/sentences.txt --prompt '...'
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.03
- Shows a System One patternnot found in the excerpt0.08
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalnot found in the excerpt0.10
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.79 / 2
- About JevFound in material0.87
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 28 Oct 2026.