Automated README summary
Automatically summarized from the README on 2 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A suite of CLI tools (grev, isv, tagv, sortv, rank, pickv, uniqv, unwrap, seg, cutv, seek, trv, lookv, probev) that behave like grep, sort, cut, uniq and friends, but select, label, route, rank or dedupe records by meaning. For developers and agents working with logs, tickets, commits and text.
How it uses Jev
Each tool sends a typed question (Choice, Score or Noul) plus the record or whole input as state to Jev, which returns calibrated probabilities. grev keeps records whose Noul clears a threshold; tagv routes by Choice; rank orders by Score; probev prints probability columns. Output is always the original input, never generated text.
Primitives:choicescorenoul
Technique worth stealing
Phrase each filter as a typed question over the record, then threshold the calibrated probability so output stays the original input.
Try it
go install github.com/aurorainfra/grev/cmd/...@latest, then grev 'is a vegan meal' examples/menu.txt
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 projectFound in material0.95
- Shows a System One patternunclear0.51
- Describes handling uncertaintyunclear0.57
- Reports measured numbersnot found in the excerpt0.15
- Is a runnable toolFound in material0.91
- Top-10 learning shortlist signalunclear0.57
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.32 / 2
- About JevFound in material0.97
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 2 Oct 2026.