Automated README summary
Automatically summarized from the README on 22 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Semantic Microscope labels each sentence of a document with calibrated probabilities from Jev (TypeSafe AI's System One model) and visualizes them as a heatmap. It is for anyone who wants to inspect a document's semantic dimensions at a glance.
How it uses Jev
For each sentence, one HTTP request carries five or six typed questions (Noul, Score, Choice) from a preset. Jev evaluates them in parallel against the same state. The answers are written to JSONL and used by the viewer to render parallel lanes or a wall, with probabilities tinting the text.
Primitives:choicescorenoul
Technique worth stealing
Use one request per sentence with multiple typed questions to get calibrated probabilities without text generation.
Try it
uv run microscope prepare samples/x.txt && uv run microscope label samples/x.txt --preset prose && uv run microscope serve
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 material0.93
- Shows a System One patternFound in material0.70
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.73
- Is a runnable toolunclear0.55
- Top-10 learning shortlist signalunclear0.50
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale0.99 / 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 22 Sept 2026.