Automated README summary
Automatically summarized from the README on 29 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Mica is a 4B model for making decisions inside software: given input material, typed questions and allowed answers, it returns a probability per answer without generating text. This repository is its HTTP server.
How it uses Jev
Jev is the decision model Mica serves: it takes a state (input material) plus typed questions (yes/no, choice, score) and returns calibrated probabilities per allowed answer. The server exposes this over HTTP at /v1/systemone; abstain_threshold flags uncertain cases.
Primitives:choicescore
Technique worth stealing
Long-input mode runs lower layers on state rows and upper layers only build what later rows read, speeding prompts over 1k tokens.
Try it
Clone the repo, install v0.5/serving/requirements.txt, then run python v0.5/serving/serve.py.
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 excerpt0.31
- Shows a System One patternunclear0.45
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.07
- Is a replica of the modelFound in material0.76
- Solves a common problem (0–2)score on a 0–2 scale1.69 / 2
- About JevFound in material0.90
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 29 Oct 2026.