Automated README summary
Automatically summarized from the README on 22 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python controller that plays Capcom's 1991 SNES shooter U.N. Squadron using the game's raw working memory rather than screen pixels, with BizHawk running the ROM and a Lua script exporting RAM each frame.
How it uses Jev
On each decision frame the emulator pauses; Python builds a state and typed questions (attack, pickup, position) and asks Jev which way to move. Jev returns per-option probabilities and a confidence; Python applies per-decision-type thresholds and writes the chosen input, which Lua injects from the observed frame.
Primitives:choicescorenoul
Technique worth stealing
Move all comparisons into code and split one overloaded question into three atomic ones with categorical verdicts, raising median confidence from 0.27 to 0.85.
Try it
On Windows with BizHawk in bizhawk\ and ROM path in config.json, run launchers\run_jev_segment.bat.
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 projectFound in material0.97
- Shows a System One patternunclear0.48
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersFound in material0.98
- Is a runnable toolnot found in the excerpt0.22
- Top-10 learning shortlist signalunclear0.46
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale0.01 / 2
- About JevFound in material0.99
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 Oct 2026.