Automated README summary
Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Python tool for researchers that screens and classifies video-platform accounts (Douyin, Kuaishou, YouTube, Bilibili) to find domain-specific sources such as sign language, news, instrument performance, and makeup creators, using titles, thumbnails, and profile metadata.
How it uses Jev
Jev ranks first-page video titles with Noul, selects Top-N thumbnails, then an independent account-category Choice uses profile metadata to judge the account's category. Results form a reviewable list of collection sources; evidence and rules are stored separately.
Primitives:noulchoice
Technique worth stealing
Screen accounts from titles, thumbnails, and profile metadata instead of downloading or watching full videos.
Try it
See docs/installation.md for environment setup, then docs/commands.md for commands.
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 material0.92
- Shows a System One patternunclear0.49
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersFound in material0.93
- Is a runnable toolFound in material0.71
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.00 / 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 19 Oct 2026.