gj0xv

Corpus Hub contributor since 2026-10-23

gj0xv's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.

1corpus

1selected commit

5files

548lines

★ 5GitHub stars on repo

Totals across every corpus @Gjusev appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.

What an agent can do with the mk-sh-v corpus

Gjusev/mk-sh-v: MK-SH-V: a 260M visual decision model. Calibrated probabilities, a choice, and a refusal below a validated gate, over document pages and…

Look up how mk-sh-v implements abstention, calibration, decision-model, with answers cited to file and line.
Reuse a worked example: the commit “Demo case set: twelve verified train-split cases in two groups (eight…” (5 files · Python).
Answer from mk-sh-v's real Python source instead of memory (Web and frontend platform).

Example questions

How does mk-sh-v implement abstention?
What does demo do in mk-sh-v?

Paste it into your AI agent. It clones the repo at the pinned commit and indexes it on your machine.

Search the GitHub repository Gjusev/mk-sh-v with XERJ (https://hub.xerj.org/corpus/gjusev--mk-sh-v).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/Gjusev/mk-sh-v mk-sh-v && git -C mk-sh-v checkout e48f63200d822276e06cb8687e9889dd79399b25
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./mk-sh-v --url http://127.0.0.1:9200 --prefix mk-sh-v --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: Apache-2.0. Keep the copyright notice and credit the authors.

corpus gjusev--mk-sh-v · Web and frontend platform
Related corpora: NandhaKishorM/laya, amyrmahdy/decima
Case study: reference coding for agents

Selected work

GitHub ★ 5

Gjusev/mk-sh-v

e48f63200d Demo case set: twelve verified train-split cases in two groups (eight…

selected commit: 5 files · 548 lines · Python · demo, assets, scripts

The corpus is the whole repository at the pinned commit, not only the files of the selected commit.

selected · in licence reviewcorpus gjusev--mk-sh-vWEBApache-2.0abstentioncalibrationdecision-modeldocument-understandinggui-agentsselective-prediction agreed 2026-10-23

Not installable yet: this corpus is not in the hub registry until its licence review passes, so xerj corpus add and xerj ask cannot fetch it. It becomes installable when this card says live in the hub.

[![XERJ Corpus Hub contributor](https://hub.xerj.org/contributors/Gjusev/badge.svg)](https://hub.xerj.org/contributors/Gjusev)

Included with the author's permission (email, 2026-10-23), under each repository's own licence, with attribution. Want it removed? Reply to the email or open an issue on xerj-org/xerj.