Wholesale & agricultural data
As managing director at Daejeon Jungang Cheonggua Co., Ltd., I work with the settlement records and shipment
patterns that pile up there every day. I run a pipeline that automatically collects and organizes eight
years of settlement data.
On top of that, I'm building a conversational agricultural-intelligence platform (Wholesale Intelligence).
It's about asking and answering — in plain language — questions on price patterns, shipment flows, and
trends by item. The goal is to let the data answer the questions I run into on the floor every day.
Details are covered separately in talks or videos. For collaboration, see Contact.
Related
When I built it
Let the data speak first
Videos & writing
Research & papers
My research is mostly about how to verify AI systems, with one more paper that looks at my day job —
the wholesale market. The actual claims and methods are in each paper.
How far can you trust what an AI returns, and how should you handle that — that's the part I find most
interesting lately. On the AI-verification side there are four papers, with a unified one submitted to
TACL and under review; the wholesale-market study is submitted to the Journal of Rural Studies and under review.
Separately, two more papers are in preparation — one on AI evaluation methodology, and one on a medical
application written together with a clinical expert.
-
2026.03
CCR (preprint)
arXiv:2603.12123
-
2026.03
D-CCR (preprint)
arXiv:2603.16244
-
2026.03
HCCA (preprint)
arXiv:2603.21454
-
2026.05
XMR — unified paper (TACL, under review)
submitted
-
2026.06
Wholesale-market trust premium — day-job research (JRS, under review)
submitted · Journal of Rural Studies
-
in prep
Model or Harness? — variables in LLM-as-judge evaluation
in preparation · for TMLR
-
in prep
Cross-model consensus for medical error detection
in preparation · for JAMIA · co-authored
The full list is on Google Scholar. For deeper discussion, please email me.
Related
Why I verify this way
Same root: security review
In time order
Security research · open source
I look for and report memory-safety bugs in open-source libraries. In 2026 I reported 15 CVEs, and for 4 of
them I submitted PRs upstream that are under review. In May I filed my first MITRE cveform directly
(Request 2041287, miniz). I'm waiting on the CVE IDs.
-
2026
brotli — size computation bounds DCHECK
PR #1472
-
2026
snappy — boundary handling
PR submitted
-
2026
protobuf-c — integer overflow review
PR under review
-
2026
jansson — memory-safety hardening
PR submitted
11 CVEs are pending at MITRE. PR links will be added as they settle.
Related
Same root: doubting results
Verification research
In time order
Content · Sapjil Coding
I run a YouTube channel called "Sapjil Coding." The rule is to share only what I've actually built and used.
No overstating, crediting AI when AI helped, and saying so when I don't know.
I also built MCP servers to make Korean public data (agricultural products, wholesale markets, and
so on) available to AI agents. Some are registered in the A2A agent ecosystem. There's also a
Naver News Scraper on the Apify Store — for
automatically collecting Korean news.
→ videos & writing
Related
A partner that looks first
From wholesale data to content
In time order