Worklog · 05/2026

Work Log: 2026-05

New blog backend, Cloudflare Pages staging, paper iteration, and experiment investigation.

May 01, 2026 updated May 30, 2026 1,918 words 9 min read
On this page
  1. Info:
  2. Rules:
  3. Resume Here
  4. Current State
  5. Do Not Forget
  6. Current Next Actions
  7. Standalone Candidates
  8. 2026-06-07
  9. Project
  10. Done
  11. Decision
  12. Risk

Info:

  • This is an append-only work log.
  • Main purpose: help future me resume work quickly.
  • Public readability is useful, but this is not a polished monthly report.
  • You can say this is a AGENT.md/CLAUDE.md/GEMINI.md for my future self.

Rules:

  • Keep entries date-stamped and in chronological order.
  • Record changes, decisions, risks, and the next actions.
  • Keep private life, job-process details, and sensitive experiment details out.
  • If one section grows too large, split it into a standalone post later.

Resume Here

Last updated: 2026-05-30 17:52 JST.

Current State

  1. Research:
  • Journal 1:
    • Headline locked = Exp1 EDA positive contribution; levels = diagnostic/limitation, NOT headline.
    • Writing artifacts(tables/figures/paired stats) under resource/materials/journal1_artifacts.
    • NO new training. Only writing-prep + organizing manuscript structure now.
    • Next blocker: organize full journal structure; decide diagnostic-chain length AFTER reading J-BHI exemplars.
  • Journal 2:
    • Direction = VL-FAU style vision-language joint learning on BP4D++ (main) + public-dataset LoRA demo (companion).
    • Starts only AFTER Journal 1 draft is out.
  1. Job preparation:
  • Coding Phase 0 (Python basics) + LeetCode Hot100 to start in June.
  • LoRA/VLM 7-day hands-on path to start in June (doubles as J2 skill-building).

Do Not Forget

  • Journal 1 draft deadline = ~June 15 (draft DONE, not “start”). This date is the load-bearing pin for the whole plan.
  • Do NOT start any new model/run for J1 unless reviewer/advisor explicitly asks.
  • In paper, report paired t + Cohen’s dz only; DROP Wilcoxon (n=3 makes min p=0.25, meaningless).
  • Do your LeetCode / coding practice.

Current Next Actions

  • [Advisor, Sat] Confirm authorship (Ziaratnia 3rd author? Sripian? Park corresponding), J-BHI venue, fold-level stats feasibility.
  • [J1] Organize manuscript skeleton (IMRaD+), fill from journal1_artifacts.
  • [J1] Write Related Work section (the biggest brand-new chunk vs the KICS short paper).
  • [J1] Read exemplar (Fontes Sensors 2024) full structure before fixing diagnostic-chain length.

Standalone Candidates

  • BP4D++ label limitations for stress estimation
  • BP4D++ dataset overview and preprocessing for stress estimation
  • Review of VLM/LLM for emotion recognition and hardware requirements
  • “Conference paper vs journal paper”: what I learned writing my first journal

2026-06-07

Project

  • Research: journal writing.

Done

  • more IMRaD+ outline.
  • more journal learning.
  • more section clarification.

Decision

None

Risk

  • Deadline
  • I wanna go IEEE

Next

  • Finish all research for journal.
  • 1 new post
  • Chinese / English switch for new blog

2026-06-03

Project

  • Research: journal writing.

Done

  • linked evidence tables/files to claims and contributions.
  • did some more IMRaD+ outline.
  • Title is mostly locked as “EDA-Augmented Multimodal CCT-LSTM for Stress-Related Task Classification on UBFC-Phys”, but subject to change.

Decision

None

Risk

  • Deadline
  • I wanna go IEEE

Next

  • J1 skeleton + Related Work; read exemplar before fixing diagnostic-chain length.
  • 1 new post
  • Chinese / English switch for new blog
  • Finish all research for journal.

2026-06-02

Project

  • Research: journal writing

Done

  • listed the claims and contributions of paper
  • did some of IMRaD+ outline.
  • Had meeting with prof. Park, paper title will not has any thing about “leakage safe”.

Decision

None

Risk

None

Next

None

2026-06-01

Project

  • Research: journal writing

Done

  • Synced job plan and research plan with claude and code repo.
  • Drafted a co-author invitation email to Ziaratnia; sent to Prof. Park for review.
  • Learned about the IMRaD+ structure of journal papers and reading exemplar J-BHI papers to understand the style differences vs normal conference papers.

Decision

  • None

Risk

  • DEADLINE: ~June 15.

Next

  • J1 skeleton + Related Work; read exemplar before fixing diagnostic-chain length.
  • 1 new post
  • Chinese / English switch for new blog
  • Finish all research for journal.

2026-05-30

Project

  • Research (Journal 1 / Journal 2 direction) + overall career-research plan consolidation

Done

  • Completed a two-round deep strategy review (job market → job family → research alignment). Outputs saved as standalone planning docs (see Decision).

  • Locked Journal 1 target = IEEE J-BHI, with a corrected framing:

    • Headline = Exp1 EDA positive contribution (P4 vs faithful baseline +9.34pp, same leakage-safe protocol).
    • Levels (Exp2) = honest diagnostic/limitation, placed in the back half.

  • J1 writing artifacts (no new training): main results table with paper-friendly names, paired stats, per-class F1, confusion matrices, EDA-feature-by-task table + figures.

  • Confirmed statistical handling: paired t + Cohen’s dz only; drop Wilcoxon (n=3 → min p=0.25). Stats are supporting; main evidence = protocol + consistent deltas + ablation.

  • Cleaned all wording that could read as criticism of the original CCT-LSTM rPPG implementation (red line for inviting Ziaratnia as co-author).

  • Locked Journal 2 direction (starts after J1 draft): VL-FAU style vision-language joint learning on BP4D++ (main) + a fully public-dataset LoRA demo on UBFC-Phys (companion, to have HR-visible artifacts under BP4D++ EULA limits).

  • Drafted (not sent) a co-author invitation email to Ziaratnia; pending advisor sign-off.

Decision

  • Detailed execution plans now live in standalone docs (the “look-up layer” when this worklog is too coarse):

    • decision-integration-v2.md — the master locked plan (research + job, full roadmap).
    • journal1-asset-inventory.md — what J1 material exists and what goes where.
    • jbhi-exemplars-and-journal-methodology.md — how to write a journal vs the KICS short paper.
    • email-draft-ziaratnia.md — the pending co-author email.

  • J1 over J2 over job-prep in priority until the J1 draft is out (~June 15).

Risk

  • Whole plan is tight under ~8–15 h/week (research-external). If research time shrinks, LeetCode yields first; floor = Hot100 + LoRA-runnable.
  • J1 timeline depends on the ~June 15 draft pin. If it slips past July, J2 + coding + spring-2027 application state all cascade.
  • BP4D++ J2 has an un-scoped preprocessing/storage risk (15TB). Do a half-day reconnaissance before committing (confirm VL-FAU likely needs only a subset → avoids moving 15TB).

Next

  • Sat advisor meeting (authorship + venue + stats).
  • Then: J1 skeleton + Related Work; read exemplar before fixing diagnostic-chain length.
  • 1 new post
  • Chinese / English switch for new blog
  • Finish all research for journal.

2026-05-21

Project

Research

Done

  • Finished the journal grade diagnostic chain:
    • CCT extraction show low/mid signal for t3 low/high classification.
    • The problem is within the concat/fusion/LSTM part.
  • Had new protocol E9 and old E6 E3 running with a minor improvement on E9 at +0.0438 macro-F1.
  • We can claim EDA does improve the CCT-LSTM model for stress classification.

Decision

  • None

Risk

  • None

Next

  • 1 new post
  • Chinese / English switch for new blog
  • Finish all research for journal.

2026-05-18

Project

New blog

Done

  • Now new astro blog is fully working and operational:
    • Intro, homepage polishes
    • Commit wall fix
    • pinned nav and blur
    • all MD converted to MDX
    • fixed font to local for better access form China
    • “Giscus” github comment system fully operational

Decision

  • None

Risk

  • None

Next

  • 1 new post
  • Chinese / English switch for new blog
  • Finish all research for journal.

2026-05-17

Project

New blog backend / Cloudflare Pages staging

Done

  • Synchronized old posts, worklogs, and draft coverage from the old blog into the new site.
  • Added a release gate for content validation, Astro check/build, artifact verification, and old-blog audit.
  • Migrated old post layout semantics into explicit MDX content components and removed the Chirpy/Kramdown compatibility layer.
  • Configured GitHub Actions as build-only release validation.
  • Disabled GitHub Pages deployment for the new repo to avoid project-path preview conflicts.
  • Documented Cloudflare Pages setup as the staging and production path.

Decision

  • Use Cloudflare Pages *.pages.dev as the only real staging environment.
  • Keep enderjones.com on the old site until the new staging deployment passes final checks.
  • Do not use GitHub project Pages for preview because this site is built for the root path.

Risk

  • Accidentally selecting Ender-Jones/Ender-Jones.github.io in Cloudflare would keep deploying the old site.
  • Binding enderjones.com before staging verification would prematurely cut over production.

Next

  • Create a new Cloudflare Pages project connected to Ender-Jones/personal_blog_astro.
  • Verify homepage, posts, worklogs, tags, about, 404, robots, sitemap, images, and Giscus behavior on the *.pages.dev URL.
  • After staging passes, archive/stop the old site and bind the production domain to the new Cloudflare Pages project.

2026-05-16

Project

New blog design

Done

  • Finalized most of the design.

Decision

  • None.

Risk

  • DO MORE LEETCODE/ACM.

Next

  • finish research and journal paper.

2026-05-15

Project

New blog design / Research

Done

  • Astro blog 4 iterations.
  • Made a levels experiment final journal-grade diagnostic chain.
  • Rewrite README.md for research for journal.

Decision

  • We can not make a levels experiments work using current model.

Risk

  • Should go for lower level place for journal.

Next

  • Finish the diagnostic chain.

2026-05-13

Project

Experiment result investigation / Context file manage

Done

  • Reconstructed md memory files.
  • Added single seed investigation script.
  • Made some investigation for low performance issue.
  • T3 low/high does not have strong signal, binary feature screening of logreg/linear_svm showed even contact BVP macro-f1 is 0.5596.
  • z-score/no z-score in Quantile MTF showed completely identical picture.

Decision

  • Do future investigation for journal writing.

Risk

  • Gonna go fast.

Next

  • More investigation.

2026-05-12

Project

Research monitoring & adjusting.

Done

  • Core run complete with lower than baseline performance.

Decision

  • Investigate problem and improve.

Risk

  • Might cost my paper can publish.

Next

  • Define the problem is in the method or data processing flow.

2026-05-11

Project

UEvolve implementation:

  • Scoped a closed-loop RAG workflow connecting indexing, retrieval, decision evidence, and knowledge write-back.
  • Scoped a self-extension validator to check scaffold, schema, tests, dry-run apply, build, execution, and rollback.
  • Scoped an export/import package flow for sharing self-generated tools as validated distributable packages.

Research experiments.

Done

  • RAG part is finished and tested, PR is merged
  • Experiment 2 core runs is up and running.

Decision

  • Do more research things

Risk

  • Journal won’t be in time at this rate.

Next

  • EDA-Augmented CCT-LSTM evaluation experiment part 2.

2026-05-10

Project

UEvolve vibe coding

Done

  • Reviewed the project with Meng.
  • Had plan for next steps.

Decision

  • Collaborate with Meng on the implementation of the UEvolve.
  • Defined a parallel plan for multi-agent orchestration.

Risk

  • Research is remain the first priority.
  • Implementation may take more time than expected, which could delay the research progress.

Next

  • Start implementing the UEvolve based on the defined plan.
  • Continue with the research experiments in parallel.

2026-05-08

Project

Paper writing

Done

  • Whole paper review and polishing.
  • Paper sent to professor for submission.

Decision

  • None

Risk

  • None

Next

  • Submit the paper.
  • Prepare for next experiments.
  • Review past exam question sets.
  • Plan next research projects.
  • Practice English.
  • Get Korea’s visa.(After passport renewal)

2026-05-07

Project

Paper writing

Done

  • Paper method section EDA-argumentation part.
  • Paper evaluation protocol description part.

Decision

  • None

Risk

  • None

Next

  • Finish the paper.

2026-05-06

Project

K.I.C.S. Paper writing

Done

  • Paper method section paper reproduction part.

Decision

  • None

Risk

  • Paper might be a little too long.

Next

  • Finish the paper.

2026-05-05

Project

Paper writing / experiment results review.

Done

  • Paper related work section.
  • Reviewed all clean p128 results for P1-P8.

Decision

  • K.I.C.S. paper should only include P0/3/4.

Risk

  • Deadline is close.

Next

  • Finish method and experiment sections.
  • Prepare for submission.

2026-05-01

Project

Paper writing

Done

  • Paper introduction.

Decision

  • None

Risk

  • Intro and abstract are little too long and may need to be shortened.

Next

  • Finish the related work section, then move on to method and experiment sections.
EnderJones
EnderJones

PhD candidate · Tokyo, Japan