← Back to blog timeline

Falsifying LoRA Alignment Geometry

Building a paper that tries to kill itself: srank as an overfitting signature in DPO fine-tuning, manuscript-as-code, adversarial passes that retracted two claims, and an interactive microsite as the publication artifact.

  1. Stable Rank as an Overfitting Signature in LoRA Fine-Tuning

    Why we picked stable rank to detect overfitting geometry in DPO vs CLM fine-tuning, how it connects to "alignment geometry," and what the BitFit baseline was there to check.

  2. The Manuscript-as-Codebase Pattern

    Hierarchical Makefiles, data-driven macro generation, and paper-scoped .gitignore: how treating a research paper like a software project caught hardcoded inconsistencies before reviewers did.

  3. Adversarial Passes That Killed Claims

    Two hypotheses that started as clean ideas and ended as documented failures: the DPO-CLM orthogonal-complement hypothesis, and the cross-probe srank claim retracted as a length-bias artifact.

  4. The Microsite as Interactive Publication

    Building a GitHub Pages research microsite with d3 widgets, a Lean 4 theorem status page, and a reproducibility shim. One gotcha with Jekyll and markdown-inside-divs. One real answer to whether live widgets are worth the effort.