diff --git a/paper.log b/paper.log index 75ad178..1bdbb91 100644 --- a/paper.log +++ b/paper.log @@ -1,4 +1,4 @@ -This is pdfTeX, Version 3.141592653-2.6-1.40.29 (TeX Live 2026/Arch Linux) (preloaded format=pdflatex 2026.3.11) 6 APR 2026 19:49 +This is pdfTeX, Version 3.141592653-2.6-1.40.29 (TeX Live 2026/Arch Linux) (preloaded format=pdflatex 2026.3.11) 6 APR 2026 19:50 entering extended mode restricted \write18 enabled. %&-line parsing enabled. @@ -435,12 +435,7 @@ Quan-ti-za-tion tested at f32/f16/bf16/int8/int4 [] [2{/usr/share/texmf-dist/fonts/enc/dvips/cm-super/cm-super-ts1.enc}] [3] -[4] [5] (./paper.aux - -Package natbib Warning: Citation(s) may have changed. -(natbib) Rerun to get citations correct. - -) +[4] [5] (./paper.aux) *********** LaTeX2e <2025-11-01> L3 programming layer <2026-01-19> @@ -451,11 +446,11 @@ Package rerunfilecheck Info: File `paper.out' has not changed. Here is how much of TeX's memory you used: 12083 strings out of 467525 178010 string characters out of 5425861 - 607805 words of memory out of 5000000 + 607900 words of memory out of 5000000 40829 multiletter control sequences out of 15000+600000 639085 words of font info for 84 fonts, out of 8000000 for 9000 1141 hyphenation exceptions out of 8191 - 75i,8n,79p,324b,518s stack positions out of 10000i,1000n,20000p,200000b,200000s + 75i,8n,79p,324b,520s stack positions out of 10000i,1000n,20000p,200000b,200000s -Output written on paper.pdf (5 pages, 196714 bytes). +Output written on paper.pdf (5 pages, 196804 bytes). PDF statistics: 210 PDF objects out of 1000 (max. 8388607) 171 compressed objects within 2 object streams diff --git a/paper.pdf b/paper.pdf index 3378fc8..bb9202a 100644 Binary files a/paper.pdf and b/paper.pdf differ diff --git a/paper.tex b/paper.tex index f618ae8..275ae22 100644 --- a/paper.tex +++ b/paper.tex @@ -237,15 +237,17 @@ weight edits. CRI modifies zero weights. %─────────────────────────────────────────────── \section{Limitations} -\textbf{Backbone lock-in}: reflexes don't transfer across models. -\textbf{Trigger collision}: similar activations fire incorrect reflexes. -\textbf{Linear scan}: $O(n)$ retrieval; needs ANN past ${\sim}100$K reflexes. -\textbf{Per-position biases}: doesn't generalize to reformulations. -\textbf{One-shot rigidity}: no reinforcement or extinction. -\textbf{Post-bias degeneration}: instruct models loop after biases exhaust. -\textbf{Discrimination degrades with instruct tuning}: RLHF compresses -activation spaces (Qwen: 0.213 spread; Gemma E4B-it: 0.056). -\textbf{Cross-precision fragility}: condition and trigger must match precision. +\begin{itemize} +\item \textbf{Backbone lock-in}: reflexes don't transfer across models. +\item \textbf{Trigger collision}: similar activations fire incorrect reflexes. +\item \textbf{Linear scan}: $O(n)$ retrieval; needs ANN past ${\sim}100$K reflexes. +\item \textbf{Per-position biases}: doesn't generalize to reformulations. +\item \textbf{One-shot rigidity}: no reinforcement or extinction. +\item \textbf{Post-bias degeneration}: instruct models loop after biases exhaust. +\item \textbf{Discrimination degrades with instruct tuning}: RLHF compresses + activation spaces (Qwen: 0.213 spread; Gemma E4B-it: 0.056). +\item \textbf{Cross-precision fragility}: condition and trigger must match precision. +\end{itemize} %─────────────────────────────────────────────── \section{Conclusion}