add Alembic SFT data cleaning section with MinHash algorithm and fix bibliography order

main.tex

@@ -91,6 +91,44 @@ Two storage backends serve the DataLoader:
 A resumable distributed sampler provides seed-based shuffle with
 epoch/iteration resume.
 
+\subsection{SFT Data Cleaning}
+
+For supervised fine-tuning (SFT), raw data requires additional curation
+beyond pretraining tokenization. {\sc Alembic}~\cite{alembic} is a companion
+pipeline that handles SFT data generation, cleaning, and quality scoring:
+three-generation strategies (topic-driven, seed-driven, self-instruct),
+built-in cleaning (HTML/URL/markdown removal, char/word repetition filters),
+and a MinHash-based near-duplicate detection system~\cite{broder1997syntactic}.
+Given a set of $P$ hash functions ($P=128$) and a text $T$, the MinHash
+pipeline proceeds as follows:
+
+\begin{enumerate}[nosep,leftmargin=*]
+  \item \textbf{Tokenization}: $T$ is split into character $n$-grams
+    ($n=3$):
+    \begin{equation}
+      \Gamma(T) = \{\,c_i c_{i+1} c_{i+2} \mid i = 1,\dots,|T|-2 \,\}.
+    \end{equation}
+  \item \textbf{Signature}: For each hash function $h_k$, the minimum hash
+    value over all $n$-grams forms the $k$-th element of the fingerprint:
+    \begin{equation}
+      s_k = \min_{t \in \Gamma(T)} h_k(t), \qquad
+      h_k(t) = \operatorname{SHA256}(42 : k : t)_{[0:63]}.
+    \end{equation}
+    The full fingerprint is $\mathbf{s} = (s_1,\dots,s_P)$.
+  \item \textbf{Similarity}: The Jaccard similarity between two sets is
+    estimated by the fraction of agreeing fingerprint positions:
+    \begin{equation}
+      \widehat{J}(\mathbf{s}^{(a)},\mathbf{s}^{(b)}) =
+      \frac{|\{\,k \mid s^{(a)}_k = s^{(b)}_k \,\}|}{P}.
+    \end{equation}
+  \item \textbf{Filtering}: Samples are processed sequentially; a sample
+    is dropped if $\widehat{J}(\mathbf{s}, \mathbf{s}') \ge 0.7$ for any
+    previously kept sample $\mathbf{s}'$.
+\end{enumerate}
+
+An optional LLM-as-Judge scoring module provides multi-dimensional
+quality scores that can be used to filter low-quality samples.
+
 % ======================================================================
 \section{Model Architecture}
 % ======================================================================
@@ -295,14 +333,23 @@ J.~Ainslie, J.~Lee-Thorp, M.~de Jong, Y.~Zemlyanskiy, F.~Lebr\'on, S.~Sanghai.
 GQA: Training generalized multi-query transformer models from multi-head
 checkpoints. \textit{EMNLP}, 2023.
 
+\bibitem{alembic}
+Alembic Contributors. \textit{Alembic: A lightweight LLM-driven SFT data
+generation, cleaning, and scoring pipeline.}
+\url{https://github.com/ViperEkura/Alembic}, 2026.
+
 \bibitem{astrai}
 AstrAI Contributors. \textit{AstrAI: An open-source training and inference
 framework for Transformer language models.}
 \url{https://github.com/ViperEkura/AstrAI}, 2026.
 
+\bibitem{broder1997syntactic}
+A.~Z.~Broder. On the resemblance and containment of documents.
+\textit{SEQUENCES '97}, 1997.
+
 \bibitem{ieee754}
 IEEE Computer Society. \textit{IEEE Standard for Floating-Point Arithmetic},
-IEEE Std 754-2008, 2008.
+IEEE Std 754-2019, 2019.
 
 \bibitem{loshchilov2019adamw}
 I.~Loshchilov, F.~Hutter. Decoupled weight decay regularization.