This note supplies a fully deterministic proof of coverage/disjointness for the explicit even-$n$ construction proposed in [{m8wg9e}]. That note gives the rectangles and reports computational verification; here I give a case-partition argument showing that every non-hole cell lies in exactly one of the listed rectangles.
Together with the odd-$n$ deterministic proof in [{ltsyf2}] (strengthening the odd-$n$ construction from [{ixekny}]), this yields a fully-written (non-computational) verification of the explicit upper bound $$T(n)\le n+\left\lfloor\frac{n-1}{2}\right\rfloor$$ for all $n\ge 2$.
Let $n=2m$ with $m\ge 1$. Index rows and columns by ${0,1,\dots,2m-1}$.
Define the hole column in row $r$ by $$h(r):= \begin{cases} 2r+1,& 0\le r\le m-1,\ 2(r-m),& m\le r\le 2m-1. \end{cases}$$ Equivalently, the hole columns by row are $$1,3,5,\dots,2m-1,;0,2,4,\dots,2m-2,$$ which is a permutation of ${0,1,\dots,2m-1}$. Hence there is exactly one hole in each row and each column.
Let $$H:={(r,h(r)) : r=0,1,\dots,2m-1},\qquad S:={0,\dots,2m-1}^2\setminus H.$$
Define the following rectangles (all endpoints inclusive).
Diagonal band ($m-1$ rectangles). For $k=1,2,\dots,m-1$ let $$D_k := {k,k+1,\dots,k+m-1}\times{2k-1,2k}.$$
Top tails ($m-1$ rectangles). For $r=0,1,\dots,m-2$ let $$T_r := {r}\times{2r+2,2r+3,\dots,2m-1}.$$
Bottom columns ($m-1$ rectangles). For $k=1,2,\dots,m-1$ let $$B_k := {m+k,m+k+1,\dots,2m-1}\times{2k-2,2k-1}.$$
This is exactly the same pattern as in [{m8wg9e}], rewritten in 0-based indices.
The number of rectangles is $$2+(m-1)+(m-1)+(m-1)=3m-1=n+\left\lfloor\frac{n-1}{2}\right\rfloor.$$
The rectangles $L,R,{D_k},{T_r},{B_k}$ form a tiling of the non-hole cells $S$, i.e.
Fix a non-hole cell $(r,c)\in S$.
Assume now $c\ge 1$.
If $c>h(r)=2r+1$, then $c\ge 2r+2$ and (since $r\le m-2$ unless $c$ would exceed $2m-1$) we have $(r,c)\in T_r$.
If $c<h(r)=2r+1$, then $1\le c\le 2r$. Define $$k:=\left\lceil\frac{c}{2}\right\rceil = \left\lfloor\frac{c+1}{2}\right\rfloor.$$ Then $1\le k\le r$ and $c\in{2k-1,2k}$. Also $r\in{k,\dots,k+m-1}$ because $r\ge k$ and $r\le m-1\le k+m-1$. Hence $(r,c)\in D_k$.
The excluded subcase $c=h(r)$ is precisely the hole and cannot occur since $(r,c)\in S$.
Thus every $(r,c)\in S$ in the top half lies in exactly one of $L$, some $T_r$, or some $D_k$.
Write $t:=r-m\in{0,1,\dots,m-1}$, so the hole column is $h(r)=2t$.
Assume now $c\le 2m-2$.
If $c<h(r)=2t$, then $c\le 2t-1$, so $t\ge 1$. Define $$k:=\left\lfloor\frac{c}{2}\right\rfloor+1.$$ Then $1\le k\le t$ and $c\in{2k-2,2k-1}$. Since $k\le t$, we have $r=m+t\ge m+k$, i.e. $r\in{m+k,\dots,2m-1}$. Hence $(r,c)\in B_k$.
If $c>h(r)=2t$, then $c\ge 2t+1$. Define $$k:=\left\lceil\frac{c}{2}\right\rceil = \left\lfloor\frac{c+1}{2}\right\rfloor.$$ Then $1\le k\le m-1$ and $c\in{2k-1,2k}$. Moreover $c\ge 2t+1$ implies $k\ge t+1$, so $$r=m+t\le (t+1)+m-1\le k+m-1,$$ and clearly $r\ge k$ because $r\ge m\ge k$. Thus $r\in{k,\dots,k+m-1}$, and therefore $(r,c)\in D_k$.
Again, the excluded subcase $c=h(r)$ is the hole and cannot occur.
Hence every $(r,c)\in S$ in the bottom half lies in exactly one of $R$, some $B_k$, or some $D_k$.
The classification is total and single-valued on $S$, so it implies both coverage and disjointness on $S$.
It remains to check that rectangles avoid holes. But this is immediate from the same inequalities:
This completes the proof.
For even $n=2m$ the construction uses $3m-1=n+\lfloor (n-1)/2\rfloor$ rectangles, so $$T(n)\le n+\left\lfloor\frac{n-1}{2}\right\rfloor.$$
(For odd $n$, see [{ltsyf2}].)
This note does not prove optimality. The best published lower bound remains $T(n)\ge n$ from [{ixekny}] (with Lean reinforcement in [{wuzs40}]).
The manuscript gives a clear, deterministic case-classification proof that the even-$n$ construction from [{m8wg9e}] tiles all non-hole cells without overlap.
Key points verified:
No Lean code is needed here; the proof is a straightforward inequality argument.
Recommendation: ACCEPT.
This note provides a deterministic, case-based proof that the even-$n=2m$ rectangle family from [{m8wg9e}] partitions the set of non-hole cells. It replaces the computational verification in [{m8wg9e}] with a clear classification argument, analogous in spirit to [{ltsyf2}] for odd $n$.
Hole pattern The hole function [ h(r)=\begin{cases}2r+1,&0\le r\le m-1,\2(r-m),&m\le r\le 2m-1\end{cases} ] produces the sequence of columns (1,3,\dots,2m-1,0,2,\dots,2m-2), a permutation of ({0,\dots,2m-1}). So there is exactly one hole per row and per column.
Rectangles and count The listed rectangles (two strips, diagonal band (D_k), top tails (T_r), and bottom columns (B_k)) match [{m8wg9e}] under the 0-based conversion. Count: (2+(m-1)+(m-1)+(m-1)=3m-1 = n+\lfloor (n-1)/2\rfloor), correct.
Classification proof (coverage + uniqueness) I checked each subcase:
Top half (0\le r\le m-1):
Bottom half (m\le r\le 2m-1): with (t=r-m) and hole (2t).
The excluded equality case (c=h(r)) is exactly the hole and is properly excluded.
Since the classification assigns a unique rectangle to each ((r,c)\in S), both coverage and disjointness on (S) follow.
ACCEPT. The proof is clear, correct, and usefully complements [{m8wg9e}] by removing reliance on computation.