problem
stringlengths 54
2.23k
| solution
stringlengths 134
24.1k
| answer
stringclasses 1
value | problem_is_valid
stringclasses 1
value | solution_is_valid
stringclasses 1
value | question_type
stringclasses 1
value | problem_type
stringclasses 8
values | problem_raw
stringlengths 54
2.21k
| solution_raw
stringlengths 134
24.1k
| metadata
dict | uuid
stringlengths 36
36
| id
int64 23.5k
612k
|
|---|---|---|---|---|---|---|---|---|---|---|---|
The diagonals of the convex quadrilateral $ABCD$ are perpendicular and intersect at $O$. The perpendicular to $(AB)$ passing through $O$ intersects $(AB)$ at $M$ and $(CD)$ at $M'$. The perpendicular to $(BC)$ passing through $O$ intersects $(BC)$ at $N$ and $(DA)$ at $N'$. The perpendicular to $(CD)$ passing through $O$ intersects $(CD)$ at $P$ and $(AB)$ at $P'$. The perpendicular to $(DA)$ passing through $O$ intersects $(DA)$ at $Q$ and $(BC)$ at $Q'$.
Prove that the points $M, N, P, Q, M', N', P', Q'$ are concyclic.
|
Let's start by proving that the quadrilateral $M N P Q$ is cyclic:
We note that the quadrilateral $B M O N$ has two right angles at $M$ and $N$, so it is inscribed in the circle with diameter $[O B]$. Similarly, the quadrilaterals $C N O P$, $D P O Q$, and $A Q O M$ are inscribed in the circles with diameters $[O C]$, $[O D]$, and $[O A]$, respectively. From this, we deduce that $\widehat{O M N} = \widehat{O B N}$, $\widehat{O M Q} = \widehat{O A Q}$, $\widehat{O P Q} = \widehat{O D Q}$, and $\widehat{O P N} = \widehat{O C N}$.
\[
\begin{aligned}
& \text{Then we have} \\
& \begin{aligned}
\widehat{Q M N} & = \widehat{Q M O} + \widehat{O M N} \\
& = \widehat{Q A O} + \widehat{O B N} \\
& = \widehat{D A C} + \widehat{D B C}
\end{aligned}
\end{aligned}
\]
And on the other hand
\[
\begin{aligned}
\widehat{Q P N} & = \widehat{Q P O} + \widehat{O P N} \\
& = \widehat{Q D O} + \widehat{O C N} \\
& = \widehat{A D B} + \widehat{A C B}
\end{aligned}
\]
Since $[A C]$ and $[D B]$ are perpendicular, we have $\widehat{D A C} + \widehat{A D B} = 90^{\circ}$, and similarly $\widehat{D B C} + \widehat{A C B} = 90^{\circ}$. Thus, $\widehat{Q M N} = 180^{\circ} - \widehat{Q P N}$. This ensures that $M N P Q$ is cyclic.
Let $\Gamma$ be the circumcircle of $M N P Q$. By symmetry of roles, to conclude, it suffices to prove that $Q^{\prime}$ is on $\Gamma$.
Suppose that $N \in [C Q^{\prime}]$, the other cases being treated similarly.
We have $\widehat{N Q^{\prime} Q} = \widehat{N Q^{\prime} O} = 180^{\circ} - \widehat{Q^{\prime} C O} - \widehat{C O Q^{\prime}}$.
But $\widehat{Q^{\prime} C O} = \widehat{N C O} = \widehat{N P O}$, since $N C P O$ is cyclic.
On the other hand, since the sides are perpendicular to each other, we have $\widehat{C O Q^{\prime}} = \widehat{O D Q} = \widehat{O P Q}$, the last equality coming from the fact that $O P D Q$ is cyclic.
Thus, we have $\widehat{N Q^{\prime} Q} = 180^{\circ} - \widehat{N P O} - \widehat{O P Q} = 180^{\circ} - \widehat{N P Q}$, which ensures that $Q^{\prime}$ belongs to the circumcircle of $N P Q$.
## Common Exercises
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Les diagonales du quadrilatère convexe $A B C D$ sont perpendiculaires et se rencontrent en $O$. La perpendiculaire à $(A B)$ passant par $O$ rencontre $(A B)$ en $M$ et $(C D)$ en $M^{\prime}$. La perpendiculaire à $(B C)$ passant par $O$ rencontre $(B C)$ en $N$ et $(D A)$ en $N^{\prime}$. La perpendiculaire à $(C D)$ passant par $O$ rencontre $(C D)$ en $P$ et $(A B)$ en $P^{\prime}$. La perpendiculaire à $(D A)$ passant par $O$ rencontre ( $D A)$ en $Q$ et $(B C)$ en $Q^{\prime}$.
Prouver que les points $M, N, P, Q, M^{\prime}, N^{\prime}, P^{\prime}, Q^{\prime}$ sont cocycliques.
|

Commençons par prouver que le quadrilatère $M N P Q$ est inscriptible :
On note que le quadrilatère $B M O N$ à deux angles droits en $M$ et en $N$, donc il est inscrit dans le cercle de diamètre $[O B]$. De même, les quadrilatères $C N O P, D P O Q$ et $A Q O M$ sont inscrits respectivement dans les cercles de diamètres $[O C],[O D]$ et $[O A]$. On en déduit que $\widehat{O M N}=\widehat{O B N}$, que $\widehat{O M Q}=\widehat{O A Q}$, que $\widehat{O P Q}=\widehat{O D Q}$ et que $\widehat{O P N}=\widehat{O C N}$.
$$
\begin{aligned}
& \text { Il vient alors } \\
& \begin{aligned}
\widehat{Q M N} & =\widehat{Q M O}+\widehat{O M N} \\
& =\widehat{Q A O}+\widehat{O B N} \\
& =\widehat{D A C}+\widehat{D B C}
\end{aligned}
\end{aligned}
$$
Et d'autre part
$$
\begin{aligned}
\widehat{Q P N} & =\widehat{Q P O}+\widehat{O P N} \\
& =\widehat{Q D O}+\widehat{O C N} \\
& =\widehat{A D B}+\widehat{A C B}
\end{aligned}
$$
Or, puisque $[A C]$ et $[D B]$ sont perpendiculaires, on a $\widehat{D A C}+\widehat{A D B}=90^{\circ}$, et de même $\widehat{D B C}+$ $\widehat{A C B}=90^{\circ}$. Ainsi $\widehat{Q M N}=180^{\circ}-\widehat{Q P N}$. Cela assure que $M N P Q$ est inscriptible.
On note $\Gamma$ le cercle circonscrit à $M N P Q$. Par symétrie des rôles, pour conclure, il suffit de prouver que $Q^{\prime}$ est sur $\Gamma$.
Supposons que $N \in\left[C Q^{\prime}\right]$, les autres cas se traitant de façons similaires.
Nous avons $\widehat{N Q^{\prime} Q}=\widehat{N Q^{\prime} O}=180^{\circ}-\widehat{Q^{\prime} C O}-\widehat{C O Q^{\prime}}$.
Mais $\widehat{Q^{\prime} C O}=\widehat{N C O}=\widehat{N P O}$, puisque $N C P O$ inscriptible.
D'autre part, comme les côtés sont perpendiculaires deux à deux, on a $\widehat{C O Q^{\prime}}=\widehat{O D Q}=\widehat{O P Q}$, la dernière égalité découlant du fait que $O P D Q$ est inscriptible.
Ainsi, on a $\widehat{N Q^{\prime} Q}=180^{\circ}-\widehat{N P O}-\widehat{O P Q}=180^{\circ}-\widehat{N P Q}$, ce qui assure que $Q^{\prime}$ appartient bien au cercle circonscrit à $N P Q$.
## Exercices communs
|
{
"resource_path": "French/segmented/envois/fr-ofm-2013-2014-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 3.",
"solution_match": "## Solution de l'exercice 3"
}
|
feabcc87-2f8c-5948-bd51-c1f0707603ed
| 607,537
|
Inside the circle $\Gamma$ there are three circles $\gamma_{1}, \gamma_{2}$ and $\gamma_{3}$, tangent to $\Gamma$ at $A, B$ and $C$ respectively, all distinct. The circles $\gamma_{2}$ and $\gamma_{3}$ have a common point $K$ which lies on $[B C]$, the circles $\gamma_{3}$ and $\gamma_{1}$ have a common point $L$ which lies on $[C A]$, and the circles $\gamma_{1}$ and $\gamma_{2}$ have a common point $M$ which lies on $[A B]$.
Prove that the center of $\Gamma$ belongs to $\gamma_{1}, \gamma_{2}$ and $\gamma_{3}$.
|
Let $X$ be a point on the common tangent to $\Gamma$ and $\gamma_{1}$, and located on the side opposite to $C$ with respect to the line $(A B)$. Then $\widehat{A L M}=\widehat{X A M}=\widehat{X A B}=\widehat{A C B}$, which ensures that $(M L)$ and $(B C)$ are parallel. Similarly, we have $(K M)$ and $(A C)$ parallel, as well as $(K L)$ and $(A B)$ parallel.
Let $x=\frac{A M}{A B}$. According to Thales' theorem, we then have:
$$
\frac{B K}{B C}=\frac{B M}{B A}=1-x \text { and } \frac{C L}{C A}=\frac{C K}{C B}=1-(1-x)=x
$$
Thus $x=\frac{A M}{A B}=\frac{A L}{A C}=1-x$, hence $x=\frac{1}{2}$.
The points $M, K, L$ are therefore the midpoints of the segments $[A B],[B C],[C A]$, and the triangles $A M L, M B K, L K C$ are all similar to $A B C$ with a ratio of $\frac{1}{2}$. If we denote $r_{1}, r_{2}, r_{3}$ and $R$ as the radii of the circles $\gamma_{1}, \gamma_{2}, \gamma_{3}$ and $\Gamma$, respectively, we deduce that $r_{1}=r_{2}=r_{3}=\frac{1}{2} R$.
Furthermore, since $\gamma_{1}$ and $\Gamma$ are tangent at $A$, the diameters from $A$ in $\gamma_{1}$ and $\Gamma$ lie on the same line. Thus, the center of $\Gamma$ lies on $\gamma_{1}$, and similarly, it lies on $\gamma_{2}$ and $\gamma_{3}$.
Remark: Another way to express the above paragraph is to use the homothety $\overline{h \text { with center } A}$ and ratio $\frac{1}{2}$. Since $h(A)=A, h(B)=M$ and $h(C)=L$, the image of $\Gamma$ under $h$ is the circumcircle of $A L M$, which is $\gamma_{1}$. Let $A^{\prime}$ be the point diametrically opposite to $A$ in the circle $\Gamma$ and let $O$ be the center of $\Gamma$. Since $h\left(A^{\prime}\right)=O$, the point $O$ lies on $\gamma_{1}$, and similarly, it lies on $\gamma_{2}$ and $\gamma_{3}$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
A l'intérieur du cercle $\Gamma$ se trouvent trois cercles $\gamma_{1}, \gamma_{2}$ et $\gamma_{3}$, et tangents à $\Gamma$ respectivement en $A, B$ et $C$, tous distincts. Les cercles $\gamma_{2}$ et $\gamma_{3}$ ont un point commun $K$ qui appartient à $[B C]$, les cercles $\gamma_{3}$ et $\gamma_{1}$ ont un point commun $L$ qui appartient à $[C A]$, et les cercles $\gamma_{1}$ et $\gamma_{2}$ ont un point commun $M$ qui appartient à $[A B]$.
Prouver que le centre de $\Gamma$ appartient à $\gamma_{1}, \gamma_{2}$ et $\gamma_{3}$.
|

Soit $X$ un point de la tangente commune à $\Gamma$ et $\gamma_{1}$, et situé du côté opposé à $C$ par rapport à la droite $(A B)$. Alors $\widehat{A L M}=\widehat{X A M}=\widehat{X A B}=\widehat{A C B}$, ce qui assure que $(M L)$ et $(B C)$ sont parallèles. De même, on a $(K M)$ et $(A C)$ parallèles, ainsi que $(K L)$ et $(A B)$ parallèles.
Posons $x=\frac{A M}{A B}$. D'après le théorème de Thalès, on a alors :
$$
\frac{B K}{B C}=\frac{B M}{B A}=1-x \text { et } \frac{C L}{C A}=\frac{C K}{C B}=1-(1-x)=x
$$
Ainsi $x=\frac{A M}{A B}=\frac{A L}{A C}=1-x$, d'où $x=\frac{1}{2}$.
Les points $M, K, L$ sont donc les milieux respectifs des segments $[A B],[B C],[C A]$, et les triangles $A M L, M B K, L K C$ sont tous semblables à $A B C$ dans un rapport $\frac{1}{2}$. Si on note $r_{1}, r_{2}, r_{3}$ et $R$ les rayons respectifs des cercles $\gamma_{1}, \gamma_{2}, \gamma_{3}$ et $\Gamma$, on en déduit que $r_{1}=r_{2}=r_{3}=\frac{1}{2} R$.
D'autre part, puisque $\gamma_{1}$ et $\Gamma$ sont tangents en $A$ les diamètres issus de $A$ dans $\gamma_{1}$ et $\Gamma$ sont portés par la même droite. Ainsi, le centre de $\Gamma$ appartient à $\gamma_{1}$, et on prouve de même qu'il appartient également à $\gamma_{2}$ et $\gamma_{3}$.
Remarque: une autre manière d'exprimer le paragraphe précédent consiste utiliser l'homothétie $\overline{h \text { de centre } A}$ et de rapport $\frac{1}{2}$. Comme $h(A)=A, h(B)=M$ et $h(C)=L$, l'image par $h$ de $\Gamma$ est le cercle circonscrit à $A L M$, c'est-à-dire $\gamma_{1}$. Soit $A^{\prime}$ le point diamétralement opposé à $A$ dans
le cercle $\Gamma$ et soit $O$ le centre de $\Gamma$. Comme $h\left(A^{\prime}\right)=O$, le point $O$ appartient à $\gamma_{1}$, et de même il appartient à $\gamma_{2}$ et $\gamma_{3}$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2013-2014-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 4.",
"solution_match": "## Solution de l'exercice 4"
}
|
d1aaabd1-7f69-5fbf-99c2-22968f2ed657
| 607,538
|
Let $n, m \geqslant 1$ be integers, with $m$ odd.
Prove that $2^{m}-1$ and $2^{n}+1$ are coprime.
|
By contradiction: suppose there exists a prime $p$ that divides both $2^{m}-1$ and $2^{n}+1$.
Then, we have $2^{m} \equiv 1 \bmod [p]$ and $2^{n} \equiv-1 \bmod [p]$,
hence $2^{2 n} \equiv 1 \bmod [p]$.
Let $\omega$ be the order of 2 modulo $p$. We know that $\omega$ divides $m$ and $2 n$. But, since $m$ is odd, $\omega$ is therefore odd, which ensures that in fact $\omega$ divides $n$.
We then have $2^{n} \equiv 1 \bmod [p]$, and still $2^{n} \equiv-1 \bmod [p]$.
Thus, $p$ divides 2, and therefore $p=2$.
But, we have $m \geqslant 1$, so $2^{m}-1$ is odd and is therefore not divisible by 2. Contradiction.
Finally, $2^{m}-1$ and $2^{n}+1$ are coprime.
Another solution
First, let's prove by induction on $a+b$ that the gcd of $2^{a}-1$ and $2^{b}-1$ is $2^{\operatorname{gcd}(a, b)}-1$. If $a=0$ or $b=0$ it is clear. Suppose the property is true for all pairs $(a^{\prime}, b^{\prime})$ such that $a^{\prime}+b^{\prime}<a+b$. We can assume $a \geqslant b>0$. We have
\[
\begin{aligned}
\operatorname{gcd}\left(2^{a}-1,2^{b}-1\right) & =\operatorname{gcd}\left(2^{b}-1,2^{a}-1-\left(2^{b}-1\right)\right) \\
& =\operatorname{gcd}\left(2^{b}-1,2^{b}\left(2^{a-b}-1\right)\right) \\
& =\operatorname{gcd}\left(2^{b}-1,2^{a-b}-1\right) \quad \text{since } 2^{b}-1 \text{ and } 2^{b} \text{ are coprime} \\
& =2^{\operatorname{gcd}(b, a-b)}-1 \quad \text{by induction hypothesis} \\
& =2^{\operatorname{gcd}(a, b)}-1
\end{aligned}
\]
which proves our assertion.
Returning to the exercise. Let $d^{\prime}=\operatorname{gcd}\left(2^{m}-1,2^{n}+1\right)$. Let $d=\operatorname{gcd}(m, n)$, then what precedes shows that $2^{d}-1=\operatorname{gcd}\left(2^{m}-1,2^{2 n}-1\right)$. Since $2^{2 n}-1$ is a multiple of $2^{n}+1$, $d^{\prime}$ divides $2^{d}-1$. Since $2^{d}-1$ divides $2^{n}-1$, $d^{\prime}$ also divides $\left(2^{n}+1\right)-\left(2^{n}-1\right)=2$. Since $2^{m}-1$ is odd, $d^{\prime}$ is odd. It follows that $d^{\prime}=1$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit $n, m \geqslant 1$ des entiers, avec $m$ impair.
Prouver que $2^{m}-1$ et $2^{n}+1$ sont premiers entre eux.
|
Par l'absurde : supposons qu'il existe un nombre premier $p$ qui divise à la fois $2^{m}-1$ et $2^{n}+1$.
Alors, on a $2^{m} \equiv 1 \bmod [p]$ et $2^{n} \equiv-1 \bmod [p]$,
d'où $2^{2 n} \equiv 1 \bmod [p]$.
Soit $\omega$ l'ordre de 2 modulo $p$. On sait qu'alors $\omega$ divise $m$ et $2 n$. Mais, comme $m$ est impair, $\omega$ est donc impair, ce qui assure qu'en fait $\omega$ divise $n$.
On a alors $2^{n} \equiv 1 \bmod [p]$, et toujours $2^{n} \equiv-1 \bmod [p]$.
Par suite, $p$ divise 2, et donc $p=2$.
Mais, on a $m \geqslant 1$, d'où $2^{m}-1$ est impair et n'est donc pas divisible par 2. Contradiction.
Finalement, $2^{m}-1$ et $2^{n}+1$ sont premiers entre eux.
Autre solution
Montrons d'abord par récurrence sur $a+b$ que le pgcd de $2^{a}-1$ et $2^{b}-1$ est $2^{\operatorname{pgcd}(a, b)}-1$. Si $a=0$ ou $b=0$ c'est clair. Supposons la propriété vraie pour tous les couples ( $a^{\prime}, b^{\prime}$ ) tels que $a^{\prime}+b^{\prime}<a+b$. On peut supposer $a \geqslant b>0$. On a
$$
\begin{aligned}
\operatorname{pgcd}\left(2^{a}-1,2^{b}-1\right) & =\operatorname{pgcd}\left(2^{b}-1,2^{a}-1-\left(2^{b}-1\right)\right) \\
& =\operatorname{pgcd}\left(2^{b}-1,2^{b}\left(2^{a-b}-1\right)\right) \\
& =\operatorname{pgcd}\left(2^{b}-1,2^{a-b}-1\right) \quad \operatorname{car} 2^{b}-1 \text { et } 2^{b} \text { premiers entre eux } \\
& =2^{\operatorname{pgcd}(b, a-b)}-1 \quad \text { par hypothèse de récurrence } \\
& =2^{\operatorname{pgcd}(a, b)}-1
\end{aligned}
$$
ce qui démontre notre assertion.
Revenons à l'exercice. Notons $d^{\prime}=\operatorname{pgcd}\left(2^{m}-1,2^{n}+1\right)$. Soit $d=\operatorname{pgcd}(m, n)$, alors ce qui précède montre que $2^{d}-1=\operatorname{pgcd}\left(2^{m}-1,2^{2 n}-1\right)$. Or, $2^{2 n}-1$ est un multiple de $2^{n}+1$, donc $d^{\prime}$ divise $2^{d}-1$. Comme $2^{d}-1$ divise $2^{n}-1$, $d^{\prime}$ divise aussi $\left(2^{n}+1\right)-\left(2^{n}-1\right)=2$. Or, $2^{m}-1$ est impair donc $d^{\prime}$ est impair. Il vient $d^{\prime}=1$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2013-2014-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 5.",
"solution_match": "## Solution de l'exercice 5"
}
|
d5e17f36-0bb6-5e78-864c-ae8d1a767449
| 607,539
|
If $n>0$ is an integer, we denote by $d(n)$ the number of positive divisors of $n$.
a) Does there exist a strictly increasing sequence $\left(a_{i}\right)_{i \geqslant 1}$ of positive integers such that, for all $i$ sufficiently large, the number $a_{i}$ is divisible by exactly $d(i)-1$ terms of the sequence (including itself)?
b) Does there exist a strictly increasing sequence $\left(a_{i}\right)_{i \geqslant 1}$ of positive integers such that, for all $i$ sufficiently large, the number $a_{i}$ is divisible by exactly $d(i)+1$ terms of the sequence (including itself)?
|
a) The answer is yes.
It suffices to find a sequence $\left(a_{i}\right)$ that satisfies the following two conditions:
- the number $a_{1}$ does not divide any other term of the sequence,
- the number $i$ divides $j$ if and only if $a_{i}$ divides $a_{j}$, for all $i, j \geqslant 2$.
Indeed, it is well known that, for all integers $i, j \geqslant 1$, we have $\operatorname{pgcd}\left(2^{i}-1,2^{j}-1\right)=2^{d}-1$, where $d=\operatorname{pgcd}(i, j)$. Consequently, the sequence defined by $a_{1}=2$ and $a_{i}=2^{i}-1$ for $i>1$ works.
b) The answer is also yes.
In fact, more generally, we will prove that if $f: \mathbb{N}^{*} \longrightarrow \mathbb{N}^{*}$ is a function and there exists an integer $N>0$ such that $f(n) \leqslant n$ for all $n \geqslant N$, then there exists a strictly increasing sequence $\left(a_{i}\right)_{i \geqslant 1}$ of strictly positive integers such that, for all $i$ sufficiently large, the number $a_{i}$ is divisible by exactly $f(i)$ terms of the sequence.
Note immediately that this answers both a) and b) since $d(n)<n$ for all $n \geqslant 3$ (the number $n-1$ does not divide $n$ for $n \geqslant 3$).
Under the above conditions, we start by choosing a strictly increasing sequence $a_{1}, a_{2}, \cdots, a_{M}$ of $M$ prime numbers. Then, by induction on $k>M$, if $a_{1}, a_{2}, \cdots, a_{k-1}$ are defined with $a_{1}<a_{2}<\cdots<a_{k-1}$, we choose a prime number $p_{k}$ such that $p_{k}>a_{k-1}$ and we set $a_{k}=a_{1} a_{2} \cdots a_{f(k)-1} p_{k}$.
We then clearly have $a_{k-1}<a_{k}$.
Moreover, for all $i>M$, the number $a_{i}$ is divisible only by $a_{1}, a_{2}, \cdots, a_{f(i)-1}$ and by itself. On the other hand, $a_{i}$ is not divisible by any other term $a_{j}$, with $j>f(i)-1$ and $j \neq i$, since such an $a_{j}$ contains a prime factor $p_{j}$ that does not divide any of the $a_{k}$ with $k \leqslant f(i)-1$ and such that $p_{j} \neq p_{i}$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Si $n>0$ est un entier, on désigne par $d(n)$ le nombre de diviseurs strictement positifs de $n$.
a) Existe-t-il une suite $\left(a_{i}\right)_{i \geqslant 1}$ strictement croissante d'entiers strictement positifs tels que, pour tout $i$ suffisamment grand, le nombre $a_{i}$ soit divisible par exactement $d(i)-1$ termes de la suite (y compris lui-même)?
b) Existe-t-il une suite $\left(a_{i}\right)_{i \geqslant 1}$ strictement croissante d'entiers strictement positifs tels que, pour tout $i$ suffisamment grand, le nombre $a_{i}$ soit divisible par exactement $d(i)+1$ termes de la suite (y compris lui-même)?
|
a) La réponse est oui.
Il suffit de trouver une suite $\left(a_{i}\right)$ qui vérifie les deux conditions suivantes :
- le nombre $a_{1}$ ne divise aucun autre terme de la suite,
- le nombre $i$ divise $j$ si et seulement si $a_{i}$ divise $a_{j}$, pour tous $i, j \geqslant 2$.
Or, il est bien connu que, pour tous entiers $i, j \geqslant 1$, on a $\operatorname{pgcd}\left(2^{i}-1,2^{j}-1\right)=2^{d}-1$, où $d=\operatorname{pgcd}(i, j)$. Par conséquent, la suite définie par $a_{1}=2$ et $a_{i}=2^{i}-1$ pour $i>1$ convient.
b) La réponse est également oui.
En fait, de façon plus générale, on va prouver que si $f: \mathbb{N}^{*} \longrightarrow \mathbb{N}^{*}$ est une fonction et qu'il existe un entier $N>0$ tel que $f(n) \leqslant n$ pour tout $n \geqslant N$, alors il existe une suite strictement croissante $\left(a_{i}\right)_{i \geqslant 1}$ d'entiers strictement positifs telle que, pour tout $i$ suffisamment grand, le nombre $a_{i}$ est divisible par exactement $f(i)$ termes de la suite.
Notons tout de suite que cela répond à la fois au a) et au b) puisque $d(n)<n$ pour tout $n \geqslant 3$ (le nombre $n-1$ ne divise pas $n$ pour $n \geqslant 3$ ).
Dans les conditions ci-dessus donc, on commence par choisir une suite strictement croissante $a_{1}, a_{2}, \cdots, a_{M}$ de $M$ nombres premiers. Puis, par récurrence sur $k>M$, si $a_{1}, a_{2}, \cdots, a_{k-1}$ sont définis avec $a_{1}<a_{2}<\cdots<a_{k-1}$, on choisit un nombre premier $p_{k}$ tel que $p_{k}>a_{k-1}$ et on pose $a_{k}=a_{1} a_{2} \cdots a_{f(k)-1} p_{k}$.
On a alors clairement $a_{k-1}<a_{k}$.
De plus, pour tout $i>M$, le nombre $a_{i}$ est divisible que par $a_{1}, a_{2}, \cdots, a_{f(i)-1}$ et par lui-même. Par contre, $a_{i}$ n'est divisible par aucun autre terme $a_{j}$, avec $j>f(i)-1$ et $j \neq i$, puisqu'un tel $a_{j}$ contient un facteur premier $p_{j}$ qui ne divise aucun des $a_{k}$ avec $k \leqslant f(i)-1$ et tel que $p_{j} \neq p_{i}$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2013-2014-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "\nSolution de l'exercice 7"
}
|
13b1dc14-51a1-5e70-9fb2-ac4d71e55aab
| 607,541
|
Let $ABC$ be a triangle. We denote by $D$ the foot of the bisector of $\widehat{BAC}$, and by $E$ the foot of the altitude from $A$. The perpendicular bisector of $[AD]$ meets the semicircles with diameters $[AB]$ and $[AC]$, constructed externally to $ABC$, at $X$ and $Y$.
Prove that the points $X, Y, D, E$ are concyclic.
|
Let $M, N,$ and $P$ be the midpoints of $[AB], [AC],$ and $[AD]$, respectively. According to the Midpoint Theorem, $N, P, M$ are collinear, and given that $(AP) = (AD)$ is the angle bisector of $\widehat{BAC}$, we have
$$
\frac{MP}{NP} = \frac{BD}{CD} = \frac{AM}{AN} = \frac{AB}{AC} = \frac{MX}{NY}.
$$
In particular, it follows that $\frac{MP}{MX} = \frac{NP}{NY}$. Using the Law of Sines in $\triangle MPX$ and $\triangle NPY$, and since $\widehat{NPY} = \widehat{MPX}$, we have $\sin \widehat{PXM} = \sin \widehat{PYN}$. (1)
Clearly, $\widehat{PXM} < \widehat{BXA} = 90^\circ$ and $\widehat{PYN} < \widehat{AYC} = 90^\circ$, so (1) implies $\widehat{PXM} = \widehat{PYN}$. Since $\widehat{MPX} = \widehat{NPY}$, the triangles $\triangle PXM$ and $\triangle PYN$ are similar, and thus $\widehat{PMX} = \widehat{PNY}$. (2)
Without loss of generality, we can assume that between $M$ and $N$, $N$ is on the same side as $A$ with respect to $(XY)$.
Thus (2) leads to $\widehat{PMA} + \widehat{AMX} = \widehat{PNC} + \widehat{CNY}$,
which gives $\widehat{CBA} + 2 \widehat{ABX} = 180^\circ - \widehat{BCA} + 180^\circ - 2 \widehat{ACY}$
and therefore
$$
\begin{aligned}
\widehat{ABX} + \widehat{ACY} & = 180^\circ - \widehat{ABC} - \widehat{BCA} + 90^\circ - \widehat{ABX} + 90^\circ - \widehat{ACY} \\
& = \widehat{BAC} + \widehat{XAB} + \widehat{CAY} \\
& = \widehat{XAY}.
\end{aligned}
$$
However, $\widehat{AEB} = \widehat{AEC} = 90^\circ$, so $E$ lies on the circles with diameters $[AB]$ and $[AC]$, which are the circumcircles of triangles $ABX$ and $ACY$. Therefore, we have $\widehat{ABX} = \widehat{AEX}$ and $\widehat{ACY} = \widehat{AEY}$. (4)
From (3) and (4), we deduce that
$$
\widehat{X E Y} = \widehat{X E A} + \widehat{A E Y} = \widehat{A B X} + \widehat{A C Y} = \widehat{X A Y}.
$$
On the other hand, since $(XY)$ is the perpendicular bisector of $[AD]$, we have $\widehat{X A Y} = \widehat{X D Y}$, and finally $\widehat{X E Y} = \widehat{X D Y}$, which concludes the proof.
Alternative solution. Apply an inversion $i$ with pole $A$. Recall that circles not passing through $A$ are transformed into circles not passing through $A$, lines passing through $A$ are preserved, and circles passing through $A$ are transformed into lines perpendicular to the line connecting $A$ and the center of the circle. Moreover, any inversion preserves the angles between two intersecting lines or circles.
We deduce that $i$ transforms the circle with diameter $[AB]$ into the perpendicular to $(AB')$ passing through $B'$, transforms the line $(BC)$ into the circle $(AB'C')$ such that $D'$ is the midpoint of the arc $B'C'$ not containing $A$ and $E'$ is the point diametrically opposite to $A$. Furthermore, $i$ maps the perpendicular bisector of $[AD]$ to the circle with center $D'$ passing through $A$. Finally, since $E$ lies on the circle with diameter $[AB]$, the points $E', B, X'$ are collinear and similarly $E', C, Y'$ are collinear.
Assume that the angles at $B$ and $C$ in triangle $ABC$ are acute (the reasoning is analogous in the opposite case). Then $E'$ lies on the arc $B'C'$ not containing $A$. Without loss of generality, we can assume that $E'$ lies on the arc $C'D'$ as shown in the figure.

The fact that $E$ does not lie on the same semicircle with diameter $[AB]$ as $X$ implies that $B'$ lies between $E'$ and $X'$. Similarly, $C'$ lies between $E'$ and $Y'$.
First, note that $\widehat{Y' E' D'}$ and $\widehat{X' E' D'}$ are supplementary since $\widehat{Y' E' D'} = \widehat{C' E' D'} = \pi - \widehat{C' A D'} = \pi - \widehat{D' A B'} = \pi - \widehat{D' E' B'} = \pi - \widehat{D' E' X'}$.
Now apply the trigonometric form of Ceva's Theorem for the point $D'$ in triangle $EX'Y'$.
$$
\frac{\sin \left(\overrightarrow{E' D'}, \overrightarrow{E' X'}\right)}{\sin \left(\overrightarrow{E' D'}, \overrightarrow{E' Y'}\right)} \times \frac{\sin \left(\overrightarrow{X' D'}, \overrightarrow{X' Y'}\right)}{\sin \left(\overrightarrow{X' D'}, \overrightarrow{X' E'}\right)} \times \frac{\sin \left(\overrightarrow{Y' D'}, \overrightarrow{Y' E'}\right)}{\sin \left(\overrightarrow{Y' D'}, \overrightarrow{Y' X'}\right)} = -1.
$$
Since $\left(\overrightarrow{E' D'}, \overrightarrow{E' X'}\right) = \left(\overrightarrow{E' D'}, \overrightarrow{E' B'}\right) = \left(\overrightarrow{A D'}, \overrightarrow{A B'}\right)$ and $\left(\overrightarrow{E' D'}, \overrightarrow{E' Y'}\right) = \left(\overrightarrow{E' D'}, \overrightarrow{E' C'}\right) = \left(\overrightarrow{A D'}, \overrightarrow{A C'}\right) + \pi$, the first fraction is equal to 1.
Moreover, since $D'X'Y'$ is isosceles at $D'$, we have $\left(\overrightarrow{X' D'}, \overrightarrow{X' Y'}\right) = -\left(\overrightarrow{Y' D'}, \overrightarrow{Y' X'}\right)$. Substituting into (1), we conclude that
$$
\sin \left(\overrightarrow{X' D'}, \overrightarrow{X' E'}\right) = \sin \left(\overrightarrow{Y' D'}, \overrightarrow{Y' E'}\right)
$$
which proves that the angles $\widehat{D' X' E'}$ and $\widehat{D' Y' E'}$ are equal or supplementary.
If they were supplementary, we would have $\widehat{X' E' D'} + \widehat{D' X' E'} + \widehat{Y' E' D'} + \widehat{D' Y' E'} = 2\pi$, so the sum of the angles of triangles $D'X'E'$ and $D'Y'E'$ would exceed $2\pi$, which is impossible. Therefore, $\widehat{D' X' E'}$ and $\widehat{D' Y' E'}$ are equal. From (2), this shows that $\left(\overrightarrow{X' D'}, \overrightarrow{X' E'}\right) = \left(\overrightarrow{Y' D'}, \overrightarrow{Y' E'}\right)$, hence the cocyclicity of $D', E', X', Y'$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle. On désigne par $D$ le pied de la bissectrice de $\widehat{B A C}$, et par $E$ le pied de la hauteur issue de $A$. La médiatrice de $[A D]$ rencontre les demi-cercles de diamètres respectifs $[A B]$ et $[A C]$ construits extérieurement à $A B C$, en $X$ et $Y$.
Prouver que les points $X, Y, D, E$ sont cocycliques.
|

On désigne par $M, N$ et $P$ les milieux respectifs de $[A B],[A C]$ et $[A D]$. D'après le théorème des milieux, on a $N, P, M$ alignés et, compte-tenu de ce que $(A P)=(A D)$ est la bissectrice de $\widehat{B A C}$, on a
$$
\frac{M P}{N P}=\frac{B D}{C D}=\frac{A M}{A N}=\frac{A B}{A C}=\frac{M X}{N Y} .
$$
En particulier, il vient $\frac{M P}{M X}=\frac{N P}{N Y}$. En utilisant la loi des sinus dans $M P X$ et $N P Y$, et puisque $\widehat{N P Y}=\widehat{M P X}$, c'est donc que $\sin \widehat{P X M}=\sin \widehat{P Y N}$. (1)
Or, on a clairement $\widehat{P X M}<\widehat{B X A}=90^{\circ}$ et $\widehat{P Y N}<\widehat{A Y C}=90^{\circ}$, donc (1) donne $\widehat{P X M}=\widehat{P Y N}$. Comme $\widehat{M P X}=\widehat{N P Y}$, c'est donc que les triangles $P X M$ et $P Y N$ sont semblables, et que $\widehat{P M X}=\widehat{P N Y}$. (2)
Sans perte de généralité, on peut supposer qu'entre $M$ et $N$, c'est $N$ qui est du même côté que $A$ par rapport à $(X Y)$.
Ainsi (2) conduit à $\widehat{P M A}+\widehat{A M X}=\widehat{P N C}+\widehat{C N Y}$,
d'où $\widehat{C B A}+2 \widehat{A B X}=180^{\circ}-\widehat{B C A}+180^{\circ}-2 \widehat{A C Y}$
et donc
$$
\begin{aligned}
\widehat{A B X}+\widehat{A C Y} & =180^{\circ}-\widehat{A B C}-\widehat{B C A}+90^{\circ}-\widehat{A B X}+90^{\circ}-\widehat{A C Y} \\
& =\widehat{B A C}+\widehat{X A B}+\widehat{C A Y} \\
& =\widehat{X A Y} .
\end{aligned}
$$
Mais, $\widehat{A E B}=\widehat{A E C}=90^{\circ}$ donc $E$ appartient aux cercles de diamètres $[A B]$ et $[A C]$, soit donc aux cercles circonscrits aux triangles $A B X$ et $A C Y$. Par suite, on a $\widehat{A B X}=\widehat{A E X}$ et $\widehat{A C Y}=\widehat{A E Y}$. (4)
De (3) et (4), on déduit que
$$
\widehat{X E Y}=\widehat{X E A}+\widehat{A E Y}=\widehat{A B X}+\widehat{A C Y}=\widehat{X A Y}
$$
D'autre part, puisque $(X Y)$ est la médiatrice de $[A D]$, on a $\widehat{X A Y}=\widehat{X D Y}$, et finalement $\widehat{X E Y}=$ $\widehat{X D Y}$, ce qui conclut.
Autre solution. On applique une inversion $i$ de pôle $A$. Rappelons que les cercles ne passant pas par $A$ sont transformés en des cercles ne passant pas par $A$, que les droites passant par $A$ sont conservées et que les cercles passant par $A$ sont transformés en des droites perpendiculaires à la droite reliant $A$ et le centre du cercle. D'autre part, toute inversion conserve les angles entre deux droites ou cercles sécants.
On en déduit que $i$ transforme le cercle de diamètre $[A B]$ en la perpendiculaire à $\left(A B^{\prime}\right)$ passant par $B^{\prime}$, transforme la droite $(B C)$ en le cercle $\left(A B^{\prime} C^{\prime}\right)$ de sorte que $D^{\prime}$ est le milieu de l'arc $B^{\prime} C^{\prime}$ ne contenant pas $A$ et $E^{\prime}$ est le point diamétralement opposé à $A$. De plus, $i$ envoie la médiatrice de $[A D]$ sur le cercle de centre $D^{\prime}$ passant par $A$. Enfin, comme $E$ sur le cercle de diamètre $[A B]$, les points $E^{\prime}, B, X^{\prime}$ sont alignés et de même $E^{\prime}, C, Y^{\prime}$ sont alignés.
Supposons que les angles en $B$ et en $C$ du triangle $A B C$ sont aigus (le raisonnement est analogue dans le cas contraire). Alors $E^{\prime}$ appartient à l'arc $B^{\prime} C^{\prime}$ ne contenant pas $A$. Quitte à échanger les rôles de $B$ et de $C$, on peut supposer que $E^{\prime}$ appartient à l'arc $C^{\prime} D^{\prime}$ comme sur la figure.

Le fait que $E$ ne se trouve pas sur le même demi-cercle de diamètre $[A B]$ que $X$ implique que $B^{\prime}$ se trouve entre $E^{\prime}$ et $X^{\prime}$. De même, $C^{\prime}$ se trouve entre $E^{\prime}$ et $Y^{\prime}$.
Remarquons d'abord que $\widehat{Y^{\prime} E^{\prime} D^{\prime}}$ et $\widehat{X^{\prime} E^{\prime} D^{\prime}}$ sont supplémentaires puisque $\widehat{Y^{\prime} E^{\prime} D^{\prime}}=\widehat{C^{\prime} E^{\prime} D^{\prime}}=$ $\pi-\widehat{C^{\prime} A D^{\prime}}=\pi-\widehat{D^{\prime} A B^{\prime}}=\pi-\widehat{D^{\prime} E^{\prime} B^{\prime}}=\pi-\widehat{D^{\prime} E^{\prime} X^{\prime}}$.
Appliquons maintenant le théorème de Ceva trigonométrique pour le point $D^{\prime}$ appartenant au triangle $E X^{\prime} Y^{\prime}$.
$$
\frac{\sin \left(\overrightarrow{E^{\prime} D^{\prime}}, \overrightarrow{E^{\prime} X^{\prime}}\right)}{\sin \left(\overrightarrow{E^{\prime} D^{\prime}}, \overrightarrow{E^{\prime} Y^{\prime}}\right)} \times \frac{\sin \left(\overrightarrow{X^{\prime} D^{\prime}}, \overrightarrow{X^{\prime} Y^{\prime}}\right)}{\sin \left(\overrightarrow{X^{\prime} D^{\prime}}, \overrightarrow{X^{\prime} E^{\prime}}\right)} \times \frac{\sin \left(\overrightarrow{Y^{\prime} D^{\prime}}, \overrightarrow{Y^{\prime} E^{\prime}}\right)}{\sin \left(\overrightarrow{Y^{\prime} D^{\prime}}, \overrightarrow{Y^{\prime} X^{\prime}}\right)}=-1 .
$$
Comme $\left(\overrightarrow{E^{\prime} D^{\prime}}, \overrightarrow{E^{\prime} X^{\prime}}\right)=\left(\overrightarrow{E^{\prime} D^{\prime}}, \overrightarrow{E^{\prime} B^{\prime}}\right)=\left(\overrightarrow{A D^{\prime}}, \overrightarrow{A B^{\prime}}\right)$ et $\left(\overrightarrow{E^{\prime} D^{\prime}}, \overrightarrow{E^{\prime} Y^{\prime}}\right)=\left(\overrightarrow{E^{\prime} D^{\prime}}, \overrightarrow{E^{\prime} C^{\prime}}\right)=\left(\overrightarrow{A D^{\prime}}, \overrightarrow{A C^{\prime}}\right)+$ $\pi$, la première fraction est égale à 1 .
De plus, comme $D^{\prime} X^{\prime} Y^{\prime}$ est isocèle en $D^{\prime}$, on a $\left(\overrightarrow{X^{\prime} D^{\prime}}, \overrightarrow{X^{\prime} Y^{\prime}}\right)=-\left(\overrightarrow{Y^{\prime} D^{\prime}}, \overrightarrow{Y^{\prime} X^{\prime}}\right)$. En reportant dans (1), on en conclut que
$$
\sin \left(\overrightarrow{X^{\prime} D^{\prime}}, \overrightarrow{X^{\prime} E^{\prime}}\right)=\sin \left(\overrightarrow{Y^{\prime} D^{\prime}}, \overrightarrow{Y^{\prime} E^{\prime}}\right)
$$
ce qui prouve que les angles $\widehat{D^{\prime} X^{\prime} E^{\prime}}$ et $\widehat{D^{\prime} Y^{\prime} E^{\prime}}$ sont égaux ou supplémentaires.
S'ils étaient supplémentaires, on aurait $\widehat{X^{\prime} E^{\prime} D^{\prime}}+\widehat{D^{\prime} X^{\prime} E^{\prime}}+\widehat{Y^{\prime} E^{\prime} D^{\prime}}+\widehat{D^{\prime} Y^{\prime} E^{\prime}}=2 \pi$, donc la somme des angles des triangles $D^{\prime} X^{\prime} E^{\prime}$ et $D^{\prime} Y^{\prime} E^{\prime}$ dépasserait $2 \pi$, ce qui est impossible. Par conséquent, $\widehat{D^{\prime} X^{\prime} E^{\prime}}$ et $\widehat{D^{\prime} Y^{\prime} E^{\prime}}$ sont égaux. D'après $(2)$, ceci montre que $\left(\overrightarrow{X^{\prime} D^{\prime}}, \overrightarrow{X^{\prime} E^{\prime}}\right)=\left(\overrightarrow{Y^{\prime} D^{\prime}}, \overrightarrow{Y^{\prime} E^{\prime}}\right)$, d'où la cocyclicité de $D^{\prime}, E^{\prime}, X^{\prime}, Y^{\prime}$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2013-2014-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 8.",
"solution_match": "\nSolution de l'exercice 8"
}
|
2610d89b-45e5-5094-8052-2ddfa94841cf
| 607,542
|
Consider a row of cells numbered $0,1, \ldots, k$ from left to right where, for each $i \geqslant 1$, cell number $i$ contains $x_{i}$ tokens. Initially, there are no tokens on cell number 0. Alice and Bob then take turns playing according to the following rules:
- Bob chooses a set $S$ of tokens, not necessarily all on the same cell.
- Alice can then either eliminate all tokens that are not in $S$ but then move each token in $S$ from the cell it occupies to the neighboring cell to its left (such a token thus moves from cell number $i$ to cell number $i-1$), or eliminate all tokens that are in $S$ but then move each token that is not in $S$ from the cell it occupies to the neighboring cell to its left.
Bob wins the game if he manages to bring a token to cell number 0, and Alice wins if she manages to eliminate all the tokens.
1) Prove that Alice has a winning strategy if $\sum_{i=1}^{k} 2^{-i} x_{i}<1$.
2) Is it true that if $\sum_{i=1}^{k} 2^{-i} x_{i} \geqslant 1$ then Bob has a winning strategy?
|
In everything that follows, we can clearly assume that Bob never chooses $S=\emptyset$ or $S$ as the set of all tokens not yet eliminated, otherwise Alice wins immediately. Therefore, the number of tokens strictly decreases after each of Alice's turns, ensuring that the game always ends in a finite number of turns, either by the elimination of all tokens or because one of them has reached position 0. Thus, there will be no draw.
Moreover, since this is a game of perfect information, it is well known that one of the two players has a winning strategy. The question is which one...
1) - Probabilistic approach: Fix a strategy for Bob. Alice will then play randomly. More precisely, at each turn, after Bob has chosen his set $S$ of tokens, Alice flips a fair coin. If it lands Heads, she eliminates the tokens in $S$ (and moves the tokens not in $S$ to the left) and, if it lands Tails, she does the opposite.
For each token $j$, let $X_{j}$ be the random variable equal to 1 if token $j$ is on position 0 at the end of the game, and 0 otherwise.
Let $X=\sum_{j} X_{j}$, the sum being over all the initial tokens.
We note that $X$ represents the total number of tokens that end up on position 0 at the end of the game, and therefore Alice wins if and only if $X<1$.
Let $j$ be one of the initial tokens. At each turn, Bob can choose $S$ such that, if $j$ has not yet been eliminated, we have $j \in S$ or $j \notin S$, but in any case, the probability that $j$ is then moved to the left is equal to $\frac{1}{2}$. If, at the beginning of the game, token $j$ is on position $i$, it reaches position 0 at the end of the game if and only if the first $i$ coin flips all result in moves to the left, which happens with a probability of $\frac{1}{2^{i}}$. Therefore, we have $E\left(X_{j}\right)=\frac{1}{2^{i}}$ for any token $j$.
By linearity of expectation, we have
$$
E(X)=\sum_{j} E\left(X_{j}\right)=\sum_{i=1}^{k} 2^{-i} x_{i}<1
$$
This ensures that the event $[X<1]$ occurs with a non-zero probability. Thus, regardless of Bob's strategy, Alice has a non-zero probability of winning, which proves that Bob does not have a winning strategy. According to our initial remark, it is therefore Alice who has one.
- Deterministic approach: Consider a given moment during the game, just before it is Bob's turn to play, and let $C$ be the resulting configuration. For each $i$, let $y_{i}$ be the number of tokens that are then on position $i$, and define the weight of $C$ by $W(C)=\sum_{i=1}^{k} y_{i} 2^{-i}$.
To link this with the probabilistic approach, we can note that $W(C)=E(Y)$, where $Y$ is the number of tokens that will end up on position 0 if Alice plays the rest of the game, starting from configuration $C$, in the random way described above.
Alice's strategy will then consist of always choosing configurations to minimize the successive weights $W$:
Let $C$ be a configuration for which the game is not yet over, with weight $W=W(C)$, and suppose Bob chooses the set $S$ of tokens.
We denote $W^{+}$ (resp. $W^{-}$) the weight of the configuration obtained if Alice moves the tokens in $S$ to the left (resp. eliminates the tokens in $S$).
For each token $j$, the contribution of $j$ is zero (the token has been eliminated) in one of the sums $W^{+}$ and $W^{-}$, and is twice what it is in $W$ for the other. This being true for each token, we therefore have $W=\frac{1}{2}\left(W^{+}+W^{-}\right)$.
In particular, Alice can then choose a configuration $C^{\prime}$ for which $W\left(C^{\prime}\right) \leqslant W(C)$. Since we start the game with a configuration of weight strictly less than 1, this ensures that, throughout the game, Alice can impose configurations of weight strictly less than 1. This clearly prevents Bob from winning since a token on position 0 alone gives a weight of 1.
2) Suppose $\sum_{i=1}^{k} 2^{-i} x_{i} \geqslant 1$.
We will prove that Bob has a winning strategy. Given our initial remark, it suffices to prove that Alice does not have a winning strategy.
Let $C$ be a configuration for which the game is not yet over. Let $J$ be the set of tokens in $C$.
If $A \subset J$, we denote $C_{A}$ the configuration obtained from $C$ by keeping only the tokens that are in $A$ (without moving them to the left).
Lemma. If $C$ is a configuration such that $W(C) \geqslant 1$, there exists a subset $S$ of $J$ such that
$$
W\left(C_{S}\right) \geqslant \frac{1}{2} \text { and } W\left(C_{\bar{S}}\right) \geqslant \frac{1}{2} \text {. }
$$
Proof of the lemma.
First, we note that if a configuration $C$ satisfies $W(C) \geqslant 1$ then there exists $i$ such that $y_{i} \geqslant 2$. Indeed, in the opposite case, we would have
$$
W(C) \leqslant \sum_{i=1}^{k} 2^{-i}=1-\frac{1}{2^{k}}<1
$$
We reason by induction on the number $n$ of tokens in the configuration:
- If the configuration considered has only two tokens, then, from the above, they are both on the same position. Moreover, if we want $W(C) \geqslant 1$, it is easy to verify that they are actually on position 1. Thus, the subset $S$ formed by one of the two tokens works.
- Let $n \geqslant 3$ and suppose the conclusion is assured for any configuration of weight at least 1 and containing $n-1$ tokens. Let then $C$ be a configuration such that $W(C) \geqslant 1$ and with $n$ tokens.
If $y_{1} \geqslant 2$, a subset $S$ formed by one of the tokens on position 1 works. Otherwise, let $i \geqslant 2$ such that $y_{i} \geqslant 2$ and let $A$ and $B$ be two tokens on position $i$. We then consider the configuration $C^{\prime}$ identical to $C$ except for $A$ and $B$ which are replaced by a single token $X$ on position $i-1$. Clearly, $W\left(C^{\prime}\right)=W(C) \geqslant 1$, and $C^{\prime}$ contains only $n-1$ tokens. By the induction hypothesis, there exists a subset $S^{\prime}$ of the set of tokens in $C^{\prime}$ such that $W\left(C_{S^{\prime}}^{\prime}\right) \geqslant \frac{1}{2}$ and $W\left(C_{\overline{S^{\prime}}}^{\prime}\right) \geqslant \frac{1}{2}$.
It is then easy to verify that if $S$ is the subset formed by the tokens in $S^{\prime}$, and by replacing $X$ with $A$ and $B$, we have $W\left(C_{S}\right) \geqslant \frac{1}{2}$ and $W\left(C_{\bar{S}}\right) \geqslant \frac{1}{2}$, which completes the induction and the proof.
Let's return to the game. Once Bob has chosen a set $S$ of tokens, whatever Alice's choice, it will lead to a configuration whose weight will be twice that of the configuration formed only by the tokens that are not eliminated. The lemma ensures that from a configuration of weight at least 1, Bob can choose $S$ such that after Alice's choice, we obtain a configuration of weight at least 1. Since the initial configuration is assumed to have a weight of at least 1, Bob can therefore ensure that the entire game takes place on such configurations. This clearly prevents Alice from winning (she is trying to obtain a configuration of weight 0), hence the conclusion.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
On considère une rangée de cases numérotées $0,1, \ldots, k$ de gauche à droite où, pour chaque $i \geqslant 1$, la case numéro $i$ contient $x_{i}$ jetons. Il n'y a initialement aucun jeton sur la case numéro 0 . A tour de rôle, Alice et Bob jouent alors selon les règles suivantes :
- Bob choisit un ensemble $S$ de jetons, pas forcément tous sur la même case.
- Alice peut ensuite soit éliminer tous les jetons qui ne sont pas dans $S$ mais alors déplacer chaque jeton de $S$ de la case qu'il occupe à la case voisine à sa gauche (un tel jeton passe donc d'une case numéro $i$ à la case numéro $i-1$, soit éliminer tous les jetons qui sont dans $S$ mais alors déplacer chaque jeton qui n'est pas dans $S$ de la case qu'il occupe à la case voisine à sa gauche.
Bob gagne la partie s'il arrive à amener un jeton sur la case numéro 0, et Alice gagne si elle arrive à éliminer tous les jetons.
1) Prouver qu'Alice possède une stratégie gagnante si $\sum_{i=1}^{k} 2^{-i} x_{i}<1$.
2) Est-il vrai que si $\sum_{i=1}^{k} 2^{-i} x_{i} \geqslant 1$ alors Bob possède une stratégie gagnante?
|
Dans tout ce qui suit, on peut clairement supposer que Bob ne choisit jamais $S=\emptyset$ ou $S$ l'ensemble de tous les jetons non encore éliminés, sans quoi Alice gagne immédiatement. Du coup, le nombre de jetons diminue strictement après chaque fois qu'Alice joue, ce qui assure que le jeu se termine toujours en un nombre fini de tours, soit par élimination de tous les jetons, soit parce que l'un d'eux aura atteint la case numéro 0 . Ainsi, il n'y aura pas de partie nulle.
De plus, s'agissant d'un jeu à information parfaite, il est bien connu que l'un des deux joueurs a alors une stratégie gagnante. Reste à savoir lequel...
1) - Approche probabiliste : Fixons une stratégie pour Bob. Alice va alors jouer de façon aléatoire. Plus précisément, à chaque tour, après que Bob ait choisi son ensemble $S$ de jetons, Alice lance une pièce équilibrée. Si elle obtient Face, elle élimine les jetons de $S$ (et déplace donc ceux qui ne sont pas dans $S$ vers la gauche) et, si elle obtient Pile, elle fait le contraire.
Pour chaque jeton $j$, on note $X_{j}$ la variable aléatoire égale à 1 si le jeton $j$ est sur la case numéro 0 à la fin de la partie, et égale à 0 sinon.
Soit enfin $X=\sum_{j} X_{j}$, la somme portant sur l'ensemble des jetons de départ.
On remarque que $X$ représente le nombre total de jetons qui arrivent sur la case numéro 0 à la fin du jeu, et donc qu'Alice gagne si et seulement si $X<1$.
Soit $j$ un des jetons de départ. A chaque tour, Bob peut choisir $S$ de sorte que, si $j$ n'a pas encore été éliminé, on ait $j \in S$ ou $j \notin S$ mais, quoi qu'il en soit, la probabilité que $j$ soit alors déplacé vers la gauche est égale à $\frac{1}{2}$. Si, au début du jeu, le jeton $j$ se trouve sur la case numéro $i$, il arrive sur la case numéro 0 à la fin du jeu si et seulement si les $i$ premiers lancers de pièces ont tous conduit à des déplacements vers la gauche, ce qui arrive donc avec une probabilité $\frac{1}{2^{i}}$. Par suite, on a $E\left(X_{j}\right)=\frac{1}{2^{i}}$ pour tout jeton $j$.
Par linéarité de l'espérance, on a donc
$$
E(X)=\sum_{j} E\left(X_{j}\right)=\sum_{i=1}^{k} 2^{-i} x_{i}<1
$$
Cela assure que l'événement $[X<1]$ se réalise avec une probabilité non nulle. Ainsi, quelle que soit la stratégie de Bob, Alice a une probabilité non nulle de gagner, ce qui prouve que Bob n'a pas de stratégie gagnante. D'après notre remarque initiale, c'est donc Alice qui en possède une.
- Approche déterministe : Plaçons nous à un instant donné au cours de la partie, juste avant que ce soit à Bob de jouer, et considérons la configuration $C$ obtenue. Pour chaque $i$, on note $y_{i}$ le nombre de jetons qui sont alors sur la case numéro $i$, et on définit le poids de $C$ par $W(C)=\sum_{i=1}^{k} y_{i} 2^{-i}$.
Pour faire le lien avec l'approche probabiliste, on peut noter que $W(C)=E(Y)$, où $Y$ est le nombre de jetons qui vont arriver sur la case numéro 0 si Alice joue le reste de la partie, depuis la configuration $C$, de la façon aléatoire ci-dessus.
La stratégie d'Alice va consister alors à toujours choisir des configurations afin de minimiser les poids $W$ successifs :
Soit donc $C$ une configuration pour laquelle le jeu ne soit pas déjà terminé, de poids $W=W(C)$, et supposons que Bob choisisse l'ensemble $S$ de jetons.
On note $W^{+}$(resp. $W^{-}$) le poids de la configuration obtenue si Alice déplace les jetons de $S$ vers la gauche (resp. élimine les jetons de $S$ ).
Pour chaque jeton $j$, la contribution de $j$ est nulle ( $j$ a été éliminé) dans l'une des sommes $W^{+}$et $W^{-}$, et vaut le double de ce qu'elle est dans $W$ pour l'autre. Ceci étant vrai pour chaque jeton, on a donc $W=\frac{1}{2}\left(W^{+}+W^{-}\right)$.
En particulier, Alice peut alors choisir une configuration $C^{\prime}$ pour laquelle $W\left(C^{\prime}\right) \leqslant W(C)$. Or, puisqu'on débute le jeu avec une configuration de poids strictement inférieur à 1 , cela assure que, tout au long du jeu, Alice peut imposer des configurations de poids strictement inférieurs à 1 . Ceci empêche clairement Bob de gagner puisqu'un jeton sur la case numéro 0 donne, à lui seul, un poids égal à 1.
2) Supposons que $\sum_{i=1}^{k} 2^{-i} x_{i} \geqslant 1$.
On va prouver que Bob possède une stratégie gagnante. Compte-tenu de notre remarque préliminaire, il suffit de prouver qu'Alice n'a pas de stratégie gagnante.
Soit $C$ une configuration pour laquelle le jeu n'est pas encore terminé. On note $J$ l'ensemble des jetons de $C$.
Si $A \subset J$, on note $C_{A}$ la configuration obtenue à partir de $C$ en ne gardant que les jetons qui sont dans $A$ (sans les déplacer vers la gauche).
Lemme. Si $C$ est une configuration telle que $W(C) \geqslant 1$, il existe une partie $S$ de $J$ telle que
$$
W\left(C_{S}\right) \geqslant \frac{1}{2} \text { et } W\left(C_{\bar{S}}\right) \geqslant \frac{1}{2} \text {. }
$$
Preuve du lemme.
Tout d'abord, on remarque que si une configuration $C$ vérifie $W(C) \geqslant 1$ alors il existe $i$ tel que $y_{i} \geqslant 2$. En effet, dans le cas contraire, on aurait
$$
W(C) \leqslant \sum_{i=1}^{k} 2^{-i}=1-\frac{1}{2^{k}}<1
$$
On raisonne par récurrence sur le nombre $n$ de jetons de la configuration :
- Si la configuration considérée ne possède que deux jetons alors, d'après ci-dessus, ils sont tous les deux sur la même case. De plus, si l'on veut que $W(C) \geqslant 1$, il est facile de vérifier qu'ils sont en fait sur la case numéro 1. Ainsi, la partie $S$ formée par l'un des deux jetons convient.
- Soit $n \geqslant 3$ et supposons la conclusion assurée pour toute configuration de poids supérieur ou égal à 1 , et contenant $n-1$ jetons. Soit alors $C$ une configuration telle que $W(C) \geqslant 1$ et à $n$ jetons.
Si $y_{1} \geqslant 2$, une partie $S$ formée uniquement d'un des jetons qui sont sur la case numéro 1 convient. Sinon, soit $i \geqslant 2$ tel que $y_{i} \geqslant 2$ et soit $A$ et $B$ deux jetons qui sont sur la case numéro $i$. On considère alors la configuration $C^{\prime}$ identique à $C$ sauf pour $A$ et $B$ qui sont remplacés par un seul jeton $X$, placé sur la case numéro $i-1$. On a clairement $W\left(C^{\prime}\right)=W(C) \geqslant 1$, et $C^{\prime}$ ne contient que $n-1$ jetons. D'après l'hypothèse de récurrence, il existe donc une partie $S^{\prime}$ de l'ensemble des jetons de $C^{\prime}$ telle que $W\left(C_{S^{\prime}}^{\prime}\right) \geqslant \frac{1}{2}$ et $W\left(C_{\overline{S^{\prime}}}^{\prime}\right) \geqslant \frac{1}{2}$.
Il est alors facile de vérifier que si $S$ est la partie formée des jetons de $S^{\prime}$, et en remplaçant $X$ par $A$ et $B$, on a bien $W\left(C_{S}\right) \geqslant \frac{1}{2}$ et $W\left(C_{\bar{S}}\right) \geqslant \frac{1}{2}$, ce qui achève la récurrence et la preuve.
Revenons au jeu. Une fois que Bob a choisi un ensemble $S$ de jetons, quel que soit le choix d'Alice, celui-ci conduira à une configuration dont le poids sera le double de celui de la configuration formée uniquement par les jetons qui ne seront pas éliminés. Le lemme assure donc qu'à partir d'une configuration de poids supérieur ou égal à 1 , Bob peut choisir $S$ de sorte qu'après le choix d'Alice, on obtienne une configuration de poids supérieur ou égal à 1. Puisque la configuration initiale est supposée de poids supérieur ou égal à 1, Bob peut donc imposer que toute la partie se déroule sur de telles configurations. Cela empêche clairement Alice de gagner (elle cherche à obtenir une configuration de poids nul), d'où la conclusion.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2013-2014-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 9.",
"solution_match": "## Solution de l'exercice 9"
}
|
18ff3b7b-1bcb-595d-8506-4106577b3b26
| 607,543
|
We take 1008 distinct integers between 1 and 2014 (inclusive).
(i) Show that there exist three integers $a, b, c$ such that the gcd of $a$ and $b$ divides $c$ (the gcd or Greatest Common Divisor of two integers is the largest natural number that divides both of them).
(ii) Show that there exist three integers $a, b, c$ such that the gcd of $a$ and $b$ does not divide $c$.
|
(i) Group the integers from 1 to 2014 into pairs of consecutive integers: (1, 2), (3, 4),..., (2013, 2014). There are 1007 such pairs. By the pigeonhole principle, if we choose 1008 integers, there will be two from the same pair, \(a\) and \(b\), with \(b = a + 1\). Their gcd is 1 (since it divides their difference), so it divides any of the other 1006 numbers, which we can take as \(c\).
(ii) There are 1007 even integers available. Therefore, among 1008 numbers, there must be at least one odd number. If there are at least two even numbers among the 1008, let's denote them as \(a\) and \(b\). Let \(c\) be an odd number among the 1008. The \(\operatorname{gcd}\) of \(a\) and \(b\) is a multiple of 2, since 2 divides both \(a\) and \(b\). (In fact, the \(\operatorname{gcd}\) of \(a\) and \(b\) is 2 times the \(\operatorname{gcd}\) of \(a / 2\) and \(b / 2\)). Therefore, if it divides \(c\), then 2 divides \(c\), which is absurd.
If there are fewer than 2 even numbers among the 1008, it means we have taken the 1007 odd numbers, plus one even number, denoted as \(c\). We can find triplets in at least two ways.
- Short solution: we have the triplet \((3, 9, 1)\), and it is clear that \(\operatorname{gcd}(3, 9)\) does not divide 1.
- Less short solution: if \(c\) is divisible by all the gcds of pairs of odd integers between 1 and 2013, it will have many prime divisors: it will be divisible by the gcd of 3 and 9, the gcd of 5 and 15, the gcd of 7 and 21, the gcd of 11 and 33, etc. So it is divisible by \(3, 5, 7, 11\) already (and by 2, since it is even). The least common multiple of these numbers is their product (since they have no common factors). It is \(2 \times 3 \times 5 \times 7 \times 11 = 2310\), so \(c > 2014\), which is not possible. Therefore, there exist two odd numbers \(a\) and \(b\) such that their gcd does not divide \(c\).
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
On prend 1008 entiers distincts compris (au sens large) entre 1 et 2014.
(i) Montrer qu'il existe trois entiers $a, b, c$ tels que le pgcd de $a$ et $b$ divise $c$ (le pgcd ou Plus Grand Diviseur Commun de deux entiers est le plus grand entier naturel qui les divise tous les deux).
(ii) Montrer qu'il existe trois entiers $a, b, c$ tels que le pgcd de $a$ et $b$ ne divise pas $c$.
|
(i) Groupons les entiers de 1 à 2014 en paires d'entiers consécutifs : (1, 2), (3, 4),..., (2013, 2014). Il y en a 1007. Par le principe des tiroirs, si on choisit 1008 entiers, il y en aura deux d'une même paire, $a$ et $b$, avec $b=a+1$. Leur pgcd vaut 1 (puisqu'il divise leur différence), donc divise n'importe lequel des 1006 autres nombres, que l'on peut prendre pour $c$.
(ii) Il y a 1007 entiers pairs prenables. Donc parmi 1008 nombres, il y a forcément un impair. S'il y a deux nombres pairs au moins parmi les 1008, notons-les $a$ et $b$. Soit $c$ un nombre impair parmi les 1008. Le $\operatorname{pgcd}$ de $a$ et $b$ est multiple de 2 , puisque 2 divise à la fois $a$ et $b$. (en fait, le $\operatorname{pgcd}$ de $a$ et $b$ vaut 2 fois le $\operatorname{pgcd}$ de $a / 2$ et $b / 2$ ). Donc s'il divise $c$, alors 2 divise $c$, ce qui est absurde.
S'il y a moins de 2 nombres pairs parmi les 1008, ça veut dire qu'on a pris les 1007 impairs, ainsi qu'un nombre pair, noté $c$. On peut trouver des triplets d'au moins deux manières.
- Solution courte : on dispose du triplet $(3,9,1)$, et il est clair que $\operatorname{pgcd}(3,9)$ ne divise pas 1.
- Solution moins courte : si $c$ est divisible par tous les pgcd de couples d'entiers impairs entre 1 et 2013, ça va lui faire beaucoup de diviseurs premiers : il sera divisible par le pgcd de 3 et 9 , le pgcd de 5 et 15, celui de 7 et 21 , celui de 11 et 33 , etc. Donc il est divisible par $3,5,7,11$ déjà (et par 2 , puisqu'il est pair). Le plus petit multiple commun de ces nombres est leur produit (puisqu'ils n'ont deux-à-deux aucun facteur commun). Il vaut $2 \times 3 \times 5 \times 7 \times 11=2310$ donc $c>2014$, ce qui n'est pas possible. Donc il existe deux nombres impairs $a$ et $b$ tels que leur pged ne divise pas $c$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 2",
"solution_match": "\nSolution "
}
|
cee30a4e-27a8-5ee1-a20e-2ed524455248
| 607,545
|
Let $n$ be a strictly positive integer. Consider $2 n+1$ distinct integers ranging from $-2 n+1$ to $2 n-1$ inclusive. Show that one can choose 3 of them whose sum is zero.
|
We reason by induction on $n$.
Initialization: For $n=1$, we take $2 n+1=3$ distinct integers from $-1,0,1$, so these three integers. Their sum is indeed zero.
Hereditary: Suppose the statement is true at rank $n$: if we take $2 n+1$ distinct integers between $-2 n+1$ and $2 n-1$ (inclusive), then we can choose 3 of them whose sum is zero. Now, we want to show that among $2 n+3$ distinct integers between $-2 n-1$ and $2 n+1$, there are always 3 whose sum is zero.
If among these $2 n+3$ integers, there are $2 n+1$ between $-2 n+1$ and $2 n-1$, then we are done by the induction hypothesis. We can therefore assume that at least 3 of these integers are among $\{-2 n-1, -2 n, 2 n, 2 n+1\}$. By symmetry between the positives and the negatives, we can assume that we have $2 n$ and $2 n+1$, as well as $-2 n-1$ or $-2 n$, so we can assume that we do not have 0, since $0+2 n+(-2 n)=0+(2 n+1)+(-2 n-1)=0$ and we would then have a triplet with a sum of zero. Now, consider the $n$ pairs
$$
\{-k, -2 n-1+k\}, \quad 1 \leq k \leq n
$$
if one of them is included in our selection of $2 n+3$ integers, then we still have three numbers with a sum of zero: $-k+(-2 n-1+k)+(2 n+1)=0$ and we are done. Suppose, therefore, that our selection contains at most one element from these $n$ pairs, so there are at least $n+1$ numbers left to choose from $(\{1, \ldots, 2 n-1\}$ and $-2 n-1$). We set $A=\{1, \ldots, 2 n-1\}$. We distinguish 2 cases.
- If we have taken $-2 n-1$, we must take at least $n$ elements from $A$. This time we look at the $n$ pairs
$$
\{k, 2 n+1-k\}, \quad 1 \leq k \leq n
$$
If one of them is complete, we have a triplet with a sum of zero with $-2 n-1$. We assumed at the beginning that $2 n$ was taken, so if we take $1$, $\{1, 2 n\}$ is complete. Otherwise, we take $n$ numbers from the remaining $n-1$ pairs, so by the pigeonhole principle, we have a complete pair.
- If we have not taken $-2 n-1$, we must take at least $n$ elements from $A$. And we have taken $-2 n$ according to the beginning of the reasoning. And $A$ can be decomposed into $n-1$ pairs
$$
\{k, 2 n-k\}, 1 \leq k \leq n-1
$$
Again, by the pigeonhole principle, we must take a complete pair, giving a triplet with a sum of zero with $-2 n$.
This closes the induction.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Soit $n$ un entier strictement positif. On considère $2 n+1$ entiers distincts compris au sens large entre $-2 n+1$ et $2 n-1$. Montrer qu'on peut en choisir 3 dont la somme soit nulle.
|
On raisonne par récurrence sur $n$.
Initialisation : Pour $n=1$, on prend $2 n+1=3$ entiers distincts parmi $-1,0,1$, donc ces trois entiers. Leur somme est bien nulle.
Hérédité : Supposons l'énoncé vrai au rang $n$ : si on prend $2 n+1$ entiers distincts compris au sens large entre $-2 n+1$ et $2 n-1$, alors on peut en choisir 3 dont la somme soit nulle. Maintenant, on veut montrer que parmi $2 n+3$ entiers distincts entre $-2 n-1$ et $2 n+1$, il y en a toujours 3 de somme nulle.
Si parmi ces $2 n+3$ entiers, il y en a $2 n+1$ entre $-2 n+1$ et $2 n-1$, alors c'est gagné par hypothèse de récurrence. On peut donc supposer que 3 au moins de ces entiers sont parmi $\{-2 n-1,-2 n, 2 n, 2 n+1\}$. Par symétrie entre les positifs et les négatifs, on peut supposer qu'on dispose de $2 n$ et $2 n+1$, ainsi que de $-2 n-1$ ou $-2 n$, donc on peut supposer qu'on ne dispose pas de 0 , puisque $0+2 n+(-2 n)=0+(2 n+1)+(-2 n-1)=0$ et on aurait alors un triplet de somme nulle. Maintenant, considérons les $n$ paires
$$
\{-k,-2 n-1+k\}, \quad 1 \leq k \leq n
$$
si l'une d'elles est incluse dans notre sélection de $2 n+3$ entiers, alors on a encore trois nombres de somme nulle : $-k+(-2 n-1+k)+(2 n+1)=0$ et on a terminé. Supposons donc que notre sélection ne contienne qu'au plus un élément de ces $n$ paires, donc il reste au moins $n+1$ nombres à choisir parmi $(\{1, \ldots, 2 n-1\}$ et $-2 n-1$ ). On pose $A=\{1, \ldots, 2 n-1\}$. On distingue 2 cas.
- Si on a pris $-2 n-1$, on doit prendre au moins $n$ éléments de $A$. On regarde cette fois les $n$ paires
$$
\{k, 2 n+1-k\}, \quad 1 \leq k \leq n
$$
Si l'une d'elles est complète, on a un triplet à somme nulle avec $-2 n-1$. On a supposé au début que $2 n$ était pris, donc si on prend $1,\{1,2 n\}$ est complète. Sinon on prend $n$ nombres dans les $n-1$ paires restantes, donc par principe des tiroirs, on a une paire complète.
- Si on n'a pas pris $-2 n-1$, on doit prendre au moins $n$ éléments de $A$. Et on a pris $-2 n$ d'après le début du raisonnement. Et $A$ peut se découper en $n-1$ paires
$$
\{k, 2 n-k\}, 1 \leq k \leq n-1
$$
De nouveau, par le principe des tiroirs on doit prendre une paire complète, donnant un triplet à somme nulle avec $-2 n$.
Ceci clôt la récurrence.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 4",
"solution_match": "\nSolution "
}
|
af546060-3f30-5e74-83b7-7f4d11ee4b9d
| 607,547
|
Consider 6 points in the plane, arranged such that the triangle formed by any three of them has three sides of distinct lengths. Show that there exists a triangle for which the shortest side is also the longest side of another triangle.
|
We color the shortest side of each triangle in red. It is sufficient to show that we have a red triangle. Let's call the points $P_{1}, \ldots, P_{6}$. Among the five segments $P_{1} P_{2}, P_{1} P_{3}, P_{1} P_{4}, P_{1} P_{5}, P_{1} P_{6}$ having $P_{1}$ as an endpoint, there are at least 3 red or at least 3 uncolored segments.
- Suppose there are 3 red segments, say $P_{1} P_{2}, P_{1} P_{3}$, and $P_{1} P_{4}$. The triangle $P_{2} P_{3} P_{4}$ has at least one red side, say $P_{2} P_{3}$, so the triangle $P_{1} P_{2} P_{3}$ is red.
- Suppose there are 3 uncolored segments, say $P_{1} P_{2}, P_{1} P_{3}$, and $P_{1} P_{4}$. Each of the three triangles $P_{1} P_{2} P_{3}$, $P_{1} P_{3} P_{4}$, $P_{1} P_{4} P_{2}$ has at least one red side, and this side is not one of those having $P_{1}$ as an endpoint, so $P_{2} P_{3}, P_{3} P_{4}, P_{4} P_{2}$ are red. Thus, the triangle $P_{2} P_{3} P_{4}$ is red.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
On considère 6 points du plan, disposés de telle sorte que le triangle formé par trois quelconques d'entre eux ait trois côtés de longueurs distinctes. Montrer qu'il existe un triangle dont le plus court côté est également le côté le plus long d'un autre triangle.
|
On colorie en rouge le plus court côté de chaque triangle. Il suffit de montrer qu'on a un triangle rouge. Appelons $P_{1}, \ldots, P_{6}$ les points. Parmi les cinq segments $P_{1} P_{2}, P_{1} P_{3}, P_{1} P_{4}, P_{1} P_{5}, P_{1} P_{6}$ ayant $P_{1}$ pour extrémité, il y en a au moins 3 rouges ou bien au moins 3 non coloriés.
- Supposons qu'il y en ait 3 rouges, disons $P_{1} P_{2}, P_{1} P_{3}$ et $P_{1} P_{4}$. Le triangle $P_{2} P_{3} P_{4}$ a au moins un côté rouge, disons $P_{2} P_{3}$, donc le triangle $P_{1} P_{2} P_{3}$ est rouge.
- Supposons qu'il y en ait 3 non coloriées, disons $P_{1} P_{2}, P_{1} P_{3}$ et $P_{1} P_{4}$. Chacun des trois triangles $P_{1} P_{2} P_{3}$, $P_{1} P_{3} P_{4}, P_{1} P_{4} P_{2}$ a au moins un côté rouge, et ce côté n'est pas l'un de ceux ayant $P_{1}$ pour extrémité, donc $P_{2} P_{3}, P_{3} P_{4}, P_{4} P_{2}$ sont rouges. Ainsi, le triangle $P_{2} P_{3} P_{4}$ est rouge.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 5",
"solution_match": "\nSolution "
}
|
2d845ac2-6177-57ac-bc73-3eceecdc1922
| 607,548
|
Consider $n^{2}+2 n+1$ points in a square of side $n$. Show that three of them are the vertices of a triangle (possibly degenerate) with area at most $1 / 2$.
We are given $n^{2}+2 n+1$ points in a square of side $n$. We need to show that there exist three points among them that form a triangle (which could be degenerate) with an area of at most $1 / 2$.
To solve this, we can use the pigeonhole principle. Divide the square into smaller squares of side length 1. Since the side length of the original square is $n$, it can be divided into $n^2$ smaller squares.
Each of these smaller squares has an area of 1. According to the pigeonhole principle, if we have $n^2 + 2n + 1$ points and $n^2$ smaller squares, at least one of these smaller squares must contain at least:
\[
\left\lceil \frac{n^2 + 2n + 1}{n^2} \right\rceil = \left\lceil 1 + \frac{2n + 1}{n^2} \right\rceil = \left\lceil 1 + \frac{2}{n} + \frac{1}{n^2} \right\rceil = 2
\]
points. This means that at least one of the smaller squares contains at least 2 points.
Now, consider the smallest square that contains at least 2 points. If this square contains exactly 2 points, we can choose these 2 points and any other point from the remaining points in the square to form a triangle. The area of this triangle will be at most the area of the smallest square, which is 1.
However, we need to show that the area of the triangle can be at most $1/2$. To do this, consider the following:
1. If the smallest square contains exactly 2 points, we can choose these 2 points and any other point from the remaining points in the square to form a triangle. The maximum area of a triangle formed by any 3 points in a unit square is $1/2$ (this can be shown by considering the maximum possible base and height within the unit square).
2. If the smallest square contains more than 2 points, we can choose any 3 points from these points to form a triangle. The area of this triangle will still be at most $1/2$.
Therefore, in any case, we can always find three points that form a triangle with an area of at most $1/2$.
Thus, we have shown that three of the points are the vertices of a triangle (possibly degenerate) with an area at most $1/2$.
\[
\boxed{\frac{1}{2}}
\]
|
We reason about the convex hull of the $(n+1)^{2}$ points: if it contains many points, there will be 3 adjacent vertices of this hull close enough to form a triangle of small area. If it does not contain many, we triangulate it and look at the many points within the small triangles to form a sufficiently small one.
Concretely, here is a proof: Let $E$ be the convex hull of our points. It is easily verified that its perimeter is less than that of the square, namely $4 n$. If $E$ has at least $4 n$ vertices, and thus as many sides, there exist two consecutive sides $c_{1}$ and $c_{2}$ such that $c_{1}+c_{2} \leq 2$ and thus $c_{1} c_{2} \leq 1$ by the arithmetic-geometric inequality. If $h$ is the height relative to $c_{1}$ in the triangle formed by the endpoints of $c_{1}$ and $c_{2}$, $h \leq c_{2}$, so the area of the triangle is at most $1 / 2$.
If $E$ has $s \leq 4 n-1$ vertices, we triangulate it into $s-2$ triangles. Now, take a remaining point and connect it to the vertices of the triangle in which it lies (or of the triangles if it lies on the common side of two triangles of the triangulation). We take another remaining point and connect it in the same way to the vertices of the triangles of the new triangulation in which it lies. We continue this process until all points are integrated into the triangulation. Thus, we have obtained what is called a triangulation of our set of points. We initially had $s-2$ triangles, and we added at least 2 at each step (or 3), so we have at least $s-2+2\left((n+1)^{2}-s\right) \geq 2 n^{2}+4 n-1-s \geq 2 n^{2}$ disjoint triangles, so one of them has an area of at most $1 / 2$.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
On considère $n^{2}+2 n+1$ points dans un carré de côté $n$. Montrer que trois d'entre eux sont les sommets d'un triangle (éventuellement dégénéré) d'aire au plus $1 / 2$.
|
On raisonne sur l'enveloppe convexe des $(n+1)^{2}$ points : si elle contient beaucoup de points, il y aura 3 sommets voisins de cette enveloppe assez proches pour faire un triangle d'aire petite. Si elle n'en contient pas beaucoup, on la triangule et on regarde les nombreux points dans les petits triangles pour en former un suffisamment petit.
Concrètement, voici une démonstration : Soit $E$ l'enveloppe convexe de nos points. On vérifie aisément que son périmètre est inférieur à celui du carré, à savoir $4 n$. Si $E$ a au moins $4 n$ sommets, donc autant de côtés, il existe deux côtés consécutifs $c_{1}$ et $c_{2}$ vérifiant $c_{1}+c_{2} \leq 2$ donc $c_{1} c_{2} \leq 1$ par inégalité arithméticogéométrique. Si $h$ est la hauteur relative à $c_{1}$ dans le triangle formé par les extrémités de $c_{1}$ et $c_{2}, h \leq c_{2}$, donc l'aire du triangle est bien d'au plus $1 / 2$.
Si $E$ a $s \leq 4 n-1$ sommets, on la triangule en $s-2$ triangles. . Maintenant, prenons un point restant et relions-le aux sommets du triangle dans lequel il se trouve (ou des triangles s'il est sur le côté commun de deux triangles de la triangulation). On prend un autre point restant et on le relie de même aux sommets des triangles de la nouvelle triangulation dans lesquels il se trouve. On continue ainsi jusqu'à ce que tous les points soient intégrés à la triangulation. Ainsi, on a obtenu ce qu'on appelle une triangulation de notre ensemble de points. On avait $s-2$ triangles initialement, on en a rajouté au moins 2 à chaque étape (voire
3), donc on a au moins $s-2+2\left((n+1)^{2}-s\right) \geq 2 n^{2}+4 n-1-s \geq 2 n^{2}$ triangles disjoints, donc l'un d'eux est d'aire au plus $1 / 2$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 7",
"solution_match": "\nSolution "
}
|
e732a909-1438-54ee-8316-910d2448fe6d
| 607,550
|
We have $n$ tokens each bearing an integer number (which can be negative). If we find among them two tokens bearing the same number $m$, we remove them and replace them with one token bearing the number $m-1$, and another bearing the number $m+1$. Show that after a finite number of such changes, all tokens will bear distinct numbers.
|
We start by showing the following lemma:
Let $m_{0}$ be the smallest of the token numbers at the beginning. We denote $m_{1}^{(k)}, \ldots, m_{j_{k}}^{(k)}$ the numbers less than or equal to $m_{0}$ carried by tokens after $k$ changes, counted with multiplicity and arranged in decreasing order so that $m_{j_{k}}^{(k)} \leq \ldots \leq m_{1}^{(k)} \leq m_{0}^{(k)}=m_{0}$. Then for all $i \in\left\{0, \ldots, j_{k}-1\right\}$, we have $m_{i+1}^{(k)}-m_{i}^{(k)} \leq 2$.
Proof: We reason by induction on $k$. The case $k=0$ is clear.
Suppose the result is true for some $k$. At the $(k+1)$-th change, if we replace two tokens carrying a number strictly greater than $m_{0}$, none of the $m_{i}^{(k)}$ change, so the property is still satisfied. Suppose now that we replace two tokens carrying the number $m_{i}^{(k)}=m_{i+1}^{(k)}=m$. Then the sequence $\left(m_{i}^{(k+1)}\right)$ is obtained from the sequence $\left(m_{i}^{(k)}\right)$ by replacing two occurrences of $m$ with one occurrence of $m-1$ and one occurrence of $m+1$. The difference between these last two is exactly 2, so even if there are still terms equal to $m$, their distance to the terms around them will be less than or equal to 1. The distance between $m-1$ and the next term is strictly less than the distance between $m$ and the same next term, hence less than 2 by the induction hypothesis. As for $m+1$, we have two cases to distinguish. Either $m=m_{0}$ and then $m+1$ is strictly greater than $m_{0}$ and no longer interests us. Or $m<m_{0}$, and then the distance between $m+1$ and the previous term is less than the distance between $m$ and the same next term, hence less than 2 by the induction hypothesis.
Consequence of the lemma: all numbers carried by tokens are greater than or equal to $m_{0}-2 n$ at any time. By adding $2 n-m_{0}+1$ to all the numbers at the start, which does not change the exercise, we can therefore assume that they are all strictly positive at any time.
We then denote $P_{k}$ the product of the numbers of all the tokens after $k$ changes. From what we have just shown, $P_{k}$ is a strictly positive integer for all $k$. Suppose the $(k+1)$-th change consists in replacing two tokens carrying the number $m$ with one token carrying the number $m-1$ and one token carrying the number $m+1$. Then $P_{k}$ can be written as $m^{2} c$ with $c>0$, and $P_{k+1}$ can be written as
$$
P_{k+1}=(m-1)(m+1) c=\left(m^{2}-1\right) c<m^{2} c=P_{k}
$$
Thus, the sequence of $\left(P_{k}\right)$ is a strictly decreasing sequence of strictly positive integers, it is therefore finite, that is, we necessarily reach a point where no change is possible.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
On dispose de $n$ jetons portant chacun un numéro entier (qui peut être négatif). Si on trouve parmi eux deux jetons portant le même numéro $m$, on les enlève et on met à leur place un jeton portant le numéro $m-1$, et un autre portant le numéro $m+1$. Montrer qu'au bout d'un nombre fini de tels changements, tous les jetons porteront des numéros distincts.
|
On commence par montrer le lemme suivant:
Soit $m_{0}$ le plus petit des numéros des jetons au début. On note $m_{1}^{(k)}, \ldots, m_{j_{k}}^{(k)}$ les numéros inférieurs ou égaux à $m_{0}$ qui sont portés par des jetons après $k$ changements, comptés avec multiplicité et rangés par ordre décroissant de sorte que $m_{j_{k}}^{(k)} \leq \ldots \leq m_{1}^{(k)} \leq m_{0}^{(k)}=m_{0}$. Alors pour tout $i \in\left\{0, \ldots, j_{k}-1\right\}$, on a $m_{i+1}^{(k)}-m_{i}^{(k)} \leq 2$.
Démonstration : on raisonne par récurrence sur $k$. Le cas $k=0$ est clair.
Supposons que le résultat soit vérifié pour un certain $k . \mathrm{Au}(k+1)$-ème changement, si nous remplaçons deux jetons portant un numéro strictement plus grand que $m_{0}$, aucun des $m_{i}^{(k)}$ ne change, donc la propriété est toujours vérifiée. Supposons maintenant que nous remplaçons deux jetons portant un numéro $m_{i}^{(k)}=$ $m_{i+1}^{(k)}=m$. Alors la suite $\left(m_{i}^{(k+1)}\right)$ s'obtient à partir de la suite $\left(m_{i}^{(k)}\right)$ en remplaçant deux occurrences de $m$ par une occurrence de $m-1$ et une occurrence de $m+1$. La différence entre ces dernières est exactement 2 , donc même s'il reste encore des termes égaux à $m$, leur distance aux termes autour d'eux sera inférieure ou égale à 1 . Celle entre $m-1$ et le terme suivant est inférieure strictement à celle entre $m$ et ce même terme suivant, donc inférieure à 2 par hypothèse de récurrence. Pour ce qui est de $m+1$, nous avons deux cas à distinguer. Soit $m=m_{0}$ et alors $m+1$ est strictement supérieur à $m_{0}$ et ne nous intéresse plus. Soit $m<m_{0}$, et alors $m+1$ a une distance au terme précédent inférieure à la distance entre $m$ et ce même terme suivant, donc inférieure à 2 par hypothèse de récurrence.
Conséquence du lemme : tous les numéros portés par des jetons sont supérieurs ou égaux à $m_{0}-2 n$ à tout moment. Quitte à ajouter $2 n-m_{0}+1$ à tous les numéros au départ, ce qui ne change pas l'exercice, on peut donc supposer qu'ils sont tous strictement positifs à tout moment.
On note alors $P_{k}$ le produit des numéros de tous les jetons après $k$ changements. D'après ce qu'on vient de montrer, $P_{k}$ est un entier strictement positif pour tout $k$. Supposons de le $k+1$-ème changement consiste à remplacer deux jetons portant le numéro $m$ par un jeton portant le numéro $m-1$ et un jeton portant le numéro $m+1$. Alors $P_{k}$ s'écrit $m^{2} c$ avec $c>0$, et $P_{k+1}$ s'écrit
$$
P_{k+1}=(m-1)(m+1) c=\left(m^{2}-1\right) c<m^{2} c=P_{k}
$$
Ainsi, la suite des $\left(P_{k}\right)$ est une suite strictement décroissante d'entiers strictement positifs, elle est donc finie, c'est-à-dire qu'on arrive nécessairement à un moment où aucun changement n'est possible.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 8",
"solution_match": "\nSolution "
}
|
343f629f-47e5-5d14-8343-c564383e4481
| 607,551
|
Let $n \in \mathbb{N}^{*}$. We call $S$ the set of sequences of $2n$ digits containing $n$ zeros and as many ones. Two sequences in $S$ are neighbors if it suffices to change the position of one digit in one to obtain the other. For example, 11100010 and 10110010 are neighbors since by moving the first 0 in the second sequence two "steps" to the right, we obtain the first sequence. Let $T$ be a dense subset of minimal cardinality. Show that $\frac{1}{n^{2}+1}|S| \leq|T| \leq \frac{1}{n+1}|S|$. Note: we denote $|A|$ the cardinality of $A$.
|
We treat the inequalities separately.
- Let's show that $\frac{1}{2 n^{2}+1}|S| \leq|T|$. Let $s$ be an element of $S$. Let $s_{i, j}$ be the sequence that can be obtained from $s$ by moving the $i$-th digit of $s$ to position $j$. If $s_{i, j} \neq s$, then $j \neq i$. Furthermore, without loss of generality, we assume that the $i$-th digit of $s$ is a 0; if $j>i$ and if the $j$-th digit of $s$ is a 0, then $s_{i, j}=s_{i, j-1}$; if $j<i$ and if the $j$-th digit of $s$ is a 0, then $s_{i, j}=s_{i, j+1}$. Thus, any sequence $s_{i, j}$ distinct from $s$ can be written in the form $s_{i, k}$, such that the $k$-th digit of $s$ is a 1: for a fixed $i$, there are at most $n$ such sequences. Since $i$ can take $2 n$ values, the sequence $s$ has, indeed, at most $2 n^{2}$ different neighbors from itself. Thus, it takes at least $\frac{1}{2 n^{2}+1}|S|$ elements to form a dense set.
- Let's show that $|T| \leq \frac{1}{n+1}|S|$. Consider the 0s as fixed posts, delimiting $n+1$ intervals of 1s (we count the outer ones), some possibly empty. If $s \in S$, let $r_{k}$ be the number of 1s in the $k$-th interval from the left. We introduce $N(s):=r_{1}+2 r_{2}+\cdots+n r_{n}$ and $R(s)$ the congruence of $N(s)$ modulo $n+1$. If we move a 0 from the $i$-th interval (there is indeed a non-empty interval) to the $j$-th, we get $s^{\prime}$ such that $N\left(s^{\prime}\right)=N(s)+j-i$. By varying $j$ between 1 and $n+1$, we obtain all possible congruences for $R\left(s^{\prime}\right)$. If, for all $0 \leq k \leq n, S_{k}$ is the set of $s \in S$ such that $R(s)=k$, every sequence in $S_{k}$ has a neighbor in $S_{k^{\prime}}$ for all $k^{\prime} \neq k$. Since "being a neighbor" is a symmetric relation (if $s$ is a neighbor of $s^{\prime}$, then $s^{\prime}$ is a neighbor of $s$), every sequence $s$ that is not in $S_{k}$ has a neighbor in $S_{k}$, so $S_{k}$ is dense. Since the $S_{k}$ form a partition of $S$ into $n+1$ subsets, there exists a $k_{0}$ such that $\left|S_{k_{0}}\right| \leq \frac{1}{n+1}|S|$, which concludes the proof.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Soit $n \in \mathbb{N}^{*}$. On appelle $S$ l'ensemble des suites de $2 n$ chiffres comportant $n$ zéros et autant de uns. Deux suites de $S$ sont voisines lorsqu'il suffit de changer la position d'un chiffre de l'une pour obtenir l'autre. Par exemple, 11100010 et 10110010 sont voisines puisqu'en décalant le premier 0 de la deuxième suite de deux "pas" vers la droite, on obtient la première suite. Soit $T$ un sous-ensemble dense de cardinal minimal. Montrer que $\frac{1}{n^{2}+1}|S| \leq|T| \leq \frac{1}{n+1}|S|$. Remarque : on note $|A|$ le cardinal de $A$.
|
On traite séparément les inégalités.
- Montrons que $\frac{1}{2 n^{2}+1}|S| \leq|T|$. Soit $s$ un élément de $S$. Soit $s_{i, j}$ la suite que l'on peut obtenir à partir de $s$, en déplaçant le $i$-ème chiffre de $s$ pour le mettre en position $j$. Si $s_{i, j} \neq s$, alors $j \neq i$. En outre, sans perte de généralité, on suppose que le $i$-ème chiffre de $s$ est un 0 ; si $j>i$ et si le $j$-ème chiffre de $s$ est un 0 , alors $s_{i, j}=s_{i, j-1}$; si $j<i$ et si le $j$-ème chiffre de $s$ est un 0 , alors $s_{i, j}=s_{i, j+1}$. Ainsi, toute suite $s_{i, j}$ distincte de $s$ peut s'écrire sous la forme $s_{i, k}$, telle que le $k$-ème chiffre de $s$ soit un 1 : à $i$ fixé, il existe au plus $n$ telles suites. Puisque $i$ peut prendre $2 n$ valeurs, la suite $s$ a donc, en effet, au plus $2 n^{2}$ voisins différents d'elle-même. Ainsi, il faut au moins $\frac{1}{2 n^{2}+1}|S|$ éléments pour faire un ensemble dense.
- Montrons que $|T| \leq \frac{1}{n+1}|S|$. Considérons les 0 comme des poteaux fixes, délimitant $n+1$ intervalles de 1 (on compte les extérieurs), certains éventuellement vides. Si $s \in S$, soit $r_{k}$ le nombre de 1 dans le $k$-ème intervalle en partant de la gauche. On introduit $N(s):=r_{1}+2 r_{2}+\cdots+n r_{n}$ et $R(s)$ la congruence de $N(s)$ modulo $n+1$. Si on déplace un 0 du $i$-ème intervalle (il y a bien un intervalle non vide) vers le $j$-ème, on obtient $s^{\prime}$ telle que $N\left(s^{\prime}\right)=N(s)+j-i$. En faisant varier $j$ entre 1 et $n+1$, on obtient toutes les congruences possibles pour $R\left(s^{\prime}\right)$. Si, pour tout $0 \leq k \leq n, S_{k}$ est l'ensemble des $s \in S$ telles que $R(s)=k$, toute suite de $S_{k}$ a une voisine dans $S_{k^{\prime}}$ pour tout $k^{\prime} \neq k$. Comme "être voisine" est une relation symétrique (si $s$ voisine de $s^{\prime}$, alors $s^{\prime}$ est voisine de $s$ ), toute suite $s$ qui n'est pas dans $S_{k}$ a une voisine dans $S_{k}$, donc $S_{k}$ est dense. Or les $S_{k}$ forment une partition de $S$ en $n+1$ sous-ensembles, donc il existe un $k_{0}$ tel que $\left|S_{k_{0}}\right| \leq \frac{1}{n+1}|S|$, ce qui conclut.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 10",
"solution_match": "\nSolution "
}
|
f2c15dcf-777d-51fd-999d-23069db1343f
| 607,553
|
Let $ABCD$ be a convex quadrilateral (i.e., its diagonals are inside $ABCD$), and $P$ the intersection of its diagonals $[AC]$ and $[BD]$. We denote $\mathrm{O}_{1}, \mathrm{O}_{2}, \mathrm{O}_{3}$, and $\mathrm{O}_{4}$ as the centers of the circumcircles of $ABP, BCP, CDP$, and $DAP$.
Show that $\mathrm{O}_{1} \mathrm{O}_{2} \mathrm{O}_{3} \mathrm{O}_{4}$ is a parallelogram.

|
$1 \quad \mathrm{O}_{1}$ and $\mathrm{O}_{2}$ are on the perpendicular bisector of $[\mathrm{PB}]$, so $\mathrm{O}_{1} \mathrm{O}_{2}$ is the perpendicular bisector of [PB]. Similarly, $\left(\mathrm{O}_{3} \mathrm{O}_{4}\right)$ is the perpendicular bisector of [PD], so $\left(\mathrm{O}_{1} \mathrm{O}_{2}\right)$ and $\left(\mathrm{O}_{3} \mathrm{O}_{4}\right)$ are both perpendicular to (BD), thus they are parallel. Similarly, $\left(\mathrm{O}_{2} \mathrm{O}_{3}\right)$ and $\left(\mathrm{O}_{4} \mathrm{O}_{1}\right)$ are both perpendicular to (AC), thus they are parallel.
ABCD has its opposite sides parallel in pairs, so it is a parallelogram.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C D$ un quadrilatère convexe (c'est-à-dire que ses diagonales sont à l'intérieur de $A B C D$ ), et $P$ l'intersection de ses diagonales $[A C]$ et $[B D]$. On note $\mathrm{O}_{1}, \mathrm{O}_{2}, \mathrm{O}_{3}$ et $\mathrm{O}_{4}$ les centres des cercles circonscrits à $A B P, B C P, C D P$ et DAP.
Montrer que $\mathrm{O}_{1} \mathrm{O}_{2} \mathrm{O}_{3} \mathrm{O}_{4}$ est un parallélogramme.

|
$1 \quad \mathrm{O}_{1}$ et $\mathrm{O}_{2}$ sont sur la médiatrice de $[\mathrm{PB}]$, donc $\mathrm{O}_{1} \mathrm{O}_{2}$ est la médiatrice de [PB]. De même, $\left(\mathrm{O}_{3} \mathrm{O}_{4}\right)$ est la médiatrice de [PD], donc $\left(\mathrm{O}_{1} \mathrm{O}_{2}\right)$ et $\left(\mathrm{O}_{3} \mathrm{O}_{4}\right)$ sont toutes deux perpendiculaires à ( BD$)$, donc elles sont parallèles. De même, $\left(\mathrm{O}_{2} \mathrm{O}_{3}\right)$ et $\left(\mathrm{O}_{4} \mathrm{O}_{1}\right)$ sont toutes deux perpendiculaires à (AC), donc elles sont parallèles.
ABCD a ses côtés opposés parallèles deux à deux, donc c'est un parallélogramme.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 1.",
"solution_match": "\nSolution de l'exercice "
}
|
08c50467-5f93-5561-93ed-17a25ec796ab
| 607,554
|
Let $A B C D E F$ be a hexagon with all its angles equal to $120^{\circ}$. Show that $A B + B C = D E + E F$.

|
We extend the sides [AB], [CD], and [EF], and call $X$ the intersection of $(AB)$ and $(CD)$, $Y$ that of $(CD)$ and $(EF)$, and $Z$ that of $(EF)$ and $(AB)$. Then $\widehat{XBC}=180^{\circ}-\widehat{ABC}=60^{\circ}$ and similarly for $\widehat{XCB}$, so:
$$
\widehat{ZXY}=\widehat{BXC}=180^{\circ}-\widehat{XBC}-\widehat{XCB}=180^{\circ}-60^{\circ}-60^{\circ}=60^{\circ}
$$
and similarly for the angles of triangle $XYZ$: we have represented the angles of $120^{\circ}$ in green and those of $60^{\circ}$ in red in the figure.
Triangle $XBC$ is therefore equilateral, so $AB+BC=AB+BX=AX$ and similarly $DE+EF=FY$. Since $XYZ$ is equilateral, $ZX=ZY$ and $ZAF$ is equilateral, so $ZA=ZF$, hence $AX=ZX-$ $ZA=ZY-ZF=FY$, which gives the result.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C D E F$ un hexagone ayant tous ses angles égaux à $120^{\circ}$. Montrer que $A B+$ $B C=D E+E F$.

|
On prolonge les côtés [AB], [CD] et [EF], et on appelle Xl l'intersection de $\left(A B\right.$ ) et (CD), $Y$ celle de (CD) et (EF), et $Z$ celle de (EF) et $\left(A B\right.$ ). Alors $\widehat{X B C}=180^{\circ}-\widehat{A B C}=60^{\circ}$ et de même pour $\widehat{X C B}$, donc:
$$
\widehat{Z X Y}=\widehat{B X C}=180^{\circ}-\widehat{X B C}-\widehat{X C B}=180^{\circ}-60^{\circ}-60^{\circ}=60^{\circ}
$$
et de même pour les angles du triangle $X Y Z$ : on a représenté les angles de $120^{\circ}$ en vert et ceux de $60^{\circ}$ en rouge sur la figure.
Le triangle $X B C$ est donc équilatéral, donc $A B+B C=A B+B X=A X$ et de même $D E+E F=F Y$. Or, $X Y Z$ est équilatéral donc $Z X=Z Y$ et $Z A F$ est équilatéral donc $Z A=Z F$, d'où $A X=Z X-$ $Z A=Z Y-Z F=F Y$, d'où le résultat.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 3.",
"solution_match": "\nSolution de l'exercice 3"
}
|
5905a4b7-c605-5ce8-8cfc-13d3cc8bff90
| 607,556
|
Let $ABCD$ be a convex quadrilateral. We denote $P, Q, R$ and $S$ as the midpoints of the sides $[AB], [BC], [CD]$ and $[DA]$. Show that the area of $PQRS$ is equal to half the area of $ABCD$.

|
Let $X$ be the intersection of the diagonals of $ABCD$. [PQ] intersects [BD] at $Y$, and $[QR]$ intersects $[AC]$ at $Z$. According to the midline theorem, ( $PQ$ ) is parallel to ( $AC$ ), so (QZ) is parallel to ( $CX$ ) and, again by the midline theorem, Z is the midpoint of $[BX]$, thus the area of triangle $XQZ$ is half the area of triangle $XQB$. Similarly, the area of triangle XQY is half that of triangle XQC.
The quadrilateral PQRS therefore covers half of triangle XBC. In the same way, it covers half of the triangles $XCD, XDA$, and $XAB$, so its area is half that of $ABCD$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C D$ un quadrilatère convexe. On note $P, Q, R$ et $S$ les milieux des côtés $[A B],[B C],[C D]$ et $[D A]$. Montrer que l'aire de PQRS est égale à la moitié de l'aire de $A B C D$.

|
On note $X$ l'intersection des diagonales de $A B C D$. [PQ] coupe [BD] en $Y$, et $[Q R]$ coupe $[A C]$ en $Z$. D'après le théorème de la droite des milieux, ( $P Q$ ) est parallèle à ( $A C$ ), donc (QZ) est parallèle à ( $C X$ ) et, de nouveau d'après le théorème de la droite des milieux, Z est le milieu de $[B X]$, donc l'aire du triangle $X Q Z$ est la moitié de l'aire du triangle $X Q B$. De même, l'aire du triangle XQY est la moitié de celle du triangle XQC.
Le quadrilatère PQRS couvre donc la moitié du triangle XBC. De la même manière, il couvre la moitié des triangles $X C D, X D A$ et $X A B$, donc son aire est la moitié de celle de $A B C D$.
## Exercices Communs
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 4.",
"solution_match": "\nSolution de l'exercice 4"
}
|
619c4894-a078-559c-b124-34f77c25d909
| 607,557
|
Two circles $\Gamma_{1}$ and $\Gamma_{2}$ with centers $\mathrm{O}_{1}$ and $\mathrm{O}_{2}$ intersect at P and Q. A line passing through $O_{1}$ intersects $\Gamma_{2}$ at $A$ and $B$, and a line passing through $O_{2}$ intersects $\Gamma_{1}$ at $C$ and $D$. Show that if there exists a circle passing through $A, B, C$ and $D$, then the center of this circle lies on (PQ).

|
We denote $\Gamma$ as the circle passing through $A, B, C$, and $D$. According to the radical axis theorem, $(\mathrm{AB}), (CD)$, and $(PQ)$ are concurrent at a point called $X$. Furthermore, $(\mathrm{AB})$ is perpendicular to $\left(\mathrm{OO}_{2}\right)$, so it is the altitude from $\mathrm{O}_{1}$ in $\mathrm{OO}_{1} \mathrm{O}_{2}$. Similarly, $(CD)$ is the altitude from $\mathrm{O}_{2}$, so $X$ is the orthocenter of $\mathrm{OO}_{1} \mathrm{O}_{2}$. Consequently, $(\mathrm{OX})$ is perpendicular to $\left(\mathrm{O}_{1} \mathrm{O}_{2}\right)$, but we already know that the perpendicular to $\left(\mathrm{O}_{1} \mathrm{O}_{2}\right)$ passing through $X$ is $(\mathrm{PQ})$, so the lines $(\mathrm{OX})$ and $(PQ)$ are coincident, and $\mathrm{O} \in (\mathrm{PQ})$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Deux cercles $\Gamma_{1}$ et $\Gamma_{2}$ de centres $\mathrm{O}_{1}$ et $\mathrm{O}_{2}$ se coupent en P et Q . Une droite passant par $O_{1}$ coupe $\Gamma_{2}$ en $A$ et $B$, et une droite passant par $O_{2}$ coupe $\Gamma_{1}$ en $C$ et $D$. Montrer que s'il existe un cercle passant par $A, B, C$ et $D$, alors le centre de ce cercle est sur (PQ).

|
On note $\Gamma$ le cercle passant par $A, B, C$ et $D$. D'après le théorème des axes radicaux, $(\mathrm{AB}),(C D)$ et (PQ) sont concourrantes en un point qu'on appelle $X$. De plus, $(\mathrm{AB})$ est perpendiculaire à $\left(\mathrm{OO}_{2}\right)$, donc est la hauteur issue de $\mathrm{O}_{1}$ dans $\mathrm{OO}_{1} \mathrm{O}_{2}$. De même, (CD) est la hauteur issue de $\mathrm{O}_{2}$, donc $X$ est l'orthocentre de $\mathrm{OO}_{1} \mathrm{O}_{2}$. Par conséquent, ( OX ) est perpendiculaire à $\left(\mathrm{O}_{1} \mathrm{O}_{2}\right)$, mais on sait déjà que la perpendiculaire à $\left(\mathrm{O}_{1} \mathrm{O}_{2}\right)$ passant par X est $(\mathrm{PQ})$, donc les droites $(\mathrm{OX})$ et ( PQ ) sont confondues, et $\mathrm{O} \in(\mathrm{PQ})$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "\nSolution de l'exercice 7"
}
|
33940914-efff-57de-be80-449d6d950ab4
| 607,560
|
Two circles $\omega_{1}$ and $\omega_{2}$ are tangent at $S$, with $\omega_{1}$ inside $\omega_{2}$. Let $O$ be the center of $\omega_{1}$. A chord $[A B]$ of $\omega_{2}$ is tangent to $\omega_{1}$ at $T$. Show that $(A O)$, the perpendicular to $(\mathrm{AB})$ passing through $B$ and the perpendicular to $(S T)$ passing through $S$ are concurrent.

|
We denote $(\mathrm{Bx})$ as the perpendicular to (AB) passing through B, and (Sy) as the perpendicular to (ST) passing through S. To obtain the result using the trigonometric form of Ceva's theorem in triangle ABS, we need to show:
$$
\frac{\sin \widehat{B A O}}{\sin \widehat{S A O}} \cdot \frac{\sin \widehat{A S y}}{\sin \widehat{B S y}} \cdot \frac{\sin \widehat{S B x}}{\sin \widehat{A B x}}=1
$$
We know that $\sin A B x=1$. Furthermore, the homothety centered at $S$ that maps $\omega_{1}$ to $\omega_{2}$ maps $T$ to the midpoint of the arc $\widehat{A B}$, so (ST) is the internal angle bisector of $\widehat{A S B}$ and (Sy) is its external angle bisector, hence $\sin \widehat{\mathrm{ASy}}=\sin \widehat{\mathrm{BSy}}$. Therefore, it remains to show:
$$
\frac{\sin \widehat{\mathrm{BAO}}}{\sin \widehat{\mathrm{SAO}}} \cdot \sin \widehat{\mathrm{SBX}}=1
$$
We have $\sin \widehat{\mathrm{BAO}}=\frac{\mathrm{OT}}{\mathrm{AO}}=\frac{\mathrm{OS}}{\mathrm{AO}}=\frac{\sin \widehat{O A S}}{\sin \widehat{A S O}}$, so it remains to show $\widehat{A S O}=\widehat{\mathrm{SBx}}$. If we denote $\mathrm{O}^{\prime}$ as the center of $\omega_{2}$, then:
$$
\widehat{\mathrm{ASO}}=\widehat{\mathrm{ASO}^{\prime}}=\frac{1}{2}\left(\pi-\widehat{\mathrm{AO}^{\prime} \mathrm{S}}\right)=\frac{\pi}{2}-\widehat{\mathrm{SBA}}=\widehat{\mathrm{SBx}}
$$
which gives the result.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Deux cercles $\omega_{1}$ et $\omega_{2}$ sont tangents en $S$, avec $\omega_{1}$ à l'intérieur de $\omega_{2}$. On note O le centre de $\omega_{1}$. Une corde $[A B]$ de $\omega_{2}$ est tangente à $\omega_{1}$ en $T$. Montrer que $(A O)$, la perpendiculaire à $(\mathrm{AB})$ passant par $B$ et la perpendiculaire à $(S T)$ passant par $S$ sont concourantes.

|
On note $(\mathrm{Bx})$ la perpendiculaire à ( AB ) passant par B, et (Sy) la perpendiculaire à (ST) passant par S. Pour obtenir le résultat grâce au théorème de Ceva trigonométrique dans le triangle ABS, on doit montrer :
$$
\frac{\sin \widehat{B A O}}{\sin \widehat{S A O}} \cdot \frac{\sin \widehat{A S y}}{\sin \widehat{B S y}} \cdot \frac{\sin \widehat{S B x}}{\sin \widehat{A B x}}=1
$$
Or, on sait que $\sin A B x=1$. De plus, l'homothétie de centre $S$ qui envoie $\omega_{1}$ sur $\omega_{2}$ envoie $T$ sur le milieu de l'arc $\widehat{A B}$, donc (ST) est la bissectrice intérieure de $\widehat{A S B}$ et (Sy) est sa bissectrice extérieure, $\mathrm{d}^{\prime}$ où $\sin \widehat{\mathrm{ASy}}=\sin \widehat{\mathrm{BSy}}$. Il reste donc à montrer :
$$
\frac{\sin \widehat{\mathrm{BAO}}}{\sin \widehat{\mathrm{SAO}}} \cdot \sin \widehat{\mathrm{SBX}}=1
$$
Or, $\sin \widehat{\mathrm{BAO}}=\frac{\mathrm{OT}}{\mathrm{AO}}=\frac{\mathrm{OS}}{\mathrm{AO}}=\frac{\sin \widehat{O A S}}{\sin \widehat{A S O}}$, donc il ne reste plus qu'à montrer $\widehat{A S O}=\widehat{\mathrm{SBx}}$. Si on note $\mathrm{O}^{\prime}$ le centre de $\omega_{2}$, alors :
$$
\widehat{\mathrm{ASO}}=\widehat{\mathrm{ASO}^{\prime}}=\frac{1}{2}\left(\pi-\widehat{\mathrm{AO}^{\prime} \mathrm{S}}\right)=\frac{\pi}{2}-\widehat{\mathrm{SBA}}=\widehat{\mathrm{SBx}}
$$
d'où le résultat.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 9.",
"solution_match": "\nSolution de l'exercice 9"
}
|
7d4f9424-2c12-5c72-8a95-a3d2db2ee840
| 607,562
|
Let $\Gamma$ be a circle with center O, and (d) a line that does not intersect $\Gamma$. We call $P$ the orthogonal projection of $O$ onto (d). Let $Q$ be a variable point on the line (d), and $\left(t_{1}\right)$ and $\left(t_{2}\right)$ the tangents to $\Gamma$ passing through $Q$. We denote $A$ and $B$ as the orthogonal projections of $P$ onto $\left(t_{1}\right)$ and $\left(t_{2}\right)$. Show that the point of intersection of $(A B)$ and ( $O P)$ remains fixed when $Q$ varies.

|
Let $X$ be the intersection of $(A B)$ and $(O P), S$ and $T$ the points where $\left(t_{1}\right)$ and $\left(t_{2}\right)$ touch $\Gamma$, and $Y$ the intersection of $(ST)$ and $(OP)$. A first remark we can make is that $O, P, Q, S$ and $T$ are concyclic on the circle with diameter [OQ]. A good figure suggests that $Y$ does not depend on $Q$. And indeed, we have:
$$
\widehat{\mathrm{OSY}}=\widehat{\mathrm{OST}}=\widehat{\mathrm{OQT}}=\widehat{\mathrm{OQS}}=\widehat{\mathrm{OPS}}
$$
so the triangles OSY and OPS are indirectly similar, thus $\frac{\mathrm{OY}}{\mathrm{OS}}=\frac{\mathrm{OS}}{\mathrm{OP}} \mathrm{d}'$ where $\mathrm{OY}=\frac{\mathrm{r}^{2}}{\mathrm{OP}}$ where $r$ is the radius of $\Gamma$, so $O Y$ does not depend on $Q$ and $Y$ is fixed (enthusiasts of projective geometry will have recognized the pole of (d) with respect to $\Gamma$).
Now let $Z$ be the orthogonal projection of $P$ on $(ST)$: since $P$ is on the circumcircle of PST, the Simson line guarantees that $Z \in(A B)$. Let's do some angle chasing:
$$
\widehat{\mathrm{PZX}}=\widehat{\mathrm{PZA}}=\widehat{\mathrm{PSA}}=\widehat{\mathrm{PSQ}}=\widehat{\mathrm{POQ}}=\widehat{\mathrm{OPZ}}
$$
where we have used successively that $P, Z, A$ and $S$ are concyclic (on the circle with diameter [PS]), that $O, P, Q, S$ are concyclic, and finally that (OQ) // (PZ). Therefore, XPZ is isosceles at $X$, so $X$ is on the perpendicular bisector of $[P Z]$. The center of the circumcircle of PYZ is on this perpendicular bisector, and is on $(PY)$ because PYZ is right-angled at $Z$.
$X$ is thus the center of the circumcircle of PYZ, and is the midpoint of [PY] because PYZ is right-angled at $Z$. Since $P$ and $Y$ do not depend on $Q$, neither does $X$.
$\mathcal{F i n}$
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soient $\Gamma$ un cercle de centre O , et ( d ) une droite qui n'intersecte pas $\Gamma$. On appelle $P$ le projeté orthogonal de $O$ sur (d). Soit $Q$ un point variable sur la droite (d), et $\left(t_{1}\right)$ et $\left(t_{2}\right)$ les tangentes à $\Gamma$ passant par $Q$. On note $A$ et $B$ les projetés orthogonaux de $P$ sur $\left(t_{1}\right)$ et $\left(t_{2}\right)$. Montrer que le point d'intersection de $(A B)$ et ( $O P)$ reste fixe quand $Q$ varie.

|
On note $X$ l'intersection de $(A B)$ et $(O P), S$ et $T$ les points où $\left(t_{1}\right)$ et $\left(t_{2}\right)$ touchent $\Gamma$, et $Y$ le point d'intersection de (ST) et (OP). Une première remarque qu'on peut faire est que $O, P, Q, S$ et $T$ sont cocycliques sur le cercle de diamètre [OQ]. Une bonne figure suggère que $Y$ ne dépend pas de $Q$. Et en effet, on a :
$$
\widehat{\mathrm{OSY}}=\widehat{\mathrm{OST}}=\widehat{\mathrm{OQT}}=\widehat{\mathrm{OQS}}=\widehat{\mathrm{OPS}}
$$
donc les triangles OSY et OPS sont indirectement semblables donc $\frac{\mathrm{OY}}{\mathrm{OS}}=\frac{\mathrm{OS}}{\mathrm{OP}} \mathrm{d}^{\prime}$ où $\mathrm{OY}=\frac{\mathrm{r}^{2}}{\mathrm{OP}}$ où $r$ est le rayon de $\Gamma$, donc $O Y$ ne dépend pas de $Q$ et $Y$ est fixe (les amateurs de géométrie projective auront reconnu le pôle de (d) par rapport à $\Gamma$ ).
Soit maintenant $Z$ le projeté orthogonal de $P$ sur (ST) : comme $P$ est sur le cercle circonscrit à PST, la droite de Simson nous garantit que $Z \in(A B)$. Faisons maintenant un peu de chasse aux angles:
$$
\widehat{\mathrm{PZX}}=\widehat{\mathrm{PZA}}=\widehat{\mathrm{PSA}}=\widehat{\mathrm{PSQ}}=\widehat{\mathrm{POQ}}=\widehat{\mathrm{OPZ}}
$$
où on a utilisé successivement que $P, Z, A$ et $S$ sont cocycliques (sur le cercle de diamètre [PS]), que $O, P, Q, S$ sont cocycliques et enfin que (OQ) // (PZ). On a donc que XPZ est isocèle en $X$, donc $X$ est sur la médiatrice de $[P Z]$. Or, le centre du cercle circonscrit à PYZ est sur cette médiatrice, et est sur (PY) car PYZ est rectangle en Z.
$X$ est donc le centre du cercle circonscrit à PYZ, donc est le milieu de [PY] car PYZ est rectangle en $Z$. Comme $P$ et $Y$ ne dépendent pas de $Q, X$ non plus.
$\mathcal{F i n}$
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 10.",
"solution_match": "\nSolution de l'exercice 10"
}
|
b4e287d5-d66b-5b95-ab17-f5ba63e2bd63
| 607,563
|
Let n be the integer $4 \times 201420142014 \ldots 2014$ (where 2014 is written 117819 times). Show that $2014^{3}$ divides n.
|
We can write
$$
4 \times 201420142014 \ldots 2014 = 4 \cdot 2014 \cdot \frac{10^{4 \cdot 117819}-1}{10^{4}-1}
$$
Since $2014 = 2 \cdot 19 \cdot 53$ and $10^{4}-1 = 3^{2} \cdot 11 \cdot 101$ are coprime, it suffices to show that $19^{2}$ and $53^{2}$ divide $10^{4 \cdot 117819}-1$. According to Euler's theorem,
$$
10^{\Phi\left(19^{2}\right)} \equiv 1 \quad\left(\bmod 19^{2}\right) \quad \text { and } \quad 10^{\Phi\left(53^{2}\right)} \equiv 1 \quad\left(\bmod 53^{2}\right),
$$
where $\phi$ denotes the Euler's totient function. It suffices to verify that $\phi\left(19^{2}\right)$ and $\phi\left(53^{2}\right)$ both divide $4 \cdot 117819$. This follows from the fact that $\phi\left(19^{2}\right) = 19^{2}-19 = 2 \cdot 3^{2} \cdot 19$, $\phi\left(53^{2}\right) = 53^{2}-53 = 2^{2} \cdot 13 \cdot 53$ and $4 \cdot 117819 = 2^{2} \cdot 3^{2} \cdot 13 \cdot 19 \cdot 53$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit n l'entier $4 \times 201420142014 \ldots 2014$ (où 2014 est écrit 117819 fois). Montrer que $2014^{3}$ divise n.
|
On peut écrire
$$
4 \times 201420142014 \ldots 2014=4 \cdot 2014 \cdot \frac{10^{4 \cdot 117819}-1}{10^{4}-1}
$$
Comme $2014=2 \cdot 19 \cdot 53$ et $10^{4}-1=3^{2} \cdot 11 \cdot 101$ sont premiers entre eux, il suffit de montrer que $19^{2}$ et $53^{2}$ divisent $10^{4 \cdot 117819}-1$. D'après le théorème d'Euler,
$$
10^{\Phi\left(19^{2}\right)} \equiv 1 \quad\left(\bmod 19^{2}\right) \quad \text { et } \quad 10^{\Phi\left(53^{2}\right)} \equiv 1 \quad\left(\bmod 53^{2}\right),
$$
où $\phi$ désigne la fonction indicatrice d'Euler. Il suffit donc de vérifier que $\phi\left(19^{2}\right)$ et $\phi\left(53^{2}\right)$ divisent tous les deux $4 \cdot 117819$. Ceci découle du fait que $\phi\left(19^{2}\right)=19^{2}-19=2 \cdot 3^{2} \cdot 19$, $\phi\left(53^{2}\right)=53^{2}-53=2^{2} \cdot 13 \cdot 53$ et $4 \cdot 117819=2^{2} \cdot 3^{2} \cdot 13 \cdot 19 \cdot 53$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 5.",
"solution_match": "\nSolution de l'exercice 5"
}
|
8e2b06a4-a295-585f-a02f-7d284574b028
| 607,568
|
Let $m$ and $n$ be integers such that $0 \leqslant m \leqslant 2 n$. Prove that the integer
$$
2^{2 n+2}+2^{m+2}+1
$$
is a perfect square if, and only if, $m=n$.
|
$\triangleright$ Note that if $\mathrm{m}=\mathrm{n}$, then $2^{2 \mathrm{n}+2}+2^{\mathrm{m}+2}+1=\left(2^{\mathrm{m}+1}+1\right)^{2}$ is indeed a perfect square.
$\triangleright$ Conversely, suppose that $2^{2 n+2}+2^{\mathrm{m}+2}+1$ is a perfect square. Since it is strictly greater than $2^{2 \mathrm{n}+2}=\left(2^{\mathrm{n}+1}\right)^{2}$, it is greater than or equal to the next square, i.e., $2^{2 n+2}+2^{m+2}+1 \geqslant\left(2^{n+1}+1\right)^{2}$.
By expanding, we get $2^{\mathfrak{m}+2} \geqslant 2^{\mathfrak{n}+2}$, hence $\mathfrak{m} \geqslant n$. Suppose, for the sake of contradiction, that $\mathrm{m}>n$, which means $2^{m}>2^{2 n-m}$.
By hypothesis, the quantity $2^{2 n+2}+2^{m+2}+1$ is the square of an odd integer $2 k+1$ strictly greater than 1, so
$$
2^{2 \mathrm{n}+2}+2^{\mathrm{m}+2}+1=(2 \mathrm{k}+1)^{2}
$$
for some integer $k \geqslant 1$, which can be rewritten as $k(k+1)=2^{2 n}+2^{m}=2^{m}\left(2^{2 n-m}+1\right)$. Since the integers $k$ and $k+1$ are coprime, we deduce that:
- either $k=2^{m} p$ and $p(k+1)=2^{2 n-m}+1$ which implies $(k+1) p<k / p+1$: contradiction.
- or $k+1=2^{m} p$ and $p k=2^{2 n-m}+1$ which implies $k p<\frac{k+1}{p}+1$ hence $k p \leqslant \frac{k+1}{p}$, or $k\left(p^{2}-1\right) \leqslant 1$, which forces $p=1$ since $k \geqslant 1$. Then, $2^{2 n-m}=2\left(2^{m-1}-1\right)$ so $2 \mathrm{n}-\mathrm{m}=1$ and $\mathrm{m}=2$: contradiction.
Thus, if $2^{2 \mathrm{n}+2}+2^{\mathrm{m}+2}+1=\left(2^{\mathrm{m}+1}+1\right)^{2}$ is a perfect square, then $\mathrm{m}=\mathrm{n}$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soient $m$ et $n$ deux entiers tels que $0 \leqslant \mathfrak{m} \leqslant 2 \boldsymbol{n}$. Prouver que le nombre entier
$$
2^{2 n+2}+2^{m+2}+1
$$
est un carré parfait $s i$, et seulement $\mathrm{si}, \mathrm{m}=\mathrm{n}$.
|
$\triangleright$ Remarquons que si $\mathrm{m}=\mathrm{n}$, alors $2^{2 \mathrm{n}+2}+2^{\mathrm{m}+2}+1=\left(2^{\mathrm{m}+1}+1\right)^{2}$ est bien un carré parfait.
$\triangleright$ Réciproquement, supposons que $2^{2 n+2}+2^{\mathrm{m}+2}+1$ est un carré parfait. Comme il est strictement plus grand que $2^{2 \mathrm{n}+2}=\left(2^{\mathrm{n}+1}\right)^{2}$, il est supérieur ou égal au carré suivant, c'est-à-dire $2^{2 n+2}+2^{m+2}+1 \geqslant\left(2^{n+1}+1\right)^{2}$.
En développant, il vient $2^{\mathfrak{m}+2} \geqslant 2^{\mathfrak{n}+2}$, donc $\mathfrak{m} \geqslant n$. Supposons par l'absurde que $\mathrm{m}>n$ soit $2^{m}>2^{2 n-m}$.
Par hypothèse, la quantité $2^{2 n+2}+2^{m+2}+1$ est le carré d'un entier impair $2 k+1$ strictement plus grand que 1 , d'où
$$
2^{2 \mathrm{n}+2}+2^{\mathrm{m}+2}+1=(2 \mathrm{k}+1)^{2}
$$
pour un certain entier $k \geqslant 1$, ce qui se réécrit sous la forme $k(k+1)=2^{2 n}+2^{m}=2^{m}\left(2^{2 n-m}+1\right)$. Or les entiers $k$ et $k+1$ sont premiers entre eux. On en déduit que :
- soit $k=2^{m} p$ et $p(k+1)=2^{2 n-m}+1$ ce qui entraîne $(k+1) p<k / p+1$ : contradiction.
- soit $k+1=2^{m} p$ et $p k=2^{2 n-m}+1$ ce qui entraîne $k p<\frac{k+1}{p}+1$ donc $k p \leqslant \frac{k+1}{p}$, ou encore $k\left(p^{2}-1\right) \leqslant 1$, ce qui impose $p=1$ puisque $k \geqslant 1$. Alors, $2^{2 n-m}=2\left(2^{m-1}-1\right)$ donc $2 \mathrm{n}-\mathrm{m}=1$ et $\mathrm{m}=2:$ contradiction.
Ainsi, si $2^{2 \mathrm{n}+2}+2^{\mathrm{m}+2}+1=\left(2^{\mathrm{m}+1}+1\right)^{2}$ est un carré parfait, alors $\mathrm{m}=\mathrm{n}$.
## Exercices du groupe A
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 6.",
"solution_match": "## Solution de l'exercice 6"
}
|
9640cec2-e25d-52c5-9f78-f3933f4b8174
| 607,569
|
Show that there are infinitely many strictly positive integers \( a \) such that \( a^2 \) divides \( 2^a + 3^a \).
|
Let's note that $a=1$ works, and then construct by induction a strictly increasing sequence $(u_n)$ of odd integers satisfying the property.
$\triangleright$ First, we verify that $a=1$ and $a=5$ work. Let us set $u_0=1$ and $u_1=5$.
$\triangleright$ Consider an integer $n \geqslant 1$ and suppose the sequence is defined up to rank $n$. By definition of $u_n$, there exists an integer $q$ such that $q u_n^2 = 2^{u_n} + 3^{u_n}$. Since $u_n \geqslant u_1 = 5$, we have $q > 1$.
Let $p \geqslant 3$ be an odd prime factor of $q$ and verify that $u_{n+1} = p u_n$ satisfies the required property. Show that
$$
p \quad \text{divides} \quad 3^{u_n(p-1)} - 2^{u_n} 3^{u_n(p-2)} + \cdots + 2^{u_n(p-1)}.
$$
This allows us to conclude, because then, given that $p u_n^2$ divides $2^{u_n} + 3^{u_n}$, it follows that $p \cdot p u_n^2$ divides
which completes the proof.
To establish (1), we note that $p$ divides $2^{u_n} + 3^{u_n}$ (since $p$ divides $q$), so we have the congruence $2^{u_n} \equiv -3^{u_n} \pmod{p}$. Thus,
$$
\begin{aligned}
3^{u_n(p-1)} - 2^{u_n} 3^{u_n(p-2)} + \cdots + 2^{u_n(p-1)} & \equiv 3^{u_n(p-1)} + 3^{u_n(p-1)} + \cdots + 3^{u_n(p-1)} \quad (\bmod p) \\
& \equiv p 3^{u_n(p-1)} \quad (\bmod p) \\
& \equiv 0 \quad (\bmod p).
\end{aligned}
$$
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Montrer qu'il existe une infinité de nombres entiers strictement positifs a tels que $a^{2}$ divise $2^{a}+3^{a}$.
|
Remarquons que $a=1$ convient puis construisons par récurrence une suite ( $u_{n}$ ) strictement croissante d'entiers impairs vérifiant la propriété.
$\triangleright$ Tout d'abord, on vérifie que $a=1$ et $a=5$ conviennent. Posons ainsi $u_{0}=1$ et $u_{1}=5$.
$\triangleright$ Considerons un entier $n \geqslant 1$ et supposons la suite définie jusqu'au rang $n$. Par définition de $u_{n}$, il existe un entier $q$ tel que $q u_{n}^{2}=2^{u_{n}}+3^{u_{n}}$. Comme $u_{n} \geqslant u_{1}=5$, on a $q>1$.
Soit $p \geqslant 3$ un facteur premier (impair) de $q$ et vérifions que $u_{n+1}=p u_{n}$ vérifie la propriété requise. Montrons que
$$
p \quad \text { divise } \quad 3^{\mathfrak{u}_{n}(\mathfrak{p}-1)}-2^{\mathfrak{u}_{n}} 3^{\mathfrak{u}_{\mathfrak{n}}(\mathfrak{p}-2)}+\cdots+2^{\mathfrak{u}_{n}(p-1)} .
$$
Ceci permet de conclure, car alors, étant donné que $p u_{n}^{2}$ divise $2^{u_{n}}+3^{\mathfrak{u}_{n}}$, il en découle que $p \cdot p u_{n}^{2}$ divise
ce qui achève la démonstration.
Pour établir (1), on remarque que $p$ divise $2^{u_{n}}+3^{\mathfrak{u}_{n}}$ (car $p$ divise $q$ ), de sorte qu'on a la congruence $2^{\mathfrak{u}_{n}} \equiv-3^{\mathfrak{u}_{n}}(\bmod p)$. Ainsi,
$$
\begin{aligned}
3^{\mathfrak{u}_{n}(\mathfrak{p}-1)}-2^{\mathfrak{u}_{n}} 3^{\mathfrak{u}_{n}(\mathfrak{p}-2)}+\cdots+2^{\mathfrak{u}_{n}(\mathfrak{p}-1)} & \equiv 3^{\mathfrak{u}_{n}(\mathfrak{p}-1)}+3^{\mathfrak{u}_{n}(\mathfrak{p}-1)}+\cdots+3^{\mathfrak{u}_{n}(\mathfrak{p}-1)} \quad(\bmod p) \\
& \equiv p 3^{\mathfrak{u}_{n}(\mathfrak{p}-1)} \quad(\bmod p) \\
& \equiv 0 \quad(\bmod p) .
\end{aligned}
$$
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "\nSolution de l'exercice 7"
}
|
0def983c-13ea-5262-941d-3fa1018ea533
| 607,570
|
Let $m, n \geqslant 1$ be two odd integers such that $m$ divides $n^{2}+2$ and $n$ divides $m^{2}+2$. Prove that $m$ and $n$ are both terms of the sequence $\left(u_{n}\right)_{n \geqslant 1}$ defined by
$$
\mathfrak{u}_{1}=\mathrm{u}_{2}=1, \quad \mathrm{u}_{\mathrm{n}}=4 \mathrm{u}_{n-1}-\mathrm{u}_{n-2} \quad \text { if } n \geqslant 3
$$
|
The structure of the solution is as follows:
- We show that $mn$ divides $m^2 + n^2 + 2$;
- We show that $m^2 + n^2 + 2 = 4mn$;
- We show that the sequence $(u_n)_{n \geq 1}$ is increasing;
- We conclude by showing that in fact $m$ and $n$ are two consecutive terms of the sequence $(u_n)_{n \geq 1}$.
$\triangleright$ Let $d$ be the GCD of $m$ and $n$. Since $m$ divides $n^2 + 2$, we deduce that $d$ divides $n^2 + 2$ and thus that $d$ divides 2. Since $m$ and $n$ are odd, we deduce that $d=1$, so $m$ and $n$ are coprime. Thus, $mn$ divides $m^2 + n^2 + 2$.
$\triangleright$ We show that $m^2 + n^2 + 2 = 4mn$ using the technique known in English as "Vieta jumping". More precisely, let $k = (m^2 + n^2 + 2) / (mn)$, and consider all pairs of positive integers $(x, y)$ such that
$$
x^2 + y^2 + 2 = kxy.
$$
Among these pairs, choose one that minimizes the sum $x + y$. We will show that $x = y$. Suppose, for the sake of contradiction, that $x > y \geq 1$. We then consider the quadratic equation
$$
t^2 - kyt + y^2 + 2 = 0
$$
in the variable $t$. We already know that $t_1 = x$ is a solution. By Vieta's formulas,
$$
t_2 = ky - x = \frac{y^2 + 2}{x}
$$
is also a solution. Equation (2) shows that $t_2$ is a positive integer. Since $1 \leq y \leq x - 1$, we have
$$
t_2 = \frac{y^2 + 2}{x} \leq \frac{(x-1)^2 + 2}{x} < x = t_1
$$
where we used the fact that $x \geq 2$ for the last inequality. Thus, $t_2 + y < t_1 + y = x + y$, which contradicts the minimality of $x + y$. It follows that $x = y$, and thus $x^2$ divides $2x^2 + 2$. We deduce that $x = 1$, hence
$$
k = \frac{1^2 + 1^2 + 2}{1} = 4
$$
We have thus established that
$$
m^2 + n^2 + 2 = 4mn
$$
$\triangleright$ Verify that the sequence $(u_n)_{n \geq 1}$ is strictly increasing, by writing that for all integers $n \geq 1$,
$$
u_{n+1} - u_n = 3u_n - u_{n-1} > u_n - u_{n-1}
$$
By induction, we deduce that for all integers $n \geq 1$, $u_{n+1} - u_n > u_2 - u_1 = 0$.
$\triangleright$ Finally, show that $m$ and $n$ are two consecutive terms of the sequence $(u_n)_{n \geq 1}$ by strong induction on $m + n$. The base case is straightforward: if $m + n = 2$, then $m = n = 1$. Let $k \geq 3$, and suppose the result is established for all pairs $(m, n)$ of positive integers satisfying (3) with $m + n < k$, and consider a pair of positive integers $(m, n)$ satisfying (3) such that $m + n = k$. First, $m \neq n$, otherwise $m = n = 1$ by (3). Without loss of generality, assume $m > n$. As in the previous paragraph, if $(m, n)$ is a solution, then $(n, 4n - m)$ is also a solution, with $m + n > n + (4n - m)$. Moreover, it is easily verified that $2n - \sqrt{3n^2 - 2} < n < 3n < 2n + \sqrt{3n^2 - 2}$ for all integers $n \geq 2$. Thus, by (3), we have $m = 2n + \sqrt{3n^2 - 2}$, so $n > 4n - m$. By the induction hypothesis, there exists an integer $i \geq 2$ such that $u_{i-1} = n$ and $u_{i-2} = 4n - m$. But then $u_i = 4n - (4n - m) = m$, which shows that $m$ and $n$ are two consecutive terms of the sequence $(u_n)_{n \geq 1}$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soient $m, n \geqslant 1$ deux entiers impairs tels que $m$ divise $n^{2}+2$ et $n$ divise $m^{2}+2$. Prouver que $m$ et $n$ sont tous les deux des termes de la suite $\left(u_{n}\right)_{n \geqslant 1}$ définie par
$$
\mathfrak{u}_{1}=\mathrm{u}_{2}=1, \quad \mathrm{u}_{\mathrm{n}}=4 \mathrm{u}_{n-1}-\mathrm{u}_{n-2} \quad \text { si } n \geqslant 3
$$
|
La structure de la solution est la suivante:
- On montre que mn divise $\mathrm{m}^{2}+\mathrm{n}^{2}+2$;
- On montre que $\mathrm{m}^{2}+\mathrm{n}^{2}+2=4 \mathrm{mn}$;
- On montre que la suite $\left(u_{n}\right)_{n \geqslant 1}$ est croissante;
- On conclut en montrant qu'en fait $m$ et $n$ sont deux termes consécutifs de la suite $\left(u_{n}\right)_{n \geqslant 1}$.
$\triangleright$ Soit $d$ le PGCD de $m$ et de $n$. Comme $m$ divise $n^{2}+2$, on en déduit que $d$ divise $n^{2}+2$ et donc que $d$ divise 2 . Comme $m$ et $n$ sont impairs, on en déduit que $d=1$, de sorte que $m$ et $n$ sont premiers entre eux. Ainsi, mn divise $\mathrm{m}^{2}+\mathrm{n}^{2}+2$.
$\triangleright$ Montrons que $\mathrm{m}^{2}+\mathrm{n}^{2}+2=4 \mathrm{mn}$ en utilisant la technique connue en anglais sous le nom de $\ll$ Vieta jumping $\gg$. Plus précisément, soit $k=\left(m^{2}+n^{2}+2\right) /(m n)$, et considérons tous les couples d'entiers strictement positifs $(x, y)$ tels que
$$
x^{2}+y^{2}+2=k x y .
$$
Parmi ces couples, choissisons-en un qui minimise la somme $x+y$. Nous allons montrer que $x=y$. Raisonnons par l'absurde en supposant, sans perte de généralité, que $x>y \geqslant 1$. On s'intéresse alors à l'équation du second degré
$$
t^{2}-k y t+y^{2}+2=0
$$
d'inconnue $t$. On sait déjà que $t_{1}=x$ est solution. D'après les formules de Viète,
$$
\mathrm{t}_{2}=\mathrm{ky}-\mathrm{x}=\frac{\mathrm{y}^{2}+2}{\mathrm{x}}
$$
est également solution. L'équation (2) montre que $t_{2}$ est un entier strictement positif. Comme $1 \leqslant y \leqslant x-1$, on a
$$
t_{2}=\frac{y^{2}+2}{x} \leqslant \frac{(x-1)^{2}+2}{x}<x=t_{1}
$$
où on a utilisé le fait que $x \geqslant 2$ pour la dernière inégalité. Ainsi, $t_{2}+y<t_{1}+y=x+y$, ce qui contredit la minimalité de $x+y$. Il en découle que $x=y$, et donc $x^{2}$ divise $2 x^{2}+2$. On en déduit que $x=1$, d'où
$$
\mathrm{k}=\frac{1^{2}+1^{2}+2}{1}=4
$$
Nous avons donc établi que
$$
m^{2}+n^{2}+2=4 m n
$$
$\triangleright$ Vérifions que la suite $\left(u_{n}\right)_{n \geqslant 1}$ est strictement croissante, en écrivant que pour tout entier $n \geqslant 1$,
$$
u_{n+1}-u_{n}=3 u_{n}-u_{n-1}>u_{n}-u_{n-1}
$$
Par récurrence, on en déduit que, pour tout entier $\boldsymbol{n} \geqslant 1, \mathfrak{u}_{n+1}-\boldsymbol{u}_{n}>\mathfrak{u}_{2}-\mathfrak{u}_{1}=0$.
$\triangleright$ Montrons finalement que $m$ et $n$ sont deux termes consécutifs de la suite $\left(u_{n}\right)_{n \geqslant 1}$ par récurrence forte sur $m+n$. L'initialisation ne pose pas de soucis: si $m+n=2$, on a $m=n=1$. Soit donc $k \geqslant 3$, supposons le résultat établi pour tous les couples ( $m, n$ ) d'entiers strictement positifs vérifiant (3) avec $m+n<k$, et considérons un couple d'entiers strictement positifs ( $m, n$ ) vérifiant (3) tels que $m+n=k$. Tout d'abord, $m \neq n$, car sinon $m=n=1$ d'après (3). Sans perte de généralité, supposons $\mathrm{m}>\mathrm{n}$. Mais, comme dans le paragraphe précédent, si $(m, n)$ est solution, alors $(n, 4 n-m)$ l'est également, avec $m+n>n+(4 n-m)$. D'autre part, on vérifie aisément que $2 n-\sqrt{3 n^{2}-2}<n<3 n<2 n+\sqrt{3 n^{2}-2}$ pour tout entier $n \geqslant 2$. Ainsi, par (3), on a $m=2 n+\sqrt{3 n^{2}-2}$ de sorte que $n>4 n-m$. Par hypothèse de récurrence, il existe un entier $i \geqslant 2$ tel que $u_{i-1}=n$ et $u_{i-2}=4 n-m$. Mais alors $u_{i}=4 n-(4 n-m)=m$, ce qui montre bien que $m$ et $n$ sont deux termes consécutifs de la suite $\left(u_{n}\right)_{n \geqslant 1}$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 8.",
"solution_match": "\nSolution de l'exercice 8"
}
|
37a73571-eab0-5aa9-8d83-430c8de6f371
| 607,571
|
Let $a, b$ and $c$ be real numbers such that
$$
|a-b| \geq|c|,|b-c| \geq|a| \text { and }|c-a| \geq|b| .
$$
Prove that one of the three numbers $a, b$ and $c$ is the sum of the other two.
|
The first inequality is written as $(a-b)^{2} \geq c^{2}$, or equivalently $(a-b+c)(a-b-c) \geq 0$. Similarly, the other two inequalities lead to $(b-c+a)(b-c-a) \geq 0$ and $(c-a+b)(c-a-b) \geq 0$.
By multiplying these three inequalities term by term, we get
$$
(a-b+c)^{2}(-a+b+c)^{2}(a+b-c)^{2} \leq 0
$$
Since a square is always non-negative, it follows that one of the factors must be zero, which concludes the proof.
|
proof
|
Yes
|
Yes
|
proof
|
Algebra
|
Soit $a, b$ et $c$ des réels tels que
$$
|a-b| \geq|c|,|b-c| \geq|a| \text { et }|c-a| \geq|b| .
$$
Prouver que l'un des trois nombres $a, b$ et $c$ est la somme des deux autres.
|
La première inégalité s'écrit $(a-b)^{2} \geq c^{2}$, ou encore $(a-b+c)(a-b-c) \geq 0$. De même, les deux autre inégalités conduisent à $(b-c+a)(b-c-a) \geq 0$ et $(c-a+b)(c-a-b) \geq 0$.
En multipliant membre à membre ces trois inégalités, il vient
$$
(a-b+c)^{2}(-a+b+c)^{2}(a+b-c)^{2} \leq 0
$$
Or, un carré étant toujours positif, c'est donc que l'un des facteurs est nul, ce qui conclut.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 1.",
"solution_match": "## Solution."
}
|
47cc265f-eb9e-5563-b953-bb5ff2813e17
| 607,573
|
Let $a, b$ and $c$ be real numbers such that
$$
|a-b| \geq|c|,|b-c| \geq|a| \text { and }|c-a| \geq|b| .
$$
Prove that one of the three numbers $a, b$ and $c$ is the sum of the other two.
|
.
The variables $a, b$, and $c$ play symmetric roles. Moreover, the problem is invariant if the signs of $a, b$, and $c$ are simultaneously changed. Therefore, there are at least two variables among $a, b$, and $c$ that have the same sign; we can thus assume, without loss of generality, that we are in one of the two cases $a \geq b \geq c \geq 0$ or $a \geq b \geq 0 \geq c$.
Let's show that the relation $b=a+c$ holds in both cases, which will conclude the problem.
1. If $a \geq b \geq c \geq 0$, then $b \geq b-c=|b-c| \geq|a|=a$; each inequality is therefore an equality, leading to the relation $b=b-c=|b-c|=|a|=a$.
2. If $a \geq b \geq 0 \geq c$, then $b-c=|b-c| \geq|a|=a$ and $a-b=|a-b| \geq|c|=-c$, leading to the relation $a+c \geq b \geq a+c$.
|
proof
|
Yes
|
Yes
|
proof
|
Algebra
|
Soit $a, b$ et $c$ des réels tels que
$$
|a-b| \geq|c|,|b-c| \geq|a| \text { et }|c-a| \geq|b| .
$$
Prouver que l'un des trois nombres $a, b$ et $c$ est la somme des deux autres.
|
.
Les variables $a, b$ et $c$ jouent des rôles symétriques. En outre, le problème est invariant si on change simultanément les signes de $a, b$ et $c$. Ainsi, il y a au moins deux variables parmi $a, b$ et $c$ qui ont le même signe ; on peut donc supposer, sans perte de généralité, que l'on est dans un des deux cas $a \geq b \geq c \geq 0$ ou $a \geq b \geq 0 \geq c$.
Montrons que la relation $b=a+c$ est vraie dans les deux cas, ce qui conclura le problème.
1. Si $a \geq b \geq c \geq 0$, alors $b \geq b-c=|b-c| \geq|a|=a$; chaque inégalité est donc une égalité, d'où la relation $b=b-c=|b-c|=|a|=a$.
2. Si $a \geq b \geq 0 \geq c$, alors $b-c=|b-c| \geq|a|=a$ et $a-b=|a-b| \geq|c|=-c$, d'où la relation $a+c \geq b \geq a+c$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 1.",
"solution_match": "## Solution alternative"
}
|
47cc265f-eb9e-5563-b953-bb5ff2813e17
| 607,573
|
(Netherlands 2014).
Let $P$ be a polynomial with integer coefficients, of degree $n$, with $n \leq 10$. Suppose that $|P(10)-P(0)|<1000$ and that, for every $k \in\{1, \ldots, 10\}$, there exists an integer $m$ such that $P(m)=k$. Show that, for every integer $k$, there exists an integer $m$ such that $P(m)=k$.
|
For $i \in\{1, \ldots, 10\}$, let $c_{i}$ be an integer such that $P\left(c_{i}\right)=i$. For $i \in\{1, \ldots, 9\}$, since $P$ has integer coefficients, the integer $c_{i+1}-c_{i}$ divides $P\left(c_{i+1}\right)-P\left(c_{i}\right)=i+1-i=1$, hence $c_{i+1}-c_{i}= \pm 1$. Furthermore, for $i, j \in\{1, \ldots, 10\}$ distinct, we have $P\left(c_{i}\right)=i \neq j=P\left(c_{j}\right)$, so $c_{i} \neq c_{j}$. Thus, $c_{1}, c_{2}, \ldots, c_{10}$ are, in this order, ten consecutive integers.
By studying the polynomial $P(10-X)$ instead of the polynomial $P(X)$ itself, we can assume that $c_{1}<c_{2}<\cdots<c_{10}$: we then have $c_{i}=c_{1}+i-1$. Let then the polynomials $Q(X)=X+1-c_{1}$ and $R(X)=P(X)-Q(X)$. The polynomial $Q$ is affine, hence of degree 1, and $R$ is of degree at most 10.
Moreover, for $i=1,2, \ldots, 10$, we have $R\left(c_{i}\right)=P\left(c_{i}\right)-Q\left(c_{i}\right)=i-i=0$, so $c_{1}, \ldots, c_{10}$ are ten distinct integer roots of the polynomial $R$, with integer coefficients. We can therefore factorize $R$ as $R(X)=S(X) T(X)$, where $S(X)=\prod_{i=1}^{10}\left(X-c_{i}\right)$ and where $T$ is a polynomial with integer coefficients. Note that $T$ is of degree at most 0, which means that $T$ is constant: there exists an integer $a$ such that $R=a S$.
If $a=0$, we have $P=Q$, so $P$ is affine with coefficient $\pm 1$ and $P(\mathbb{Z})=\mathbb{Z}$: we now assume that $a \neq 0$. Then note that $S(n) \equiv 0(\bmod 10!)$ for all integer $n$. Indeed, let $k \geq 10$ be an integer. Then
$$
S\left(c_{1}+k\right)=\prod_{i=0}^{9}(k-i)=10!\binom{k}{10} \equiv 0 \quad(\bmod 10!)
$$
The relation $S\left(c_{1}+k\right) \equiv 0$ is therefore true in $\mathbb{Z} / 10!\mathbb{Z}$, which means that $S(n) \equiv 0$ $(\bmod 10!)$ for all integer $n$.
In particular, it follows that $R(n) \equiv 0(\bmod 10!)$ for all integer $n$. However,
$$
|R(10)-R(0)| \leq|P(10)-P(0)|+|Q(10)-Q(0)| \leq 1010<10!
$$
Thus, $R(10)=R(0)$, so $S(10)=S(0)$. The polynomial $S$ is strictly monotonic on $\left.]-\infty, c_{1}\right]$ and on $\left[c_{10},+\infty\left[\right.\right.$, so we cannot have either $10 \leq c_{1}$ or $0 \geq c_{10}$. Thus, one of the integers 0 and 10 must be a root of $S$, but then the other must be as well, which is impossible since the roots of $S$ are mutually at most 9 apart.
The case $a \neq 0$ is therefore impossible, which concludes the problem.
|
proof
|
Yes
|
Yes
|
proof
|
Algebra
|
(Pays-Bas 2014).
Soit $P$ un polynôme à coefficients entiers, de degré $n$, avec $n \leq 10$. On suppose que $|P(10)-P(0)|<1000$ et que, pour tout $k \in\{1, \ldots, 10\}$, il existe un entier $m$ tel que $P(m)=k$. Montrer que, pour tout entier $k$ il existe un entier $m$ tel que $P(m)=k$.
|
Pour $i \in\{1, \ldots, 10\}$, on désigne par $c_{i}$ un entier tel que $P\left(c_{i}\right)=i$. Pour $i \in\{1, \ldots, 9\}$, puisque $P$ est à coefficients entiers, l'entier $c_{i+1}-c_{i}$ divise $P\left(c_{i+1}\right)-P\left(c_{i}\right)=i+1-i=1$, d'où $c_{i+1}-c_{i}= \pm 1$. De plus, pour $i, j \in\{1, \ldots, 10\}$ distincts, on a $P\left(c_{i}\right)=i \neq j=P\left(c_{j}\right)$, donc $c_{i} \neq c_{j}$. Ainsi, $c_{1}, c_{2}, \ldots, c_{10}$ sont, dans cet ordre, dix entiers consécutifs.
Quitte à étudier le polynôme $P(10-X)$ plutôt que le polynôme $P(X)$ lui-même, on peut supposer que $c_{1}<c_{2}<\cdots<c_{10}$ : on a donc $c_{i}=c_{1}+i-1$. Soit alors les polynômes $Q(X)=X+1-c_{1}$ et $R(X)=P(X)-Q(X)$. Le polynôme $Q$ est affine, donc de degré 1 , et $R$ est de degré au plus 10 .
En outre, pour $i=1,2, \ldots, 10$, on a $R\left(c_{i}\right)=P\left(c_{i}\right)-Q\left(c_{i}\right)=i-i=0$, donc $c_{1}, \ldots, c_{10}$ sont dix racines distinctes entières du polynôme $R$, à coefficients entiers. On peut donc factoriser $R$ sous la forme $R(X)=S(X) T(X)$, où $S(X)=\prod_{i=1}^{10}\left(X-c_{i}\right)$ et où $T$ est un polynôme à coefficients entiers. Remarquons que $T$ est de degré au plus 0 , ce qui signifie que $T$ est constant : il existe un entier $a$ tel que $R=a S$.
Si $a=0$, on a bien $P=Q$, donc $P$ est affine de coefficient $\pm 1$ et $P(\mathbb{Z})=\mathbb{Z}$ : on suppose désormais que $a \neq 0$. Notons alors que $S(n) \equiv 0(\bmod 10!)$ pour tout entier $n$. En effet, soit $k \geq 10$ un entier. Alors
$$
S\left(c_{1}+k\right)=\prod_{i=0}^{9}(k-i)=10!\binom{k}{10} \equiv 0 \quad(\bmod 10!)
$$
La relation $S\left(c_{1}+k\right) \equiv 0$ est donc vraie dans $\mathbb{Z} / 10!\mathbb{Z}$, ce qui signifie bien que $S(n) \equiv 0$ $(\bmod 10!)$ pour tout entier $n$.
En particulier, il s'ensuit que $R(n) \equiv 0(\bmod 10!)$ pour tout entier $n$. Or,
$$
|R(10)-R(0)| \leq|P(10)-P(0)|+|Q(10)-Q(0)| \leq 1010<10!
$$
Ainsi, $R(10)=R(0)$, donc $S(10)=S(0)$. Le polynôme $S$ est strictement monotone sur $\left.]-\infty, c_{1}\right]$ et sur $\left[c_{10},+\infty\left[\right.\right.$, donc on ne peut avoir ni $10 \leq c_{1}$ ni $0 \geq c_{10}$. Ainsi, l'un des entiers 0 et 10 doit être une racine de $S$, mais alors l'autre aussi, ce qui est impossible car les racines de $S$ sont mutuellement distantes d'au plus 9 .
Le cas $a \neq 0$ est donc impossible, ce qui conclut le problème.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 6",
"solution_match": "## Solution."
}
|
82bbe829-2a69-593b-9505-e53ef044967e
| 607,578
|
Let $n \geq 0$ be an integer, and $x_{1}, x_{2}, \ldots, x_{n+1}$ be strictly positive real numbers such that $\prod_{k=1}^{n+1} x_{i}=1$. Prove that
$$
\sqrt[x_{1}]{n}+\sqrt[x_{2}]{n}+\cdots+\sqrt[x_{n+1}]{n} \geq n \sqrt[n]{x_{1}}+n \sqrt[n]{x_{2}}+\cdots+n \sqrt[n]{x_{n+1}}
$$
|
By IAG (twice), we have
$$
\begin{aligned}
n \cdot \sum_{i=1}^{n+1} \sqrt[x_{i}]{n} & =\sum_{j=1}^{n+1}\left(\sum_{i \neq j} n^{\frac{1}{x_{i}}}\right) \\
& \geq \sum_{j=1}^{n+1}\left(n \cdot n^{\frac{1}{n} \sum_{i \neq j} \frac{1}{x_{i}}}\right) \\
& \geq \sum_{j=1}^{n+1} n \cdot n \sqrt[n]{\prod_{i \neq j} \frac{1}{x_{i}}} \\
& =\sum_{j=1}^{n+1} n \cdot n \sqrt[{n \sqrt{x_{j}}}]{ } \text{ since } x_{1} x_{2} \cdots x_{n+1}=1
\end{aligned}
$$
and it only remains to divide the first and last members by $n$ to obtain the desired inequality.
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
Soit $n \geq 0$ un entier, et $x_{1}, x_{2}, \ldots, x_{n+1}$ des réels strictement positifs tels que $\prod_{k=1}^{n+1} x_{i}=1$. Prouver que
$$
\sqrt[x_{1}]{n}+\sqrt[x_{2}]{n}+\cdots+\sqrt[x_{n+1}]{n} \geq n \sqrt[n]{x_{1}}+n \sqrt[n]{x_{2}}+\cdots+n \sqrt[n]{x_{n+1}}
$$
|
Par IAG (deux fois), on a
$$
\begin{aligned}
n \cdot \sum_{i=1}^{n+1} \sqrt[x_{i}]{n} & =\sum_{j=1}^{n+1}\left(\sum_{i \neq j} n^{\frac{1}{x_{i}}}\right) \\
& \geq \sum_{j=1}^{n+1}\left(n \cdot n^{\frac{1}{n} \sum_{i \neq j} \frac{1}{x_{i}}}\right) \\
& \geq \sum_{j=1}^{n+1} n \cdot n \sqrt[n]{\prod_{i \neq j} \frac{1}{x_{i}}} \\
& =\sum_{j=1}^{n+1} n \cdot n \sqrt[{n \sqrt{x_{j}}}]{ } \operatorname{car} x_{1} x_{2} \cdots x_{n+1}=1
\end{aligned}
$$
et il ne reste plus qu'à diviser par $n$ les premier et dernier membres pour obtenir l'inégalité demandée.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 7.",
"solution_match": "## Solution."
}
|
7cddad7b-6c2f-584d-8297-31d51b4d628a
| 607,579
|
Let $a \in] 0 ; 1\left[\right.$ and $n>0$ be an integer. We denote $f_{n}$ the function defined on $\mathbb{R}$ by $f_{n}(x)=x+\frac{x^{2}}{n}$, for all real $x$. Prove that
$$
\frac{a(1-a) n^{2}+2 a^{2} n+a^{3}}{(1-a)^{2} n^{2}+a(2-a) n+a^{2}}<\underbrace{\left(f_{n} \circ f_{n} \circ \cdots \circ f_{n}\right)}_{n}(a)<\frac{a n+a^{2}}{(1-a) n+a} .
$$
|
For any integer $k \geq 0$, let $a_{k}=\underbrace{\left(f_{n} \circ f_{n} \circ \cdots \circ f_{n}\right)}_{k}(a)$. In particular, $a_{0}=a$.
We observe that, for all $k \geq 0$, we have $a_{k+1}=a_{k}+\frac{a_{k}^{2}}{n}>a_{k}$, so the sequence $\left(a_{k}\right)$ is strictly increasing. In particular, $a_{k} \geq a>0$ for all $k \geq 0$.
Moreover, for all $k \geq 0$, we have $a_{k+1}=\frac{a_{k}\left(a_{k}+n\right)}{n}$ and thus
$$
\frac{1}{a_{k+1}}=\frac{1}{a_{k}}-\frac{1}{a_{k}+n} .
$$
Thus, after summing these equalities for $k=0, \ldots, n-1$, we have
$$
\frac{1}{a_{n}}=\frac{1}{a}-\sum_{k=0}^{n-1} \frac{1}{a_{k}+n}
$$
Since $\left(a_{k}\right)$ is strictly increasing and positive, we have
$$
\frac{n}{a_{n}+n}<\sum_{k=0}^{n-1} \frac{1}{a_{k}+n}<\frac{n}{a+n}
$$
and thus
$$
\frac{1}{a}-\frac{n}{a+n}<\frac{1}{a_{n}}<\frac{1}{a}-\frac{n}{a_{n}+n} .
$$
The left inequality is equivalent to $a_{n}<\frac{a n+a^{2}}{(1-a) n+a}$, which is the right inequality of the desired bound.
Now, substitute this last inequality into the right inequality of (1). We get
$$
\frac{1}{a_{n}}<\frac{1}{a}-\frac{n}{\frac{a n+a^{2}}{(1-a) n+a}+n}
$$
or equivalently,
$$
\frac{a(1-a) n^{2}+2 a^{2} n+a^{3}}{(1-a)^{2} n^{2}+a(2-a) n+a^{2}}<a_{n}
$$
which is the left inequality of the desired bound.
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
Soit $a \in] 0 ; 1\left[\right.$ et $n>0$ un entier. On note $f_{n}$ la fonction définie sur $\mathbb{R}$ par $f_{n}(x)=x+\frac{x^{2}}{n}$, pour tout réel $x$. Prouver que
$$
\frac{a(1-a) n^{2}+2 a^{2} n+a^{3}}{(1-a)^{2} n^{2}+a(2-a) n+a^{2}}<\underbrace{\left(f_{n} \circ f_{n} \circ \cdots \circ f_{n}\right)}_{n}(a)<\frac{a n+a^{2}}{(1-a) n+a} .
$$
|
Pour tout entier $k \geq 0$, posons $a_{k}=\underbrace{\left(f_{n} \circ f_{n} \circ \cdots \circ f_{n}\right)}_{k}(a)$. En particulier, $a_{0}=a$.
On remarque que, pour tout $k \geq 0$, on a $a_{k+1}=a_{k}+\frac{a_{k}^{2}}{n}>a_{k}$, donc la suite $\left(a_{k}\right)$ est strictement croissante. En particulier, $a_{k} \geq a>0$ pour tout $k \geq 0$.
De plus, pour tout $k \geq 0$, on a $a_{k+1}=\frac{a_{k}\left(a_{k}+n\right)}{n}$ et donc
$$
\frac{1}{a_{k+1}}=\frac{1}{a_{k}}-\frac{1}{a_{k}+n} .
$$
Ainsi, après sommation de ces égalités pour $k=0, \ldots, n-1$, on a
$$
\frac{1}{a_{n}}=\frac{1}{a}-\sum_{k=0}^{n-1} \frac{1}{a_{k}+n}
$$
Puisque $\left(a_{k}\right)$ est strictement croissante et à valeurs positives, on a
$$
\frac{n}{a_{n}+n}<\sum_{k=0}^{n-1} \frac{1}{a_{k}+n}<\frac{n}{a+n}
$$
et ainsi
$$
\frac{1}{a}-\frac{n}{a+n}<\frac{1}{a_{n}}<\frac{1}{a}-\frac{n}{a_{n}+n} .
$$
L'inégalité de gauche est équivalente à $a_{n}<\frac{a n+a^{2}}{(1-a) n+a}$, ce qui est l'inégalité de droite de l'encadrement demandé.
Reportons maintenant cette dernière inégalité dans l'inégalité de droite de (1). Il vient
$$
\frac{1}{a_{n}}<\frac{1}{a}-\frac{n}{\frac{a n+a^{2}}{(1-a) n+a}+n}
$$
ou encore
$$
\frac{a(1-a) n^{2}+2 a^{2} n+a^{3}}{(1-a)^{2} n^{2}+a(2-a) n+a^{2}}<a_{n}
$$
ce qui est l'inégalité de gauche de l'encadrement demandé.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 9.",
"solution_match": "## Solution."
}
|
8a39deab-ed5c-54c1-916c-f7fc40b92c38
| 607,581
|
A polyhedron has 6 vertices and 12 edges. Show that each face is a triangle.
|
Let $F$ be the number of faces, $A$ be the number of edges, and $S$ be the number of vertices. Euler's formula gives $F-A+S=2$, so $F=A-S+2=8$.
Let $x_{i}(i=1,2, \ldots, 8)$ be the number of edges of face $i$. We have $x_{1}+\cdots+x_{8}=2 A=24$ because each edge belongs to exactly two faces. We deduce that
$$
\frac{x_{1}+\cdots+x_{8}}{8}=3
$$
in other words, the average number of edges per face is 3. Since each face has at least 3 edges, it follows that each face is a triangle.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Un polyèdre a 6 sommets et 12 arêtes. Montrer que chaque face est un triangle.
|
Notons $F$ le nombre de faces, $A$ le nombre d'arêtes et $S$ le nombre de sommets. La formule d'Euler donne $F-A+S=2$, donc $F=A-S+2=8$.
Notons $x_{i}(i=1,2, \ldots, 8)$ le nombre d'arêtes de la face $i$. On a $x_{1}+\cdots+x_{8}=2 A=24$ car chaque arête appartient à exactement deux faces. On en déduit que
$$
\frac{x_{1}+\cdots+x_{8}}{8}=3
$$
autrement dit le nombre moyen d'arêtes par face est 3 . Or, chaque face possède au moins 3 arêtes, donc finalement chaque face est un triangle.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 1.",
"solution_match": "\nSolution de l'exercice 1"
}
|
303c2973-8819-58a1-a6f5-d30b0826e796
| 607,583
|
Consider a $2015 \times 2015$ chessboard, from which the $2 \times 2$ square at the bottom right has been removed. Show that it can be tiled with pieces composed of 3 squares in the shape of an L (the pieces can be rotated).
|
As the chessboard can be decomposed into three rectangles $2010 \times 2015$, $5 \times 2004$, and $5 \times 11$, and since 2010 and 2004 are divisible by 6, it suffices to show that
1) For all $n \geqslant 2$ and any integer $m$, a chessboard $6 m \times n$ can be tiled with L-shaped pieces;
2) The chessboard $5 \times 11$ minus the $2 \times 2$ square at the bottom right can be tiled with L-shaped pieces.
For point 1), since such a chessboard is the union of $6 \times n$ chessboards, we reduce to the case $m=1$.
It is clear that one can tile a $3 \times 2$ chessboard, and therefore also $6 \times 2$ and $6 \times 3$ chessboards. We can therefore tile any chessboard of size $6 \times 2k$ or $6 \times (2k+3)$. Now, any integer $n \geqslant 2$ can be written as $2k$ if it is even, and $2k+3$ if it is odd, which concludes the proof.
Point 2) is demonstrated by constructing an example of tiling:

## Exercises of Group A
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
On considère un échiquier $2015 \times 2015$, auquel on a retiré le carré $2 \times 2$ en bas à droite. Montrer qu'on peut le paver par des pièces composées de 3 cases en forme de L (les pièces peuvent être pivotées).
|
Comme l'échiquier peut être décomposé en trois rectangles $2010 \times 2015$, $5 \times 2004$ et $5 \times 11$, et comme 2010 et 2004 sont divisibles par 6 , il suffit de montrer que
1) Pour tout $n \geqslant 2$ et tout entier $m$, un échiquier $6 m \times n$ peut être pavé par des pièces en forme de L;
2) L'échiquier $5 \times 11$ privé du carré $2 \times 2$ en bas à droite peut être pavé par des pièces en forme de L.
Pour le point 1), comme un tel échiquier est réunion d'échiquiers $6 \times \mathrm{n}$, on se ramène à traiter le cas $\mathrm{m}=1$.
Il est clair que l'on peut paver un échiquier $3 \times 2$, donc aussi des échiquiers $6 \times 2$ et $6 \times 3$. On peut donc paver tout échiquier de taille $6 \times 2 k$ ou $6 \times(2 k+3)$. Or, tout entier $n \geqslant 2$ s'écrit sous la forme $2 k$ s'il est pair, et $2 k+3$ s'il est impair, ce qui conclut.
Le point 2) se démontre en construisant un exemple de pavage:

## Exercices du groupe A
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 6.",
"solution_match": "\nSolution de l'exercice 6"
}
|
74d3121a-2c87-5a74-9595-e538a7b53d0b
| 607,588
|
n players participate in a chess tournament. Each player plays exactly one game with each of the other players. A win earns 1 point, a draw earns half a point, and a loss earns no points. A game is said to be abnormal if the winner of the game ends up with a strictly lower score in the tournament than the loser.
a) Show that the proportion of abnormal games is less than or equal to $75 \%$.
b) Is it possible for it to be greater than or equal to $70 \%$?
|
a) Let $m=[n / 2]$. We rank the players according to their scores (among players with the same score, we rank them arbitrarily). We will say that a player ranked among the $m$ best is strong; otherwise, we will say that he is weak.
Let $x$ be the number of normal matches between strong and weak players. The strong players have scored a total of $m(m-1) / 2$ points among themselves, and at most $x$ points in matches against weak players.
Let $S_{1}$ be the total score of the strong players and $S_{2}$ be the total score of the weak players. We then have $S_{1} \leqslant m(m-1) / 2 + x$ and $S_{1} + S_{2} = n(n-1) / 2$.
The average score of the strong players, $\frac{S_{1}}{m}$, is greater than the average score of all players: $\frac{S_{1}}{m} > \frac{n(n-1) / 2}{n}$, i.e., $S_{1} > m(n-1) / 2$. Consequently,
$$
x \geqslant S_{1} - m(m-1) / 2 > \frac{m(n-m)}{2} \geqslant n(n-1) / 8
$$
Since there are a total of $n(n-1) / 2$ matches, the proportion of normal matches is greater than $1 / 4$.
b) Consider a tournament consisting of $2 k+1$ groups of $k$ players (so $n=k(2 k+1)$). We assume that the players in group $i$ draw with each other, lose to the players in groups $i+1, \ldots, i+k$, and win all other matches (here, $i$ is taken modulo $k$). Then all players have the same score.
We will modify the matches of the players in the $(k+1)$-th group so that the scores are different. For all $i$, we replace $i k$ wins of players in the $(k+1)$-th group against players in the $(k+1-i)$-th group with draws, so that each player in the $(k+1)$-th group sees their score decrease by $i / 2$ while each player in the $(k+1-i)$-th group sees their score increase by $i / 2$.
Similarly, we replace $i k$ losses of the $(k+1)$-th group against the $(k+1+i)$-th group with draws.
Then the top places in the tournament are taken by the players in the first group, then the second, etc.
The players in groups $i \leqslant k$ have lost $k^{3} - i k$ matches, the players in groups $i > k+1$ have lost $(2 k+1-i) k^{2}$ abnormal matches, and the players in the $(k+1)$-th group have lost $k^{3} - k\left(\frac{1}{2} k(k+1)\right)$ abnormal matches. After all calculations, we obtain a total of
$$
\frac{3}{2} k^{4} - \frac{1}{2} k^{3} - k^{2}
$$
abnormal matches.
There are a total of $k(2 k+1)(k(2 k+1)-1) / 2$ matches. We verify that for $k=100$, the proportion of abnormal matches exceeds $70 \%$.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
n joueurs participent à un tournoi d'échecs. Chaque joueur fait exactement une partie avec chacun des autres joueurs. Une victoire rapporte 1 point, un match nul un demipoint et une défaite aucun point. Une partie est dite anormale si le gagnant de cette partie obtient un score au tournoi strictement plus faible que le perdant.
a) Montrer que la proportion de parties anormales est inférieure ou égale à $75 \%$.
b) Est-il possible qu'elle soit supérieure ou égale à $70 \%$ ?
|
a) Soit $m=[n / 2]$. On classe les joueurs suivant leur score (parmi les joueurs ayant le même score, on les classe arbitrairement). On dira qu'un joueur classé parmi les $m$ meilleurs est fort; sinon, on dira qu'il est faible.
Soit x le nombre de parties normales entre les joueurs forts et les joueurs faibles. Les joueurs forts ont marqué au total $m(m-1) / 2$ points entre eux, et au plus $x$ lors de parties contre les joueurs faibles.
Notons $S_{1}$ le score total des joueurs forts et $S_{2}$ le score total des joueurs faibles. On a donc $S_{1} \leqslant \mathrm{~m}(\mathrm{~m}-1) / 2+x$ et $\mathrm{S}_{1}+\mathrm{S}_{2}=\mathrm{n}(\mathrm{n}-1) / 2$.
Le score moyen des joueurs forts, $\frac{\mathrm{S}_{1}}{\mathrm{~m}}$, est supérieur au score moyen de tous les joueurs: $\frac{S_{1}}{m}>\frac{n(n-1) / 2}{n}$, i.e. $S_{1}>m(n-1) / 2$. Par conséquent,
$$
x \geqslant S_{1}-m(m-1) / 2>\frac{m(n-m)}{2} \geqslant n(n-1) / 8
$$
Comme il y a au total $n(n-1) / 2$ parties, la proportion de parties normales est supérieure à $1 / 4$.
b) Considérons un tournoi constitué de $2 k+1$ groupes de $k$ joueurs (on a donc $n=k(2 k+1)$ ). On suppose que les joueurs du groupe $i$ font match nul entre eux, perdent contre les joueurs des groupes $i+1, \ldots, i+k$ et gagnent tous les autres matchs (ici, $i$ est pris modulo $k$ ). Alors tous les joueurs ont le même score.
On va modifier les parties des joueurs du $k+1$-ième groupe afin que les scores soient différents. Pour tout $i$, on remplace $i k$ victoires de joueurs du $(k+1)$-ième groupe contre des joueurs du $(k+1-i)$-ème groupe par des matchs nuls, de sorte que chaque joueur $\mathrm{du}(k+1)$ ième groupe voie son score décroître de $i / 2$ tandis que chaque joueur du ( $k+1-\mathfrak{i}$ )-ème score voie son score augmenter de $i / 2$.
De même, on remplace $i k$ défaites du $(k+1)$-ième groupe contre les $(k+1+i)$-ème groupe par des matchs nuls.
Alors les premières places dans le tournoi sont prises par les joueurs du premier groupe, puis du deuxième, etc.
Les joueurs des groupes $i \leqslant k$ ont perdu $k^{3}-i k$ parties, les joueurs des groupes $i>k+1$ perdu $(2 k+1-i) k^{2}$ parties anormales, et les joueurs du $(k+1)$-ième groupe ont perdu $k^{3}-$ $k\left(\frac{1}{2} k(k+1)\right)$ parties anormales. Tous calculs faits, on obtient en tout
$$
\frac{3}{2} k^{4}-\frac{1}{2} k^{3}-k^{2}
$$
parties anormales.
Il y a au total $k(2 k+1)(k(2 k+1)-1) / 2$ parties. On vérifie que pour $k=100$, la proportion de parties anormales dépasse $70 \%$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "\nSolution de l'exercice 7"
}
|
29af45a8-62e3-5b78-9e5f-bd3616505820
| 607,589
|
Let \( a \) and \( b \) be two integers such that \( \mathrm{a}+\mathrm{b} \) is not divisible by 3. Show that it is not possible to color the integers in three colors such that for any integer \( n \), the three numbers \( n, n+a \), and \( n+b \) are of different colors.
|
Suppose by contradiction that such a coloring exists. We will denote $x \sim y$ if $x$ and $y$ are of the same color.
For all $n$, the integers $(n+a)+b$ and $x+a$ are not of the same color, and similarly $n+a+b$ is not of the same color as $n+b$, so $n+a+b \sim n$. It immediately follows that $0 \sim p(a+b)$ for all integers $p$, and in particular $0 \sim a(a+b)$.
On the other hand, $n+a, n+2a$, and $n+a+b$ are of different colors, so $n, n+a$, and $n+2a$ are of different colors. By applying the above to $n+a$, we deduce that $n+3a$ is of the same color as $n$, so for any integer $j$, the number $ja$ is of the same color as $ra$ where $r$ is the remainder of the Euclidean division of $j$ by 3.
By applying this to $j=a+b$, we deduce that $0 \sim ra$ where $r$ is the remainder of the Euclidean division of $a+b$ by 3, which is impossible since 0, $a$, and $2a$ are of different colors and $r \in \{1,2\}$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soient a et b deux entiers tels que $\mathrm{a}+\mathrm{b}$ n'est pas divisible par 3. Montrer que l'on ne peut pas colorier les entiers relatifs en trois couleurs de sorte que que pour tout entier $n$, les trois nombres $n, n+a$ et $n+b$ soient de couleurs différentes.
|
Supposons par l'absurde qu'il existe un tel coloriage. On notera $x \sim y$ si $x$ et $y$ sont de la même couleur.
Pour tout $n$, les entiers $(n+a)+b$ et $x+a$ ne sont pas de la même couleur, et de même $n+a+b$ n'est pas de la même couleur que $n+b$, donc $n+a+b \sim n$. Il vient immédiatement $0 \sim p(a+b)$ pour tout entier $p$, et en particulier $0 \sim a(a+b)$.
D'autre part, $n+a, n+2 a$ et $n+a+b$ sont de couleurs différentes, donc $n, n+a$ et $n+2 a$ sont de couleurs différentes. En appliquant ce qui précède à $n+a$, on en déduit que $n+3 a$ est de même couleur que $n$, donc pour tout entier $j$, le nombre ja est de la même couleur que ra où $r$ est le reste de la division Euclidienne de j par 3.
En appliquant ceci à $j=a+b$, on en déduit que $0 \sim r a$ où $r$ est le reste de la division Euclidienne de $\mathrm{a}+\mathrm{b}$ par 3, ce qui est impossible puisque 0 , a et 2 a sont de couleurs différentes et $\mathrm{r} \in\{1,2\}$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 8.",
"solution_match": "\nSolution de l'exercice 8"
}
|
42f850ed-a82d-545d-9dbb-792806b4f143
| 607,590
|
Let $\mathrm{n} \geqslant 1$ be an integer.
Consider a set of $4 \mathrm{n}+5$ points in the plane, no three of which are collinear, and each colored either red or blue.
Prove that there exist $n$ triangles whose vertices are all of the same color (the same for all triangles), and whose respective interiors are pairwise disjoint and do not contain any colored points.
|
Lemme. Let $\mathrm{n} \geqslant 3$ and $\mathrm{m} \geqslant 1$ be integers.
Consider a convex $n$-gon $P$ and $m$ of its interior points, with no three of the $n+m$ points being collinear. Then, $P$ can be triangulated into $n+2 m-2$ triangles whose vertices are all among the $n+m$ points, and none of these triangles contain any of the $m$ points in their interior.
## Proof of the lemma. We proceed by induction on $m$.
For $\mathrm{m}=1$, it suffices to connect the interior point to each of the vertices, which gives a suitable triangulation of $P$ into $k$ triangles.
Suppose the statement is true for the value $m$ and consider $m+1$ interior points of $P$. Let $I$ be one of these interior points. Using the other $m$ interior points, by the induction hypothesis, we can triangulate $P$ as desired into $k+2 m-2$ triangles. Since $I$ is interior to $P$, it is therefore interior to one of these triangles. By connecting $I$ to each of the three vertices of this triangle, we obtain a suitable triangulation into $k+2 m-2+2=k+2(m+1)-2$ triangles, which completes the proof.
Returning to the exercise. Let $r$ (resp. $b$) be the number of red (resp. blue) points. We have $r+b=4 n+5$.
Without loss of generality, we can assume that $r \geqslant b$ and thus $r \geqslant 2 n+3$.
Let $P$ be the convex hull of the red points, and suppose $P$ is a $k$-gon. In particular, there are no red points outside of $P$, so there are $m$ red points interior to $P$, with $\mathrm{k}+\mathrm{m}=\mathrm{r} \geqslant 2 \mathrm{n}+3$. (1)
Let $w$ be the number of blue points interior to $P$.
According to the lemma, considering only the red points, we can obtain a triangulation of $P$ into $k+2 m-2$ triangles with red vertices and containing no red points in their interior. If at least $n$ of these triangles contain no blue points, we are done.
Otherwise, at most $n-1$ of the triangles with red vertices contain no blue points. This ensures that at least $k+2 m-2-(n-1)=k+2 m-(n+1)$ triangles with red vertices contain at least one blue point, and since these triangles have pairwise disjoint interiors, we have $w \geqslant k+2 m-(n+1)$.
Let $Q$ be the convex hull of these $w$ blue points interior to $P$. As above, we can triangulate $Q$ into at least $w-2$ triangles that do not contain any blue points in their interiors.
By contradiction: suppose that at most $n-1$ of these blue triangles do not contain any red points.
Then, at least $w-2-(n-1)$ blue triangles contain at least one red point, and we have $m \geqslant w-(n+1)$. Consequently, we have $m \geqslant k+2 m-(n+1)-(n+1)$, hence $k+m \leqslant 2 n+2$, contradicting (1).
Thus, at least $n$ of these triangles with blue vertices contain no red points, which concludes the proof.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Soit $\mathrm{n} \geqslant 1$ un entier.
On considère un ensemble de $4 \mathrm{n}+5$ points du plan, trois jamais alignés, et chacun coloré soit en rouge soit en bleu.
Prouver qu'il existe $n$ triangles dont les sommets sont tous d'une même couleur (la même pour tous les triangles), et dont les intérieurs respectifs sont deux à deux disjoints et ne contiennent aucun point coloré.
|
Lemme. Soit $\mathrm{n} \geqslant 3$ et $\mathrm{m} \geqslant 1$ des entiers.
On considère un n-gone convexe $P$ et $m$ de ses points intérieurs, trois des $n+m$ points jamais alignés. Alors, on peut trianguler $P$ en $n+2 m-2$ triangles dont les somments sont tous parmi les $n+m$ points, aucun de ces triangles ne contenant un des $m$ points en son intérieur.
## Preuve du lemme. On procède par récurrence sur m.
Pour $\mathrm{m}=1$, il suffit de joindre le point intérieur à chacun des sommets, ce qui donne une triangulation adéquate de $P$ en $k$ triangles.
Supposons que l'affirmation soit vraie pour la valeur $m$ et donnons-nous $m+1$ points intérieurs à $P$. Soit I un de ces points intérieurs. A l'aide des m autres points intérieurs, d'après l'hypothèse de récurrence, on peut trianguler $P$ de la façon souhaitée en $k+2 m-2$ triangles. Comme I est intérieur à $P$, il est donc intérieur à l'un de ces triangles. En joignant I à chacun des trois sommets de ce triangle, on obtient ainsi une triangulation adéquate en $k+2 \mathrm{~m}-2+2=\mathrm{k}+$ $2(m+1)-2$ triangles, ce qui achève la preuve.
Revenons à l'exercice. Notons $r$ (resp. b) le nombre de points rouges (resp. bleus). On a donc $r+b=4 n+5$.
Sans perte de généralité, on peut supposer que $r \geqslant b$ et donc $r \geqslant 2 \mathfrak{n}+3$.
Soit $P$ l'enveloppe convexe des points rouges, et on suppose que $P$ est un k-gone. En particulier, il n'existe aucun point rouge en dehors de $P$, donc il y a $m$ points rouges intérieurs à $P$, avec $\mathrm{k}+\mathrm{m}=\mathrm{r} \geqslant 2 \mathrm{n}+3$. (1)
On note $w$ le nombre points bleus intérieurs à $P$.
D'après le lemme, en ne considérant que les points rouges, on peut obtenir une triangulation de $P$ en $k+2 m-2$ triangles à sommets rouges et ne contenant intérieurement aucun point rouge. Si au moins n de ces triangles ne contiennent aucun point bleu, c'est fini.
Sans quoi, au plus $n-1$ des triangles à sommets rouges ne contiennent pas de point bleu. Cela assure qu'au moins $k+2 m-2-(n-1)=k+2 m-(n+1)$ triangles à sommets rouges contiennent chacun au moins un point bleu et, ces triangles étant d'intérieurs deux à deux disjoints, on a donc $w \geqslant k+2 m-(n+1)$.
Soit $Q$ l'enveloppe convexe de ces $w$ points bleus intérieurs à $P$. Comme ci-dessus, on peut trianguler $Q$ en au moins $w-2$ triangles ne contenant aucun point bleu en leurs intérieurs.
Par l'absurde : supposons qu'au plus $n-1$ de ces triangles bleus ne contiennent pas de point rouge.
Alors, au moins $w-2-(n-1)$ triangles bleus contiennent au moins un point rouge et on a $m \geqslant w-(n+1)$. Par suite, on a $m \geqslant k+2 m-(n+1)-(n+1)$, d'où $k+m \leqslant 2 n+2$, en contradiction avec (1).
Ainsi, au moins $n$ de ces triangles à sommets bleus ne contiennent aucun point rouge, ce qui conclut.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 4.",
"solution_match": "## Solution de l'exercice 4"
}
|
112b903f-304b-5940-8ef7-9741b474ea93
| 607,595
|
Let $ABC$ be a non-isosceles triangle inscribed in a circle $\Gamma$ of radius $R$. The circle passing through $A$ and tangent to $[BC]$ at $C$ intersects the circle passing through $B$ and tangent to $[AC]$ at $C$ at point $D$.
a) Show that $CD \leqslant R$.
b) Show that as $C$ moves on $\Gamma$, the line $(CD)$ passes through a fixed point.
|
a) First, we observe that $(A D, A C)=(C D, C B)$ and $(B C, B D)=(C A, C D)$, so $D A C$ and $D C B$ are directly similar. We deduce that $D^{2}=D A \cdot D B$.
Furthermore, denoting $\gamma=(\overrightarrow{C A}, \overrightarrow{C B})$, we have $(\overrightarrow{D C}, \overrightarrow{D A})=\pi-\gamma$ and similarly $(\overrightarrow{D B}, \overrightarrow{D C})=\pi-\gamma$, so $(\overrightarrow{D A}, \overrightarrow{D B})=2 \gamma$. It follows that
$$
\begin{aligned}
A^{2} & =D^{2}+D^{2}-2 D A \cdot D B \cos 2 \gamma=D A^{2}+D^{2}-2 D A \cdot D B\left(1-2 \sin ^{2} \gamma\right) \\
& =(D A-D B)^{2}+4 D A \cdot D B \sin ^{2} \gamma \geqslant 4 D A \cdot D B \sin ^{2} \gamma=(2 D C \sin \gamma)^{2} .
\end{aligned}
$$
Since $2 R=\frac{A B}{\sin \gamma}$, we have $R \geqslant C D$.
b) We will show that (CD) passes through the point of intersection of the tangents at $A$ and $B$ to the circumcircle, which we will call $S$. It is known that (CS) is the symmedian of the triangle passing through C, so it suffices to show that (CD) is a symmedian.
Let $M$ be the midpoint of $[A B]$. Since the areas of $A C M$ and $B C M$ are equal, we have $\frac{1}{2} C A \times C M \times$ $\sin \widehat{A C M}=\frac{1}{2} C B \times C M \times \sin \widehat{M C B}$, so $C A \sin \widehat{A C M}=C B \sin \widehat{M C B}$.
We deduce that if $\Delta$ is the symmedian and $\theta$ is the angle between $(C A)$ and $\Delta$, then $\frac{\sin \theta}{\sin (\gamma-\theta)}=$ $\frac{\sin \widehat{M C B}}{\sin \widehat{A C M}}=\frac{C A}{C B}$. It suffices to show that $\frac{\sin \widehat{A C D}}{\sin \widehat{D C B}}=\frac{C A}{C B}$.
$$
\begin{aligned}
\frac{\sin \widehat{A C D}}{\sin \widehat{D C B}} & =\frac{\sin \widehat{A C D}}{A D} \times \frac{D B}{\sin \widehat{D C B}} \times \frac{D A}{D B} \\
& =\frac{\sin \widehat{C D A}}{A C} \times \frac{B C}{\sin \widehat{B D C}} \times \frac{D A}{D B}
\end{aligned}
$$
Since $\widehat{C D A}=\widehat{B D C}=\pi-\gamma$ and $\frac{B C}{A C}=\frac{D C}{D A}=\frac{D B}{D C}$, we have
$$
\frac{\sin \widehat{A C D}}{\sin \widehat{D C B}}=\frac{B C}{A C} \times \frac{D A}{D C} \times \frac{D C}{D B}=\frac{D C}{D B}=\frac{C A}{C B}
$$
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle non isocèle inscrit dans un cercle $\Gamma$ de rayon $R$. Le cercle passant par $A$ et tangent en $C$ à $[B C]$ recoupe le cercle passant par $B$ et tangent en $C$ à $[A C]$ au point D .
a) Montrer que $C D \leqslant R$.
b) Montrer que lorsque $C$ se déplace sur $\Gamma$, la droite (CD) passe par un point fixe.
|

a) On observe d'abord que $(A D, A C)=(C D, C B)$ et $(B C, B D)=(C A, C D)$, donc $D A C$ et $D C B$ sont directement semblables. On en déduit que $D^{2}=D A \cdot D B$.
De plus, en notant $\gamma=(\overrightarrow{C A}, \overrightarrow{C B})$, on a $(\overrightarrow{D C}, \overrightarrow{D A})=\pi-\gamma$ et de même $(\overrightarrow{D B}, \overrightarrow{D C})=\pi-\gamma$, donc $(\overrightarrow{D A}, \overrightarrow{D B})=2 \gamma$. Il vient
$$
\begin{aligned}
A^{2} & =D^{2}+D^{2}-2 D A \cdot D B \cos 2 \gamma=D A^{2}+D^{2}-2 D A \cdot D B\left(1-2 \sin ^{2} \gamma\right) \\
& =(D A-D B)^{2}+4 D A \cdot D B \sin ^{2} \gamma \geqslant 4 D A \cdot D B \sin ^{2} \gamma=(2 D C \sin \gamma)^{2} .
\end{aligned}
$$
Or, $2 R=\frac{A B}{\sin \gamma}$, donc $R \geqslant C D$.
b) On va montrer que (CD) passe par le point de rencontre des tangentes en $A$ et $B$ au cercle circonscrit, que nous appellerons $S$. Il est connu que (CS) est la symédiane du triangle passant par C, donc il suffit de montrer que (CD) est une symédiane.
Notons $M$ le milieu de $[A B]$. Comme les aires de $A C M$ et $B C M$ sont égales, on a $\frac{1}{2} C A \times C M \times$ $\sin \widehat{A C M}=\frac{1}{2} C B \times C M \times \sin \widehat{M C B}$, donc $C A \sin \widehat{A C M}=C B \sin \widehat{M C B}$.
On en déduit que si $\Delta$ est la symédiane et $\theta$ est l'angle entre $(C A)$ et $\Delta$, alors $\frac{\sin \theta}{\sin (\gamma-\theta)}=$ $\frac{\sin \widehat{M C B}}{\sin \widehat{A C M}}=\frac{C A}{C B}$. Il suffit donc de montrer que $\frac{\sin \widehat{A C D}}{\sin \widehat{D C B}}=\frac{C A}{C B}$.
$$
\begin{aligned}
\frac{\sin \widehat{A C D}}{\sin \widehat{D C B}} & =\frac{\sin \widehat{A C D}}{A D} \times \frac{D B}{\sin \widehat{D C B}} \times \frac{D A}{D B} \\
& =\frac{\sin \widehat{C D A}}{A C} \times \frac{B C}{\sin \widehat{B D C}} \times \frac{D A}{D B}
\end{aligned}
$$
Or, $\widehat{C D A}=\widehat{B D C}=\pi-\gamma$ et $\frac{B C}{A C}=\frac{D C}{D A}=\frac{D B}{D C}$, donc
$$
\frac{\sin \widehat{A C D}}{\sin \widehat{D C B}}=\frac{B C}{A C} \times \frac{D A}{D C} \times \frac{D C}{D B}=\frac{D C}{D B}=\frac{C A}{C B}
$$
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 5.",
"solution_match": "## Solution de l'exercice 5"
}
|
e3041d67-221d-54c5-82b4-5d1b43971452
| 607,596
|
Do there exist strictly positive integers $a$ and $b$ such that $a^{n}+n^{b}$ and $b^{n}+n^{a}$ are coprime for all integers $n \geqslant 0$?
|
By contradiction: suppose there exist such integers $a$ and $b$.
By symmetry, we can assume that $a \geqslant b$.
If $d=\operatorname{gcd}(a, b)$, then for $n=d$, it is clear that $d$ divides $a^{d}+d^{b}$ and $b^{d}+d^{a}$. Since these two numbers are supposed to be coprime, it follows that $d=1$.
Let $N=a^{a}+b^{b}$. We have $N>1$ so there exists a prime number $p$ that divides $N$. Moreover, $p$ cannot divide $a$ without also dividing $b$, which contradicts $d=1$. Thus, $a$ is invertible modulo $p$ and there exists an integer $k \in\{0, \cdots, p-1\}$ such that $k a=b \bmod [p]$.
We then choose $n=k+p(a-b-k+p-1)$. By Fermat's little theorem, we get:
$$
a^{n}+n^{b} \equiv a^{k} \cdot a^{a-b-k+p-1}+k^{b} \equiv a^{a-b}+k^{b} \bmod [p]
$$
where $a^{b}\left(a^{n}+n^{b}\right) \equiv a^{a}+b^{b} \equiv 0 \bmod [p]$,
and since $p$ does not divide $a$, we have $a^{n}+n^{b} \equiv 0 \bmod [p]$.
Similarly, we have $b^{n}+n^{a} \equiv 0 \bmod [p]$.
But then $p$ divides both $a^{n}+n^{b}$ and $b^{n}+n^{a}$, which contradicts their being coprime.
Finally, there do not exist such integers.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Existe-t-il des entiers strictement positifs $a$ et $b$ tels que $a^{n}+n^{b}$ et $b^{n}+n^{a}$ soient premiers entre eux pour tout entier $n \geqslant 0$ ?
|
Par l'absurde : supposons qu'il existe de tels entiers a et b.
Par symétrie, on peut supposer que $a \geqslant b$.
Si $d=\operatorname{pgcd}(a, b)$ alors, pour $n=d$, il est clair que $d$ divise $a^{d}+d^{b}$ et $b^{d}+d^{a}$. Or ces deux nombres étant censés être premiers entre eux, c'est que $d=1$.
Soit $N=a^{a}+b^{b}$. On a $N>1$ donc il existe un nombre premier $p$ qui divise $N$. De plus, $p$ ne peut diviser a sans quoi il devrait diviser également $b$, en contradiction avec $d=1$. Ainsi, $a$ est inversible modulo $p$ et il existe un entier $k \in\{0, \cdots, p-1\}$ tel que $k a=b \bmod [p]$.
On choisit alors $n=k+p(a-b-k+p-1)$. D'après le petit théorème de Fermat, il vient :
$$
a^{n}+n^{b} \equiv a^{k} \cdot a^{a-b-k+p-1}+k^{b} \equiv a^{a-b}+k^{b} \bmod [p]
$$
$d^{\prime}$ où $a^{b}\left(a^{n}+n^{b}\right) \equiv a^{a}+b^{b} \equiv 0 \bmod [p]$,
et, puisque $p$ ne divise par $a$, on a alors $a^{n}+n^{b} \equiv 0 \bmod [p]$.
On prouve de même, on a $b^{n}+n^{a} \equiv 0 \bmod [p]$.
Mais, alors $p$ divise à la fois $a^{n}+n^{b}$ et $b^{n}+n^{a}$, ce qui contredit qu'ils soient premiers entre eux.
Finalement, il n'existe pas de tels entiers.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 6.",
"solution_match": "## Solution de l'exercice 6"
}
|
4f192284-4eee-54b0-a9a3-a3bddde8d80a
| 607,597
|
The Xantians are the inhabitants, potentially in infinite number, of the planet Xanta. Regarding themselves and their peers, the Xantians are capable of feeling two types of emotions, which they call love and respect. It has been observed that:
- Each Xantian loves one and only one Xantian, and respects one and only one Xantian.
- If $A$ loves $B$, then any Xantian who respects $A$ also loves $B$.
- If $A$ respects $B$, then any Xantian who loves $A$ also respects $B$.
- Each Xantian is loved by at least one Xantian.
Is it true that each Xantian respects the Xantian they love?
|
For each Xantian $x$, let $f(x)$ and $g(x)$ denote the Xantians loved and respected by $x$.
The first condition ensures that we have well-defined functions $f$ and $g$ from the set $X$ of Xantiens to itself.
The question is whether, for all $x$, we have $f(x)=g(x)$.
In fact, we will even prove that, for all $x$, we have $f(x)=g(x)=x$.
Let $x$ be a Xantian.
He respects $g(x)$, who, in turn, loves $f(g(x))$.
The second condition therefore ensures that $f(g(x))=f(x)$ for all $x$. (1)
Similarly, the third condition leads to $g(f(x))=g(x)$ for all $x$. (2)
Finally, the fourth condition means that $f$ is surjective.
Let $x$ be a Xantian. There therefore exists a Xantian $y$ such that $f(y)=x$.
We have $f(g(f(y)))=f(g(y))$ according to (2),
and thus, according to (1), it follows that $f(f(y))=f(y)$, or $f(x)=x$.
From (1), we immediately deduce that $g(x)=x$.
Ultimately, for all $x$, we have $f(x)=g(x)=x$.
|
proof
|
Yes
|
Yes
|
proof
|
Logic and Puzzles
|
Les Xantiens sont les habitants, en nombre éventuellement infini, de la planète Xanta. Vis-à-vis d'eux-mêmes et de leurs semblables, les Xantiens sont capables de ressentir deux types d'émotions, qu'ils appellent amour et respect. Il a été observé que:
- Chaque Xantien aime un et un seul Xantien, et respecte un et un seul Xantien.
- Si $A$ aime $B$, alors tout Xantien qui respecte $A$ aime également $B$.
- Si $A$ respecte $B$, alors tout Xantien qui aime $A$ respecte également $B$.
- Chaque Xantien est aimé d'au moins un Xantien.
Est-il vrai que chaque Xantien respecte le Xantien qu'il aime?
|
Pour chaque Xantien $x$, désignons respectivement par $f(x)$ et $g(x)$ les Xantiens aimés et respectés par $x$.
La première condition assure que l'on a bien défini des fonctions $f$ et $g$ de l'ensemble $X$ des Xantiens sur lui-même.
Il s'agit de savoir si, pour tout $x$, on a $f(x)=g(x)$.
En fait, nous allons même prouver que, pour tout $x$, on a $f(x)=g(x)=x$.
Soit $x$ un Xantien.
Il respecte $g(x)$ qui, de son côté, aime $f(g(x))$.
La seconde condition assure donc que $f(g(x))=f(x)$ pour tout $x$. (1)
De même, la troisième condition conduit à $g(f(x))=g(x)$ pour tout $x$. (2)
Enfin, la quatrième condition signifie que f est surjective.
Soit $x$ un Xantien. Il existe donc un Xantien $y$ tel que $f(y)=x$.
Or, on a $f(g(f(y)))=f(g(y))$ d'après (2)
et ainsi, d'après (1), il vient $f(f(y))=f(y)$, ou encore $f(x)=x$.
De (1), on déduit alors immédiatement que $g(x)=x$.
Finalement, pour tout $x$, on a bien $f(x)=g(x)=x$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "## Solution de l'exercice 7"
}
|
2cdc2e8a-a498-57aa-8158-657061821486
| 607,598
|
Let $ABC$ be a triangle such that $\widehat{A}=40^{\circ}$ and $\widehat{B}=60^{\circ}$. Let $D$ and $E$ be points on $[AC]$ and $[\mathrm{AB}]$ such that $\widehat{\mathrm{CBD}}=40^{\circ}$ and $\widehat{\mathrm{ECB}}=70^{\circ}$. We denote $F$ as the intersection of $(BD)$ and $(CE)$. Show that $(A F) \perp(B C)$.
|

In $\widehat{\mathrm{BFC}}=180^{\circ}-\widehat{\mathrm{CBF}}-\widehat{\mathrm{FCB}}=180^{\circ}-40^{\circ}-70^{\circ}=70^{\circ}=\widehat{\mathrm{FCB}}$, so BCF is isosceles at B. It follows that $B C=B F$.
Let $M$ be the intersection point between the bisector of $\widehat{C B F}$ and ( $A C$ ). We have $\widehat{B M A}=40^{\circ}=\widehat{B A M}$, so $M A=M B$.
On the other hand, $\widehat{B M C}=180^{\circ}-\widehat{C B M}-\widehat{M C B}=180^{\circ}-20^{\circ}-80^{\circ}=80^{\circ}=\widehat{M C B}$, so $B C=B M$.
From the above, we deduce that $M A=B F$.
Let $\mathrm{B}^{\prime} \in(\mathrm{BC})$ such that $A B^{\prime}$ is equilateral. Let $\Delta$ be the bisector of $\widehat{\mathrm{B}^{\prime} \mathrm{BA}}$. Since $\mathrm{BF}=\mathrm{BM}$ and $\widehat{\mathrm{FBA}}=\widehat{\mathrm{CBM}}$, the points $M$ and $F$ are symmetric with respect to $\Delta$. Also, $A$ and $B^{\prime}$ are symmetric with respect to $\Delta$, so $M A=\mathrm{FB}^{\prime}$.
Finally, $\mathrm{FB}^{\prime}=\mathrm{FB}$, so $F$ lies on the perpendicular bisector of $\left[\mathrm{BB}^{\prime}\right]$, which is also the altitude ( $A F$ ) of the triangle $A B B^{\prime}$.
Another solution. Let $H$ be the projection of $F$ on $[B C]$ and $H^{\prime}$ the projection of $A$ on [BC]. It suffices to show that $\mathrm{H}=\mathrm{H}^{\prime}$. For this, it is enough to see that $\mathrm{BH}=\mathrm{BH}^{\prime}$.
We have $B^{\prime}=A B \cos 60$ and $B H=B F \cos 40=B C \cos 40$. Since $\frac{A B}{B C}=\frac{\sin 80}{\sin 40}$, it suffices to show that $\sin 80 \cos 60=\sin 40 \cos 40$, which is equivalent (given that $\cos 60=\frac{1}{2}$) to $\sin 80=2 \sin 40 \cos 40$, which is true according to the general formula $\sin 2 x=2 \sin x \cos x$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle tel que $\widehat{A}=40^{\circ}$ et $\widehat{B}=60^{\circ}$. Soient $D$ et $E$ des points de [AC] et $[\mathrm{AB}]$ tels que $\widehat{\mathrm{CBD}}=40^{\circ}$ et $\widehat{\mathrm{ECB}}=70^{\circ}$. On note F l'intersection de (BD) et (CE). Monter que $(A F) \perp(B C)$.
|

On a $\widehat{\mathrm{BFC}}=180^{\circ}-\widehat{\mathrm{CBF}}-\widehat{\mathrm{FCB}}=180^{\circ}-40^{\circ}-70^{\circ}=70^{\circ}=\widehat{\mathrm{FCB}}$ donc BCF est isocèle en B . Il vient $B C=B F$.
Soit $M$ le point d'intersection entre la bissectrice de $\widehat{C B F}$ et ( $A C$ ). On a $\widehat{B M A}=40^{\circ}=\widehat{B A M}$ donc $M A=M B$.
D'autre part, $\widehat{B M C}=180^{\circ}-\widehat{C B M}-\widehat{M C B}=180^{\circ}-20^{\circ}-80^{\circ}=80^{\circ}=\widehat{M C B}$ donc $B C=B M$.
On déduit de ce qui précède que $M A=B F$.
Soit $\mathrm{B}^{\prime} \in(\mathrm{BC})$ tel que $A B^{\prime}$ est équilatéral. Soit $\Delta$ la bissectrice de $\widehat{\mathrm{B}^{\prime} \mathrm{BA}}$. Comme $\mathrm{BF}=\mathrm{BM}$ et $\widehat{\mathrm{FBA}}=\widehat{\mathrm{CBM}}$, les points $M$ et $F$ sont symétriques par rapport à $\Delta$. Or, $A$ et $B^{\prime}$ sont aussi symétriques par rapport à $\Delta$, donc $M A=\mathrm{FB}^{\prime}$.
Finalement, $\mathrm{FB}^{\prime}=\mathrm{FB}$, donc $F$ appartient à la médiatrice de $\left[\mathrm{BB}^{\prime}\right]$, qui est aussi la hauteur ( $A F$ ) du triangle $A B B^{\prime}$.
Autre solution. Notons $H$ le projeté de $F$ sur $[B C]$ et $H^{\prime}$ le projeté de $A$ sur [BC]. Il s'agit de montrer que $\mathrm{H}=\mathrm{H}^{\prime}$. Pour cela, il suffit de voir que $\mathrm{BH}=\mathrm{BH}^{\prime}$.
On a $B^{\prime}=A B \cos 60$ et $B H=B F \cos 40=B C \cos 40$. Comme $\frac{A B}{B C}=\frac{\sin 80}{\sin 40}$, il suffit de montrer que $\sin 80 \cos 60=\sin 40 \cos 40$, c'est-à-dire (compte tenu de $\cos 60=\frac{1}{2}$ ) que $\sin 80=$ $2 \sin 40 \cos 40$, ce qui est vrai d'après la formule générale $\sin 2 x=2 \sin x \cos x$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 9.",
"solution_match": "## Solution de l'exercice 9"
}
|
a5dcc28a-cdea-51ce-8a4d-e7fc1e277754
| 607,600
|
For any strictly positive integer $x$, we denote $S(x)$ as the sum of the digits of its decimal representation.
Let $k>0$ be an integer. We define the sequence $\left(x_{n}\right)$ by $x_{1}=1$ and $x_{n+1}=S\left(k x_{n}\right)$ for all $n>0$.
Prove that $x_{n}<27 \sqrt{k}$, for all $n>0$.
|
Lemme. For any integer $s \geqslant 0$, we have $10^{s} \geqslant(s+1)^{3}$.
Proof of the lemma. We reason by induction on $s$.
For $s=0$, we have $10^{0}=1=(0+1)^{3}$.
Suppose the inequality is true for the value $s$. Then:
$10^{\mathrm{s}+1} \geqslant 10(\mathrm{~s}+1)^{3}$ according to the induction hypothesis
$=10 s^{3}+30 s^{2}+30 s+10$
$\geqslant \mathrm{s}^{3}+6 \mathrm{~s}^{2}+12 \mathrm{~s}+8$
$=(s+2)^{3}$, which completes the proof.
If $x>0$ is an integer whose decimal representation uses $s+1$ digits, we have $S(x) \leqslant 9(s+1)$ and $10^{s} \leqslant x<10^{s+1}$. From the lemma, we have $s+1 \leqslant 10^{\frac{s}{3}}$, so $s+1 \leqslant x^{\frac{1}{3}}$ and thus $S(x) \leqslant 9 x^{\frac{1}{3}}$.
Now let's show by induction that $x_{n}<27 \sqrt{k}$ for all $n$. The statement is clear for $n=1$. Suppose $x_{n}<27 \sqrt{k}$, then $x_{n+1}=S\left(k x_{n}\right) \leqslant 9\left(k x_{n}\right)^{\frac{1}{3}}<9(27 k \sqrt{k})^{\frac{1}{3}}=9 \times 3 \times \sqrt{k}=$ $27 \sqrt{\mathrm{k}}$, hence the result.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Pour tout entier strictement positif $x$, on note $S(x)$ la somme des chiffres de son écriture décimale.
Soit $k>0$ un entier. On définit la suite $\left(x_{n}\right)$ par $x_{1}=1$ et $x_{n+1}=S\left(k x_{n}\right)$ pour tout $n>0$.
Prouver que $x_{n}<27 \sqrt{k}$, pour tout $n>0$.
|
Lemme. Pour tout entier $s \geqslant 0$, on a $10^{s} \geqslant(s+1)^{3}$.
Preuve du lemme. On raisonne par récurrence sur s.
Pour $s=0$, on a $10^{0}=1=(0+1)^{3}$.
Supposons l'inégalité vraie pour la valeur s. Alors :
$10^{\mathrm{s}+1} \geqslant 10(\mathrm{~s}+1)^{3}$ d'après l'hypothèse de récurrence
$=10 s^{3}+30 s^{2}+30 s+10$
$\geqslant \mathrm{s}^{3}+6 \mathrm{~s}^{2}+12 \mathrm{~s}+8$
$=(s+2)^{3}$, ce qui achève la preuve.
Si $x>0$ est un entier dont l'écriture décimale utilise $s+1$ chiffres, on a $S(x) \leqslant 9(s+1)$ et $10^{s} \leqslant x<10^{s+1}$. Or, d'après le lemme, on a $s+1 \leqslant 10^{\frac{s}{3}}$, donc $s+1 \leqslant x^{\frac{1}{3}}$ et ainsi $S(x) \leqslant 9 x^{\frac{1}{3}}$.
Montrons maintenant par récurrence que $x_{n}<27 \sqrt{k}$ pour tout $n$. L'assertion est claire pour $n=1$. Supposons $x_{n}<27 \sqrt{k}$, alors $x_{n+1}=S\left(k x_{n}\right) \leqslant 9\left(k x_{n}\right)^{\frac{1}{3}}<9(27 k \sqrt{k})^{\frac{1}{3}}=9 \times 3 \times \sqrt{k}=$ $27 \sqrt{\mathrm{k}}$, d'où le résultat.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 10.",
"solution_match": "## Solution de l'exercice 10"
}
|
2f78c3d0-ba71-581e-9239-8708dbc6eea8
| 607,601
|
Let $a, b, c$ be three strictly positive real numbers such that $a+b+c=9$. Show that
$$
\frac{a^{3}+b^{3}}{a b+9}+\frac{b^{3}+c^{3}}{b c+9}+\frac{c^{3}+a^{3}}{c a+9} \geqslant 9
$$
|
We are looking for a lower bound of the form $\frac{a^{3}+b^{3}}{a b+9} \geqslant u(a+b)+v$, that is, $f(a) \geqslant 0$ where $f(a)=a^{3}+b^{3}-(u(a+b)+v)(a b+9)$.
By summing the three inequalities, we would deduce $\frac{a^{3}+b^{3}}{a b+9}+\frac{b^{3}+c^{3}}{b c+9}+\frac{c^{3}+a^{3}}{c a+9} \geqslant 2 u(a+b+c)+3 v = 3(6 u+v)$, so it suffices that $6 u+v=3$.
On the other hand, if such a lower bound exists, since the inequality becomes an equality when $a = b = c = 3$, we must have $f(3)=0$ if $b=3$. Since $f(a) \geqslant 0$ for all $a$, we must necessarily have $f'(3)=0$ for $b=3$.
This imposes the condition $0=f'(3)=27-18 u-(6 u+v) \times 3=18(1-u)$, so $u=1$ and $v=-3$.
Let's show $\frac{a^{3}+b^{3}}{a b+9} \geqslant(a+b)-3$. Since $a^{3}+b^{3} \geqslant \frac{(a+b)^{3}}{4}$ and $a b+9 \leqslant\left(\frac{a+b}{2}\right)^{2}+9$, it suffices to show that
$$
\frac{s^{3}}{s^{2}+36} \geqslant s-3
$$
where $s=a+b$. We reduce to a common denominator; the inequality simplifies to $3 s^{2}-36 s+108 \geqslant 0$, or equivalently $3(s-6)^{2} \geqslant 0$, which is true.
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
Soient $a, b, c$ trois nombres réels strictement positifs tels que $a+b+c=9$. Montrer que
$$
\frac{a^{3}+b^{3}}{a b+9}+\frac{b^{3}+c^{3}}{b c+9}+\frac{c^{3}+a^{3}}{c a+9} \geqslant 9
$$
|
On cherche une minoration de la forme $\frac{a^{3}+b^{3}}{a b+9} \geqslant u(a+b)+v, c^{\prime}$ est-àdire $f(a) \geqslant 0$ où $f(a)=a^{3}+b^{3}-(u(a+b)+v)(a b+9)$.
En sommant les trois inégalités, on en déduirait $\frac{a^{3}+b^{3}}{a b+9}+\frac{b^{3}+c^{3}}{b c+9}+\frac{c^{3}+a^{3}}{c a+9} \geqslant 2 u(a+b+c)+3 v=$ $3(6 u+v)$, donc il suffit que $6 u+v=3$.
D'autre part, si une telle minoration existe, comme l'inégalité devient une égalité lorsque $\mathrm{a}=$ $\mathrm{b}=\mathrm{c}=3$, on doit avoir $\mathrm{f}(3)=0$ si $\mathrm{b}=3$. Comme de plus $\mathrm{f}(\mathrm{a}) \geqslant 0$ pour tout a , on doit nécessairement avoir $\mathrm{f}^{\prime}(3)=0$ pour $\mathrm{b}=3$.
Ceci impose la condition $0=f^{\prime}(3)=27-18 \mathbf{u}-(6 \mathbf{u}+\boldsymbol{v}) \times 3=18(1-\mathfrak{u})$, donc $\mathbf{u}=1$ et $v=-3$.
Montrons donc $\frac{a^{3}+b^{3}}{a b+9} \geqslant(a+b)-3$. Comme $a^{3}+b^{3} \geqslant \frac{(a+b)^{3}}{4}$ et $a b+9 \leqslant\left(\frac{a+b}{2}\right)^{2}+9$, il suffit de montrer que
$$
\frac{s^{3}}{s^{2}+36} \geqslant s-3
$$
où $s=a+b$. On réduit au même dénominateur; l'inégalité se simplifie en $3 s^{2}-36 s+108 \geqslant 0$, ou encore en $3(s-6)^{2} \geqslant 0$, ce qui est vrai.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2014-2015-envoi-6-solutions.jsonl",
"problem_match": "\nExercice 11.",
"solution_match": "\nSolution de l'exercice 11"
}
|
098afa21-881d-5f05-8a50-bd047f58696b
| 607,602
|
Prove that there are only a finite number of prime numbers that can be written in the form $n^{3}+2 n+3$ with $n \in \mathbb{N}$.
|
Note that $n^{3}-n=n(n-1)(n+1)$ is a product of three consecutive integers. Since among three consecutive integers there is always a multiple of 3, we obtain that $n^{3}-n$ is divisible by 3, that is, $n^{3} \equiv n(\bmod 3)$. (This can also be seen using Fermat's little theorem.) Therefore, $n^{3}+2 n+3 \equiv n+2 n+3 \equiv 3 n+3 \equiv 0(\bmod 3)$, so $n^{3}+2 n+3$ is always divisible by 3. On the other hand, it can only be equal to 3 for a finite number of values of $n$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Prouver qu'il n'existe qu'un nombre fini de nombres premiers s'écrivant sous la forme $n^{3}+2 n+3$ avec $n \in \mathbb{N}$.
|
: Remarquons que $n^{3}-n=n(n-1)(n+1)$ est un produit de trois entiers consécutifs. Puisque parmi trois entiers consécutifs il y a toujours un multiple de 3 , on obtient que $n^{3}-n$ est divisible par 3, c'est-à-dire $n^{3} \equiv n(\bmod 3)$. (On peut le voir aussi en utilisant le petit théorème de Fermat.) On a donc $n^{3}+2 n+3 \equiv n+2 n+3 \equiv 3 n+3 \equiv 0(\bmod 3)$, donc $n^{3}+2 n+3$ est toujours divisible par 3 . D'autre part, il ne peut être égal à 3 que pour un nombre fini de valeurs de $n$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 1",
"solution_match": "\nSolution de l'exercice 1"
}
|
e748d031-fa99-51a8-99f3-60f2247487ca
| 607,604
|
Let $x>1$ and $y$ be integers satisfying $2 x^{2}-1=y^{15}$. Show that $x$ is divisible by 5.
|
The integer $y$ is clearly odd and strictly greater than 1. We factorize the equation as follows:
$$
x^{2}=\left(\frac{y^{5}+1}{2}\right)\left(y^{10}-y^{5}+1\right)
$$
Notice that
$$
y^{10}-y^{5}+1 \equiv 3\left(\bmod y^{5}+1\right)
$$
and thus $\operatorname{pgcd}\left(y^{5}+1, y^{10}-y^{5}+1\right)$ is equal to 1 or 3. If it were 1, then $y^{10}-y^{5}+1$ would be a square. However, for $y>0$ we have
$$
\left(y^{5}-1\right)^{2}=y^{10}-2 y^{5}+1<y^{10}-y^{5}+1<y^{10}=\left(y^{5}\right)^{2},
$$
which means that $y^{10}-y^{5}+1$ is strictly between two consecutive squares and cannot be a square itself. Therefore, $\operatorname{pgcd}\left(y^{5}+1, y^{10}-y^{5}+1\right)=3$, so there exist integers $a$ and $b$ such that
$$
y^{5}+1=6 a^{2} \quad \text { and } \quad y^{10}-y^{5}+1=3 b^{2} .
$$
We can factorize $(y+1)\left(y^{4}-y^{3}+y^{2}-y+1\right)=6 a^{2}$. Since $y^{5} \equiv-1(\bmod 3)$, we must have $y \equiv-1$ $(\bmod 3)$, so $y+1$ is divisible by 6. Similarly as above, we have
$$
y^{4}-y^{3}+y^{2}-y+1 \equiv 5(\bmod y+1)
$$
and thus $\operatorname{pgcd}\left(y+1, y^{4}-y^{3}+y^{2}-y+1\right)$ is equal to 1 or 5. If it is 5, then $a$ is divisible by 5 and so is $x$, and we are done. Suppose it is 1. Then $y^{4}-y^{3}+y^{2}-y+1$ is a square. In this case, $4\left(y^{4}-y^{3}+y^{2}-y+1\right)$ is also a square, which is impossible, because for $y>1$, we have
$$
\left(2 y^{2}-y\right)^{2}=4 y^{4}-4 y^{3}+y^{2}<4\left(y^{4}-y^{3}+y^{2}-y+1\right)<4 y^{4}-4 y^{3}+5 y^{2}-2 y+1=\left(2 y^{2}-y+1\right)^{2}
$$
## 3 Exercices groupe A
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soient $x>1$ et $y$ des entiers vérifiant $2 x^{2}-1=y^{15}$. Montrer que $x$ est divisible par 5 .
|
: L'entier $y$ est clairement impair et strictement plus grand que 1. On factorise l'équation sous la forme
$$
x^{2}=\left(\frac{y^{5}+1}{2}\right)\left(y^{10}-y^{5}+1\right)
$$
Remarquons que
$$
y^{10}-y^{5}+1 \equiv 3\left(\bmod y^{5}+1\right)
$$
et que donc $\operatorname{pgcd}\left(y^{5}+1, y^{10}-y^{5}+1\right)$ est égal à 1 ou à 3 . S'il valait 1 , alors $y^{10}-y^{5}+1$ serait un carré. Or pour $y>0$ nous avons
$$
\left(y^{5}-1\right)^{2}=y^{10}-2 y^{5}+1<y^{10}-y^{5}+1<y^{10}=\left(y^{5}\right)^{2},
$$
c'est-à-dire que $y^{10}-y^{5}+1$ est strictement compris entre deux carrés consécutifs, et ne peut pas être lui-même un carré. Donc $\operatorname{pgcd}\left(y^{5}+1, y^{10}-y^{5}+1\right)=3$, de sorte qu'il existe des entiers $a$ et $b$ tels que
$$
y^{5}+1=6 a^{2} \quad \text { et } \quad y^{10}-y^{5}+1=3 b^{2} .
$$
On peut factoriser $(y+1)\left(y^{4}-y^{3}+y^{2}-y+1\right)=6 a^{2}$. Puisque $y^{5} \equiv-1(\bmod 3)$, on a nécessairement $y \equiv-1$ $(\bmod 3)$, donc $y+1$ est divisible par 6 . De même que plus haut, on a
$$
y^{4}-y^{3}+y^{2}-y+1 \equiv 5(\bmod y+1)
$$
et donc $\operatorname{pgcd}\left(y+1, y^{4}-y^{3}+y^{2}-y+1\right)$ est égal à 1 ou à 5 . S'il vaut 5 , alors $a$ est divisible par 5 et donc $x$ aussi, et nous avons terminé. Supposons donc qu'il vaut 1. Alors $y^{4}-y^{3}+y^{2}-y+1$ est un carré. Dans ce cas, $4\left(y^{4}-y^{3}+y^{2}-y+1\right)$ est aussi un carré, ce qui est impossible, car pour $y>1$, on a
$$
\left(2 y^{2}-y\right)^{2}=4 y^{4}-4 y^{3}+y^{2}<4\left(y^{4}-y^{3}+y^{2}-y+1\right)<4 y^{4}-4 y^{3}+5 y^{2}-2 y+1=\left(2 y^{2}-y+1\right)^{2}
$$
## 3 Exercices groupe A
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 6",
"solution_match": "\nSolution de l'exercice 6"
}
|
a48b914d-452b-593b-9cc2-1b66f54912b2
| 607,609
|
Let $k \geq 3$ be an integer. We define the sequence $\left(a_{n}\right)_{n \geq k}$ by $a_{k}=2 k$, and
$$
a_{n}= \begin{cases}a_{n-1}+1 & \text { if } \operatorname{gcd}\left(a_{n-1}, n\right)=1 \\ 2 n & \text { otherwise. }\end{cases}
$$
Show that the sequence $\left(a_{n+1}-a_{n}\right)_{n \geq k}$ has infinitely many terms that are prime numbers.
|
: Let's start with an integer $n$ such that $a_{n}=2 n$. We will show by induction that if $p$ is the smallest prime factor of $n-1$, then for all $i \in\{0, \ldots, p-2\}, a_{n+i}=2 n+i$. Indeed, it is true for $i=0$, and if it is true for some $i<p-2$, then
$$
\operatorname{gcd}(n+i+1,2 n+i)=\operatorname{gcd}(n+i+1, n-1)=\operatorname{gcd}(i+2, n-1)=1
$$
since $i+2<p$, and thus $i+2$ is coprime with $n-1$ by the definition of $p$, which concludes the induction. Similarly, $\operatorname{gcd}(n+p-1,2 n+p-2)=\operatorname{gcd}(p, n-1)=p \neq 1$, and thus $a_{n+p-1}=2(n+p-1)$. In particular,
$$
a_{n+p-1}-a_{n+p-2}=2 n+2 p-2-(2 n+p-2)=p
$$
is prime.
Since $a_{k}=2 k$, we have thus shown that there are infinitely many $n$ satisfying $\operatorname{gcd}\left(a_{n-1}, n\right) \neq 1$, and that for such values of $n, a_{n}-a_{n-1}$ is prime.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit $k \geq 3$ un entier. On définit la suite $\left(a_{n}\right)_{n \geq k}$ par $a_{k}=2 k$, et
$$
a_{n}= \begin{cases}a_{n-1}+1 & \text { si } \operatorname{pgcd}\left(a_{n-1}, n\right)=1 \\ 2 n & \text { sinon. }\end{cases}
$$
Montrer que la suite $\left(a_{n+1}-a_{n}\right)_{n \geq k}$ a une infinité de termes qui sont des nombres premiers.
|
: Partons d'un entier $n$ tel que $a_{n}=2 n$. Montrons par récurrence que si $p$ est le plus petit facteur premier de $n-1$, alors pour tout $i \in\{0, \ldots, p-2\}, a_{n+i}=2 n+i$. En effet, c'est vrai pour $i=0$, et si c'est vrai pour un certain $i<p-2$, alors
$$
\operatorname{pgcd}(n+i+1,2 n+i)=\operatorname{pgcd}(n+i+1, n-1)=\operatorname{pgcd}(i+2, n-1)=1
$$
car $i+2<p$, et donc $i+2$ est premier avec $n-1$ par définition de $p$, ce qui conclut la récurrence. De même, $\operatorname{pgcd}(n+p-1,2 n+p-2)=\operatorname{pgcd}(p, n-1)=p \neq 1$, et donc $a_{n+p-1}=2(n+p-1)$. En particulier,
$$
a_{n+p-1}-a_{n+p-2}=2 n+2 p-2-(2 n+p-2)=p
$$
est premier.
Puisque $a_{k}=2 k$, avons donc montré qu'il existe une infinité de $n$ satisfaisant $\operatorname{pgcd}\left(a_{n-1}, n\right) \neq 1$, et que pour de telles valeurs de $n, a_{n}-a_{n-1}$ est premier.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 8",
"solution_match": "\nSolution de l'exercice 8"
}
|
4ae8ffc9-036a-5b3e-8451-ccb5da484c50
| 607,611
|
Let $t$ be a non-zero natural number. Show that there exists an integer $n>1$ coprime with $t$ such that for any integer $k \geq 1$, the integer $n^{k}+t$ is not a power (i.e., it is not of the form $m^{r}$ with $m \geq 1$ and $r \geq 2$).
|
To ensure that $n$ is coprime with $t$, we will look for it in the form $1 + ts$ where $s$ is an integer. We will then have $n^{k} + t \equiv 1 + t \pmod{s}$. In particular, if $s$ is divisible by $(t+1)$, then $n^{k} + t$ is also divisible by $(t+1)$.
First, we will handle the case where $t+1$ is not a power. In this case, it would suffice to ensure that we can choose $s$ such that $n^{k} + t$ is divisible by $t+1$, and that the quotient is coprime with $t+1$. For this, let's take $s = (t+1)^2$. Then $n = 1 + t(t+1)^2$, and
$$
n^{k} + t = \underbrace{\sum_{i=1}^{k} \binom{k}{i} t^i (t+1)^{2i}}_{\text{terms divisible by } (t+1)^2} + 1 + t = (t+1)(a(t+1) + 1)
$$
for some integer $a$, so we are done.
Now suppose that $t+1$ is a power: $t+1 = m^r$ with $m$ not a power. If we keep the same $n$ as above, we see that if $n^{k} + t = b^d$ is a power (with $d \geq 2$), then $t+1$ must necessarily be a $d$-th power, and thus $d$ divides $r$. Therefore, we have a bound on the $d$ such that $n^{k} + t$ is a $d$-th power for some $k$. We then observe that by replacing $n$ with its $r$-th power, i.e., by setting $n = n_0^r$ where $n_0 = 1 + t(t+1)^2$ (which does not change the fact that $t+1$ divides $n^{k} + t$, that the quotient is coprime with $t+1$, and that $n^{k} + t = b^d$ implies $d \mid r$ as above), we can write $t$ as the difference of two $d$-th powers:
$$
t = b^d - (n_0^{ke})^d
$$
where $e$ is the natural number such that $r = de$. This is not possible because $n_0$ is large relative to $t$. More precisely, we have:
$$
t = b^d - (n_0^{ke})^d = (b - n_0^{ke})(b^{d-1} + b^{d-2} n_0^{ke} + \ldots + b n_0^{ke(d-2)} + n_0^{ke(d-1)}) \geq n_0 > t
$$
contradiction. Therefore, for all $k$ and for all $d$, $n^{k} + t$ is not a $d$-th power, and we are done.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit $t$ un entier naturel non-nul. Montrer qu'il existe un entier $n>1$ premier avec $t$ tel que pour tout entier $k \geq 1$, l'entier $n^{k}+t$ ne soit pas une puissance (c'est-à-dire qu'il ne soit pas de la forme $m^{r}$ avec $m \geq 1$ et $r \geq 2$ ).
|
: Pour que $n$ soit premier avec $t$, on va le chercher sous la forme $1+t s$ où $s$ est entier. On aura alors $n^{k}+t \equiv 1+t(\bmod s)$. En particulier, si $s$ est divisible par $(t+1)$, alors $n^{k}+t$ l'est également.
On va d'abord traiter le cas où $t+1$ n'est pas une puissance. Dans ce cas, il suffirait de s'assurer qu'on peut choisir $s$ de telle sorte que $n^{k}+t$ soit divisible par $t+1$, et que le quotient soit premier avec $t+1$. Pour cela, prenons $s=(t+1)^{2}$. Alors $n=1+t(t+1)^{2}$, et
$$
n^{k}+t=\underbrace{\sum_{i=1}^{k}\binom{k}{i} t^{i}(t+1)^{2 i}}_{\text {termes divisibles par }(t+1)^{2}}+1+t=(t+1)(a(t+1)+1)
$$
pour un certain entier $a$, donc on a gagné.
Supposons maintenant que $t+1$ soit une puissance : $t+1=m^{r}$ avec $m$ qui n'est pas une puissance. Si on garde le même $n$ que ci-dessus, on voit que si $n^{k}+t=b^{d}$ est une puissance (avec $d \geq 2$ ), alors $t+1$ est nécessairement une puissance $d$-ième, et donc $d$ divise $r$. Ainsi, nous avons une borne sur les $d$ tels que $n^{k}+t$ est puissance $d$-ième pour un certain $k$. On constate alors qu'en remplaçant $n$ par sa puissance $r$-ième, c'est-à-dire en posant $n=n_{0}^{r}$ où $n_{0}=1+t(t+1)^{2}$ (ce qui ne change pas le fait que $t+1$ divise $n^{k}+t$, que le quotient soit premier avec $t+1$, et que donc $n^{k}+t=b^{d}$ implique $d \mid r$ comme ci-dessus), on arrive à écrire $t$ comme une différence de deux puissances $d$-ièmes :
$$
t=b^{d}-\left(n_{0}^{k e}\right)^{d}
$$
où $e$ est l'entier naturel tel que $r=d e$. Cela n'est pas possible car $n_{0}$ est grand par rapport à $t$. Plus précisément, nous avons:
$$
t=b^{d}-\left(n_{0}^{k e}\right)^{d}=\left(b-n_{0}^{k e}\right)\left(b^{d-1}+b^{d-2} n_{0}^{k e}+\ldots+b n_{0}^{k e(d-2)}+n_{0}^{k e(d-1)}\right) \geq n_{0}>t
$$
contradiction. Donc pour tout $k$ et pour tout $d, n^{k}+t$ n'est pas une puissance $d$-ième et nous avons terminé.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 9",
"solution_match": "\nSolution de l'exercice 9"
}
|
e5e8f378-1b00-5ed9-bf67-1786e5f7a837
| 607,612
|
Let $A$ be a point outside a circle $\mathscr{C}$ with center $O$. A point $P$ moves on $\mathscr{C}$. Let $M$ be the intersection point between $(A P)$ and the bisector of $\widehat{P O A}$. Show that $M$ moves on a circle that we will describe.
|
Let $d=OA$ and $R$ be the radius of the circle.
According to the Angle Bisector Theorem, we have $MP/MA = OP/OA$, so $\frac{MA}{AP} = \frac{MA}{MA + MP} = \frac{1}{1 + \frac{MP}{MA}} = \frac{1}{1 + \frac{OP}{OA}} = \frac{OA}{OA + OP} = \frac{d}{d + R}$. Let $k$ be this value. Let $O'$ be the point on $[AO]$ such that $AO' = kAO$. According to Thales' Theorem, the lines $(O'M)$ and $(OP)$ are parallel, so $\frac{O'M}{OP} = \frac{AM}{AP} = k$, thus $O'M = kR$. This proves that $M$ describes the circle with center $O'$ and radius $kR$.
Notice that $AO' + kR = k(d + R) = d$, so this circle passes through $O$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A$ un point extérieur à un cercle $\mathscr{C}$ de centre $O$. Un point $P$ se déplace sur $\mathscr{C}$. Soit $M$ le point d'intersection entre $(A P)$ et la bissectrice de $\widehat{P O A}$. Montrer que $M$ se déplace sur un cercle que l'on décrira.
|

Notons $d=O A$ et $R$ le rayon du cercle.
D'après le théorème de la bissectrice, on a $M P / M A=O P / O A$, donc $\frac{M A}{A P}=\frac{M A}{M A+M P}=$ $\frac{1}{1+\frac{M P}{M A}}=\frac{1}{1+\frac{O P}{O A}}=\frac{O A}{O A+O P}=\frac{d}{d+R}$. Notons $k$ cette valeur. Soit $O^{\prime}$ le point de $[A O]$ tel que $A O^{\prime}=k A O$. D'après le théorème de Thalès, les droites $\left(O^{\prime} M\right)$ et $(O P)$ sont parallèles, donc $\frac{O^{\prime} M}{O P}=\frac{A M}{A P}=k$, donc $O^{\prime} M=k R$. Ceci prouve que $M$ décrit le cercle de centre $O^{\prime}$ et de rayon kR.
Remarquons que $A O^{\prime}+k R=k(d+R)=d$, donc ce cercle passe par $O$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 1.",
"solution_match": "\nSolution de l'exercice 1"
}
|
1c679424-5e0e-594e-ab39-af53219c64ad
| 607,613
|
Let $ABC$ be a triangle such that $\widehat{A}=60^{\circ}$. We denote $O$ as the center of the circumcircle, $I$ as the center of the incircle, and $H$ as the orthocenter. Show that
1) $B, C, O, I, H$ are concyclic
2) $OIH$ is isosceles.
|

We use angles of lines. The angles are modulo $180^{\circ}$.
1) $(H B, H C)=(H B, A C)+(A C, A B)+(A B, H C)=D-(A B, A C)+D=-(A B, A C)=-60^{\circ}=$ $120^{\circ}=(O B, O C)$ (where we have denoted $D$ as the right angle), so $B, H, O, C$ are concyclic.
$(I B, I C)=(I B, B C)+(B C, I C)=-\widehat{B} / 2-\widehat{C} / 2=-120 / 2=-60^{\circ}=120^{\circ}$, so $I$ is also on this circle.
2) $(C O, C I)-(C I, C H)=(C O, C B)+(C B, C I)-(C I, C B)-(C B, C H)=(C O, C B)+$ $(C H, C B)+2(C B, C I)=(90-\widehat{A})+(90-\widehat{B})-\widehat{C}=0$, so $(C O, C I)=(C I, C H)$. Therefore, $(O I, O H)=(C I, C H)=(C O, C I)=(H O, H I)$, so $O I H$ is isosceles at $I$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle tel que $\widehat{A}=60^{\circ}$. On note $O$ le centre du cercle circonscrit, $I$ le centre du cercle inscrit et $H$ l'orthocentre. Montrer que
1) $B, C, O, I, H$ sont cocycliques
2) $O I H$ est isocèle.
|

On utilise les angles de droites. Les angles sont modulo $180^{\circ}$.
1) $(H B, H C)=(H B, A C)+(A C, A B)+(A B, H C)=D-(A B, A C)+D=-(A B, A C)=-60^{\circ}=$ $120^{\circ}=(O B, O C)$ (où on a noté $D$ l'angle droit), donc $B, H, O, C$ sont cocycliques.
$(I B, I C)=(I B, B C)+(B C, I C)=-\widehat{B} / 2-\widehat{C} / 2=-120 / 2=-60^{\circ}=120^{\circ}$, donc $I$ se trouve également sur ce cercle.
2) $(C O, C I)-(C I, C H)=(C O, C B)+(C B, C I)-(C I, C B)-(C B, C H)=(C O, C B)+$ $(C H, C B)+2(C B, C I)=(90-\widehat{A})+(90-\widehat{B})-\widehat{C}=0$, donc $(C O, C I)=(C I, C H)$. On a donc $(O I, O H)=(C I, C H)=(C O, C I)=(H O, H I)$, donc $O I H$ est isocèle en $I$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 2.",
"solution_match": "## Solution de l'exercice 2"
}
|
22f4164b-7472-5835-8639-6a1d0d48ab35
| 607,614
|
From a point $A$ on a circle with center $O$, a tangent to this circle is drawn, and two points $B$ and $C$ are taken on this tangent, with $C$ between $A$ and $B$. From $B$ and $C$, $(B D)$ and $(C E)$ are drawn tangent to the circle. Prove that $\widehat{B O C}=\widehat{D A E}$.
|
Let $\alpha=\widehat{B D E}$ and $\beta=\widehat{C E A}$. According to the inscribed angle theorem, we have $\alpha=\widehat{D A E}$.
Since $(C A)$ and $(C E)$ are the two tangents drawn from $C$, we have $\widehat{E A C}=\widehat{C E A}=\beta$. $\widehat{B O C}=\widehat{B O A}-\widehat{C O A}$. Now, $(B O) \perp(A D)$ and $(O A) \perp(A C)$, so $\widehat{B O A}=\widehat{D A C}=\alpha+\beta$, and similarly $\widehat{C O A}=\beta$, thus $\widehat{B O C}=\alpha=\widehat{D A E}$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Par un point $A$ d'un cercle de centre $O$, on mène une tangente à ce cercle, et on prend deux points $B$ et $C$ sur cette tangente, avec $C$ entre $A$ et $B$. De $B$ et $C$, on mène $(B D)$ et $(C E)$ tangentes au cercle. Démontrer que $\widehat{B O C}=\widehat{D A E}$.
|

Notons $\alpha=\widehat{B D E}$ et $\beta=\widehat{C E A}$. D'après le théorème de l'angle inscrit, on a $\alpha=\widehat{D A E}$.
Comme $(C A)$ et $(C E)$ sont les deux tangentes menées à partir de $C$, on a $\widehat{E A C}=\widehat{C E A}=\beta$. $\widehat{B O C}=\widehat{B O A}-\widehat{C O A} . \mathrm{Or},(B O) \perp(A D)$ et $(O A) \perp(A C)$, donc $\widehat{B O A}=\widehat{D A C}=\alpha+\beta$, et de même $\widehat{C O A}=\beta$, donc $\widehat{B O C}=\alpha=\widehat{D A E}$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 3.",
"solution_match": "\nSolution de l'exercice 3"
}
|
65a8b627-adf3-530e-865e-c418229c19f4
| 607,615
|
Let $ABC$ be a triangle. Let $P$ belong to the circumcircle. We know that the projections of $P$ onto $(BC)$, $(CA)$, and $(AB)$ are aligned on the line known as the Simson line. We assume that this line passes through the point diametrically opposite to $P$. Show that it also passes through the centroid of $ABC$.
|
Let $P^{\prime}$ be the point diametrically opposite to $P$. Let $\Delta$ be the Simson line. Let $h$ be the homothety with center $P$ and ratio 2. Then $h(\Delta)$ is the Steiner line. We know that it passes through the orthocenter $H$, so $\Delta$ passes through the midpoint of $[P H]$. We deduce that $\Delta$ is the median of $P P^{\prime} H$ from $P^{\prime}$.
Furthermore, (HO) is the median of $P P^{\prime} H$ from $H$. Since $\overrightarrow{H G}=\frac{2}{3} \overrightarrow{H O}$, the point $G$ is the centroid of $P H P^{\prime}$, so $\Delta$ passes through $G$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle. Soit $P$ appartenant au cercle circonscrit. On sait que les projetés de $P$ sur $(B C),(C A)$ et $(A B)$ sont alignés sur la droite dite de Simson. On suppose que cette droite passe par le point diamétralement opposé à $P$. Montrer qu'elle passe également par le centre de gravité de $A B C$.
|

Notons $P^{\prime}$ le point diamétralement opposé à $P$. Soit $\Delta$ la droite de Simson. Soit $h$ l'homothétie de centre $P$ et de rapport 2. Alors $h(\Delta)$ est la droite de Steiner. On sait qu'elle passe par l'orthocentre $H$, donc $\Delta$ passe par le milieu de $[P H]$. On en déduit que $\Delta$ est la médiane de $P P^{\prime} H$ issue de $P^{\prime}$.
Par ailleurs, (HO) est la médiane de $P P^{\prime} H$ issue de $H$. Comme $\overrightarrow{H G}=\frac{2}{3} \overrightarrow{H O}$, le point $G$ est le centre de gravité de $P H P^{\prime}$, donc $\Delta$ passe par $G$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 4.",
"solution_match": "## Solution de l'exercice 4"
}
|
48e6e5d6-8ac8-5af3-9d5d-350eea0a63bd
| 607,616
|
Let $ABC$ be a triangle. Suppose that the median $(BM)$ and the angle bisector $(CD)$ intersect at a point $J$ such that $JB=JC$. Let $H$ be the foot of the altitude from $A$. Show that $JM=JH$.
Soit $ABC$ un triangle. On suppose que la médiane $(BM)$ et la bissectrice $(CD)$ se coupent en un point $J$ tel que $JB=JC$. Soit $H$ le pied de la hauteur issue de $A$. Montrer que $JM=JH$.
(Note: The second part is the original French text, which is kept as requested.)
|
Let $\gamma=\widehat{A C B}$. We have $M A=M C=M H$, so $\widehat{C H M}=\gamma$.
We also have $\widehat{C H M}=180^{\circ}-\widehat{M H B}=\widehat{H B M}+\widehat{B M H}$.
Furthermore, $\widehat{H B M}=\widehat{D C B}=\gamma / 2$, so $\widehat{B M H}=\widehat{H M B}=\gamma / 2$.
We deduce that $B H=H M=M C$. The triangles $B H J$ and $C M J$ satisfy $B J=C J, \widehat{H B J}=$ $\widehat{M C J}$ and $B H=C M$ so they are congruent. Consequently, $J H=H M$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle. On suppose que la médiane $(B M)$ et la bissectrice $(C D)$ se coupent en un point $J$ tel que $J B=J C$. Soit $H$ le pied de la hauteur issue de $A$. Montrer que $J M=J H$.
|

Notons $\gamma=\widehat{A C B}$. On a $M A=M C=M H$, donc $\widehat{C H M}=\gamma$.
On a aussi $\widehat{C H M}=180^{\circ}-\widehat{M H B}=\widehat{H B M}+\widehat{B M H}$.
De plus, $\widehat{H B M}=\widehat{D C B}=\gamma / 2$, donc $\widehat{B M H}=\widehat{H M B}=\gamma / 2$.
On en déduit que $B H=H M=M C$. Les triangles $B H J$ et $C M J$ vérifient $B J=C J, \widehat{H B J}=$ $\widehat{M C J}$ et $B H=C M$ donc sont isométriques. Par conséquent, $J H=H M$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 5.",
"solution_match": "## \nSolution de l'exercice 5"
}
|
31474eab-7c20-5bac-a06f-14dd5793de51
| 607,617
|
Let $ABC$ be a triangle, and $D, E, F$ the feet of the altitudes from $A, B, C$ respectively. We also define $H$ as the orthocenter of $ABC$, $O$ as the center of its circumcircle, and $X$ as the point on the line $(EF)$ that satisfies $XA = XD$. Show that the lines $(AX)$ and $(OH)$ are perpendicular.
|
We know that the radical axis of two circles is a line perpendicular to the line passing through the centers of the two circles.
The condition \( XA = XD \) means that \( X \) is on the perpendicular bisector of \([AD]\), which is none other than the midline \((B' C')\) (with \( B' \) and \( C' \) being the midpoints of \([AC]\) and \([AB]\)). We also know that the points \( A, E, F, H \) are concyclic according to the converse of the inscribed angle theorem. Furthermore, since \([AH]\) is a diameter of the circle passing through these four points, the midpoint \( H' \) of \([AH]\) is the center of this circle.
The center of the circle passing through \( A, B', C' \) is the midpoint \( O' \) of \([AO]\) (by the property of the homothety centered at \( A \) with a ratio of 1/2). We know that \((O' H')\) and \((OH)\) are parallel. The problem thus reduces to showing that \((AX)\) and \((O' H')\) are perpendicular. We will show here that \((AX)\) is actually the radical axis of the two circles mentioned earlier, which will complete the exercise according to the property mentioned at the beginning of the proof.
Since \( A \) is on both circles, it is indeed on their radical axis. We also know that \( B', C', E, F \) are concyclic on the Euler circle of triangle \( ABC \). Thus, we have the equality of lengths: \( XC' \times XB' = XE \times XF \), which means that \( X \) is indeed on the radical axis of our two circles.
Therefore, we have \((AX)\) and \((OH)\) being perpendicular.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle, et $D, E, F$ les pieds des hauteurs de $A, B, C$ respectivement. On définit aussi $H$ l'orthocentre de $A B C, O$ le centre de son cercle circonscrit, et $X$ le point de la droite $(E F)$ qui vérifie $X A=X D$. Montrer que les droites $(A X)$ et $(O H)$ sont perpendiculaires.
|

On sait que l'axe radical de deux cercles est une droite perpendiculaire à la droite passant par les centres des deux cercles.
La condition $X A=X D$ signifie que X est sur la médiatrice de $[A D]$, qui n'est autre que le droite des milieux $\left(B^{\prime} C^{\prime}\right)$ (avec $B^{\prime}$ et $C^{\prime}$ les milieux de $[A C]$ et de $[A B]$ ). On sait aussi que les points
$A, E, F, H$ sont cocycliques d'après la réciproque du théorème de l'angle inscrit. De, plus $[A H]$ étant un diamètre du cercle passant par ces quatre points, le milieu $H^{\prime}$ de $[A H]$ est le centre de ce cercle.
Le centre du cercle passant par $A, B^{\prime}, C^{\prime}$ est le milieu $O^{\prime}$ de $[A O]$ (par propriété de l'homothétie de centre $A$ et de rapport 1/2). On sait que $\left(O^{\prime} H^{\prime}\right)$ et $(O H)$ sont parallèles. Le problème revient donc à montrer que $(A X)$ et $\left(O^{\prime} H^{\prime}\right)$ sont perpendiculaires. Nous allons montrer ici que $(A X)$ est en fait l'axe radical des deux cercles évoqués précédemment, ce qui terminera l'exercice d'après la propriété évoquée au début de la preuve.
$A$ étant sur les deux cercles, est bien sur leur axe radical. On sait de plus que $B^{\prime}, C^{\prime}, E, F$ sont cocycliques sur le cercle d'Euler du triangle $A B C$. Ainsi on a l'égalité de longueurs : $X C^{\prime} \times X B^{\prime}=X E \times X F$, ce qui signifie que $X$ est bien sur l'axe radical de nos deux cercles.
Ainsi on a bien $(A X)$ et $(O H)$ qui sont perpendiculaires.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 6.",
"solution_match": "## Solution de l'exercice 6"
}
|
4ca638d9-175e-5b25-89cb-25ba565b163f
| 607,618
|
Let $ABC$ be a triangle, and $\Gamma$ its circumcircle. Let $M$ be the midpoint of the arc $BC$ not containing $A$. A circle $\mathscr{C}$ is tangent to $[AB), [AC)$ at $D$ and $E$ respectively, and internally tangent to $\Gamma$ at $F$. Show that $(DE), (BC)$, and $(FM)$ are concurrent.
|
Let $I$ be the center of the incircle of $ABC$. The line $(EF)$ intersects $\Gamma$ at a point $H$. Let $J$ be the intersection of $(BC)$ with $(FM)$.
It is easy to see that $H$ is the midpoint of the arc $AC$ not containing $B$: indeed, the homothety centered at $F$ that maps $\mathscr{C}$ to $\Gamma$ maps $(AC)$ to the tangent at $H$ to $\Gamma$; this tangent is parallel to $(AC)$, which implies that $H$ is the midpoint of the arc, and consequently $B, I, H$ are collinear.
By applying Pascal's theorem to the hexagon $AMFHB C$, we obtain that $I, E, J$ are collinear. Similarly, $D, I, J$ are collinear. Thus, $(DE)$, $(BC)$, and $(FM)$ meet at $J$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle, et $\Gamma$ son cercle circonscrit. Soit $M$ le milieu de l'arc $B C$ ne contenant pas $A$. Un cercle $\mathscr{C}$ est tangent à $[A B),[A C)$ en $D$ et $E$ respectivement, et tangent intérieurement à $\Gamma$ en $F$. Montrer que $(D E),(B C)$ et $(F M)$ sont concourantes.
|

Soit $I$ le centre du cercle inscrit dans $A B C$. La droite $(E F)$ recoupe $\Gamma$ en un point $H$. Soit $J$ le point d'intersection de $(B C)$ avec $(F M)$.
Il est facile de voir que $H$ est le milieu de l'arc $A C$ ne contenant pas $B$ : en effet, l'homothétie de centre $F$ qui envoie $\mathscr{C}$ sur $\Gamma$ envoie $(A C)$ sur la tangente en $H$ à $\Gamma$; celle-ci est parallèle à $(A C)$, ce qui entraîne que $H$ est le milieu de l'arc, et par conséquent $B, I, H$ sont alignés.
En appliquant le théorème de Pascal à l'hexagone $A M F H B C$, on obtient que $I, E, J$ sont alignés. De même, $D, I, J$ sont alignés. Ainsi, $(D E),(B C)$ et $(F M)$ se rencontrent en $J$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "\nSolution de l'exercice 7"
}
|
ebb6cf66-955d-59e5-95c3-1ce257ab2e2c
| 607,619
|
Let $ABC$ be a triangle, $D, E, F$ the points of tangency of the incircle on the sides $(BC), (AC)$, and $(AB)$, $M$ the midpoint of $[BC]$, $I$ the incenter of $ABC$. $G$ and $H$ are defined as the reflections of $E$ and $F$ with respect to $I$. We denote $Q$ as the intersection between the lines $(BC)$ and $(GH)$. Show that the lines $(IQ)$ and $(IM)$ are perpendicular.
|
Let $\omega$ be the incircle of $ABC$.
We will denote for any point $X$ in the plane $p(X)$ the polar of $X$ with respect to $\omega$. We know that for any point $X$ in the plane, $p(X)$ is a line perpendicular to $(IX)$. We will therefore show that $p(Q)$ and $(IM)$ are parallel to deduce the result.
We know that $p(D) = (BC)$, and that $Q \in (BC)$, so $Q \in p(D)$. Thus, by the property of polars (with respect to a fixed circle), we deduce that $D \in p(Q)$. Moreover, by the construction of the polar, we know that $A'$, the intersection of the tangents to $\omega$ at $G$ and $H$, is also on the polar of $Q$. Thus we have: $p(Q) = (DA')$. By symmetry of the construction, we know that $A$ and $A'$ are symmetric with respect to $I$.
Now let $D'$ be the symmetric of $D$ with respect to $I$ (which is therefore on $\omega$) and $D''$ the point on $(BC)$ such that $M$ is the midpoint of $[D D'']$. Since a homothety maps a line to a parallel line, we know that the lines $(DA')$ and $(D'A)$ are parallel, as well as the lines $(IM)$ and $(D'D'')$. It is known that the points $A, D', D''$ are collinear (which can be shown by a homothety centered at $A$).
Thus the lines $(DA')$ and $(IM)$ are parallel, and since $(DA')$ and $(QI)$ are perpendicular, we deduce that $(IQ)$ and $(IM)$ are indeed perpendicular.
Another solution. Let $\alpha, \beta$, and $\gamma$ be the angles of $DEF$ and $R$ the radius of the circumcircle of $DEF$. We have $BD = R \tan \beta, CD = R \tan \gamma$ so
$$
2DM = BC - 2BD = R(\tan \gamma - \tan \beta) = R \frac{\sin \gamma \cos \beta - \sin \beta \cos \gamma}{\cos \beta \cos \gamma} = R \frac{\sin (\gamma - \beta)}{\cos \beta \cos \gamma}.
$$
On the other hand, the law of sines in $QDH$ gives $DQ = DH \frac{\cos \gamma}{\sin (\beta - \gamma)} = 2R \frac{\cos \beta \cos \gamma}{\sin (\beta - \gamma)}$ so $QD \cdot DM = R^2 = DI^2$. Since $[ID]$ is the altitude of $IQM$ from $I$, $IQM$ is a right triangle at $I$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle, $D, E, F$ les points de tangence du cercle inscrit sur les côtés $(B C),(A C)$ et $(A B), M$ le milieu de $[B C], I$ le centre du cercle inscrit de $A B C . G$ et $H$ sont définis comme les symétriques de $E$ et $F$ par rapport à $I$. On note $Q$ l'intersection entre les droites $(B C)$ et $(G H)$. Montrer que les droites $(I Q)$ et $(I M)$ sont perpendiculaires.
|

Soit $\omega$ le cercle inscrit de $A B C$.
On notera pour tout point $X$ du plan $p(X)$ la polaire de $X$ par rapport à $\omega$. On sait que pour tout point $X$ du plan, $p(X)$ est une droite perpendiculaire à $(I X)$. Nous allons donc montrer que $p(Q)$ et $(I M)$ sont parallèles pour en déduire le résultat.
On sait que $p(D)=(B C)$, et que $Q \in(B C)$ donc $Q \in p(D)$. Ainsi par propriété des polaires (par rapport à un cercle fixé), on en déduit que $D \in p(Q)$. De plus par construction de la polaire, on sait que $A^{\prime}$ le point d'intersection des tangentes à $\omega$ en $G$ et $H$ est aussi sur la polaire de $Q$. Ainsi on a : $p(Q)=\left(D A^{\prime}\right)$. Par symétrie de la construction, on sait que $A$ et $A^{\prime}$ sont symétriques par rapport à $I$.
Soit maintenant $D^{\prime}$ le symétrique de $D$ par rapport à $I$ (qui est donc sur $\omega$ ) et $D^{\prime \prime}$ le point de $(B C)$ tel que $M$ soit le milieu de [ $\left.D D^{\prime \prime}\right]$. Une homothétie envoyant une droite sur une droite qui lui est parallèle, on sait que les droites $\left(D A^{\prime}\right)$ et $\left(D^{\prime} A\right)$ sont parallèles, ainsi que les droites $(I M)$ et $\left(D^{\prime} D^{\prime \prime}\right)$. Or il est connu que les points $A, D^{\prime}, D^{\prime \prime}$ sont alignés (se montre par une homothétie de centre $A$ ).
Ainsi les droites $\left(D A^{\prime}\right)$ et $(I M)$ sont parallèles, et $\left(D A^{\prime}\right)$ et $(Q I)$ étant perpendiculaires, on en déduit que $(I Q)$ et $(I M)$ sont bien perpendiculaires.
Autre solution. Notons $\alpha, \beta$ et $\gamma$ les angles de $D E F$ et $R$ le rayon du cercle circonscrit à $D E F$. On a $B D=R \tan \beta, C D=R \tan \gamma$ donc
$$
2 D M=B C-2 B D=R(\tan \gamma-\tan \beta)=R \frac{\sin \gamma \cos \beta-\sin \beta \cos \gamma}{\cos \beta \cos \gamma}=R \frac{\sin (\gamma-\beta)}{\cos \beta \cos \gamma} .
$$
D'autre part, la loi des sinus dans $Q D H$ donne $D Q=D H \frac{\cos \gamma}{\sin (\beta-\gamma)}=2 R \frac{\cos \beta \cos \gamma}{\sin (\beta-\gamma)}$ donc $Q D . D M=R^{2}=D I^{2}$. Or, $[I D]$ est la hauteur de $I Q M$ issue de $I$, donc $I Q M$ est rectangle en $I$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-2-solutions.jsonl",
"problem_match": "\nExercice 8.",
"solution_match": "## Solution de l'exercice 8"
}
|
854e579b-6357-57bd-9730-ba09befc574f
| 607,620
|
Let $n \geqslant 3$ be an integer and $a_{1}, a_{2}, \ldots, a_{n}$ be real numbers.
(a) Suppose that $a_{i}<\max \left(a_{i-1}, a_{i+1}\right)$ for all $i \in\{2,3, \ldots, n-1\}$. Show that $a_{i}<$ $\max \left(a_{1}, a_{n}\right)$ for all $i \in\{2,3, \ldots, n-1\}$.
(b) Suppose that $a_{i} \leqslant \max \left(a_{i-1}, a_{i+1}\right)$ for all $i \in\{2,3, \ldots, n-1\}$. Is it true that $a_{i} \leqslant \max \left(a_{1}, a_{n}\right)$ for all $i \in\{2,3, \ldots, n-1\}$?
N.B. If $x$ and $y$ are two real numbers, we denote $\max (x, y)$ the largest of the two.
|
(a) Let $i \in\{1,2, \ldots, n\}$ be an integer such that $a_{i}=\max \left(a_{1}, \ldots, a_{n}\right)$. The statement indicates that $i \notin\{2,3, \ldots, n-1\}$. This shows both that $i \in\{1, n\}$, and thus that $a_{i}=\max \left(a_{1}, a_{n}\right)$, and that $a_{k}<a_{i}$ if $k \in\{2,3, \ldots, n-1\}$, which is the required inequality.
(b) The result is clearly true for $n=3$. Let's show that it is not always true for $n \geqslant 4$ by providing a counterexample: take $a_{1}=a_{n}=1$ and $a_{i}=2$. The condition of the statement is satisfied, but $a_{i}>\max \left(a_{1}, a_{n}\right)$ for all $2 \leqslant i \leqslant n-1$.
Another solution for (a). The idea is to look at where the sequence "rises" for the first time. For this, we will distinguish two cases:
First case: there exists a smallest integer $1 \leqslant \mathfrak{i}_{0} \leqslant n-1$ such that $a_{i_{0}} \leqslant a_{i_{0}+1}$. Thus, $a_{1}>\cdots>a_{i_{0}}$ and $a_{i_{0}} \leqslant a_{i_{0}+1}$. In particular, if $i_{0}=n-1$, we note that we have the desired result (since then $a_{n-1}<a_{1}$ and $a_{n-1} \leqslant a_{n}$). Suppose now that $\mathfrak{i}_{0}<n-1$ and show that $a_{j}<a_{j+1}$ for all integers $\mathfrak{i}_{0}+1 \leqslant j \leqslant n-1$ by induction on $j$.
Initialization: we have $a_{i_{0}+1}<\max \left(a_{i_{0}}, a_{i_{0}+2}\right)$. Since $a_{i_{0}} \leqslant a_{i_{0}+1}$, we must have $\max \left(a_{i_{0}}, a_{i_{0}+2}\right)=$ $a_{i_{0}+2}$, which implies that $a_{i_{0}+1}<a_{i_{0}+2}$.
Induction step: let $\mathfrak{i}_{0}+1 \leqslant \mathfrak{j}<n-1$ be an integer such that $a_{j}<a_{j+1}$. Show that $a_{j+1}<a_{j+2}$. Since $a_{\mathfrak{j}+1}<\max \left(a_{\mathfrak{j}}, a_{\mathfrak{j}+2}\right)$ and $a_{\mathfrak{j}}<\mathfrak{a}_{\mathfrak{j}+1}$, we must have $\max \left(a_{j}, a_{j+2}\right)=a_{j+2}$, which implies that $a_{j+1}<a_{j+2}$.
We therefore have:
$$
a_{1}>\cdots>a_{i_{0}} \leqslant a_{i_{0}+1}<a_{i_{0}+2}<a_{i_{0}+3}<\cdots<a_{n}
$$
which implies that $a_{i}<\max \left(a_{1}, a_{n}\right)$ for all $i \in\{2,3, \ldots, n-1\}$.
Second case: there does not exist an integer $1 \leqslant \mathfrak{i}_{0} \leqslant n-1$ such that $a_{i_{0}} \leqslant a_{i_{0}+1}$. Then $a_{1}>a_{2}>\cdots>$ $a_{n}$ and we have the desired result.
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
Soit $n \geqslant 3$ un nombre entier et $a_{1}, a_{2}, \ldots, a_{n}$ des nombres réels.
(a) On suppose que $a_{i}<\max \left(a_{i-1}, a_{i+1}\right)$ pour tout $i \in\{2,3, \ldots, n-1\}$. Montrer que $a_{i}<$ $\max \left(a_{1}, a_{n}\right)$ pour tout $i \in\{2,3, \ldots, n-1\}$.
(b) On suppose que $a_{i} \leqslant \max \left(a_{i-1}, a_{i+1}\right)$ pour tout $i \in\{2,3, \ldots, n-1\}$. Est-il vrai que $a_{i} \leqslant \max \left(a_{1}, a_{n}\right)$ pour tout $i \in\{2,3, \ldots, n-1\}$ ?
N.B. Si $x$ et y sont deux nombres réels, on note $\max (x, y)$ le plus grand des deux.
|
(a) Soit $i \in\{1,2, \ldots, n\}$ un entier tel que $a_{i}=\max \left(a_{1}, \ldots, a_{n}\right)$. L'énoncé indique que $i \notin\{2,3, \ldots, n-1\}$. Cela montre à la fois que $i \in\{1, n\}$, donc que $a_{i}=\max \left(a_{1}, a_{n}\right)$, et que $a_{k}<a_{i}$ si $k \in\{2,3, \ldots, n-1\}$, ce qui était l'inégalité demandée.
(b) Le résultat est clairement vrai pour $\mathrm{n}=3$. Montrons qu'il n'est pas toujours vrai pour $\mathrm{n} \geqslant 4$ en exhibant un contre-exemple : prenons $a_{1}=a_{n}=1$ et $a_{i}=2$. La consigne de l'énoncé est respectée mais $a_{i}>\max \left(a_{1}, a_{n}\right)$ pour tout $2 \leqslant i \leqslant n-1$.
Autre solution pour (a). L'idée est de regarder où la suite "remonte" pour la première fois. Pour cela, nous allons distinguer deux cas :
Premier cas : il existe un plus petit entier $1 \leqslant \mathfrak{i}_{0} \leqslant n-1$ tel que $a_{i_{0}} \leqslant a_{i_{0}+1}$. Ainsi, $a_{1}>\cdots>a_{i_{0}}$ et $a_{i_{0}} \leqslant a_{i_{0}+1}$. En particulier, si $i_{0}=n-1$, on remarque qu'on a bien le résultat voulu (car alors $a_{n-1}<a_{1}$ at $a_{n-1} \leqslant a_{n}$ ). Supposons maintenant que $\mathfrak{i}_{0}<n-1$ et montrons que $a_{j}<a_{j+1}$ pour tout entier $\mathfrak{i}_{0}+1 \leqslant j \leqslant n-1$ par récurrence sur $j$.
Initialisation : on a $a_{i_{0}+1}<\max \left(a_{i_{0}}, a_{i_{0}+2}\right)$. Comme $a_{i_{0}} \leqslant a_{i_{0}+1}$, on doit avoir max $\left(a_{i_{0}}, a_{i_{0}+2}\right)=$ $a_{i_{0}+2}$, ce qui implique que $a_{i_{0}+1}<a_{i_{0}+2}$.
Hérédité : soit $\mathfrak{i}_{0}+1 \leqslant \mathfrak{j}<n-1$ un entier tel que $a_{j}<a_{j+1}$. Montrons que $a_{j+1}<a_{j+2}$. Comme $a_{\mathfrak{j}+1}<\max \left(a_{\mathfrak{j}}, a_{\mathfrak{j}+2}\right)$ et $a_{\mathfrak{j}}<\mathfrak{a}_{\mathfrak{j}+1}$, on doit avoir $\max \left(a_{j}, a_{j+2}\right)=a_{j+2}$, ce qui implique que $a_{j+1}<a_{j+2}$.
On a donc:
$$
a_{1}>\cdots>a_{i_{0}} \leqslant a_{i_{0}+1}<a_{i_{0}+2}<a_{i_{0}+3}<\cdots<a_{n}
$$
ce qui implique que $a_{i}<\max \left(a_{1}, a_{n}\right)$ pour tout $i \in\{2,3, \ldots, n-1\}$.
Deuxième cas : il n'existe pas d'entier $1 \leqslant \mathfrak{i}_{0} \leqslant n-1$ tel que $a_{i_{0}} \leqslant a_{i_{0}+1}$. Alors $a_{1}>a_{2}>\cdots>$ $a_{n}$ et on a bien le résultat voulu.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 2.",
"solution_match": "\nSolution de l'exercice 2"
}
|
174a401f-07b0-5683-9763-739494431ddb
| 607,622
|
Let $0 \leqslant a, b, c, d, e \leqslant 1$ be real numbers. Show that
$$
(1+a+b+c+d+e)^{2} \geqslant 4\left(a^{2}+b^{2}+c^{2}+d^{2}+e^{2}\right)
$$
|
The idea is to use the inequality $(x+y)^{2} \geqslant 4 x y$ for $x=1$ and a particular value of $y$.
More precisely, for all $x, y \geqslant 0$, we have $(x-y)^{2} \geqslant 0$, and thus $(x+y)^{2} \geqslant 4 x y$ (this inequality is also the arithmetic-geometric mean inequality for two variables). By evaluating this inequality with $x=1$ and $y=a+b+c+d+e$, we get:
$$
(1+a+b+c+d+e)^{2} \geqslant 4(a+b+c+d+e)
$$
For any real number $x$ such that $0 \leqslant x \leqslant 1$, we have $x \geqslant x^{2}$. Therefore,
$$
4(a+b+c+d+e) \geqslant 4\left(a^{2}+b^{2}+c^{2}+d^{2}+e^{2}\right)
$$
which finally shows that $(1+a+b+c+d+e)^{2} \geqslant 4\left(a^{2}+b^{2}+c^{2}+d^{2}+e^{2}\right)$.
## Common Exercises
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
Soient $0 \leqslant a, b, c, d, e \leqslant 1$ des nombres réels. Montrer que
$$
(1+a+b+c+d+e)^{2} \geqslant 4\left(a^{2}+b^{2}+c^{2}+d^{2}+e^{2}\right)
$$
|
L'idée est d'utiliser l'inégalité $(x+y)^{2} \geqslant 4 x y$ pour $x=1$ et une valeur particulière de $y$.
Plus précisément, pour tous $x, y \geqslant 0$, on a $(x-y)^{2} \geqslant 0$, et donc $(x+y)^{2} \geqslant 4 x y$ (cette inégalité est aussi l'inégalité arithmético-géométrique à deux variables). En évaluant cette inégalité avec $x=1$ et $y=a+b+c+d+e$, on obtient:
$$
(1+a+b+c+d+e)^{2} \geqslant 4(a+b+c+d+e)
$$
Or pour tout nombre réel $x$ tel que $0 \leqslant x \leqslant 1$, on a $x \geqslant x^{2}$. Donc
$$
4(a+b+c+d+e) \geqslant 4\left(a^{2}+b^{2}+c^{2}+d^{2}+e^{2}\right)
$$
ce qui montre finalement que $(1+a+b+c+d+e)^{2} \geqslant 4\left(a^{2}+b^{2}+c^{2}+d^{2}+e^{2}\right)$.
## Exercices communs
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 3.",
"solution_match": "\nSolution de l'exercice 3"
}
|
1559e25b-fe9a-5a7a-8918-0a4241309afc
| 607,623
|
Let \( a, b, c > 0 \). Show that
\[
\sqrt{\frac{a}{b+c}} + \sqrt{\frac{b}{c+a}} + \sqrt{\frac{c}{a+b}} > 2.
\]
|
The idea is to use the arithmetic-geometric mean inequality to lower bound $\frac{1}{\sqrt{x+y}}$. More precisely, by the arithmetic-geometric mean inequality:
$$
\sqrt{\frac{a}{b+c}}=\frac{a}{\sqrt{a(b+c)}} \geqslant \frac{a}{(a+b+c) / 2} \geqslant \frac{2 a}{a+b+c}
$$
We proceed similarly to show that $\sqrt{\frac{b}{c+a}} \geqslant \frac{2 b}{a+b+c}$ and that $\sqrt{\frac{c}{a+b}} \geqslant \frac{2 c}{a+b+c}$. We deduce that
$$
\sqrt{\frac{a}{b+c}}+\sqrt{\frac{b}{c+a}}+\sqrt{\frac{c}{a+b}} \geqslant 2
$$
Equality holds if and only if we are in the equality case of each of the three arithmetic-geometric mean inequalities used, i.e., $a=b+c, b=a+c$ and $c=a+b$, which is impossible.
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
Soient a, b, $c>0$. Montrer que
$$
\sqrt{\frac{a}{b+c}}+\sqrt{\frac{b}{c+a}}+\sqrt{\frac{c}{a+b}}>2 .
$$
|
L'idée est d'utiliser inégalité arithmético-géométrique pour minorer $\frac{1}{\sqrt{x+y}}$. Plus précisément, on a, par inégalité arithmético-géométrique :
$$
\sqrt{\frac{a}{b+c}}=\frac{a}{\sqrt{a(b+c)}} \geqslant \frac{a}{(a+b+c) / 2} \geqslant \frac{2 a}{a+b+c}
$$
On procède de même pour montrer que $\sqrt{\frac{b}{c+a}} \geqslant \frac{2 b}{a+b+c}$ et que $\sqrt{\frac{c}{a+b}} \geqslant \frac{2 c}{a+b+c}$. On en déduit que
$$
\sqrt{\frac{a}{b+c}}+\sqrt{\frac{b}{c+a}}+\sqrt{\frac{c}{a+b}} \geqslant 2
$$
Il y a égalité seulement si et seulement si on est dans le cas d'égalité de chacune des trois inégalités arithmético-géométrique utilisées, soit : $a=b+c, b=a+c$ et $c=a+b$, ce qui est impossible.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 5.",
"solution_match": "\nSolution de l'exercice 5"
}
|
93d6d295-0dcf-5bd8-b333-dd0c5af6d0b7
| 607,625
|
. Let $n \geqslant 2$ be an integer and let $x_{1}, \ldots, x_{n}$ be positive real numbers such that $x_{1} x_{2} \cdots x_{n}=1$. Show that
$$
\frac{1}{n-1+x_{1}}+\frac{1}{n-1+x_{2}}+\cdots+\frac{1}{n-1+x_{n}} \leqslant 1
$$
|
By reducing to a common denominator, it is a matter of showing that
$$
\sum_{k=1}^{n} \prod_{j \neq k}\left(x_{j}+n-1\right) \leqslant \prod_{k=1}^{n}\left(x_{k}+n-1\right)
$$
We denote
$$
\sigma_{k}=\sum_{1 \leqslant i_{1}<\cdots<i_{k} \leqslant n} x_{i_{1}} x_{i_{2}} \cdots x_{i_{k}}
$$
the $k$-th elementary polynomial (of degree $k$ therefore) in $x_{1}, \cdots, x_{n}$. Then, by expanding both sides of (5), we see that the coefficient of $\sigma_{k}$ is $(n-1)^{n-k}$ on the right side for $1 \leqslant k \leqslant n$, and $(n-k)(n-1)^{n-k-1}$ on the left side for $1 \leqslant k \leqslant n-1$. The constant coefficient is $(n-1)^{n}$ on the right and $n(n-1)^{n-1}$ on the left. In other words,
$$
\prod_{k=1}^{n}\left(x_{j}+n-1\right)=\sum_{k=1}^{n}(n-1)^{n-k} \sigma_{k}+(n-1)^{n}
$$
and
$$
\sum_{k=1}^{n} \prod_{j \neq k}\left(x_{j}+n-1\right)=\sum_{k=1}^{n-1}(n-k)(n-1)^{n-k-1} \sigma_{k}+n(n-1)^{n-1}
$$
By noting $D=\prod_{k=1}^{n}\left(x_{k}+n-1\right)-\sum_{k=1}^{n} \prod_{j \neq k}\left(x_{j}+n-1\right)$, we therefore have
$$
D=x_{1} x_{2} \cdots x_{n}+\sum_{k=1}^{n-1}(k-1)(n-1)^{n-k-1} \sigma_{k}-(n-1)^{n-1}
$$
Now, $\sigma_{k} \geqslant\binom{ n}{k}$ by the arithmetic-geometric inequality (since $x_{1} x_{2} \cdots x_{n}=1$), so that:
$$
D \geqslant \sum_{k=1}^{n}(k-1)(n-1)^{n-k-1}\binom{n}{k}-(n-1)^{n-1}
$$
or, by dividing both sides by $(n-1)^{n-1}$,
$$
\frac{D}{(n-1)^{n-1}} \geqslant \sum_{k=1}^{n}(k-1)(n-1)^{-k}\binom{n}{k}-1=\sum_{k=1}^{n} k(n-1)^{-k}\binom{n}{k}-\sum_{k=1}^{n}(n-1)^{-k}\binom{n}{k}-1 .
$$
Now,
$$
\sum_{k=1}^{n} k\binom{n}{k}(n-1)^{-k}=\frac{n}{n-1} \sum_{k=1}^{n}\binom{n-1}{k-1} \cdot\left(\frac{1}{n-1}\right)^{k-1}=\frac{n}{n-1} \times\left(\frac{n}{n-1}\right)^{n-1}=\left(\frac{n}{n-1}\right)^{n}
$$
and
$$
\sum_{k=1}^{n}(n-1)^{-k}\binom{n}{k}=\sum_{k=0}^{n}(n-1)^{-k}\binom{n}{k}-1=\left(\frac{n}{n-1}\right)^{n}-1 .
$$
We deduce that $D \geqslant 0$, which concludes the proof.
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
. Soit $n \geqslant 2$ un nombre entier et soient $x_{1}, \ldots, x_{n}$ des nombres réels positifs tels que $x_{1} x_{2} \cdots x_{n}=1$. Montrer que
$$
\frac{1}{n-1+x_{1}}+\frac{1}{n-1+x_{2}}+\cdots+\frac{1}{n-1+x_{n}} \leqslant 1
$$
|
En réduisant au même dénominateur, il s'agit de montrer que
$$
\sum_{k=1}^{n} \prod_{j \neq k}\left(x_{j}+n-1\right) \leqslant \prod_{k=1}^{n}\left(x_{k}+n-1\right)
$$
On note
$$
\sigma_{k}=\sum_{1 \leqslant i_{1}<\cdots<i_{k} \leqslant n} x_{i_{1}} x_{i_{2}} \cdots x_{i_{k}}
$$
le $k$-ème polynôme élémentaire (de degré $k$ donc) en $x_{1}, \cdots, x_{n}$. Alors, en développant les deux côtés de (5), on voit que le coefficient de $\sigma_{k}$ est $(n-1)^{n-k}$ dans celui de droite pour $1 \leqslant k \leqslant n$, et $(n-k)(n-1)^{n-k-1}$ dans celui de gauche pour $1 \leqslant k \leqslant n-1$. Le coefficient constant vaut $(n-1)^{n}$ à droite et $n(n-1)^{n-1}$ à gauche. Autrement dit,
$$
\prod_{k=1}^{n}\left(x_{j}+n-1\right)=\sum_{k=1}^{n}(n-1)^{n-k} \sigma_{k}+(n-1)^{n}
$$
et
$$
\sum_{k=1}^{n} \prod_{j \neq k}\left(x_{j}+n-1\right)=\sum_{k=1}^{n-1}(n-k)(n-1)^{n-k-1} \sigma_{k}+n(n-1)^{n-1}
$$
En notant $D=\prod_{k=1}^{n}\left(x_{k}+n-1\right)-\sum_{k=1}^{n} \prod_{j \neq k}\left(x_{j}+n-1\right)$, on a donc
$$
D=x_{1} x_{2} \cdots x_{n}+\sum_{k=1}^{n-1}(k-1)(n-1)^{n-k-1} \sigma_{k}-(n-1)^{n-1}
$$
Or $\sigma_{k} \geqslant\binom{ n}{k}$ par l'inégalité arithmético-géométrique ( $\operatorname{car} x_{1} x_{2} \cdots x_{n}=1$,) de sorte que :
$$
D \geqslant \sum_{k=1}^{n}(k-1)(n-1)^{n-k-1}\binom{n}{k}-(n-1)^{n-1}
$$
ou encore, en divisant les deux côtés par $(\mathrm{n}-1)^{\mathrm{n}-1}$,
$$
\frac{D}{(n-1)^{n-1}} \geqslant \sum_{k=1}^{n}(k-1)(n-1)^{-k}\binom{n}{k}-1=\sum_{k=1}^{n} k(n-1)^{-k}\binom{n}{k}-\sum_{k=1}^{n}(n-1)^{-k}\binom{n}{k}-1 .
$$
Or
$$
\sum_{k=1}^{n} k\binom{n}{k}(n-1)^{-k}=\frac{n}{n-1} \sum_{k=1}^{n}\binom{n-1}{k-1} \cdot\left(\frac{1}{n-1}\right)^{k-1}=\frac{n}{n-1} \times\left(\frac{n}{n-1}\right)^{n-1}=\left(\frac{n}{n-1}\right)^{n}
$$
et
$$
\sum_{k=1}^{n}(n-1)^{-k}\binom{n}{k}=\sum_{k=0}^{n}(n-1)^{-k}\binom{n}{k}-1=\left(\frac{n}{n-1}\right)^{n}-1 .
$$
On en déduit que $D \geqslant 0$, ce qui conclut.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 7",
"solution_match": "\nSolution de l'exercice 7"
}
|
0f8aafcf-e32c-59dc-9e96-9082f4b00014
| 607,627
|
We denote $S(k)$ as the sum of the digits of an integer $k$. We say that an integer $a$ is of order $n$ if there exists a sequence of integers $a_{0}, a_{1}, \ldots, a_{n}$ such that $a_{n}=a$ and $a_{i+1}=a_{i}-S\left(a_{i}\right)$ for all $i=0,1, \ldots, n-1$. Show that for every integer $n \geqslant 1$ there exists an integer $b$ which is of order $n$ but not of order $n+1$.
|
We set $F(x)=x-S(x)$, and consider the sequence defined by $u_{0}=1$ and $u_{i+1}=10^{u_{i}}$ for $i \geqslant 0$. Let $n \geqslant 1$ be fixed, and consider an integer $N>u_{n+1}$. We will show that $X=F^{(n)}\left(10^{N}-5 N\right)$ (we iterate $F$ $n$ times) is of order $n$ but not $n+1$. For this, it suffices to show that $X$ is not of order $n+1$.
First, we note that $F(a)-F(b)$ is always divisible by 9, and that if $a$ and $b$ differ only in their last $k$ digits, then $|a-b| \leqslant 10^{k}$.
Now let's establish a kind of converse to this remark. Let $a, b$ be two integers and write $a=\sum_{i \geqslant 0} c_{i} 10^{i}$ and $b=\sum_{i \geqslant 0} c_{i}^{\prime} 10^{i}$. We have $F(a)-F(b)=\sum_{i \geqslant 0}\left(c_{i}-c_{i}^{\prime}\right)\left(10^{i}-1\right)$. If $j$ is the largest index such that $c_{j}>c_{j}^{\prime}$, then
$$
F(a)-F(b) \geqslant\left(10^{j}-1\right)+\sum_{i=0}^{j-1}\left(c_{i}-c_{i}^{\prime}\right)\left(10^{i}-1\right) \geqslant\left(10^{j}-1\right)-9 \sum_{i=0}^{j-1}\left(10^{i}-1\right)=9 j
$$
We deduce that if $|F(a)-F(b)|=9 k$, then $j \leqslant k$, and therefore
if $|F(a)-F(b)|=9 k$, then $a$ and $b$ can only differ in their last $k+1$ digits. (6)
Let's now prove the following lemma:
Lemma. If $F^{(n)}(a)=F^{(n)}(b)$, then $a$ and $b$ can only differ in their last $u_{n}$ digits.
Let's return to the proof of the lemma by induction on $n$. The initialization for $n=1$ comes from (6) applied with $k=0$. For the induction step, let $n \geqslant 1$ such that the lemma is true up to rank $n$. Let $a, b$ be two integers such that $F^{(n+1)}(a)=F^{(n+1)}(b)$. Then $F^{(n)}(F(a))=F^{(n)}(F(b))$, and therefore $|F(a)-F(b)| \leqslant 10^{u_{n}}$ by the induction hypothesis. Since $|F(a)-F(b)|$ is divisible by 9, write $|F(a)-F(b)|=9 k$ (with $9 k \leqslant 10^{u_{n}}$). Then, according to (6), $a$ and $b$ can only differ in their last $k+1$ digits. Since $k+1 \leqslant 10^{u_{n}} / 9+1 \leqslant 10^{u_{n}}$, $a$ and $b$ can only differ in their last $10^{u_{n}}=u_{n+1}$ digits, which concludes the proof.
Let's return to the exercise. Reason by contradiction, assuming the existence of an integer $y$ such that $X=F^{(n+1)}(y)=F^{(n)}\left(10^{N}-5 N\right)$. Then
$$
F^{(n)}\left(10^{N}-5 N\right)=F^{(n)}(F(y))
$$
and therefore, according to the lemma,
$$
\left|10^{\mathrm{N}}-5 \mathrm{~N}-\mathrm{F}(\mathrm{y})\right| \leqslant 10^{\mathbf{u}_{\mathrm{n}}} \leqslant \mathrm{~N} .
$$
Thus,
$$
10^{\mathrm{N}}-4 \mathrm{~N} \leqslant \mathrm{~F}(\mathrm{y}) \leqslant 10^{\mathrm{N}}-6 \mathrm{~N}
$$
However, we observe that if $\mathrm{y} \geqslant 10^{\mathrm{N}}$, then $\mathrm{F}(\mathrm{y}) \geqslant 10^{\mathrm{N}}-1$ (indeed, it is easily verified that $F$ is increasing and that $\left.F\left(10^{N}\right)=10^{N}-1\right)$. Moreover, if $y \leqslant 10^{N}-1$, then $F(y) \leqslant 10^{N}-9 \mathrm{~N}-1$; indeed, if $y=\sum_{i=0}^{N-1} c_{i} 10^{i}$, then
$$
F(y)=\sum_{i=0}^{N-1} c_{i}\left(10^{i}-1\right) \leqslant \sum_{i=0}^{N-1} 9\left(10^{i}-1\right)=10^{N}-9 N-1
$$
This contradicts (7), and $X$ satisfies the desired condition.
Another solution, a bit shorter: As above, we set $F(x)=x-S(x)$. It immediately follows that $F(a+1)=F(a)$ if $a \not \equiv 9(\bmod 10)$ and that $F(a+1)>F(a)$ if $a \equiv 9(\bmod 10)$. Consequently, any integer $k$ has at most 10 antecedents by $F$, and a fortiori it has at most $10^{\mathrm{n}}$ antecedents by $F^{(n)}$, where $F^{(n)}$ is the $n^{\text {th }}$ iterate of $F$. It follows that $F^{(n)}\left(k+10^{n}\right)>F^{(n)}(k)$ for any integer $k \geqslant 1$ (indeed, if $F^{(n)}\left(k+10^{n}\right)=F^{(n)}(k)$ for some integer $k \geqslant 1$, we would have $F^{(n)}(k)=F^{(n)}(i)$ for all $k \leqslant i \leqslant k+10^{n}$, so the integer $F^{(n)}(k)$ would have at least $10^{n}+1$ antecedents which are $\left.k, k+1, k+2, \ldots, k+10^{n}\right)$.
Now, let $\ell$ be an integer such that $9 \ell \geqslant 2 \cdot 10^{n}$. We observe that $F\left(10^{\ell}\right)=10^{\ell}-1$ and that $F\left(10^{\ell}-1\right)=10^{\ell}-1-9 \ell$, and we set $a_{k}=F^{(k)}\left(10^{\ell}-10^{n}-1\right)$ and $b_{k}=F^{(k)}\left(10^{\ell}-1\right)$, for $k \geqslant 0$. Since $b_{0} \geqslant a_{0}+10^{n}$, we deduce that $b_{n}>a_{n}$. Similarly, since $a_{0} \geqslant b_{1}+10^{n}$, we deduce that $a_{n}>b_{n+1}$. This shows that $b_{0}>i>b_{1}$ for any integer $i$ such that $a_{n}=F^{(n)}(i)$.
Now, we have $F(k) \geqslant b_{0}$ for all $k \geqslant 10^{\ell}$ and $F(k) \leqslant b_{1}$ for all $k \leqslant 10^{\ell}-1$, which shows that the elements of the set $\left\{b_{1}+1, \ldots, b_{0}-1\right\}$ are all of order 0 but not of order 1. It follows that $a_{n}$ is of order $n$ but not of order $n+1$, which concludes the proof.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
On note $S(k)$ la somme des chiffres d'un nombre entier $k$. On dit qu'un entier a est d'ordre $n$ s'il existe une suite d'entiers $a_{0}, a_{1}, \ldots, a_{n}$ tels que $a_{n}=a$ et $a_{i+1}=a_{i}-S\left(a_{i}\right)$ pour tout $i=0,1, \ldots, n-1$. Montrer que pour tout entier $n \geqslant 1$ il existe un entier $b$ qui soit d'ordre $n$ mais qui ne soit pas d'ordre $n+1$.
|
On pose $F(x)=x-S(x)$, et on considère la suite définie par $u_{0}=1$ et $u_{i+1}=10^{u_{i}}$ pour $i \geqslant 0$. Soit $n \geqslant 1$ fixé, et considérons un entier $N>u_{n+1}$. Nous allons montrer que $X=F^{(n)}\left(10^{N}-5 N\right.$ ) (on itère $n$ fois $F$ ) est d'ordre $n$ mais pas $n+1$. Pour cela, il suffit de montrer que X n'est pas d'ordre $\mathrm{n}+1$.
On remarque pour commencer que $F(a)-F(b)$ est toujours divisible par 9, et que si $a$ et $b$ ne différent que sur leurs $k$ derniers chiffres, alors $|a-b| \leqslant 10^{k}$.
Établissons maintenant une sorte de réciproque à cette remarque. Soient $a, b$ deux entiers et écrivons $a=\sum_{i \geqslant 0} c_{i} 10^{i}$ et $b=\sum_{i \geqslant 0} c_{i}^{\prime} 10^{i}$. On a $F(a)-F(b)=\sum_{i \geqslant 0}\left(c_{i}-c_{i}^{\prime}\right)\left(10^{i}-1\right)$. Si $j$ est le plus grand indice tel que $c_{j}>c_{j}^{\prime}$, alors
$$
F(a)-F(b) \geqslant\left(10^{j}-1\right)+\sum_{i=0}^{j-1}\left(c_{i}-c_{i}^{\prime}\right)\left(10^{i}-1\right) \geqslant\left(10^{j}-1\right)-9 \sum_{i=0}^{j-1}\left(10^{i}-1\right)=9 j
$$
On en déduit que si $|F(a)-F(b)|=9 k$, alors $j \leqslant k$, et donc
si $|F(a)-F(b)|=9 k, \quad$ alors $a$ et $b$ ne peuvent différer que sur leurs $k+1$ derniers chiffres. (6)
Montrons maintenant le lemme suivant:
Lemme. Si $F^{(n)}(a)=F^{(n)}(b)$ alors $a$ et b ne peuvent différer que sur leurs $u_{n}$ derniers chiffres.
Revenons maintenant à la preuve du lemme en raisonnant par récurrence sur n . L'initialisation pour $n=1$ provient de (6) appliqué avec $k=0$. Pour l'hérédité, soit $n \geqslant 1$ tel que le lemme est vrai jusqu'au rang $n$. Soient $a, b$ deux entiers tels que $F^{(n+1)}(a)=F^{(n+1)}(b)$. Alors $F^{(n)}(F(a))=$ $F^{(n)}(F(b))$, et donc $|F(a)-F(b)| \leqslant 10^{u_{n}}$ par hypothèse de récurrence. Comme $|F(a)-F(b)|$ est divisible par 9 , écrivons $|F(a)-F(b)|=9 k$ (avec $9 k \leqslant 10^{u_{n}}$ ). Alors d'après (6), a et b ne peuvent différer que sur leurs $k+1$ derniers chiffres. Comme $k+1 \leqslant 10^{u_{n}} / 9+1 \leqslant 10^{u_{n}}$, a et b ne peuvent différer que sur leurs $10^{u_{n}}=u_{n+1}$ derniers chiffres, ce qui conclut.
Revenons à l'exercice. Raisonnons par l'absurde en supposant l'existence d'un entier y tel que $X=F^{(n+1)}(y)=F^{(n)}\left(10^{N}-5 N\right)$. Alors
$$
F^{(n)}\left(10^{N}-5 N\right)=F^{(n)}(F(y))
$$
et donc d'après le lemme
$$
\left|10^{\mathrm{N}}-5 \mathrm{~N}-\mathrm{F}(\mathrm{y})\right| \leqslant 10^{\mathbf{u}_{\mathrm{n}}} \leqslant \mathrm{~N} .
$$
Donc
$$
10^{\mathrm{N}}-4 \mathrm{~N} \leqslant \mathrm{~F}(\mathrm{y}) \leqslant 10^{\mathrm{N}}-6 \mathrm{~N}
$$
Or on constate que si $\mathrm{y} \geqslant 10^{\mathrm{N}}$, alors $\mathrm{F}(\mathrm{y}) \geqslant 10^{\mathrm{N}}-1$ (en effet, on vérifie aisément que F est croissante et que $\left.F\left(10^{N}\right)=10^{N}-1\right)$. De plus, si $y \leqslant 10^{N}-1$, alors $F(y) \leqslant 10^{N}-9 \mathrm{~N}-1$; en effet si $y=\sum_{i=0}^{N-1} c_{i} 10^{i}$, alors
$$
F(y)=\sum_{i=0}^{N-1} c_{i}\left(10^{i}-1\right) \leqslant \sum_{i=0}^{N-1} 9\left(10^{i}-1\right)=10^{N}-9 N-1
$$
Ceci contredit (7), et $X$ vérifie bien la condition cherchée.
Autre solution, un peu plus courte : Comme ci-dessus, on pose $F(x)=x-S(x)$. Il vient immédiatement que $F(a+1)=F(a)$ si $a \not \equiv 9(\bmod 10)$ et que $F(a+1)>F(a)$ si $a \equiv 9(\bmod 10)$. Par conséquent, tout entier k a au plus 10 antécédents par F , et a fortiori il a au plus $10^{\mathrm{n}}$ antécédents par $F^{(n)}$, où $F^{(n)}$ est la $n^{\text {ème }}$ itérée de $F$. Il s'ensuit que $F^{(n)}\left(k+10^{n}\right)>F^{(n)}(k)$ pour tout entier $k \geqslant 1$ (en effet, si $F^{(n)}\left(k+10^{n}\right)=F^{(n)}(k)$ pour un certain entier $k \geqslant 1$, on aurait $F^{(n)}(k)=F^{(n)}(i)$ pour tout $k \leqslant i \leqslant k+10^{n}$, de sorte que $l^{\prime}$ entier $F^{(n)}(k)$ aurait au moins $10^{n}+1$ antécédents qui sont $\left.k, k+1, k+2, \ldots, k+10^{n}\right)$.
Maintenant, soit $\ell$ un entier tel que $9 \ell \geqslant 2 \cdot 10^{n}$. On observe que $F\left(10^{\ell}\right)=10^{\ell}-1$ et que $F\left(10^{\ell}-1\right)=10^{\ell}-1-9 \ell$, puis on pose $a_{k}=F^{(k)}\left(10^{\ell}-10^{n}-1\right)$ et $b_{k}=F^{(k)}\left(10^{\ell}-1\right)$, pour $k \geqslant 0$. Puisque $b_{0} \geqslant a_{0}+10^{n}$, on en déduit que $b_{n}>a_{n}$. De même, puisque $a_{0} \geqslant b_{1}+10^{n}$, on en déduit que $a_{n}>b_{n+1}$. Cela montre que $b_{0}>i>b_{1}$ pour tout entier $i$ tel que $a_{n}=F^{(n)}(i)$.
Or, on a $F(k) \geqslant b_{0}$ pour tout $k \geqslant 10^{\ell}$ et $F(k) \leqslant b_{1}$ pour tout $k \leqslant 10^{\ell}-1$, ce qui montre que les éléments de l'ensemble $\left\{b_{1}+1, \ldots, b_{0}-1\right\}$ sont tous d'ordre 0 mais pas d'ordre 1 . Il s'ensuit que $a_{n}$ est d'ordre $n$ mais pas d'ordre $n+1$, ce qui conclut.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 8.",
"solution_match": "\nSolution de l'exercice 8"
}
|
123450b3-8da3-5607-94c3-cec5e87e9c32
| 607,628
|
Let A be a set of 13 integers between 1 and 37. Show that there exist four distinct numbers in $A$ such that the sum of two of them is equal to the sum of the other two.
|
A contains 13 integers, so there are $\frac{13 \times 12}{2}=78$ ways to choose two different numbers from A (13 ways to choose the first, 12 ways to choose the second, and we divide by 2 because we have counted each set of 2 numbers twice). Now, the sum of two numbers from $\mathcal{A}$ is always at least $1+2=3$ and at most $36+37=73$, so it can take 71 different values. According to the pigeonhole principle, there exist $\mathrm{a} \neq \mathrm{d}$ and $\mathrm{b} \neq \mathrm{c}$ in $A$ such that $\mathrm{a}+\mathrm{d}=\mathrm{b}+\mathrm{c}$, and the set $\{a, d\}$ is different from $\{b, c\}$. To conclude, we need to ensure that $a, b, c$ and $d$ are all distinct.
But if, for example, $a=b$, then since $a+d=b+c$, we must have $d=c$ so $\{a, d\}=\{b, c\}$, which is false. Therefore, we have indeed found 4 numbers that satisfy the desired property.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Soit A un ensemble de 13 entiers entre 1 et 37 . Montrer qu'il existe quatre nombres deux à deux distincts dans $A$ tels que la somme de deux d'entre eux est égale à la somme des deux autres.
|
A contient 13 entiers, donc il y a $\frac{13 \times 12}{2}=78$ manières de choisir deux nombres de A différents ( 13 manières de choisir le premier, 12 manières de choisir le deuxième et on divise par 2 car on a compté deux fois chaque ensemble de 2 nombres). Or, la somme de deux nombres de $\mathcal{A}$ vaut toujours au moins $1+2=3$ et au plus $36+37=73$, donc elle peut prendre 71 valeurs différentes. D'après le principe des tiroirs, il existe donc $\mathrm{a} \neq \mathrm{d}$ et $\mathrm{b} \neq \mathrm{c}$ dans $A$ tels que $\mathrm{a}+\mathrm{d}=\mathrm{b}+\mathrm{c}$, et l'ensemble $\{a, d\}$ est différent de $\{b, c\}$. Pour conclure, il suffit de s'assurer que $a, b, c$ et $d$ sont deux à deux distincts.
Mais si par exemple $a=b$, alors comme $a+d=b+c$, on doit avoir $d=c$ donc $\{a, d\}=\{b, c\}$, ce qui est faux. On a donc bien trouvé 4 nombres qui vérifient la propriété voulue.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-4-solutions.jsonl",
"problem_match": "\nExercice 2.",
"solution_match": "\nSolution de l'exercice 2"
}
|
5d344152-ec00-53ac-90b4-4eaf4d88c6c1
| 607,631
|
Let $n \geqslant 1$. We have a finite number of bottles, each containing an amount of water less than 1 liter, such that the total amount of water is $\frac{\mathfrak{n}}{2}$ liters. We also have $n$ empty buckets.
Show that it is possible to empty each bottle into a bucket (we can empty several bottles into the same bucket, but not empty a bottle partially into one bucket and partially into another) in such a way that there is at most 1 liter of water in each bucket.
|
We reason by induction on $n$: for $\mathrm{n}=1$, it suffices to empty everything into the unique bucket.
Suppose the result is true at rank $n$: if we manage to empty into a bucket a certain number of bottles representing in total at least $\frac{1}{2}$ liter and at most 1 liter, then there will remain $\frac{\mathrm{n}-1}{2}$ liters to empty into the $\mathrm{n}-1$ remaining buckets, and we can apply the induction hypothesis to conclude.
If there exists a bottle containing at least $\frac{1}{2}$ liter, we can therefore empty it into the first bucket. Otherwise, all the bottles contain less than $\frac{1}{2}$ liter. We therefore empty them one by one into the first bucket, and stop as soon as the content of the bucket exceeds $\frac{1}{2}$ liter: the bucket then contains more than $\frac{1}{2}$ liter. Moreover, just before emptying the last bottle, it contained less than $\frac{1}{2}$ liter, and we added a bottle, thus less than $\frac{1}{2}$ liter. The bucket therefore contains less than 1 liter, and we can conclude by induction hypothesis.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Soit $n \geqslant 1$. On a un nombre fini de bouteilles, chacune contenant une quantité d'eau inférieure à 1 litre, telles que la quantité totale d'eau est de $\frac{\mathfrak{n}}{2}$ litres. On dispose également de n seaux vides.
Montrer qu'il est possible de vider chaque bouteille dans un seau (on peut vider plusieurs bouteilles dans le même seau, mais pas vider une bouteille en partie dans un seau et en partie dans un autre) de manière à avoir au plus 1 litre d'eau dans chaque seau.
|
On raisonne par récurrence sur $n$ : pour $\mathrm{n}=1$, il suffit de tout vider dans l'unique seau.
Supposons le résultat vrai au rang n : si on arrive à vider dans un seau un certain nombre de bouteilles représentant au total au moins $\frac{1}{2}$ litre et au plus 1 litre, alors il restera $\frac{\mathrm{n}-1}{2}$ litres à vider dans les $\mathrm{n}-1$ seaux restants, et on pourra appliquer l'hypothèse de récurrence pour conclure.
Si il existe une bouteille contenant au moins $\frac{1}{2}$ litre, on peut donc la vider dans le premier seau. Sinon, toutes les bouteilles contiennent moins de $\frac{1}{2}$ litre. On les vide donc une par une dans le premier seau, et on s'arrête dès que le contenu du seau dépasse $\frac{1}{2}$ litre : le seau contient alors plus de $\frac{1}{2}$ litre. De plus, juste avant de vider la dernière bouteille, il contenait moins de $\frac{1}{2}$ litre, et on a ajouté une bouteille, donc moins de $\frac{1}{2}$ litre. Le seau contient donc moins de 1 litre, et on peut conclure par hypothèse de récurrence.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-4-solutions.jsonl",
"problem_match": "\nExercice 4.",
"solution_match": "\nSolution de l'exercice 4"
}
|
3ce63c47-e0f2-5e48-a28d-c66f9504be54
| 607,633
|
Let $n \geqslant 2$. We draw a circuit on an $n \times n$ chessboard that passes exactly once through each square and returns to its starting point (two consecutive squares on the circuit must share a side).
Show that there exist two adjacent squares on the chessboard such that, if we "cut" the circuit at these two squares, the two paths obtained have a length of at least a quarter of the length of the original circuit.
Note. The length of a path is the number of times it changes squares. In particular, if the circuit is cut into two paths, the sum of the lengths of the two paths will always be $n^2$.
|
First, note that if the chessboard is tiled in black and white in the usual way, the circuit must alternate between black and white squares and return to its starting square, so its length must be even, and thus $n^{2}$ must be even. We write $n=2 m$.

We consider the set of corners of the squares that are inside the circuit (these are the blue points in the figure), and we connect two of these points when they are 1 unit apart (these are the blue edges in the figure). The graph obtained is a tree: it is connected because the circuit is, and it has no cycle because a cycle would either create a second circuit inside the first, or enclose the center of a square that would therefore not be in the red circuit. Moreover, in this tree, each vertex has at most 4 neighbors.
The following lemma allows us to link the length of the red path to the number of vertices of the blue tree:
Lemma (Lemma 1). Let $T$ be a tree whose vertices are on the corners of a grid, and $C$ a circuit passing through the centers of the squares and surrounding the tree. We denote $|\mathrm{C}|$ the length of this circuit. Then $|C|=2|T|+2$.
Proof of Lemma 1. Each vertex of the tree is the center of a square of side 1. We compute the sum $S$ of the perimeters of these squares in two different ways. On one hand, we have $S=4|T|$. But on the other hand, to compute $S$, we take into account each edge of $C$ once, and each edge that separates two vertices of the tree twice. Since the tree has $|\mathrm{T}|-1$ edges, we have $S=|C|+2(|T|-1)$. We deduce the lemma from this.
We know that $|C|=n^{2}=4 m^{2}$. We deduce that $|T|=\frac{1}{2}(|C|-1)=2 m^{2}-1$. Moreover, cutting the circuit between two adjacent squares is essentially equivalent to cutting an edge of the tree. We will therefore show the following lemma:
Lemma (Lemma 2). We denote $|T|$ the number of vertices of a tree. Let $T$ be a tree with at least two vertices and where all vertices have a degree of at most 4. There exists an edge $e$ of $T$ such that by cutting the edge $e$, the tree $T$ is split into two trees $T_{1}$ and $T_{2}$ such that $\left|T_{1}\right| \geqslant \frac{1}{4}(|T|-1)$ and $\left|T_{2}\right| \geqslant \frac{1}{4}(|T|-1)$.
Proof of Lemma 2. We reason by contradiction. We fix $\mathrm{x}_{0}$ a vertex of $T$: removing $\mathrm{x}_{0}$ divides $T$ into $\mathrm{T}_{1}, \mathrm{~T}_{2}, \mathrm{~T}_{3}$ and $\mathrm{T}_{4}$ (if $\times$ does not have four neighbors, some of these trees have zero vertices). According to the pigeonhole principle, there exists $i$ such that $\left|T_{i}\right| \geqslant \frac{1}{4}(|T|-1)$. Suppose it is $T_{1}$, and we denote $x_{1}$ the vertex of $T_{1}$ that is connected to $x_{0}$. But if $T$ does not satisfy the lemma, then $\left|\mathrm{T}_{1}\right|>|\mathrm{T}|-\frac{1}{4}(|\mathrm{~T}|-1)=\frac{3}{4}(|\mathrm{~T}|-1)+1$.
We can now perform the same reasoning with $x_{1}$: it has at most three neighbors different from $x_{0}$ which correspond to three trees $\mathrm{T}_{1}^{\prime}, \mathrm{T}_{2}^{\prime}$ and $\mathrm{T}_{3}^{\prime}$, and the total number of vertices of these three trees is at least $\frac{3}{4}(|T|-1)$. By the pigeonhole principle, there exists $i$ such that $\left|T_{i}^{\prime}\right| \geqslant \frac{1}{4}(|T|-1)$, so, as $T$ does not satisfy the lemma, $\left|\mathrm{T}_{1}^{\prime}\right|>\frac{3}{4}(|\mathrm{~T}|-1)+1$. We denote $x_{2}$ the vertex by which $\mathrm{T}_{1}^{\prime}$ is connected to $x_{1}$. Since we only considered the neighbors of $x_{1}$ that are different from $x_{0}$, we have $x_{2} \neq x_{0}$. We can then iterate this argument. Since $T$ does not satisfy the lemma, the process never stops and we construct a sequence $\left(x_{n}\right)$ of vertices such that $x_{n+2} \neq x_{n}$ for all $n$. Since $T$ is a tree, $\left(x_{n}\right)$ never passes through the same vertex twice, so $T$ is infinite, which is absurd.
According to Lemma 2, there therefore exists an edge $e$ of the tree (in green in the figure) such that, if we cut $e$, we obtain $T_{1}$ and $T_{2}$ such that $\left|T_{1}\right|,\left|T_{2}\right| \geqslant \frac{1}{4}(|T|-1)=\frac{\mathrm{m}^{2}-1}{2}$. If we denote $C_{1}$ and $C_{2}$ the circuits that surround $T_{1}$ and $T_{2}$, we therefore have, according to Lemma 1, the inequalities $\left|C_{1}\right|,\left|C_{2}\right| \geqslant m^{2}+1$. But the two parts of the circuit obtained by cutting it have lengths $\left|C_{1}\right|-1$ and $\left|C_{2}\right|-1$ (we remove the orange edge) which are at least $\mathrm{m}^{2}$, hence the result.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Soit $n \geqslant 2$. On trace un circuit sur un échiquier $n \times n$ qui passe exactement une fois par chaque case et revient à son point de départ (deux cases consécutives sur le circuit doivent avoir un côté commun).
Montrer qu'il existe deux cases voisines sur l'échiquier telles que, si on "coupe" le circuit en ces deux cases, les deux chemins obtenus ont pour longueur au moins le quart de la longueur du circuit de départ.
Remarque. La longueur d'un chemin est le nombre de fois où il change de case. En particulier, si le circuit est découpé en deux chemins, la somme des longueurs des deux chemins vaudra toujours $\mathrm{n}^{2}$.
|
Remarquons tout d'abord que si l'échiquier est pavé en noir et blanc de la manière habituelle, le circuit doit alterner des cases noires et blanches et revenir à sa case de départ donc sa longueur doit être paire donc $n^{2}$ et pair. On écrit donc $n=2 m$.

On considère l'ensemble des coins des carrés qui se trouvent à l'intérieur du circuit (ce sont les points bleus sur la figure), et on relie deux de ces points quand ils sont à distance 1 l'un de l'autre (ce sont les
arêtes bleues sur la figure). Le graphe obtenu est un arbre : il est connexe car le circuit l'est, et il n'a pas de cycle car un cycle soit créerait un deuxième circuit à l'intérieur du premier, soit enfermerait le centre d'une case qui ne serait donc pas dans le circuit rouge. De plus, dans cet arbre, chaque sommet a au plus 4 voisins.
Le lemme suivant permet de faire le lien entre la longueur du chemin rouge et le nombre de sommets de l'arbre bleu :
Lemme (Lemme 1). Soit $T$ un arbre dont les sommets sont sur les coins d'un quadrillage, et $C$ un circuit passant par les centres des cases et faisant le tour de l'arbre. On note $|\mathrm{C}|$ la longueur de ce circuit. Alors $|C|=2|T|+2$.
Preuve du lemme 1. Chaque sommet de l'arbre est le centre d'un carré de côté 1. On calcule de deux manières différentes la somme $S$ des périmètres de ces carrés. D'un part on a $S=4|T|$. Mais d'autre part, pour calculer $S$, on prend en compte une fois chaque arête de $C$, et deux fois chaque arête qui sépare deux sommets de l'arbre. Comme l'arbre a $|\mathrm{T}|-1$ arêtes, on a donc $S=|C|+2(|T|-1)$. On en déduit le lemme.
On sait que $|C|=n^{2}=4 m^{2}$. On en déduit $|T|=\frac{1}{2}(|C|-1)=2 m^{2}-1$. De plus, couper le circuit en deux cases voisines revient essentiellement à couper une arête de l'arbre. On va donc montrer le lemme suivant:
Lemme (Lemme 2). On note |T| le nombre de sommets d'un arbre. Soit T un arbre ayant au moins deux sommets et dont tous les sommets sont de degré au plus 4. Il existe une arête e de T telle qu'en coupant l'arête $e$, l'arbre $T$ est coupé en deux arbres $T_{1}$ et $T_{2}$ tels que $\left|T_{1}\right| \geqslant \frac{1}{4}(|T|-1)$ et $\left|T_{2}\right| \geqslant \frac{1}{4}(|T|-1)$.
Preuve du lemme 2. On raisonne par l'absurde. On fixe $\mathrm{x}_{0}$ un sommet de T : supprimer $\mathrm{x}_{0}$ divise T en $\mathrm{T}_{1}, \mathrm{~T}_{2}, \mathrm{~T}_{3}$ et $\mathrm{T}_{4}$ (si $\times$ n'a pas quatre voisins, certains de ces arbres ont un nombre de sommets nul). D'après le principe des tiroirs, il existe $i$ tel que $\left|T_{i}\right| \geqslant \frac{1}{4}(|T|-1)$. On suppose que c'est $T_{1}$, et on note $x_{1}$ le sommet de $T_{1}$ qui est relié à $x_{0}$. Mais si $T$ ne vérifie pas le lemme, alors $\left|\mathrm{T}_{1}\right|>|\mathrm{T}|-\frac{1}{4}(|\mathrm{~T}|-1)=\frac{3}{4}(|\mathrm{~T}|-1)+1$.
On peut maintenant effectuer le même raisonnement avec $x_{1}$ : il a au plus trois voisins différents de $x_{0}$ qui correspondent à trois arbres $\mathrm{T}_{1}^{\prime}, \mathrm{T}_{2}^{\prime}$ et $\mathrm{T}_{3}^{\prime}$, et le nombre total de sommets de ces trois arbres vaut au moins $\frac{3}{4}(|T|-1)$. Par le principe des tiroirs il existe $i$ tel que $\left|T_{i}^{\prime}\right| \geqslant \frac{1}{4}(|T|-1)$ donc, comme $T$ ne vérifie pas le lemme, $\left|\mathrm{T}_{1}^{\prime}\right|>\frac{3}{4}(|\mathrm{~T}|-1)+1$. On note $x_{2}$ le sommet par lequel $\mathrm{T}_{1}^{\prime}$ est relié à $x_{1}$. Comme on n'a considéré que les voisins de $x_{1}$ qui sont différents de $x_{0}$, on a $x_{2} \neq x_{0}$. On peut alors itérer cet argument. Comme T ne vérifie pas le lemme, le procédé ne s'arrête jamais et on construit une suite $\left(x_{n}\right)$ de sommets telle que $x_{n+2} \neq x_{n}$ pour tout $n$. Comme $T$ est un arbre, $\left(x_{n}\right)$ ne passe jamais deux fois par le même sommet donc $T$ est infini, ce qui est absurde.
D'après le lemme 2, il existe donc une arête $e$ de l'arbre (en vert sur la figure) telle que, si on coupe $e$, on obtient $T_{1}$ et $T_{2}$ tels que $\left|T_{1}\right|,\left|T_{2}\right| \geqslant \frac{1}{4}(|T|-1)=\frac{\mathrm{m}^{2}-1}{2}$. Si on note $C_{1}$ et $C_{2}$ les circuits qui font le tour
de $T_{1}$ et de $T_{2}$, on a donc d'après le lemme 1 les inégalités $\left|C_{1}\right|,\left|C_{2}\right| \geqslant m^{2}+1$. Mais les deux parties du circuit obtenues en le coupant ont pour longueurs $\left|C_{1}\right|-1$ et $\left|C_{2}\right|-1$ (on retire l'arête orange) qui valent au moins $\mathrm{m}^{2}$, d'où le résultat.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-4-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "\nSolution de l'exercice 7"
}
|
4fdeb9f2-100c-5f4e-92ec-98dc130cced2
| 607,636
|
Let $n \geqslant 2$ and $a_{1}, \ldots, a_{n}, b_{1}, \ldots, b_{n}$ be strictly positive real numbers. The $a_{i}$ are assumed to be pairwise distinct, as are the $b_{i}$. It is assumed that it is possible to separate the $a_{i}$ into two subsets of equal sum, and the same for the $b_{i}$.
Show that there exists a simple 2n-gon having exactly n horizontal sides and n vertical sides, the lengths of the horizontal sides being exactly the $a_{i}$ and the lengths of the vertical sides being exactly the $b_{i}$.
Note. A simple polygon is a polygon whose sides do not intersect, except of course two consecutive sides at their common endpoint.
|
By changing the indices and possibly swapping the roles of $a$ and $b$, we can assume that there exist $\ell \leqslant m \leqslant \frac{n}{2}$ such that $a_{1}+\cdots+a_{\ell}=a_{\ell+1}+\cdots+a_{n}=S_{a}$ and $b_{1}+\cdots+b_{m}=$ $b_{m+1}+\cdots+b_{n}$, that $b_{1} \geqslant \cdots \geqslant b_{m}$ and that $b_{m+1} \leqslant \cdots \leqslant b_{n}$. When we go around our polygon in a clockwise direction, the $a_{i}$ with $i \leqslant \ell$ will correspond to the lengths of the sides where we go to the right, the $a_{i}$ with $i \geqslant \ell+1$ to those where we go to the left, the $b_{i}$ with $i \leqslant m$ to those where we go up, and the $b_{i}$ with $i \geqslant m+1$ to those where we go down. It remains to place these sides correctly relative to each other, so that they do not intersect.
We denote $b_{i}^{\prime}=b_{i}$ for $i \leqslant m$ and $b_{i}^{\prime}=-b_{i}$ for $i \geqslant m+1$, so that $\sum_{i=1}^{n} b_{i}^{\prime}=0$ (this change of notation will allow us to measure the change in ordinate when moving from one vertex of the polygon to another). The $b_{i}^{\prime}$ are then arranged in decreasing order.
Lemma. There exists a subset $\mathrm{I} \subset \llbracket 2, n-1 \rrbracket$ of cardinality $\ell-1$ such that $b_{1}^{\prime}+\sum_{i \in I} b_{i}^{\prime}>0$ and $b_{n}^{\prime}+\sum_{i \in \mathrm{I}} \mathrm{b}_{\mathrm{i}}^{\prime}<0$.
Proof of the lemma. The statement of the lemma is equivalent to finding $\mathrm{I}$ of cardinality $\ell-1$ with $\left.\sum_{i \in I} b_{i}^{\prime} \in\right]-$ $\mathrm{b}_{1}^{\prime},-\mathrm{b}_{n}^{\prime}\left[\right.$. Let $\mathrm{I}_{\max }=\{2, \ldots, \ell\}$ and $\mathrm{I}_{\min }=\{\mathrm{n}-\ell+1, \ldots, \mathrm{n}-1\}$. It is clear that $\sum_{i \in \mathrm{I}_{\max }} \mathrm{b}_{\mathrm{i}}^{\prime}>-\mathrm{b}_{1}^{\prime}$ (if we have $n$ numbers with a sum of zero, the sum of the $\ell$ largest is positive) and that $\sum_{i \in \mathrm{I}_{\mathrm{min}}} b_{i}^{\prime}<$ $-b_{n}^{\prime}$.
If we replace one by one the elements of $I_{\min }$ with those of $I_{\max }$, the sum increases at each step by a number of the form $b_{i}^{\prime}-b_{j}^{\prime}<b_{1}^{\prime}-b_{n}^{\prime}$ (the inequality is strict because the $b_{i}$ are pairwise distinct). We thus pass from a number less than $-b_{n}^{\prime}$ to a number greater than $-b_{1}^{\prime}$, increasing at each step by a number strictly less than $b_{1}^{\prime}-b_{n}^{\prime}$, so at some point the sum will be strictly between $-b_{1}^{\prime}$ and $-b_{n}^{\prime}$.
We want to construct our polygon as follows: $b_{1}$ will be the length of the leftmost vertical side (we denote $A$ the bottom vertex and $B$ the top vertex of this side) and $b_{n}$ the length of the rightmost vertical side (we name $C$ the top vertex and $D$ the bottom vertex of this side), and the horizontal distance between these two sides is $S_{a}$. To go from $B$ to $C$, we use the horizontal sides of length $a_{i}$ with $1 \leqslant i \leqslant \ell$ between which we interleave the $\ell-1$ sides of lengths $b_{i}$ with $i \in I$, starting with those such that $i \leqslant m$. We thus obtain a broken line (in blue) that connects the top of $b_{1}$ to the top of $b_{n}$ by alternating moves to the right and up, then moves to the right and down.
Then, to connect $D$ to $A$, we use the $n-\ell$ horizontal sides of length $a_{i}$ with $\ell+1 \leqslant i \leqslant n$, between which we interleave the remaining $b_{i}$, this time starting with the $i \geqslant m+1$ to go down before going up (this corresponds to the green line in the figure).

The polygon thus constructed has the desired side lengths. It remains to verify that these sides do not intersect. The two red sides do not cut any other because by construction, they are respectively the farthest to the left and the farthest to the right of all the others. Moreover, two blue sides cannot intersect because there is always one to the left of the other, and the same for two green sides.
It is therefore sufficient to verify that a blue side cannot intersect a green vertex. We will show that in fact, the blue line is entirely above the green line. Since the blue line goes up and then down, its ordinate is everywhere greater than $\min \left\{\mathrm{y}_{\mathrm{B}}, \mathrm{y}_{\mathrm{C}}\right\}$. Similarly, the ordinate on the green line is everywhere less than $\max \left\{y_{A}, y_{D}\right\}$. It is therefore sufficient to show that $\min \left\{y_{B}, y_{C}\right\}>\max \left\{y_{A}, y_{D}\right\}$. Since it is obvious that $y_{B}>y_{A}$ and $y_{C}>y_{D}$, it is sufficient to show $y_{C}>y_{A}$ and $y_{B}>y_{D}$. Now, $y_{C}-y_{A}=$ $b_{1}+\sum_{i \in I} b_{i}^{\prime}$, which is strictly positive according to the lemma. Similarly, $y_{D}-y_{B}=\sum_{i \in I} b_{i}^{\prime}-b_{n}^{\prime}$, which is strictly negative according to the lemma. We can therefore draw a horizontal line (in orange in the figure) such that the blue line is strictly above and the green line is strictly below.
Remark. The original statement omitted the condition "the $b_{i}$ are pairwise distinct". A fairly simple counterexample without this hypothesis is the following: $n=4$ with $a_{1}=a_{2}=a_{3}=a_{4}$ and $b_{1}=b_{2}=b_{3}=b_{4}$. However, the proof above can be adapted as long as the $a_{i}$ are not all equal or the $b_{i}$ are not all equal.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soient $n \geqslant 2$ et $a_{1}, \ldots, a_{n}, b_{1}, \ldots, b_{n}$ des réels strictement positifs. Les $a_{i}$ sont supposés deux à deux distincts, de même que les $b_{i}$. On suppose qu'il est possible de séparer les $a_{i}$ en deux sous-ensembles de même somme, et de même pour les $b_{i}$.
Montrer qu'il existe un 2 n -gone simple ayant exactement n côtés horizontaux et n côtés verticaux, dont les longueurs des côtés horizontaux sont exactement les $a_{i}$ et dont les longueurs des côtés verticaux sont exactement les $b_{i}$.
Remarque. Un polygone simple est un polygone dont les côtés ne s'intersectent pas, sauf bien sûr deux côtés consécutifs en leur extrémité commune.
|
Quitte à changer les indices et éventuellement à échanger les rôles de $a$ et $b$, on peut supposer qu'il existe $\ell \leqslant m \leqslant \frac{n}{2}$ tels que $a_{1}+\cdots+a_{\ell}=a_{\ell+1}+\cdots+a_{n}=S_{a}$ et $b_{1}+\cdots+b_{m}=$ $b_{m+1}+\cdots+b_{n}$, que $b_{1} \geqslant \cdots \geqslant b_{m}$ et que $b_{m+1} \leqslant \cdots \leqslant b_{n}$. Quand on fait le tour de notre polygone dans le sens horaire, les $a_{i}$ avec $i \leqslant \ell$ correspondront aux longueurs des côtés où on va vers la droite, les $a_{i}$ avec $i \geqslant \ell+1$ à ceux où on va vers la gauche, les $b_{i}$ avec $i \leqslant m$ à ceux où on va vers le haut et les $b_{i}$ avec $i \geqslant m+1$ à ceux où on va vers le bas. Il reste à placer ces côtés correctement les uns par rapport aux autres, de manière à ce qu'ils ne s'intersectent pas.
On note $b_{i}^{\prime}=b_{i}$ pour $i \leqslant m$ et $b_{i}^{\prime}=-b_{i}$ pour $i \geqslant m+1$, de manière à avoir $\sum_{i=1}^{n} b_{i}^{\prime}=0$ (ce changement de notation permettra de mesurer la variation d'ordonnée quand on passe d'un sommet du polygone à un autre). Les $b_{i}^{\prime}$ sont alors rangés dans l'ordre décroissant.
Lemme. Il existe un sous-ensemble $\mathrm{I} \subset \llbracket 2, n-1 \rrbracket$ de cardinal $\ell-1$ tel que $b_{1}^{\prime}+\sum_{i \in I} b_{i}^{\prime}>0$ et $b_{n}^{\prime}+\sum_{i \in \mathrm{I}} \mathrm{b}_{\mathrm{i}}^{\prime}<0$.
Preuve du lemme. L'énoncé du lemme revient à trouver I de cardinal $\ell-1$ avec $\left.\sum_{i \in I} b_{i}^{\prime} \in\right]-$ $\mathrm{b}_{1}^{\prime},-\mathrm{b}_{n}^{\prime}\left[\right.$. Soient $\mathrm{I}_{\max }=\{2, \ldots, \ell\}$ et $\mathrm{I}_{\min }=\{\mathrm{n}-\ell+1, \ldots, \mathrm{n}-1\}$. Il est clair que $\sum_{i \in \mathrm{I}_{\max }} \mathrm{b}_{\mathrm{i}}^{\prime}>-\mathrm{b}_{1}^{\prime}$ (si on a $n$ nombres de somme nulle, la somme des $\ell$ plus grand est positive) et que $\sum_{i \in \mathrm{I}_{\mathrm{min}}} b_{i}^{\prime}<$ $-b_{n}^{\prime}$.
Si on remplace un par un les éléments de $I_{\min }$ par ceux de $I_{\max }$, la somme augmente à chaque étape d'un nombre de la forme $b_{i}^{\prime}-b_{j}^{\prime}<b_{1}^{\prime}-b_{n}^{\prime}$ (l'inégalité est stricte car les $b_{i}$ sont deux à deux distincts). On passe donc d'un nombre inférieur à $-b_{n}^{\prime}$ à un nombre supérieur à $-b_{1}^{\prime}$ en augmentant à chaque étape $d^{\prime}$ un nombre strictement inférieur à $b_{1}^{\prime}-b_{n}^{\prime}$ donc à un moment la somme se trouvera strictement entre $-b_{1}^{\prime}$ et $-b_{n}^{\prime}$.
On veut construire notre polygone de la manière suivante : $b_{1}$ sera la longueur du côté vertical le plus à gauche (on note $A$ le sommet en bas et $B$ le sommet en haut de ce côté) et $b_{n}$ celle du côté vertical le plus à droite (on nomme C le sommet en haut et D le sommet en bas de ce côté), et l'écart horizontal entre ces deux côtés vaut $S_{a}$. Pour passer de $B$ à $C$, on utilise les côtés horizontaux de longueur $a_{i}$ avec $1 \leqslant i \leqslant \ell$ entre lesquels on intercale les $\ell-1$ côtés de longueurs $b_{i}$ avec $i \in I$, en commençant par ceux tels que $i \leqslant m$. On obtient ainsi une ligne brisée (en bleu) qui relie le haut de $b_{1}$ au haut de $b_{n}$ en alternant les déplacements vers la droite et vers le haut, puis les déplacements vers la droite et vers le bas.
Puis, pour relier $D$ à $A$, on utilise les $n-\ell$ côtés horizontaux de longueur $a_{i}$ avec $\ell+1 \leqslant i \leqslant n$, entre lesquels on intercale les $b_{i}$ restants, cette fois en commençant par les $i \geqslant m+1$ pour descendre avant de remonter (cela correspond à la ligne verte sur la figure).

Le polygone ainsi construit a bien les longueurs de côtés voulues. il reste à vérifier que ces côtés ne s'intersectent pas. Les deux côtés rouges n'en coupent aucun autre car par construction, ils sont respec-
tivement plus à gauche et plus à droite que tous les autres. De plus, deux côtés bleus ne peuvent pas s'intersecter car il y en a toujours un plus à gauche que l'autre, et de même pour deux côtés verts.
Il suffit donc de vérifier qu'un côté bleu ne peut pas intersecter un sommet vert. On va montrer qu'en fait, la ligne bleue est entièrement située au-dessus de la ligne verte. Comme la ligne bleue monte puis redescend, son ordonnée est partout supérieure à $\min \left\{\mathrm{y}_{\mathrm{B}}, \mathrm{y}_{\mathrm{C}}\right\}$. De même, l'ordonnée sur la ligne verte est partout inférieure à $\max \left\{y_{A}, y_{D}\right\}$. Il suffit donc de montrer que $\min \left\{y_{B}, y_{C}\right\}>\max \left\{y_{A}, y_{D}\right\}$. Comme il est évident que $y_{B}>y_{A}$ et $y_{C}>y_{D}$, il suffit de montrer $y_{C}>y_{A}$ et $y_{B}>y_{D}$. Or, $y_{C}-y_{A}=$ $b_{1}+\sum_{i \in I} b_{i}^{\prime}$, qui est strictement positive d'après le lemme. De même, $y_{D}-y_{B}=\sum_{i \in I} b_{i}^{\prime}-b_{n}^{\prime}$ qui est strictement négative d'après le lemme. On peut donc tracer une ligne horizontale (en orange sur la figure) telle que la ligne bleue soit strictement au-dessus et la verte strictement en-dessous.
Remarque. L'énoncé original omettait la condition "les $b_{i}$ sont deux à deux distincts". Un contre-exemple assez simple sans cette hypothèse est le suivant: $n=4$ avec $a_{1}=a_{2}=a_{3}=a_{4}$ et $b_{1}=b_{2}=b_{3}=b_{4}$. En revanche, la preuve ci-dessus peut être adaptée dès que les $a_{i}$ ne sont pas tous égaux ou que les $b_{i}$ ne sont pas tous égaux.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-4-solutions.jsonl",
"problem_match": "\nExercice 9.",
"solution_match": "\nSolution de l'exercice 9"
}
|
560ec7bf-8acb-5c9e-82d9-bda843c5e50a
| 607,638
|
Let $A B C D$ be a convex quadrilateral whose diagonals are not perpendicular and such that the lines $(A B)$ and $(C D)$ are not parallel. We denote by $O$ the point of intersection of $[A C]$ and $[B D]$. Let $\mathrm{H}_{1}$ and $\mathrm{H}_{2}$ be the orthocenters of triangles $A O B$ and $C O D$, respectively. We denote by $M$ and $N$ the midpoints of $[A B]$ and $[C D]$, respectively.
Prove that the lines $\left(H_{1} H_{2}\right)$ and $(M N)$ are parallel if and only if $A C = B D$.
|
The points considered are defined only by intersections of lines and orthogonality relations (but do not involve equalities of angles or intersections of circles or circle and line), so we can attempt an analytical approach, which will be tedious but humanly feasible.
Let us place ourselves in an orthonormal frame centered at \(O\) such that the points \(A, B, C, D, O\) have the following coordinates respectively:
$$
\binom{-a}{0},\binom{-1}{-b},\binom{c}{0},\binom{d}{b \mathrm{~d}},\binom{0}{0}
$$
Then the points \(\mathrm{H}_{1}, \mathrm{H}_{2}, \mathrm{M}, \mathrm{N}\) have the following coordinates respectively:
$$
\binom{-1}{y_{1}}, \quad\binom{d}{y_{2}}, \quad\binom{-(a+1) / 2}{-b / 2}, \quad\binom{(c+d) / 2}{b d / 2}
$$
with \(\overrightarrow{\mathrm{AH}_{1}} \cdot \overrightarrow{\mathrm{OB}}=-(\mathrm{a}-1)-\mathrm{y}_{1} \mathrm{~b}=0\) and \(\overrightarrow{\mathrm{CH}_{2}} \cdot \overrightarrow{\mathrm{OD}}=(\mathrm{d}-\mathrm{c}) \mathrm{d}+\mathrm{y}_{2} \mathrm{bd}=0\), that is,
$$
\mathrm{y}_{1}=\frac{1-\mathrm{a}}{\mathrm{~b}} \text { and } \mathrm{y}_{2}=\frac{\mathrm{c}-\mathrm{d}}{\mathrm{~b}}
$$
The lines \(\left(\mathrm{H}_{1} \mathrm{H}_{2}\right)\) and \((\mathrm{MN})\) are parallel if and only if they have the same slope, that is, if the equality
$$
\frac{y_{2}-y_{1}}{d+1}=\frac{b d+b}{c+d+a+1}
$$
is satisfied. We therefore calculate that
$$
\text { (1) } \begin{aligned}
& \Leftrightarrow b(d+1)^{2}=(c+d+a+1)\left(y_{2}-y_{1}\right)=\frac{1}{b}(c+d+a+1)(c-d+a-1) \\
& \Leftrightarrow b^{2}(d+1)^{2}=(c+a)^{2}-(d+1)^{2} \\
& \Leftrightarrow B D^{2}=(d+1)^{2}\left(b^{2}+1\right)=(c+a)^{2}=A C^{2}
\end{aligned}
$$
which allows us to conclude.

|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C D$ un quadrilatère convexe dont les diagonales ne sont pas perpendiculaires et tel que les droites $(A B)$ et $(C D)$ ne sont pas parallèles. On note O le point d'intersection de $[A C]$ et $[B D]$. Soit $\mathrm{H}_{1}$ et $\mathrm{H}_{2}$ les orthocentres respectifs des triangles $A O B$ et $C O D$. On désigne par $M$ et $N$ les milieux respectifs de $[A B]$ et [CD].
Prouver que les droites $\left(H_{1} H_{2}\right)$ et $(M N)$ sont parallèles si et seulement si $A C=B D$.
|
Les points considérés étant définis uniquement par des intersections de droite et de relations d'orthogonalité (mais ne faisant intervenir ni égalités d'angles ni intersections de cercles ou de cercle et droite), on peut tenter une approche analytique, qui sera pénible mais humainement faisable.
Plaçons-nous dans un repère orthonormé de centre $O$ et tel que les points $A, B, C, D, O$ aient pour coordonnées respectives
$$
\binom{-a}{0},\binom{-1}{-b},\binom{c}{0},\binom{d}{b \mathrm{~d}},\binom{0}{0}
$$
Alors les points $\mathrm{H}_{1}, \mathrm{H}_{2}, \mathrm{M}, \mathrm{N}$ ont pour coordonnées respectives
$$
\binom{-1}{y_{1}}, \quad\binom{d}{y_{2}}, \quad\binom{-(a+1) / 2}{-b / 2}, \quad\binom{(c+d) / 2}{b d / 2}
$$
avec $\overrightarrow{\mathrm{AH}_{1}} \cdot \overrightarrow{\mathrm{OB}}=-(\mathrm{a}-1)-\mathrm{y}_{1} \mathrm{~b}=0$ et $\overrightarrow{\mathrm{CH}_{2}} \cdot \overrightarrow{\mathrm{OD}}=(\mathrm{d}-\mathrm{c}) \mathrm{d}+\mathrm{y}_{2} \mathrm{bd}=0$, c'est-à-dire
$$
\mathrm{y}_{1}=\frac{1-\mathrm{a}}{\mathrm{~b}} \text { et } \mathrm{y}_{2}=\frac{\mathrm{c}-\mathrm{d}}{\mathrm{~b}}
$$
Les droites $\left(\mathrm{H}_{1} \mathrm{H}_{2}\right)$ et $(\mathrm{MN})$ sont parallèles si et seulement si elles ont même pente, c'est-à-dire si l'égalité
$$
\frac{y_{2}-y_{1}}{d+1}=\frac{b d+b}{c+d+a+1}
$$
est vérifiée. On calcule donc que
$$
\text { (1) } \begin{aligned}
& \Leftrightarrow b(d+1)^{2}=(c+d+a+1)\left(y_{2}-y_{1}\right)=\frac{1}{b}(c+d+a+1)(c-d+a-1) \\
& \Leftrightarrow b^{2}(d+1)^{2}=(c+a)^{2}-(d+1)^{2} \\
& \Leftrightarrow B D^{2}=(d+1)^{2}\left(b^{2}+1\right)=(c+a)^{2}=A C^{2}
\end{aligned}
$$
ce qui permet de conclure.

|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 3.",
"solution_match": "\nSolution alternative"
}
|
8e05340a-c96c-5575-b2f8-98c403b3ca0e
| 607,641
|
Let $S$ be a set of strictly positive integers such that
$$
\lfloor\sqrt{x}\rfloor=\lfloor\sqrt{y}\rfloor \text{ for all } x, y \in S
$$
Prove that if $x, y, z, t \in S$ with $(x, y) \neq(z, t)$ and $(x, y) \neq(t, z)$, then $x y \neq z t$.
( $\lfloor.$.$\rfloor$ denotes the floor function.)
|
Suppose first that there exist integers $x_{1}, x_{2}, x_{3}, x_{4}$ in $S$ such that $x_{1} x_{2} \leqslant x_{3} x_{4}$ and $x_{1}+x_{2}>x_{3}+x_{4}$. Since these are integers, we have $x_{1}+x_{2}-x_{3}-x_{4} \geqslant 1$. Let $n=\left\lfloor\sqrt{x_{1}}\right\rfloor$. By definition of $S$, for $i=1,2,3,4$, there exists an integer $w_{i}$ such that $0 \leqslant w_{i} \leqslant 2 n$ and $x_{i}=n^{2}+w_{i}$.
The inequalities $x_{1} x_{2} \leqslant x_{3} x_{4}$ and $x_{1}+x_{2}>x_{3}+x_{4}$ become respectively
$$
w_{1}+w_{2}-w_{3}-w_{4} \geqslant 1 \quad \text { and } \quad\left(w_{1}+w_{2}-w_{3}+w_{4}\right) n^{2} \leqslant w_{3} w_{4}-w_{1} w_{2}
$$
In particular, we must have $\boldsymbol{w}_{3}>0$, and therefore
$$
\begin{aligned}
\mathrm{n}^{2} & \leqslant\left(w_{1}+w_{2}-w_{3}+w_{4}\right) n^{2} \leqslant w_{3} w_{4}-w_{1} w_{2} \\
& <w_{3}\left(w_{1}+w_{2}-w_{3}\right)-w_{1} w_{2}=\left(w_{1}-w_{3}\right)\left(w_{3}-w_{2}\right) \\
& <\frac{\left(\left(w_{1}-w_{3}\right)+\left(w_{3}-w_{2}\right)\right)^{2}}{4}=\frac{\left(w_{1}-w_{2}\right)^{2}}{4} \leqslant n^{2}
\end{aligned}
$$
leading to a contradiction.
Let then $x_{1}, x_{2}, x_{3}, x_{4}$ in $S$ such that $x_{1} x_{2}=x_{3} x_{4}=a$. According to the lemma above, we have $x_{1}+x_{2}=$ $x_{3}+x_{4}=b$. The numbers $x_{1}$ and $x_{2}$ on one hand, $x_{3}$ and $x_{4}$ on the other hand, are then the roots of the polynomial $X^{2}-a X+b$. We then have $x_{1}=x_{3}$ and $x_{2}=x_{4}$, or $x_{1}=x_{4}$ and $x_{2}=x_{3}$, which concludes.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit $S$ un ensemble d'entiers strictement positifs tel que
$$
\lfloor\sqrt{x}\rfloor=\lfloor\sqrt{y}\rfloor \text { pour tous } x, y \in S
$$
Prouver que si $x, y, z, t \in S$ avec $(x, y) \neq(z, t)$ et $(x, y) \neq(t, z)$, alors $x y \neq z t$.
( $\lfloor.$.$\rfloor désigne la partie entière.)$
|
Supposons tout d'abord qu'il existe des entiers $x_{1}, x_{2}, x_{3}, x_{4}$ dans $S$ tels que $x_{1} x_{2} \leqslant x_{3} x_{4}$ et $x_{1}+x_{2}>x_{3}+x_{4}$. Puisqu'il s'agit d'entiers, on a donc $x_{1}+x_{2}-x_{3}-x_{4} \geqslant 1$. Soit $n=\left\lfloor\sqrt{x_{1}}\right\rfloor$. Par définition de $S$, pour $i=1,2,3,4$, il existe donc un entier $w_{i}$ tel que $0 \leqslant w_{i} \leqslant 2 n$ et $x_{i}=n^{2}+w_{i}$.
Les inégalités $x_{1} x_{2} \leqslant x_{3} x_{4}$ et $x_{1}+x_{2}>x_{3}+x_{4}$ deviennent respectivement
$$
w_{1}+w_{2}-w_{3}-w_{4} \geqslant 1 \quad \text { et } \quad\left(w_{1}+w_{2}-w_{3}+w_{4}\right) n^{2} \leqslant w_{3} w_{4}-w_{1} w_{2}
$$
En particulier, on doit avoir $\boldsymbol{w}_{3}>0$, et donc
$$
\begin{aligned}
\mathrm{n}^{2} & \leqslant\left(w_{1}+w_{2}-w_{3}+w_{4}\right) n^{2} \leqslant w_{3} w_{4}-w_{1} w_{2} \\
& <w_{3}\left(w_{1}+w_{2}-w_{3}\right)-w_{1} w_{2}=\left(w_{1}-w_{3}\right)\left(w_{3}-w_{2}\right) \\
& <\frac{\left(\left(w_{1}-w_{3}\right)+\left(w_{3}-w_{2}\right)\right)^{2}}{4}=\frac{\left(w_{1}-w_{2}\right)^{2}}{4} \leqslant n^{2}
\end{aligned}
$$
d'où la contradiction.
Soit alors $x_{1}, x_{2}, x_{3}, x_{4}$ dans $S$ tels que $x_{1} x_{2}=x_{3} x_{4}=a$. D'après le lemme ci-dessus, on a donc $x_{1}+x_{2}=$ $x_{3}+x_{4}=b$. Les nombres $x_{1}$ et $x_{2}$ d'une part, $x_{3}$ et $x_{4}$ d'autre part, sont alors les racines du polynôme $X^{2}-a X+b$. On a alors $x_{1}=x_{3}$ et $x_{2}=x_{4}$, ou $x_{1}=x_{4}$ et $x_{2}=x_{3}$, ce qui conclut.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 4.",
"solution_match": "\nSolution de l'exercice 4"
}
|
aed1dd21-0044-5fb4-8dce-d59b9c9b0a56
| 607,642
|
Let $n \geqslant 5$ be an integer, and $\left\{a_{1}, a_{2}, \cdots, a_{n}\right\}=\{1,2, \cdots, n\}$. Prove that the numbers $a_{1}, a_{1}+a_{2}, a_{1}+a_{2}+a_{3}, \cdots, a_{1}+a_{2}+\cdots+a_{n}$ give at least $\lfloor\sqrt{n}\rfloor+1$ distinct remainders modulo $n$.
( $\lfloor.\rfloor$ denotes the floor function.)
|
For $i=1, \cdots, n$, let $b_{i}=a_{1}+\cdots+a_{i}$. Proceed by contradiction and assume that the numbers $b_{1}, \cdots, b_{n}$ give at most $\sqrt{n}$ distinct remainders modulo $n$.
Note that, for $i=1, \cdots, n-1$, we have $a_{i+1}=b_{i+1}-b_{i}$, and only the $a_{i}$ that equals $n$ can lead to $b_{i+1}-b_{i} \equiv 0(\bmod n)$. The numbers $b_{i+1}-b_{i}$ can therefore take, modulo $n$, at most $\sqrt{n}(\sqrt{n}-1)$ distinct non-zero values. Taking into account the $a_{i}$ that is equal to $n$ and $a_{n}$ (which is not of the form $b_{i+1}-b_{i}$), and since $n \geqslant 5$, the $a_{i}$ can therefore take at most
$$
n-\sqrt{n}+2 \leqslant n-\sqrt{5}+2<n
$$
distinct values modulo $n$. However, the $a_{i}$ form a permutation of $\{1, \cdots, n\}$, so they represent all the remainders modulo $n$: this is a contradiction.
The numbers $b_{1}, \cdots, b_{n}$ therefore give at least $\lfloor\sqrt{n}\rfloor+1$ distinct remainders modulo $n$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit $n \geqslant 5$ un entier, et $\left\{a_{1}, a_{2}, \cdots, a_{n}\right\}=\{1,2, \cdots, n\}$. Prouver que les nombres $a_{1}, a_{1}+$ $a_{2}, a_{1}+a_{2}+a_{3}, \cdots, a_{1}+a_{2}+\cdots+a_{n}$ donnent au moins $\lfloor\sqrt{n}\rfloor+1$ restes distincts modulo $n$.
( $\lfloor.$.$\rfloor désigne la partie entière.)$
|
Pour $i=1, \cdots, n$, on pose $b_{i}=a_{1}+\cdots+a_{i}$. Procédons par l'absurde et supposons que les nombres $b_{1}, \cdots, b_{n}$ ne donnent qu'au plus $\sqrt{n}$ restes distincts modulo $n$.
Notons que, pour $i=1, \cdots, n-1$, on a $a_{i+1}=b_{i+1}-b_{i}$, et seul celui des $a_{i}$ qui vaut $n$ peut donc conduire à $b_{i+1}-b_{i} \equiv 0(\bmod n)$. Les nombres $b_{i+1}-b_{i}$ ne peuvent donc prendre, modulo $n$, qu'au plus $\sqrt{n}(\sqrt{n}-1)$ valeurs non nulles distinctes. En tenant compte du $a_{i}$ qui est égal à $n$ et de $a_{n}$ (qui n'est pas de la forme $b_{i+1}-b_{i}$ ), et puisque $n \geqslant 5$, les $a_{i}$ prennent donc au plus
$$
\mathrm{n}-\sqrt{\mathrm{n}}+2 \leqslant \mathrm{n}-\sqrt{5}+2<\mathrm{n}
$$
valeurs distinctes modulo $n$. Or, les $a_{i}$ forment une permutation de $\{1, \cdots, n\}$ donc ils représentent tous les restes modulo n : il y a là une contradiction.
Les nombres $b_{1}, \cdots, b_{n}$ donnent donc au moins $\lfloor\sqrt{n}\rfloor+1$ restes distincts modulo $n$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 5.",
"solution_match": "\nSolution de l'exercice 5"
}
|
b7176b7e-0983-5bc4-bb0a-2a558d96c657
| 607,643
|
Let $H$ be the foot of the altitude from $A$ in the acute triangle $ABC$, and $H'$ be the symmetric point of $H$ with respect to the midpoint of $[BC]$. The tangents to the circumcircle of $ABC$ at $B$ and $C$ meet at $X$. The perpendicular to $(XH')$ at $H'$ intersects the line $(AB)$ at $Y$, and the line $(AC)$ at $Z$.
Prove that $\widehat{YXB} = \widehat{ZXC}$.
|
Let $P, Q$ and $M$ be the orthogonal projections of $X$ onto $(AB), (AC)$, and $(BC)$, respectively. Clearly, $M$ is the midpoint of $[BC]$. The points $X, H', Y, P$ lie on the circle with diameter $[XY]$, and the points $X, H', Z, Q$ lie on the circle with diameter $[XZ]$, hence
$$
\widehat{H'XY} = \widehat{YPH'} = \widehat{APH'} \text{ and } \widehat{H'XZ} = \widehat{ZQH'} = \widehat{AQH'},
$$
which shows that $\widehat{ZXY} = \widehat{ZXH'} + \widehat{H'XY} = \widehat{AQH'} + \widehat{APH'} = \widehat{PH'Q} - \widehat{ABC}$.
Since $\widehat{BXC} = 180^\circ - 2 \widehat{BAC}$, to conclude, it suffices to prove that $\widehat{PH'Q} = 180^\circ - \widehat{BAC}$. The points $B, P, X, M$ lie on the circle with diameter $[BX]$, so
$$
\widehat{APM} = \widehat{BPM} = \widehat{BXM} = 90^\circ - \widehat{BAC},
$$
which shows that $(PM) \perp (AQ)$.
Similarly, $(QM)$ is perpendicular to $(AP)$, and $M$ is therefore the orthocenter of triangle $APQ$. This ensures that $(AM) \perp (PQ)$ and that $AM = 2r \cos (\widehat{PAQ})$, where $r$ is the radius of the circumcircle of $APQ$.
Let $R$ be the orthogonal projection of $A$ onto $(XM)$. Then $ARHM$ is a parallelogram, so $ARH'M$ is also a parallelogram. The lines $(RH')$ and $(AM)$ are then parallel, and thus $(RH')$ and $(PQ)$ are perpendicular. On the other hand, since $A, R, Q, X$, and $P$ are all on the circle with diameter $[AX]$, we have $\widehat{PRQ} = \widehat{PAQ} = \widehat{BAC}$. Therefore, $RH' = AM = 2r \cos (\widehat{PAQ}) = 2r \cos (\widehat{PRQ})$, which proves that $H'$ is in fact the orthocenter of $PRQ$.
In particular, we have $\widehat{PH'Q} = 180^\circ - \widehat{PRQ} = 180^\circ - \widehat{BAC}$, which completes the proof.

|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit H le pied de la hauteur issue de $A$ dans le triangle acutangle $A B C$, et $\mathrm{H}^{\prime}$ le symétrique de $H$ par rapport au milieu de $[B C]$. Les tangentes au cercle circonscrit à $A B C$ en $B$ et en $C$ se rencontrent en $X$. La perpendiculaire à $\left(\mathrm{XH}^{\prime}\right)$ en $\mathrm{H}^{\prime}$ rencontre la droite $(A B)$ en $Y$, et la droite $(A C)$ en $Z$.
Prouver que $\widehat{\mathrm{YXB}}=\widehat{\mathrm{ZXC}}$.
|
Soit $P, Q$ et $M$ les projetés orthogonaux respectifs de $X \operatorname{sur}(A B),(A C)$ et (BC). Clairement $M$ est le milieu de $[B C]$. Les points $X, H^{\prime}, Y, P$ sont sur le cercle de diamètre $[X Y]$, et les points $\mathrm{X}, \mathrm{H}^{\prime}, \mathrm{Z}, \mathrm{Q}$ sont sur le cercle de diamètre $[\mathrm{XZ}]$ donc
$$
\widehat{\mathrm{H}^{\prime} \mathrm{XY}}=\widehat{\mathrm{YPH}^{\prime}}=\widehat{\mathrm{APH}^{\prime}} \text { et } \widehat{\mathrm{H}^{\prime} \mathrm{XZ}}=\widehat{\mathrm{ZQH}^{\prime}}=\widehat{\mathrm{AQH}^{\prime}} \text {, }
$$
ce qui montre que $\widehat{Z X Y}=\widehat{\mathrm{ZXH}^{\prime}}+\widehat{\mathrm{H}^{\prime} X Y}=\widehat{\mathrm{AQH}^{\prime}}+\widehat{\mathrm{APH}^{\prime}}=\widehat{\mathrm{PH}^{\prime} \mathrm{Q}}-\widehat{\mathrm{ABC}}$.
Puisque $\widehat{\mathrm{BXC}}=180^{\circ}-2 \widehat{\mathrm{BAC}}$, pour conclure il suffit donc de prouver que $\widehat{\mathrm{PH}^{\prime} \mathrm{Q}}=180^{\circ}-\widehat{\mathrm{BAC}}$. Or, les points $B, P, X, M$ sont sur le cercle de diamètre $[B X]$, donc
$$
\widehat{A P M}=\widehat{B P M}=\widehat{B X M}=90^{\circ}-\widehat{B A C},
$$
ce qui montre que $(P M) \perp(A Q)$.
De même, $(Q M)$ est perpendiculaire à ( $A P)$, et $M$ est donc l'orthocentre du triangle $A P Q$. Cela assure que $(A M) \perp(P Q)$ et que $A M=2 r \cos (\widehat{P A Q})$, où $r$ est le rayon du cercle circonscrit à $A P Q$.
Soit $R$ le projeté orthogonal de $A$ sur ( $X M$ ). Alors $A R M H$ est un parallélogramme, donc $A R H^{\prime} M$ est aussi un parallélogramme. Les droites $\left(\mathrm{RH}^{\prime}\right)$ et $(A M)$ sont alors parallèles, et ainsi $\left(\mathrm{RH}^{\prime}\right)$ et $(P Q)$ sont perpendiculaires. D'autre part, puisque $A, R, Q, X$ et $P$ sont tous sur le cercle de diamètre $[A X]$, on a $\widehat{\mathrm{PRQ}}=\widehat{\mathrm{PAQ}}=\widehat{\mathrm{BAC}}$. Par suite $\mathrm{RH}^{\prime}=\mathrm{AM}=2 \mathrm{r} \cos (\widehat{\mathrm{PAQ}})=2 \mathrm{r} \cos (\widehat{\mathrm{PRQ}})$, ce qui prouve que $\mathrm{H}^{\prime}$ est en fait l'orthocentre de PRQ.
En particulier, on a $\widehat{\mathrm{PH}^{\prime} \mathrm{Q}}=180^{\circ}-\widehat{\mathrm{PRQ}}=180^{\circ}-\widehat{\mathrm{BAC}}$, ce qui achève la démonstration.

|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 6.",
"solution_match": "\nSolution de l'exercice 6"
}
|
d5cfaf9c-6dd5-5341-b951-ce2112b63bb8
| 607,644
|
Let $a_{1}, a_{2}, a_{3}$ be strictly positive integers. For any integer $n \geqslant 3$, we set
$$
a_{n+1}=\operatorname{lcm}\left(a_{n}, a_{n-1}\right)-\operatorname{lcm}\left(a_{n-1}, a_{n-2}\right)
$$
with the understanding that $\operatorname{lcm}(0, x)=0$ for any integer $x$.
Prove that there exists a natural number $k$ such that $k \leqslant a_{3}+4$ and $a_{k} \leqslant 0$.
|
If $x$ and $y$ are integers, we denote $x \vee y=\operatorname{ppcm}(x, y)$ and $x \wedge y=\operatorname{pgcd}(x, y)$, with $\operatorname{pgcd}(0, x)=x$ for all $x$. We recall that then $x y=(x \vee y)(x \wedge y)$.
For any integer $n \geqslant 3, a_{n-1}$ divides $a_{n} \vee a_{n-1}$ and $a_{n-1} \vee a_{n-2}$, and therefore $a_{n-1}$ also divides $a_{n+1}$. But then, for any $n \geqslant 4$, the number $a_{n-2}$ divides $a_{n}$, and thus divides $a_{n} \vee a_{n-1}$ and $a_{n-1} \vee a_{n-2}$, and finally divides $a_{n+1}$. The number $a_{n+1}$ is therefore divisible by $a_{n-1} \vee a_{n-2}$. We now set $c_{4}=\frac{a_{5}}{a_{2} \vee a_{3}}$. Let's show the equality ( $E_{n}$ ) for any integer $n \geqslant 4$ such that $a_{4}, \ldots, a_{n}>0$:
$$
\left(a_{n-1} \vee a_{n-2}\right)\left(4+c_{4}-n\right)=a_{n+1}
$$
First, by construction, the equality ( $E_{4}$ ) is true. Suppose now that the equality ( $E_{n-1}$ ) is true, and deduce that, if $a_{4}, \ldots, a_{n}>0$, then ( $E_{n}$ ) is also true. Since $a_{n-3}$ divides $a_{n-1}$, we observe that
$$
\begin{aligned}
\left(a_{n-1} \wedge a_{n}\right)\left(a_{n-1} \vee a_{n-2}\right) & =\left(a_{n-1} \wedge\left(a_{n-1} \vee a_{n-2}-a_{n-2} \vee a_{n-3}\right)\right) \cdot\left(a_{n-1} \vee a_{n-2} \vee a_{n-3}\right) \\
& =\left(a_{n-1} \wedge\left(a_{n-2} \vee a_{n-3}\right)\right) \cdot\left(a_{n-1} \vee\left(a_{n-2} \vee a_{n-3}\right)\right) \\
& =a_{n-1}\left(a_{n-2} \vee a_{n-3}\right) .
\end{aligned}
$$
Since
$$
\begin{aligned}
\left(E_{n}\right) & \Leftrightarrow \frac{a_{n+1}}{a_{n-1} \vee a_{n-2}}=4+c_{4}-n=\frac{a_{n}}{a_{n-2} \vee a_{n-3}}-1 \\
& \Leftrightarrow \frac{a_{n} \vee a_{n-1}}{a_{n-1} \vee a_{n-2}}=\frac{a_{n}}{a_{n-1} \vee a_{n-2}}+1=\frac{a_{n}}{a_{n-2} \vee a_{n-3}} \\
& \Leftrightarrow\left(a_{n-1} \vee a_{n-2}\right) a_{n}=\left(a_{n-2} \vee a_{n-3}\right)\left(a_{n} \vee a_{n-1}\right) \\
& \Leftrightarrow\left(a_{n-1} \vee a_{n-2}\right) a_{n}\left(a_{n} \wedge a_{n-1}\right)=\left(a_{n-2} \vee a_{n-3}\right) a_{n} a_{n-1},
\end{aligned}
$$
we deduce that ( $E_{n}$ ) is indeed true.
It follows that there exists a natural number $k$, minimal, such that $k \leqslant c_{4}+5$ and $a_{k} \leqslant 0$. If $k \leqslant 5$, then we have $k \leqslant a_{3}+4$. Otherwise, then $0<a_{5}<a_{3} \vee a_{4}$ and $0<a_{4}<a_{2} \vee a_{3}$, so
$$
c_{4}=\frac{a_{5}}{a_{2} \vee a_{3}}<\frac{a_{3} \vee a_{4}}{a_{2} \vee a_{3}} \leqslant \frac{a_{3} a_{4}}{a_{2} \vee a_{3}}<a_{3},
$$
thus $k \leqslant c_{4}+5 \leqslant a_{3}+4$, which concludes.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit $a_{1}, a_{2} a_{3}$ des entiers strictement positifs. Pour tout entier $n \geqslant 3$, on pose
$$
a_{n+1}=\operatorname{ppcm}\left(a_{n}, a_{n-1}\right)-\operatorname{ppcm}\left(a_{n-1}, a_{n-2}\right)
$$
étant entendu que l'on a $\operatorname{ppcm}(0, x)=0$ pour tout entier $x$.
Prouver qu'il existe un entier naturel $k$ tel que $k \leqslant a_{3}+4$ et $a_{k} \leqslant 0$.
|
Si $x$ et $y$ sont des entiers, on note $x \vee y=\operatorname{ppcm}(x, y)$ et $x \wedge y=\operatorname{pgcd}(x, y)$, avec $\operatorname{pgcd}(0, x)=x$ pour tout $x$. On rappelle qu'alors $x y=(x \vee y)(x \wedge y)$.
Pour tout entier $n \geqslant 3, a_{n-1}$ divise $a_{n} \vee a_{n-1}$ et $a_{n-1} \vee a_{n-2}$, donc que $a_{n-1}$ divise $a_{n+1}$ également. Mais alors, pour tout $n \geqslant 4$, le nombre $a_{n-2}$ divise $a_{n}$, donc divise $a_{n} \vee a_{n-1}$ et $a_{n-1} \vee a_{n-2}$, et enfin divise $a_{n+1}$. Le nombre $a_{n+1}$ est donc divisible par $a_{n-1} \vee a_{n-2}$. On pose maintenant $c_{4}=\frac{a_{5}}{a_{2} \vee a_{3}}$. Montrons alors l'égalité ( $E_{n}$ ) suivante pour tout entier $n \geqslant 4$ tel que $a_{4}, \ldots, a_{n}>0$ :
$$
\left(a_{n-1} \vee a_{n-2}\right)\left(4+c_{4}-n\right)=a_{n+1}
$$
Tout d'abord, par construction, l'égalité ( $E_{4}$ ) est vraie. Supposons maintenant que l'égalités ( $E_{n-1}$ ) est vraie, et déduisons-en que, si $a_{4}, \ldots, a_{n}>0$, alors ( $E_{n}$ ) est vraie aussi. Puisque $a_{n-3}$ divise $a_{n-1}$, on observe que
$$
\begin{aligned}
\left(a_{n-1} \wedge a_{n}\right)\left(a_{n-1} \vee a_{n-2}\right) & =\left(a_{n-1} \wedge\left(a_{n-1} \vee a_{n-2}-a_{n-2} \vee a_{n-3}\right)\right) \cdot\left(a_{n-1} \vee a_{n-2} \vee a_{n-3}\right) \\
& =\left(a_{n-1} \wedge\left(a_{n-2} \vee a_{n-3}\right)\right) \cdot\left(a_{n-1} \vee\left(a_{n-2} \vee a_{n-3}\right)\right) \\
& =a_{n-1}\left(a_{n-2} \vee a_{n-3}\right) .
\end{aligned}
$$
Or, puisque
$$
\begin{aligned}
\left(E_{n}\right) & \Leftrightarrow \frac{a_{n+1}}{a_{n-1} \vee a_{n-2}}=4+c_{4}-n=\frac{a_{n}}{a_{n-2} \vee a_{n-3}}-1 \\
& \Leftrightarrow \frac{a_{n} \vee a_{n-1}}{a_{n-1} \vee a_{n-2}}=\frac{a_{n}}{a_{n-1} \vee a_{n-2}}+1=\frac{a_{n}}{a_{n-2} \vee a_{n-3}} \\
& \Leftrightarrow\left(a_{n-1} \vee a_{n-2}\right) a_{n}=\left(a_{n-2} \vee a_{n-3}\right)\left(a_{n} \vee a_{n-1}\right) \\
& \Leftrightarrow\left(a_{n-1} \vee a_{n-2}\right) a_{n}\left(a_{n} \wedge a_{n-1}\right)=\left(a_{n-2} \vee a_{n-3}\right) a_{n} a_{n-1},
\end{aligned}
$$
on en déduit que ( $E_{n}$ ) est bien vraie.
Il s'ensuit qu'il existe un entier naturel $k$, minimal, tel que $k \leqslant c_{4}+5$ et $a_{k} \leqslant 0$. Si $k \leqslant 5$, alors on a bien $k \leqslant a_{3}+4$. Sinon, alors $0<a_{5}<a_{3} \vee a_{4}$ et $0<a_{4}<a_{2} \vee a_{3}$, donc
$$
c_{4}=\frac{a_{5}}{a_{2} \vee a_{3}}<\frac{a_{3} \vee a_{4}}{a_{2} \vee a_{3}} \leqslant \frac{a_{3} a_{4}}{a_{2} \vee a_{3}}<a_{3},
$$
donc $k \leqslant \mathrm{c}_{4}+5 \leqslant \mathrm{a}_{3}+4$, ce qui conclut.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2015-2016-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "\nSolution de l'exercice 7"
}
|
2ff8ebaa-f29d-50dc-acd5-401ec897222a
| 607,645
|
Show that for any integer $n \geq 1$, there exists $m$ a multiple of $n$ such that the sum of the digits of $m$ is $n$.
|
The sequence of powers of 10, i.e., $1, 10, 100, \cdots$, contains an infinite number of terms, which can take a finite number of residues modulo $n$. Therefore, there exists a residue $k$ such that an infinite number of powers of 10 are congruent to $k$ modulo $n$. Let $0 \leqslant a_{1}<a_{2}<a_{n}$ be integers such that
$$
10^{a_{i}} \equiv k \quad(\bmod n)
$$
for all $i \in\{1,2, \cdots, n\}$. We set $m=10^{a_{n}}+10^{a_{n-1}}+\cdots+10^{a_{2}}+10^{a_{1}}$. $m$ is written with $n$ digits "1" and a certain number of zeros, so the sum of its digits is $n$.
And $m \equiv k+\cdots+k \equiv k n \equiv 0(\bmod n)$, so $m$ is divisible by $n$, hence this integer satisfies the conditions of the statement.
## Common Exercises
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Montrer que pour tout entier $n \geq 1$, il existe $m$ un multiple de $n$ tel que la somme des chiffres de $m$ fasse $n$.
|
La suite des puissances de 10, donc $1,10,100, \cdots$ contient une infinité de termes, qui peuvent prendre un nombre fini de résidus modulo $n$. Il existe donc un résidu $k$ tel qu'une infinité de puissances de 10 soient congrues kmodulon.Soientdonc $0 \leqslant a_{1}<a_{2}<a_{n}$ des entiers tels que
$$
10^{a_{i}} \equiv k \quad(\bmod n)
$$
pour tout $i \in\{1,2, \cdots, n\}$. On pose $m=10^{a_{n}}+10^{a_{n-1}}+\cdots+10^{a_{2}}+10^{a_{1}}$. $m$ s'écrit avec $n$ chiffres "1" et un certain nombre de zéros, donc sa somme des chiffres vaut $n$.
Et $m \equiv k+\cdots+k \equiv k n \equiv 0(\bmod n)$, donc $m$ est divisible par $n$, donc cet entier satisfait aux conditions de l'énoncé.
## Exercices Communs
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 3.",
"solution_match": "\nSolution de l'exercice 3"
}
|
590ceb79-e704-5339-addc-d113a40b6609
| 607,649
|
Prove that there are infinitely many integers $n$ such that $2^{2^{n}+1}+1$ is divisible by $n$, but $2^{n}+1$ is not.
|
For $m \geqslant 1$, let $a_{m}=2^{3^{m}}+1$. We have
$a_{m}=\left(2^{3^{m-1}}+1\right)\left(\left(2^{3^{m-1}}\right)^{2}-2^{3^{m-1}}+1\right)=a_{m-1}\left(\left(2^{3^{m-1}}\right)^{2}-2^{3^{m-1}}+1\right)$.
Note that for $a \in \mathbb{N}^{*}$, if $p \mid a+1$ and $p \mid a^{2}-a+1$, then $p \mid 2 a-1$ because $2 a-1=a(a+1)-\left(a^{2}-a+1\right)$. And $p \mid 2 a+2$, so $p \mid 3$. Therefore, $\left(a_{m-1} \wedge a_{m}\right) \mid 3$ for all $m \in \mathbb{N} *$. Therefore, $a_{m}$ has an odd prime factor (since $a_{m}$ is odd) other than 3 that does not divide $a_{m-1}$, unless possibly if $a_{m}$ is a power of 3, in which case $a_{m+1}$ has a prime factor that $a_{m}$ does not have.
Thus, for an infinite number of integers $m \in \mathbb{N}^{*}, a_{m}$ has a prime factor $p_{m}>3$ that does not divide $a_{m-1}$. Let $b_{m}=3^{m-1} p_{m}$. According to Fermat's Little Theorem,
$$
2^{b_{m}}+1 \equiv 2^{3^{m-1}}+1 \equiv a_{m-1} \quad(\bmod p)_{m}
$$
Therefore, $p_{m} \nmid 2^{b_{m}}+1$, so $b_{m} \nmid 2^{b_{m}}+1$.
Since $p_{m}$ and 3 are coprime, it suffices to show that $p_{m} \mid 2^{2^{b_{m}}+1}+1$ and that $3^{m_{1}} \mid 2^{2^{b_{m}}+1}+1$. This can be done quite directly with LTE, but we might find an alternative solution. Research is ongoing.
Thus, an infinite number of integers $b_{m}$ satisfy the condition of the statement.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Prouver qu'il existe une infinité d'entiers $n$ tels que $2^{2^{n}+1}+1$ est divisible par $n$, mais $2^{n}+1$ ne l'est pas.
|
Pour $m \geqslant 1$, posons $a_{m}=2^{3^{m}}+1$. On a
$a_{m}=\left(2^{3^{m-1}}+1\right)\left(\left(2^{3^{m-1}}\right)^{2}-2^{3^{m-1}}+1\right)=a_{m-1}\left(\left(2^{3^{m-1}}\right)^{2}-2^{3^{m-1}}+1\right)$.
Notons que pour $a \in \mathbb{N}^{*}$, si $p \mid a+1$ et $p \mid a^{2}-a+1$, alors $p \mid 2 a-1$ car $2 a-1=a(a+1)-\left(a^{2}-a+1\right)$. Et $p \mid 2 a+2$, donc $p \mid 3$. Donc $\left(a_{m-1} \wedge a_{m}\right) \mid 3$ pour tout $m \in \mathbb{N} *$. Donc $a_{m}$ possède un facteur premier impair (car $a_{m}$ impair) autre que 3 qui ne divise pas $a_{m-1}$, sauf éventuellement si $a_{m}$ est une puissance de 3 , auquel cas $a_{m+1}$ possède un facteur premier que n'a pas $a_{m}$.
Donc pour une infinité d'entiers $m \in \mathbb{N}^{*}, a_{m}$ possède un facteur premier $p_{m}>3$ qui ne divise pas $a_{m-1}$. Posons $b_{m}=3^{m-1} p_{m}$. D'après le petit théorème de Fermat,
$$
2^{b_{m}}+1 \equiv 2^{3^{m-1}}+1 \equiv a_{m-1} \quad(\bmod p)_{m}
$$
Donc $p_{m} \nmid 2^{b_{m}}+1$, donc $b_{m} \nmid 2^{b_{m}}+1$.
Comme $p_{m}$ et 3 sont premiers entre eux, il suffit de montrer que $p_{m} \mid 2^{2^{b m}+1}+1$ et que $3^{m_{1}} \mid 2^{2^{b_{m}}+1}+1$. Cela se fait assez directement avec LTE mais on peut peut-être trouver une solution alternative. Recherche en cours.
Ainsi, une infinité d'entiers $b_{m}$ satisfont la condition de l'énoncé.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-1-solutions.jsonl",
"problem_match": "\nExercice 9.",
"solution_match": "\nSolution de l'exercice 9"
}
|
64d92468-9a18-5969-88f1-2581df524284
| 607,654
|
Let $m$ and $n$ be non-zero natural numbers. Prove that
$$
\frac{(m+n)!}{(m+n)^{m+n}}<\frac{m!}{m^{m}} \frac{n!}{n^{n}}
$$
|
According to the binomial formula, we have
$$
(m+n)^{m+n}=\sum_{k=0}^{m+n}\binom{m+n}{k} m^{k} n^{m+n-k}
$$
The right-hand side being a sum of $m+n+1$ strictly positive numbers, it is strictly greater than any of these numbers. In particular, for $k=m$, we have
$$
(m+n)^{m+n}>\binom{m+n}{m} m^{m} n^{n}
$$
Since $\binom{m+n}{m}=\frac{(m+n)!}{m!n!}$, this concludes.
Remark The required inequality can be interpreted in probabilistic terms. Indeed, consider an urn containing $m$ white balls and $n$ black balls indistinguishable by touch, from which $m+n$ balls are drawn successively with replacement. It is easy to verify that the probability $p_{m}$ of obtaining exactly $m$ white balls during these $m+n$ draws is
$$
p_{m}=\binom{m+n}{m}\left(\frac{m}{m+n}\right)^{m}\left(\frac{n}{m+n}\right)^{n}
$$
If we denote $q_{m}$ as the probability of not obtaining exactly $m$ white balls, we have $q_{m}>0$ and $p_{m}+q_{m}=1$, hence $p_{m}=1-q_{m}<1$.
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
Soit $m$ et $n$ des entiers naturels non nuls. Prouver que
$$
\frac{(m+n)!}{(m+n)^{m+n}}<\frac{m!}{m^{m}} \frac{n!}{n^{n}}
$$
|
D'après la formule du binôme, on a
$$
(m+n)^{m+n}=\sum_{k=0}^{m+n}\binom{m+n}{k} m^{k} n^{m+n-k}
$$
Le membre de droite étant une somme de $m+n+1$ nombres strictement positifs, elle est strictement plus grande que n'importe lequel de ces nombres. En particulier, pour $k=m$, on a donc
$$
(m+n)^{m+n}>\binom{m+n}{m} m^{m} n^{n}
$$
Puisque $\binom{m+n}{m}=\frac{(m+n)!}{m!n!}$, cela conclut.
Remarque L'inégalité demandée peut s'interpréter en termes probabilistes. En effet, considérons une urne contenant $m$ boules blanches et $n$ boules noires indiscernables au toucher, et de laquelle on tire successivement $m+n$ boules avec remise. Il est facile de vérifier que la probabilité $p_{m}$ d'obtenir exactement $m$ boules blanches au cours de ces $m+n$ tirages est
$$
p_{m}=\binom{m+n}{m}\left(\frac{m}{m+n}\right)^{m}\left(\frac{n}{m+n}\right)^{n}
$$
Si on note $q_{m}$ la probabilité de ne pas obtenir exactement $m$ boules blanches, on a $q_{m}>0$ et $p_{m}+q_{m}=1$, d'où $p_{m}=1-q_{m}<1$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-2-solutions.jsonl",
"problem_match": "## Exercice 2.",
"solution_match": "## Solution de l'exercice 2"
}
|
2b0c4e44-7c4e-55be-8a62-71f2d1ca4d6e
| 607,656
|
Let $a_{0}<a_{1}<a_{2}<\ldots$ be an infinite sequence of strictly positive integers. Prove that there exists a unique integer $n \geqslant 1$ such that
$$
a_{n}<\frac{a_{0}+a_{1}+a_{2}+\cdots+a_{n}}{n} \leqslant a_{n+1} .
$$
|
For $n \geqslant 1$, we set $d_{n}=a_{0}+a_{1}+\cdots+a_{n}-n a_{n}$.
Clearly, the left inequality of the desired bound is equivalent to $d_{n}>0$.
On the other hand, we have $d_{n+1}=a_{0}+\cdots+a_{n}-n a_{n+1}$, so the right inequality is equivalent to $d_{n+1} \leqslant 0$. Therefore, it is necessary to prove that there exists a unique $n \geqslant 1$ such that $d_{n+1} \leqslant 0 < d_{n}$, which naturally leads us to study the variations of the sequence $(d_{i})$.
For all $n \geqslant 1$, we have $d_{n+1}-d_{n}=n(a_{n}-a_{n+1})<0$ because the sequence $(a_{i})$ is strictly increasing. Moreover, we have $d_{1}=a_{0}>0$.
Thus, the sequence $(d_{i})$ is a strictly decreasing sequence of integers, which ensures that it will only take non-positive values from a certain rank, and with a strictly positive first term. Therefore, there indeed exists a unique index $n$ for which $d_{n+1} \leqslant 0 < d_{n}$, namely the largest integer such that $d_{n}>0$.
Remark The conclusion is no longer guaranteed without the assumption that the $a_{i}$ are all integers. A counterexample is given by $a_{n}=2-\frac{1}{2^{n}}$ for all $n \geqslant 0$.
## Common Exercises
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit $a_{0}<a_{1}<a_{2}<\ldots$ une suite infinie d'entiers strictement positifs. Prouver qu'il existe un unique entier $n \geqslant 1$ tel que
$$
a_{n}<\frac{a_{0}+a_{1}+a_{2}+\cdots+a_{n}}{n} \leqslant a_{n+1} .
$$
|
Pour $n \geqslant 1$, on pose $d_{n}=a_{0}+a_{1}+\cdots+a_{n}-n a_{n}$.
Clairement, l'inégalité de gauche de l'encadrement souhaité est équivalente à $\mathrm{d}_{\mathrm{n}}>0$.
D'autre part, on a $d_{n+1}=a_{0}+\cdots+a_{n}-n a_{n+1}$, donc l'inégalité de droite est équivalente à $d_{n+1} \leqslant 0$. Il s'agit donc de prouver qu'il existe un unique $n \geqslant 1$ tel que $d_{n+1} \leqslant 0<d_{n}$, ce qui nous pousse naturellement à étudier les variations de la suite ( $d_{i}$ ).
Pour tout $n \geqslant 1$, on a $d_{n+1}-d_{n}=n\left(a_{n}-a_{n+1}\right)<0$ car la suite $\left(a_{i}\right)$ est strictement croissante. De plus, on a $d_{1}=a_{0}>0$.
Ainsi, la suite ( $\mathrm{d}_{\mathrm{i}}$ ) est une suite strictement décroissante $\mathrm{d}^{\prime}$ entiers, ce qui assure qu'elle ne prendra des valeurs négatives ou nulles qu'à partir d'un certain rang, et de premier terme strictement positif. Il existe donc bien un unique indice $n$ pour lequel $d_{n+1} \leqslant 0<d_{n}$, à savoir le plus grand entier tel que $d_{n}>0$.
Remarque La conclusion n'est plus assurée sans l'hypothèse que les $a_{i}$ sont tous des entiers. Un contre-exemple est donné par $a_{n}=2-\frac{1}{2^{n}}$ pour tout $n \geqslant 0$.
## Exercices communs
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-2-solutions.jsonl",
"problem_match": "## Exercice 3.",
"solution_match": "## Solution de l'exercice 3"
}
|
b979f399-3a86-5176-9c3a-e8df1b427b35
| 607,657
|
a) Let $x_{1} \geqslant x_{2}>0$ and $y_{1} \geqslant y_{2}>0$ be real numbers such that
$$
x_{1} \geqslant y_{1} \text { and } x_{1} x_{2} \geqslant y_{1} y_{2}
$$
Prove that
$$
x_{1}+x_{2} \geqslant y_{1}+y_{2}
$$
b) Let $x_{1} \geqslant x_{2} \geqslant \ldots \geqslant x_{n}>0$ and $y_{1} \geqslant y_{2} \geqslant \ldots \geqslant y_{n}>0$ be real numbers such that
$$
x_{1} x_{2} \cdots x_{i} \geqslant y_{1} y_{2} \cdots y_{i} \text { for } i=1, \ldots, n
$$
Prove that
$$
x_{1}+x_{2}+\cdots+x_{n} \geqslant y_{1}+y_{2}+\cdots+y_{n}
$$
|
a) Proceed by contradiction: suppose that $y_{1}+y_{2}>x_{1}+x_{2}$. Then $y_{2}>x_{1}+x_{2}-y_{1}$ and we have
$$
0 \geqslant y_{1} y_{2}-x_{1} x_{2}>y_{1}\left(x_{1}+x_{2}-y_{1}\right)-x_{1} x_{2}=\left(x_{1}-y_{1}\right)\left(y_{1}-x_{2}\right)
$$
Since $x_{1} \geqslant y_{1}$, then $y_{1}<x_{2}$. But then $x_{1}+x_{2} \geqslant 2 y_{1} \geqslant y_{1}+y_{2}$, which contradicts our assumption. Therefore, we must have $y_{1}+y_{2} \leqslant x_{1}+x_{2}$.
b) Proceed by strong induction on $n$. First, the result is obvious for $n=1$, and we have just proved it for $n=2$. Assume therefore that $n \geqslant 3$.
Let $\lambda=\min _{1 \leqslant k<n} \frac{x_{1}+\ldots+x_{k}}{y_{1}+\ldots+y_{k}}$, and let $\ell$ be an integer such that $1 \leqslant \ell<n$ and such that
$$
x_{1}+\ldots+x_{\ell}=\lambda\left(y_{1}+\ldots+y_{\ell}\right)
$$
We then set $y_{1}^{\prime}=\lambda y_{1}, y_{n}^{\prime}=\frac{y_{n}}{\lambda}$ and $y_{k}^{\prime}=y_{k}$ for $k=2, \ldots, n-1$. By construction, we have $y_{1}^{\prime} \geqslant y_{2} \geqslant \ldots \geqslant y_{n}^{\prime}$ and, for $k=1, \ldots, n$, we also have $x_{1} \ldots x_{k} \geqslant y_{1}^{\prime} \ldots y_{k}^{\prime}$, with equality when $k=\ell<n$. By the induction hypothesis, we know that $x_{1}+\ldots+x_{\ell} \geqslant y_{1}^{\prime}+\ldots+y_{\ell}^{\prime}$.
Furthermore, note that $y_{1}^{\prime} \geqslant y_{n}^{\prime}, y_{1} \geqslant y_{n}, y_{1}^{\prime} \geqslant y_{1}$ and $y_{1}^{\prime} y_{n}^{\prime}=y_{1} y_{n}$. Applying the induction hypothesis (for $n=2$), we get $y_{1}^{\prime}+y_{n}^{\prime} \geqslant y_{1}+y_{n}$, and even $y_{1}^{\prime}+y_{2}^{\prime}+\ldots+y_{n}^{\prime} \geqslant y_{1}+y_{2}+\ldots+y_{n}$.
Finally, let $\bar{x}_{i}=x_{\ell+i}$ and $\bar{y}_{i}=y_{\ell+1}^{\prime}$, for $i=1, \ldots, n-\ell$. Then $\bar{x}_{1} \geqslant \ldots \geqslant \bar{x}_{n-\ell}>0$ and $\bar{y}_{1} \geqslant \ldots \geqslant \bar{y}_{n-\ell}>0$. Moreover, for $i=1, \ldots, n-\ell$, we have
$$
\left(x_{1} \ldots x_{\ell}\right)\left(\bar{x}_{1} \ldots \bar{x}_{i}\right)=x_{1} \ldots x_{\ell+i} \geqslant y_{1}^{\prime} \ldots y_{\ell+i}^{\prime}=\left(y_{1}^{\prime} \ldots y_{\ell}^{\prime}\right)\left(\bar{y}_{1} \ldots \bar{y}_{i}\right)
$$
Since $x_{1} \ldots x_{\ell}=y_{1}^{\prime} \ldots y_{\ell}^{\prime}>0$, this shows that $\bar{x}_{1} \ldots \bar{x}_{i} \geqslant \bar{y}_{1} \ldots \bar{y}_{i}$. We have $n-\ell<n$, and the induction hypothesis shows that $\bar{x}_{1}+\ldots+\bar{x}_{n-\ell} \geqslant \bar{y}_{1}+\ldots+\bar{y}_{n-\ell}$.
Putting these inequalities together, we get
$$
\begin{aligned}
x_{1}+\ldots+x_{n} & =\left(x_{1}+\ldots+x_{\ell}\right)+\left(\bar{x}_{1}+\ldots+\bar{x}_{n-\ell}\right) \\
& \geqslant y_{1}^{\prime}+\ldots+y_{\ell}^{\prime}+\bar{y}_{1}+\ldots+\bar{y}_{n-\ell}=y_{1}^{\prime}+\ldots+y_{n}^{\prime} \\
& \geqslant y_{1}+\ldots+y_{n} .
\end{aligned}
$$
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
a) Soit $x_{1} \geqslant x_{2}>0$ et $y_{1} \geqslant y_{2}>0$ des réels tels que
$$
x_{1} \geqslant y_{1} \text { et } x_{1} x_{2} \geqslant y_{1} y_{2}
$$
Prouver que
$$
x_{1}+x_{2} \geqslant y_{1}+y_{2}
$$
b) Soit $x_{1} \geqslant x_{2} \geqslant \ldots \geqslant x_{n}>0$ et $y_{1} \geqslant y_{2} \geqslant \ldots \geqslant y_{n}>0$ des réels tels que
$$
x_{1} x_{2} \cdots x_{i} \geqslant y_{1} y_{2} \cdots y_{i} \text { pour } i=1, \ldots, n
$$
Prouver que
$$
x_{1}+x_{2}+\cdots+x_{n} \geqslant y_{1}+y_{2}+\cdots+y_{n}
$$
|
a) Procédons par l'absurde: supposons que $y_{1}+y_{2}>x_{1}+x_{2}$. Alors $y_{2}>x_{1}+x_{2}-y_{1}$ et on a
$$
0 \geqslant y_{1} y_{2}-x_{1} x_{2}>y_{1}\left(x_{1}+x_{2}-y_{1}\right)-x_{1} x_{2}=\left(x_{1}-y_{1}\right)\left(y_{1}-x_{2}\right)
$$
Puisque $x_{1} \geqslant y_{1}$, alors $y_{1}<x_{2}$. Mais alors $x_{1}+x_{2} \geqslant 2 y_{1} \geqslant y_{1}+y_{2}$, ce qui contredit notre hypothèse. On a donc bien $y_{1}+y_{2} \leqslant x_{1}+x_{2}$.
b) Procédons par récurrence forte sur $n$. Tout d'abord, le résultat est évident pour $n=1$, et on vient de le prouver pour $\mathrm{n}=2$. On suppose donc $\mathrm{n} \geqslant 3$.
Soit $\lambda=\min _{1 \leqslant k<n} \frac{x_{1}+\ldots+x_{k}}{y_{1}+\ldots+y_{k}}$, et soit $\ell$ un entier tel que $1 \leqslant \ell<n$ et tel que
$$
x_{1}+\ldots+x_{\ell}=\lambda\left(y_{1}+\ldots+y_{\ell}\right)
$$
On pose alors $y_{1}^{\prime}=\lambda y_{1}, y_{n}^{\prime}=\frac{y_{n}}{\lambda}$ et $y_{k}^{\prime}=y_{k}$ pour $k=2, \ldots, n-1$. Par construction, on a bien $y_{1}^{\prime} \geqslant y_{2} \geqslant \ldots \geqslant y_{n}^{\prime}$ et, pour $k=1, \ldots, n$, on a également $x_{1} \ldots x_{k} \geqslant y_{1}^{\prime} \ldots y_{k}^{\prime}$, avec égalité quand $k=\ell<n$. Par hypothèse de récurrence, on sait que $x_{1}+\ldots+x_{\ell} \geqslant$ $y_{1}^{\prime}+\ldots+y_{\ell}^{\prime}$.
En outre, remarquons que $y_{1}^{\prime} \geqslant y_{n}^{\prime}, y_{1} \geqslant y_{n}, y_{1}^{\prime} \geqslant y_{1}$ et $y_{1}^{\prime} y_{n}^{\prime}=y_{1} y_{n}$. En appliquant l'hypothèse de récurrence (pour $n=2$ ), on obtient donc $y_{1}^{\prime}+y_{n}^{\prime} \geqslant y_{1}+y_{n}$, et même $y_{1}^{\prime}+y_{2}^{\prime}+\ldots+y_{n}^{\prime} \geqslant y_{1}+y_{2}+\ldots+y_{n}$.
Enfin, posons $\bar{x}_{i}=x_{\ell+i}$ et $\bar{y}_{i}=y_{\ell+1}^{\prime}$, pour $i=1, \ldots, n-\ell$. Alors $\bar{x}_{1} \geqslant \ldots \geqslant \bar{x}_{n-\ell}>0$ et $\bar{y}_{1} \geqslant \ldots \geqslant \bar{y}_{n-\ell}>0$. En outre, pour $i=1, \ldots, n-\ell$, on a
$$
\left(x_{1} \ldots x_{\ell}\right)\left(\bar{x}_{1} \ldots \bar{x}_{i}\right)=x_{1} \ldots x_{\ell+i} \geqslant y_{1}^{\prime} \ldots y_{\ell+i}^{\prime}=\left(y_{1}^{\prime} \ldots y_{\ell}^{\prime}\right)\left(\bar{y}_{1} \ldots \bar{y}_{i}\right)
$$
Puisque $x_{1} \ldots x_{\ell}=y_{1}^{\prime} \ldots y_{\ell}^{\prime}>0$, cela montre que $\bar{x}_{1} \ldots \bar{x}_{i} \geqslant \bar{y}_{1} \ldots \bar{y}_{i}$. On a $n-\ell<n$, et l'hypothèse de récurrence montre donc que $\bar{x}_{1}+\ldots+\bar{x}_{n-\ell} \geqslant \bar{y}_{1}+\ldots+\bar{y}_{n-\ell}$.
Mises bout à bout, ces inégalités montrent que
$$
\begin{aligned}
x_{1}+\ldots+x_{n} & =\left(x_{1}+\ldots+x_{\ell}\right)+\left(\bar{x}_{1}+\ldots+\bar{x}_{n-\ell}\right) \\
& \geqslant y_{1}^{\prime}+\ldots+y_{\ell}^{\prime}+\bar{y}_{1}+\ldots+\bar{y}_{n-\ell}=y_{1}^{\prime}+\ldots+y_{n}^{\prime} \\
& \geqslant y_{1}+\ldots+y_{n} .
\end{aligned}
$$
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-2-solutions.jsonl",
"problem_match": "## Exercice 6.",
"solution_match": "## Solution de l'exercice 6"
}
|
8c5a6cfb-9a49-5a67-8bde-87fb868a462b
| 607,660
|
a) Let $x_{1} \geqslant x_{2}>0$ and $y_{1} \geqslant y_{2}>0$ be real numbers such that
$$
x_{1} \geqslant y_{1} \text { and } x_{1} x_{2} \geqslant y_{1} y_{2}
$$
Prove that
$$
x_{1}+x_{2} \geqslant y_{1}+y_{2}
$$
b) Let $x_{1} \geqslant x_{2} \geqslant \ldots \geqslant x_{n}>0$ and $y_{1} \geqslant y_{2} \geqslant \ldots \geqslant y_{n}>0$ be real numbers such that
$$
x_{1} x_{2} \cdots x_{i} \geqslant y_{1} y_{2} \cdots y_{i} \text { for } i=1, \ldots, n
$$
Prove that
$$
x_{1}+x_{2}+\cdots+x_{n} \geqslant y_{1}+y_{2}+\cdots+y_{n}
$$
|
We set
$$
x_{n+1}=\min \left(x_{n}, y_{n}\right) \frac{y_{1} \cdots y_{n}}{x_{1} \cdots x_{n}} \text { and } y_{n+1}=\min \left(x_{n}, y_{n}\right)
$$
We then have $0<x_{n+1} \leqslant x_{n}, 0<y_{n+1} \leqslant y_{n}, x_{n+1} \leqslant y_{n+1}$ and $x_{1} \cdots x_{n} x_{n+1}=y_{1} \cdots y_{n} y_{n+1}$. Since everything is homogeneous, by multiplying the $x_{i}$ and the $y_{i}$ by the same constant, we can assume that $x_{i}, y_{i}>1$ for all $i$. We then set $\alpha_{i}=\ln \left(x_{i}\right)$ and $\beta_{i}=\ln \left(y_{i}\right)$, for all $i$. We then have:
$-\alpha_{1} \geqslant \ldots \geqslant \alpha_{n+1}>0$ and $\beta_{1} \geqslant \ldots \geqslant \beta_{n+1}>0 ;$
$-\beta_{1}+\cdots+\beta_{i} \leqslant \alpha_{1}+\cdots+\alpha_{i}$, for $i=1, \ldots, n$;
$-\beta_{1}+\cdots \beta_{n+1}=\alpha_{1}+\cdots+\alpha_{n+1}$.
We can therefore use Muirhead's inequality, which ensures that, for all positive real numbers $\mathrm{x}_{1}, \ldots, \chi_{n+1}$, we have
$$
\sum_{\text {sym. }} x_{1}^{\beta_{1}} \cdots x_{n+1}^{\beta_{n+1}} \leqslant \sum_{\text {sym. }} x_{1}^{\alpha_{1}} \cdots x_{n+1}^{\alpha_{n+1}} .
$$
In particular, if $x_{1}=e$ and $x_{i}=1$ for $i \geqslant 2$, it follows that $\sum_{i=1}^{n+1} y_{i} \leqslant \sum_{i=1}^{n+1} x_{i}$. Since $x_{n+1} \leqslant y_{n+1}$, it actually follows that $\sum_{i=1}^{n} y_{i} \leqslant \sum_{i=1}^{n} x_{i}$.
Remark Once the numbers $\alpha_{i}$ and $\beta_{i}$ are introduced, instead of using Muirhead's inequality, we could have directly used Karamata's inequality with the exponential function (which is convex on $\mathbb{R}$ ).
## Exercises of group $\mathcal{A}$
|
proof
|
Yes
|
Yes
|
proof
|
Inequalities
|
a) Soit $x_{1} \geqslant x_{2}>0$ et $y_{1} \geqslant y_{2}>0$ des réels tels que
$$
x_{1} \geqslant y_{1} \text { et } x_{1} x_{2} \geqslant y_{1} y_{2}
$$
Prouver que
$$
x_{1}+x_{2} \geqslant y_{1}+y_{2}
$$
b) Soit $x_{1} \geqslant x_{2} \geqslant \ldots \geqslant x_{n}>0$ et $y_{1} \geqslant y_{2} \geqslant \ldots \geqslant y_{n}>0$ des réels tels que
$$
x_{1} x_{2} \cdots x_{i} \geqslant y_{1} y_{2} \cdots y_{i} \text { pour } i=1, \ldots, n
$$
Prouver que
$$
x_{1}+x_{2}+\cdots+x_{n} \geqslant y_{1}+y_{2}+\cdots+y_{n}
$$
|
On pose
$$
x_{n+1}=\min \left(x_{n}, y_{n}\right) \frac{y_{1} \cdots y_{n}}{x_{1} \cdots x_{n}} \text { et } y_{n+1}=\min \left(x_{n}, y_{n}\right)
$$
On a alors $0<x_{n+1} \leqslant x_{n}, 0<y_{n+1} \leqslant y_{n}, x_{n+1} \leqslant y_{n+1}$ et $x_{1} \cdots x_{n} x_{n+1}=y_{1} \cdots y_{n} y_{n+1}$. Tout étant homogène, quitte à multiplier les $x_{i}$ et les $y_{i}$ par une même constante, on peut supposer que $x_{i}, y_{i}>1$ pour tout $i$. On pose ensuite $\alpha_{i}=\ln \left(x_{i}\right)$ et $\beta_{i}=\ln \left(y_{i}\right)$, pour tout i. On a alors:
$-\alpha_{1} \geqslant \ldots \geqslant \alpha_{n+1}>0$ et $\beta_{1} \geqslant \ldots \geqslant \beta_{n+1}>0 ;$
$-\beta_{1}+\cdots+\beta_{i} \leqslant \alpha_{1}+\cdots+\alpha_{i}$, pour $i=1, \ldots, n$;
$-\beta_{1}+\cdots \beta_{n+1}=\alpha_{1}+\cdots+\alpha_{n+1}$.
On peut donc utiliser l'inégalité de Muirhead, qui assure que, pour tous réels $\mathrm{x}_{1}, \ldots, \chi_{n+1}$ strictement positifs, on a
$$
\sum_{\text {sym. }} x_{1}^{\beta_{1}} \cdots x_{n+1}^{\beta_{n+1}} \leqslant \sum_{\text {sym. }} x_{1}^{\alpha_{1}} \cdots x_{n+1}^{\alpha_{n+1}} .
$$
En particulier, si $x_{1}=e$ et $x_{i}=1$ pour $i \geqslant 2$, il vient $\sum_{i=1}^{n+1} y_{i} \leqslant \sum_{i=1}^{n+1} x_{i}$. Puisque $x_{n+1} \leqslant y_{n+1}$, il s'ensuit en fait $\sum_{i=1}^{n} y_{i} \leqslant \sum_{i=1}^{n} x_{i}$.
Remarque Une fois introduits les nombres $\alpha_{i}$ et $\beta_{i}$, au lieu d'utiliser l'inégalité de Muirhead, on aurait pu directement utiliser l'inégalité de Karamata à la fonction exponentielle (qui est convexe sur $\mathbb{R}$ ).
## Exercices du groupe $\mathcal{A}$
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-2-solutions.jsonl",
"problem_match": "## Exercice 6.",
"solution_match": "## Solution alternative"
}
|
8c5a6cfb-9a49-5a67-8bde-87fb868a462b
| 607,660
|
Let $a_{0}$ and $b_{0}$ be strictly positive integers. For all $i \geqslant 0$, we set
$$
a_{i+1}=a_{i}+\left\lfloor\sqrt{b_{i}}\right\rfloor \text { and } b_{i+1}=b_{i}+\left\lfloor\sqrt{a_{i}}\right\rfloor \text {. }
$$
Prove that there exists an integer $n \geqslant 0$ such that $a_{n}=b_{n}$.
|
For all $i \geqslant 0$, let $c_{i}=b_{i}-a_{i}, \alpha_{i}=\left\lfloor\sqrt{a_{i}}\right\rfloor$ and $\beta_{i}=\left\lfloor\sqrt{b_{i}}\right\rfloor$. Without loss of generality, we assume that $c_{0} \geqslant 0$. We first show by induction that $c_{i} \geqslant 0$ for all $i \geqslant 0$. Indeed, for all $n \geqslant 0$, we have $\lfloor\sqrt{n+1}\rfloor \leqslant\lfloor\sqrt{n}\rfloor+1$. The function $f: n \longmapsto n-\lfloor\sqrt{n}\rfloor$ is therefore increasing on $\mathbb{N}$, because
$$
f(n+1)-f(n)=n+1-\lfloor\sqrt{n+1}\rfloor-n+\lfloor\sqrt{n}\rfloor \geqslant n+1-\lfloor\sqrt{n}\rfloor-1-n+\lfloor\sqrt{n}\rfloor=0
$$
for all $n \geqslant 0$. Consequently, if $c_{i} \geqslant 0$, then $b_{i} \geqslant a_{i}$, so
$$
c_{i+1}=\left(b_{i}-\left\lfloor\sqrt{b_{i}}\right\rfloor\right)-\left(a_{i}-\left\lfloor\sqrt{a_{i}}\right\rfloor\right)=f\left(b_{i}\right)-f\left(a_{i}\right) \geqslant 0
$$
This concludes the induction, and shows that $\boldsymbol{c}_{\boldsymbol{i}} \geqslant 0$ for all $i \geqslant 0$.
On the other hand, if $c_{i} \geqslant 0$, and still since $b_{i} \geqslant a_{i}$, we also have $c_{i+1}=c_{i}+\left\lfloor\sqrt{a_{i}}\right\rfloor-\left\lfloor\sqrt{b_{i}}\right\rfloor \leqslant$ $c_{i}$. The sequence $\left(c_{i}\right)_{i \geqslant 0}$ is therefore decreasing, with values in the natural numbers. There exists an integer $n \geqslant 0$ such that $c_{i}=c_{n}$ for all $i \geqslant n$. It is therefore sufficient to prove that $c_{n}=0$.
Proceed by contradiction: suppose that $c_{n} \geqslant 1$. For all $i \geqslant n$, we know that $c_{i}=c_{i+1}=$ $c_{i}+\alpha_{i}-\beta_{i}$, so that $\alpha_{i}=\beta_{i}$. The sequence $\left(b_{i}-\beta_{i}^{2}\right)_{i \geqslant n}$ has positive integer values; there therefore exists an integer $m \geqslant n$ such that $b_{i}-\beta_{i}^{2} \geqslant b_{m}-\beta_{m}^{2}$ for all $i \geqslant n$. By increasing the value of $n$, we assume in addition that $m=n$.
Finally, note that the sequences $\left(a_{i}\right)_{i \geqslant 0}$ and $\left(\alpha_{i}\right)_{i \geqslant 0}$ are clearly increasing. Two cases are then possible:
— If $\alpha_{n}=\alpha_{n+1}$, then
$$
\begin{aligned}
& b_{n+2}=b_{n}+\alpha_{n}+\alpha_{n+1} \geqslant a_{n}+c_{n}+2 \beta_{n} \geqslant \beta_{n}^{2}+2 \beta_{n}+1=\left(\beta_{n}+1\right)^{2} \text { and } \\
& b_{n+2}=b_{n}+\alpha_{n}+\alpha_{n+1}<\left(\beta_{n}+1\right)^{2}+2 \beta_{n}<\left(\beta_{n}+2\right)^{2}
\end{aligned}
$$
so $\beta_{n+2}=\beta_{n}+1$. This shows that
$$
b_{n+2}-\beta_{n+2}^{2}=b_{n}+2 \beta_{n}-\left(\beta_{n}+1\right)^{2}=\left(b_{n}-\beta_{n}^{2}\right)-1<b_{n}-\beta_{n}^{2}
$$
which contradicts our assumption.

- If $\alpha_{n}<\alpha_{n+1}$, then
$$
\begin{aligned}
& b_{n+1} \geqslant \beta_{n+1}^{2}=\alpha_{n+1}^{2} \geqslant\left(\alpha_{n}+1\right)^{2}=\left(\beta_{n}+1\right)^{2} \text { and } \\
& b_{n+1}=b_{n}+\alpha_{n}<\left(\beta_{n}+1\right)^{2}+\beta_{n}<\left(\beta_{n}+2\right)^{2}
\end{aligned}
$$
so $\beta_{n+1}=\beta_{n}+1$. This shows that
$$
b_{n+1}-\beta_{n+1}^{2}=b_{n}+\beta_{n}-\left(\beta_{n}+1\right)^{2}=\left(b_{n}-\beta_{n}^{2}\right)-\beta_{n}-1<b_{n}-\beta_{n}^{2}
$$
which once again contradicts our assumption.
Our assumption that $c_{n} \geqslant 1$ was therefore false, which shows that $c_{n}=0$, thus concluding the exercise.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Soit $a_{0}$ et $b_{0}$ des entiers strictement positifs. Pour tout $i \geqslant 0$, on pose
$$
a_{i+1}=a_{i}+\left\lfloor\sqrt{b_{i}}\right\rfloor \text { et } b_{i+1}=b_{i}+\left\lfloor\sqrt{a_{i}}\right\rfloor \text {. }
$$
Prouver qu'il existe un entier $n \geqslant 0$ tel que $a_{n}=b_{n}$.
|
Pour tout $i \geqslant 0$, posons $c_{i}=b_{i}-a_{i}, \alpha_{i}=\left\lfloor\sqrt{a_{i}}\right\rfloor$ et $\beta_{i}=\left\lfloor\sqrt{b_{i}}\right\rfloor$. Sans perte de généralité, on suppose que $c_{0} \geqslant 0$. On montre tout d'abord par récurrence que $c_{i} \geqslant 0$ pour tout $i \geqslant 0$. En effet, pour tout $n \geqslant 0$, on a $\lfloor\sqrt{n+1}\rfloor \leqslant\lfloor\sqrt{n}\rfloor+1$. La fonction $f: n \longmapsto n-\lfloor\sqrt{n}\rfloor$ est donc croissante sur $\mathbb{N}$, car
$$
f(n+1)-f(n)=n+1-\lfloor\sqrt{n+1}\rfloor-n+\lfloor\sqrt{n}\rfloor \geqslant n+1-\lfloor\sqrt{n}\rfloor-1-n+\lfloor\sqrt{n}\rfloor=0
$$
pour tout $n \geqslant 0$. Par conséquent, si $c_{i} \geqslant 0$, alors $b_{i} \geqslant a_{i}$, donc
$$
c_{i+1}=\left(b_{i}-\left\lfloor\sqrt{b_{i}}\right\rfloor\right)-\left(a_{i}-\left\lfloor\sqrt{a_{i}}\right\rfloor\right)=f\left(b_{i}\right)-f\left(a_{i}\right) \geqslant 0
$$
Ceci conclut la récurrence, et montre bien que $\boldsymbol{c}_{\boldsymbol{i}} \geqslant 0$ pour tout $i \geqslant 0$.
D'autre part, si $c_{i} \geqslant 0$, et toujours puisque $b_{i} \geqslant a_{i}$, on a aussi $c_{i+1}=c_{i}+\left\lfloor\sqrt{a_{i}}\right\rfloor-\left\lfloor\sqrt{b_{i}}\right\rfloor \leqslant$ $c_{i}$. La suite $\left(c_{i}\right)_{i \geqslant 0}$ est donc décroissante, à valeurs dans les entiers naturels. Il existe donc un entier $n \geqslant 0$ tel que $c_{i}=c_{n}$ pour tout $i \geqslant n$. Il suffit donc de prouver que $c_{n}=0$.
Procédons par l'absurde : supposons que $c_{n} \geqslant 1$. Pour tout $i \geqslant n$, on sait que $c_{i}=c_{i+1}=$ $c_{i}+\alpha_{i}-\beta_{i}$, donc que $\alpha_{i}=\beta_{i}$. La suite $\left(b_{i}-\beta_{i}^{2}\right)_{i \geqslant n}$ est à valeurs entières positives ; il existe donc un entier $m \geqslant n$ tel que $b_{i}-\beta_{i}^{2} \geqslant b_{m}-\beta_{m}^{2}$ pour tout $i \geqslant n$. Quitte à augmenter la valeur de $n$, on suppose en outre que $m=n$.
Notons enfin que les suites $\left(a_{i}\right)_{i \geqslant 0}$ et $\left(\alpha_{i}\right)_{i \geqslant 0}$ sont clairement croissantes. Deux cas sont alors possibles :
— Si $\alpha_{n}=\alpha_{n+1}$, alors
$$
\begin{aligned}
& b_{n+2}=b_{n}+\alpha_{n}+\alpha_{n+1} \geqslant a_{n}+c_{n}+2 \beta_{n} \geqslant \beta_{n}^{2}+2 \beta_{n}+1=\left(\beta_{n}+1\right)^{2} \text { et } \\
& b_{n+2}=b_{n}+\alpha_{n}+\alpha_{n+1}<\left(\beta_{n}+1\right)^{2}+2 \beta_{n}<\left(\beta_{n}+2\right)^{2}
\end{aligned}
$$
donc $\beta_{n+2}=\beta_{n}+1$. Ceci montre que
$$
b_{n+2}-\beta_{n+2}^{2}=b_{n}+2 \beta_{n}-\left(\beta_{n}+1\right)^{2}=\left(b_{n}-\beta_{n}^{2}\right)-1<b_{n}-\beta_{n}^{2}
$$
ce qui contredit notre hypothèse.

- Si $\alpha_{n}<\alpha_{n+1}$, alors
$$
\begin{aligned}
& b_{n+1} \geqslant \beta_{n+1}^{2}=\alpha_{n+1}^{2} \geqslant\left(\alpha_{n}+1\right)^{2}=\left(\beta_{n}+1\right)^{2} \text { et } \\
& b_{n+1}=b_{n}+\alpha_{n}<\left(\beta_{n}+1\right)^{2}+\beta_{n}<\left(\beta_{n}+2\right)^{2}
\end{aligned}
$$
donc $\beta_{n+1}=\beta_{n}+1$. Ceci montre que
$$
b_{n+1}-\beta_{n+1}^{2}=b_{n}+\beta_{n}-\left(\beta_{n}+1\right)^{2}=\left(b_{n}-\beta_{n}^{2}\right)-\beta_{n}-1<b_{n}-\beta_{n}^{2}
$$
ce qui contredit une fois encore notre hypothèse.
Notre hypothèse selon laquelle $c_{n} \geqslant 1$ était donc fausse, ce qui montre que $c_{n}=0$, concluant donc l'exercice.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-2-solutions.jsonl",
"problem_match": "## Exercice 7.",
"solution_match": "## Solution de l'exercice 7"
}
|
9147e1d7-182c-5773-8623-54f6762dca62
| 607,661
|
A polynomial is said to be "monic" if the coefficient of its highest degree monomial is 1. Let $a<b$ be real numbers, and let $P$ be a non-constant monic polynomial such that $\max _{x \in[a, b]}|P(x)|<2$.
Prove that there exists a non-constant monic polynomial $Q$ such that $\max _{x \in[\mathbf{a}, \mathbf{b}]}|\mathrm{Q}(\mathrm{x})|<\frac{1}{2017}$.
|
If $Q$ denotes a polynomial, we set
$$
\|Q\|=\frac{1}{2} \max _{x \in[a, b]}|Q(x)| \text { and } T(Q)(x)=Q(x)^{2}-2\|Q\|^{2}
$$
It is clear that if $Q$ is a non-constant unitary polynomial, then $T(Q)$ is also a non-constant unitary polynomial. Moreover, we have $\|T(Q)\|=\|Q\|^{2}$. If we denote $T^{n}$ as the $n$-th iterate of $T$, then an immediate induction ensures that for any integer $n \geqslant 0, T^{n}(Q)$ is a non-constant polynomial whose leading coefficient is 1 and that $\left\|T^{\mathrm{n}}(Q)\right\|=\|Q\|^{2^{n}}$. Let $P$ be a non-constant unitary polynomial such that $\max _{\mathrm{x} \in[\mathrm{a}, \mathbf{b}]}|\mathrm{P}(\mathrm{x})|<2$. Since $0<$ $\|P\|<1$, we have $\lim _{n \rightarrow+\infty}\left\|T^{n}(P)\right\|=0$. In particular, there exists $n \geqslant 0$ sufficiently large such that $\left\|\mathrm{T}^{\mathrm{n}}(\mathrm{P})\right\|<\frac{1}{2 \times 2017}$, and the polynomial $\mathrm{Q}=\mathrm{T}^{\mathrm{n}}(\mathrm{P})$ then answers the question.
|
proof
|
Yes
|
Yes
|
proof
|
Algebra
|
Un polynôme est dit «unitaire » si le coefficient de son monôme de plus haut de degré vaut 1. Soit $a<b$ des réels, et soit $P$ un polynôme unitaire non constant tel que $\max _{x \in[a, b]}|P(x)|<2$.
Prouver qu'il existe un polynôme $Q$, unitaire et non constant, tel que $\max _{x \in[\mathbf{a}, \mathbf{b}]}|\mathrm{Q}(\mathrm{x})|<\frac{1}{2017}$.
|
Si Q désigne un polynôme, on pose
$$
\|Q\|=\frac{1}{2} \max _{x \in[a, b]}|Q(x)| \text { et } T(Q)(x)=Q(x)^{2}-2\|Q\|^{2}
$$
Il est clair que si Q est un polynôme unitaire non constant, alors $\mathrm{T}(\mathrm{Q})$ l'est également. De plus, on a $\|T(Q)\|=\|Q\|^{2}$. Si $l^{\prime}$ on note $T^{n}$ la $n$-ieme itérée de $T$, alors une récurrence immédiate assure que pour tout entier $n \geqslant 0, T^{n}(Q)$ est un polynôme non constant dont le coefficient du monôme de plus haut de degré vaut 1 et que $\left\|T^{\mathrm{n}}(Q)\right\|=\|Q\|^{2^{n}}$. Soit donc P un polynôme unitaire non constant, tel que $\max _{\mathrm{x} \in[\mathrm{a}, \mathbf{b}]}|\mathrm{P}(\mathrm{x})|<2$. Puisque $0<$ $\|P\|<1$, on a $\lim _{n \rightarrow+\infty}\left\|T^{n}(P)\right\|=0$. En particulier, il existe $n \geqslant 0$ suffisamment grand pour que $\left\|\mathrm{T}^{\mathrm{n}}(\mathrm{P})\right\|<\frac{1}{2 \times 2017}$, et le polynôme $\mathrm{Q}=\mathrm{T}^{\mathrm{n}}(\mathrm{P})$ répond alors à la question.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-2-solutions.jsonl",
"problem_match": "## Exercice 8.",
"solution_match": "## Solution de l'exercice 8"
}
|
36371854-e1c4-58ff-bdb4-a5e1b230791b
| 607,662
|
a) Prove that there exist integers $\mathbf{a}, \boldsymbol{b}$, $\mathbf{c}$ such that $(\mathbf{a}, \mathbf{b}, \mathbf{c}) \neq (0,0,0)$ and $|\mathbf{a}|,|\mathbf{b}|,|\mathbf{c}| < 10^{6}$ for which
$$
|a + b \sqrt{2} + c \sqrt{3}| < 10^{-11}
$$
b) Let $\mathbf{a}, \mathbf{b}, \mathrm{c}$ be integers such that $(\mathbf{a}, \boldsymbol{b}, \mathrm{c}) \neq (0,0,0)$ and $|\mathbf{a}|,|\mathbf{b}|,|\mathbf{c}| < 10^{6}$. Prove that
$$
|a + b \sqrt{2} + c \sqrt{3}| > 10^{-21}
$$
|
a) Let E be the set of $10^{18}$ numbers of the form $a+b \sqrt{2}+c \sqrt{3}$, with $a, b, c$ natural integers and $a, b, c<10^{6}$. We set $d=(1+\sqrt{2}+\sqrt{3}) 10^{6}$.
For all $x \in \mathrm{E}$, we have $0 \leqslant x<\mathrm{d}$. Moreover, $0<\mathrm{d}<(1+2+3) \times 10^{6}<10^{7}-10^{-11}$. We then divide the interval [0; d[ into $10^{18}-1$ intervals
$$
\left[\frac{(\mathrm{k}-1) \mathrm{d}}{10^{18}-1} ; \frac{\mathrm{kd}}{10^{18}-1}[,\right.
$$
for $k=1, \ldots, 10^{18}-1$. According to the pigeonhole principle, at least two of the $10^{18}$ elements of $E$, say $x$ and $y$, belong to one of these intervals. Their difference $z=x-y$ is indeed of the form $z=a+b \sqrt{2}+c \sqrt{3}$ with $a, b, c$ integers and $|a|,|b|,|c|<10^{6}$. Moreover, $|z|=|x-y|<\frac{d}{10^{18}-1}<10^{-11}$.
b) Let $a, b, c$ be integers such that $(a, b, c) \neq(0,0,0)$ and $|a|,|b|,|c|<10^{6}$. For $\epsilon= \pm 1$ and $\varepsilon= \pm 1$, we set
$$
F_{\epsilon, \varepsilon}=a+\epsilon b \sqrt{2}+\varepsilon c \sqrt{3} .
$$
As above, we have $\left|\mathrm{F}_{\epsilon, \varepsilon}\right|<10^{7}$.
We easily verify that
$$
\begin{aligned}
F_{1,1} F_{1,-1} F_{-1,1} F_{-1,-1} & =\left((a+b \sqrt{2})^{2}-3 c^{2}\right)\left((a-b \sqrt{2})^{2}-3 c^{2}\right) \\
& =\left(a^{2}+2 b^{2}-3 c^{2}+2 a b \sqrt{2}\right)\left(a^{2}+2 b^{2}-3 c^{2}-2 a b \sqrt{2}\right) \\
& =\left(a^{2}+2 b^{2}-3 c^{2}\right)^{2}-2(2 a b)^{2}
\end{aligned}
$$
is an integer.
To show that it is non-zero, we proceed by contradiction and assume that
$$
\mathrm{F}_{1,1} \mathrm{~F}_{1,-1} \mathrm{~F}_{-1,1} \mathrm{~F}_{-1,-1}=0
$$
It follows that $x^{2}=2 y^{2}$, with $x=a^{2}+2 b^{2}-3 c^{2}$ and $y=2 a b$. If $x$ and $y$ are non-zero, by considering the 2-adic valuation, we get $2 v_{2}(x)=1+2 v_{2}(\mathrm{y})$. This is absurd, which shows that $x=y=0$. Then:
— if $a=0$, and since $x=0$, we have $2 b^{2}=3 c^{2}$, and the 2-adic valuation shows again that $\mathrm{b}=\mathrm{c}=0$;
- if $b=0$, and since $x=0$, we have $a^{2}=3 c^{2}$, and the 3-adic valuation also shows that $a=c=0$.
Consequently, if $(a, b, c) \neq 0$, the integer $F_{1,1} F_{1,-1} F_{-1,1} F_{-1,-1}$ is non-zero.
Thus, $\left|\mathrm{F}_{1,1} \mathrm{~F}_{1,-1} \mathrm{~F}_{-1,1} \mathrm{~F}_{-1,-1}\right| \geqslant 1$, so $\left|\mathrm{F}_{1,1}\right| \geqslant \frac{1}{\left|\mathrm{~F}_{1,-1} \mathrm{~F}_{-1,1} \mathrm{~F}_{-1,-1}\right|}>10^{-21}$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
a) Prouver qu'il existe des entiers $\mathbf{a}, \boldsymbol{b}$, $\mathbf{c}$ tels que $(\mathbf{a}, \mathbf{b}, \mathbf{c}) \neq(0,0,0)$ et $|\mathbf{a}|,|\mathbf{b}|,|\mathbf{c}|<10^{6}$ pour lesquels
$$
|a+b \sqrt{2}+c \sqrt{3}|<10^{-11}
$$
b) Soit $\mathbf{a}, \mathbf{b}, \mathrm{c}$ des entiers tels que $(\mathbf{a}, \boldsymbol{b}, \mathrm{c}) \neq(0,0,0)$ et $|\mathbf{a}|,|\mathbf{b}|,|\mathbf{c}|<10^{6}$. Prouver que
$$
|a+b \sqrt{2}+c \sqrt{3}|>10^{-21}
$$
|
a) Soit E l'ensemble des $10^{18}$ nombres de la forme $a+b \sqrt{2}+c \sqrt{3}$, avec $a, b, c$ entiers naturels et $a, b, c<10^{6}$. On pose $d=(1+\sqrt{2}+\sqrt{3}) 10^{6}$.
Pour tout $x \in \mathrm{E}$, on a $0 \leqslant x<\mathrm{d}$. De plus $0<\mathrm{d}<(1+2+3) \times 10^{6}<10^{7}-10^{-11}$. On divise alors l'intervalle [0; d[ en $10^{18}-1$ intervalles
$$
\left[\frac{(\mathrm{k}-1) \mathrm{d}}{10^{18}-1} ; \frac{\mathrm{kd}}{10^{18}-1}[,\right.
$$
pour $k=1, \ldots, 10^{18}-1$. D'après le principe des tiroirs, au moins deux des $10^{18}$ élements de $E$, disons $x$ et $y$, appartiennent à un même de ces intervalles. Leur différence $z=x-y$ est bien de la forme $z=a+b \sqrt{2}+c \sqrt{3}$ avec $a, b, c$ entiers et $|a|,|b|,|c|<10^{6}$. De plus, $|z|=|x-y|<\frac{d}{10^{18}-1}<10^{-11}$.
b) Soit $a, b, c$ des entiers tels que $(a, b, c) \neq(0,0,0)$ et $|a|,|b|,|c|<10^{6}$. Pour $\epsilon= \pm 1$ et $\varepsilon= \pm 1$, on pose
$$
F_{\epsilon, \varepsilon}=a+\epsilon b \sqrt{2}+\varepsilon c \sqrt{3} .
$$
Comme ci-dessus, on a $\left|\mathrm{F}_{\epsilon, \varepsilon}\right|<10^{7}$.
On vérifie facilement que
$$
\begin{aligned}
F_{1,1} F_{1,-1} F_{-1,1} F_{-1,-1} & =\left((a+b \sqrt{2})^{2}-3 c^{2}\right)\left((a-b \sqrt{2})^{2}-3 c^{2}\right) \\
& =\left(a^{2}+2 b^{2}-3 c^{2}+2 a b \sqrt{2}\right)\left(a^{2}+2 b^{2}-3 c^{2}-2 a b \sqrt{2}\right) \\
& =\left(a^{2}+2 b^{2}-3 c^{2}\right)^{2}-2(2 a b)^{2}
\end{aligned}
$$
est un entier.
Afin de montrer qu'il est non nul, on procède par l'absurde, et on suppose que
$$
\mathrm{F}_{1,1} \mathrm{~F}_{1,-1} \mathrm{~F}_{-1,1} \mathrm{~F}_{-1,-1}=0
$$
Il s'ensuit que $x^{2}=2 y^{2}$, avec $x=a^{2}+2 b^{2}-3 c^{2}$ et $y=2 a b$. Si $x$ et $y$ sont non nuls, en considérant la valuation 2-adique, il vient $2 v_{2}(x)=1+2 v_{2}(\mathrm{y})$. C'est absurde, ce qui montre que $x=y=0$. Puis :
— si $a=0$, et puisque $x=0$, on a $2 b^{2}=3 c^{2}$, et la valuation 2 -adique montre de nouveau que $\mathrm{b}=\mathrm{c}=0$;
- si $b=0$, et puisque $x=0$, on a $a^{2}=3 c^{2}$, et la valuation 3-adique montre aussi que $a=c=0$.
Par conséquent, si $(a, b, c) \neq 0$, l'entier $F_{1,1} F_{1,-1} F_{-1,1} F_{-1,-1}$ est non nul.
Ainsi, $\left|\mathrm{F}_{1,1} \mathrm{~F}_{1,-1} \mathrm{~F}_{-1,1} \mathrm{~F}_{-1,-1}\right| \geqslant 1$, donc $\left|\mathrm{F}_{1,1}\right| \geqslant \frac{1}{\left|\mathrm{~F}_{1,-1} \mathrm{~F}_{-1,1} \mathrm{~F}_{-1,-1}\right|}>10^{-21}$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-2-solutions.jsonl",
"problem_match": "## Exercice 9.",
"solution_match": "## Solution de l'exercice 9"
}
|
4ad3e650-5e46-5de0-b60a-f7fa6e1f613e
| 607,663
|
Let $A B C D$ be a convex quadrilateral (i.e., its diagonals are inside $A B C D$), and $P$ the intersection of its diagonals $[A C]$ and $[B D]$. We denote $O_{1}, O_{2}, O_{3}$, and $O_{4}$ as the centers of the circumcircles of $A B P, B C P, C D P$, and $D A P$.
Show that $O_{1} O_{2} O_{3} O_{4}$ is a parallelogram.

|
$1 O_{1}$ and $O_{2}$ are on the perpendicular bisector of $[P B]$, so $O_{1} O_{2}$ is the perpendicular bisector of $[P B]$. Similarly, $\left(O_{3} O_{4}\right)$ is the perpendicular bisector of $[P D]$, so $\left(O_{1} O_{2}\right)$ and $\left(O_{3} O_{4}\right)$ are both perpendicular to $(B D)$, thus they are parallel. Similarly, $\left(O_{2} O_{3}\right)$ and $\left(O_{4} O_{1}\right)$ are both perpendicular to $(A C)$, so they are parallel.
$A B C D$ has its opposite sides parallel in pairs, so it is a parallelogram.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C D$ un quadrilatère convexe (c'est-à-dire que ses diagonales sont à l'intérieur de $A B C D)$, et $P$ l'intersection de ses diagonales $[A C]$ et $[B D]$. On note $O_{1}, O_{2}, O_{3}$ et $O_{4}$ les centres des cercles circonscrits à $A B P, B C P, C D P$ et $D A P$.
Montrer que $O_{1} O_{2} O_{3} O_{4}$ est un parallélogramme.

|
$1 O_{1}$ et $O_{2}$ sont sur la médiatrice de $[P B]$, donc $O_{1} O_{2}$ est la médiatrice de $[P B]$. De même, $\left(O_{3} O_{4}\right)$ est la médiatrice de $[P D]$, donc $\left(O_{1} O_{2}\right)$ et $\left(O_{3} O_{4}\right)$ sont toutes deux perpendiculaires à $(B D)$, donc elles sont parallèles. De même, $\left(O_{2} O_{3}\right)$ et $\left(O_{4} O_{1}\right)$ sont toutes deux perpendiculaires à $(A C)$, donc elles sont parallèles.
$A B C D$ a ses côtés opposés parallèles deux à deux, donc c'est un parallélogramme.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 1.",
"solution_match": "\nSolution de l'exercice "
}
|
d1f52aa1-ed29-530f-971a-84830575597e
| 607,664
|
Let $ABC$ be a triangle. $H$ its orthocenter and $P, Q$ and $R$ the feet of the altitudes from $A$, $B$ and $C$.
Show that $H$ is the center of the inscribed circle of $PQR$.

|
We know that points $A, B, P$ and $Q$ are concyclic on the circle with diameter $[A B]$, so:
$$
\widehat{H P Q}=\widehat{A P Q}=\widehat{A B Q}=90-\widehat{B A Q}=90-\widehat{B A C}
$$
Similarly, $A, C, P$ and $R$ are concyclic on the circle with diameter $[A C]$ so:
$$
\widehat{H P R}=\widehat{A P R}=\widehat{A C R}=90-\widehat{C A R}=90-\widehat{B A C}
$$
Therefore, $\widehat{H P Q}=\widehat{H P R}$, so $(P H)$ is the angle bisector of $\widehat{Q P R}$. Similarly, we can show that $(Q H)$ and $(R H)$ are the angle bisectors of $\widehat{P Q R}$ and $\widehat{P R Q}$, so $H$ is the incenter of $\triangle P Q R$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle. $H$ son orthocentre et $P, Q$ et $R$ les pieds des hauteurs issues de $A$, $B$ et $C$.
Montrer que $H$ est le centre du cercle inscrit à $P Q R$.

|
On sait que les points $A, B, P$ et $Q$ sont cocycliques sur le cercle de diamètre $[A B]$, donc :
$$
\widehat{H P Q}=\widehat{A P Q}=\widehat{A B Q}=90-\widehat{B A Q}=90-\widehat{B A C}
$$
De même, $A, C, P$ et $R$ sont cocycliques sur le cercle de diamètre $[A C]$ donc:
$$
\widehat{H P R}=\widehat{A P R}=\widehat{A C R}=90-\widehat{C A R}=90-\widehat{B A C}
$$
On a donc $\widehat{H P Q}=\widehat{H P R}$ donc $(P H)$ est la bissectrice de $\widehat{Q P R}$. On montre de même que $(Q H)$ et $(R H)$ sont les bissectrices de $\widehat{P Q R}$ et $\widehat{P R Q}$, donc $H$ est le centre du cercle inscrit à $P Q R$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 2.",
"solution_match": "\nSolution de l'exercice 2"
}
|
f137db4b-51dc-5930-803e-c1ed3790cee7
| 607,665
|
Two circles $\mathcal{C}$ and $\mathcal{C}^{\prime}$ with centers $O$ and $O^{\prime}$ are externally tangent at $B$. A common external tangent touches $\mathcal{C}$ at $M$ and $\mathcal{C}^{\prime}$ at $N$. The common tangent to $\mathcal{C}$ and $\mathcal{C}^{\prime}$ at $B$ intersects $(M N)$ at $A$. We denote $C$ as the intersection of $(O A)$ and $(B M)$, and $D$ as the intersection of $\left(O^{\prime} A\right)$ and $(B N)$.
Show that $(C D)$ is parallel to $(M N)$.
|
Since $(A M)$ and $(A B)$ are tangent to the circle with center $O$, we have $A M=A B$. We also have $O M=O B$, so $(O A)$ is the perpendicular bisector of $[M B]$, and thus $C$ is the midpoint of $[M B]$. Similarly, $D$ is the midpoint of $[B N]$, so $(C D)$ is parallel to ( $M N$ ).
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Deux cercles $\mathcal{C}$ et $\mathcal{C}^{\prime}$ de centres $O$ et $O^{\prime}$ sont tangents extérieurement en $B$. Une tangente commune extérieure touche $\mathcal{C}$ en $M$ et $\mathcal{C}^{\prime}$ en $N$. La tangente commune à $\mathcal{C}$ et $\mathcal{C}^{\prime}$ en $B$ coupe $(M N)$ en $A$. On note $C$ l'intersection de $(O A)$ et $(B M)$, et $D$ l'intersection de $\left(O^{\prime} A\right)$ et $(B N)$.
Montrer que $(C D)$ est parallèle à $(M N)$.
|
Comme $(A M)$ et $(A B)$ sont tangents au cercle de centre $O$, on a $A M=A B$. On a aussi $O M=O B$, donc $(O A)$ est la médiatrice de $[M B]$, et donc $C$ est le milieu de $[M B]$. De même, $D$ est le milieu de $[B N]$, donc $(C D)$ est parallèle à ( $M N$ ).
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 4.",
"solution_match": "\nSolution de l'exercice 4"
}
|
a6e75b4b-c4a4-5bf9-9901-6a538b264f67
| 607,667
|
Let $ABC$ be a triangle with all three angles acute and $\Gamma$ its circumcircle. The tangent to $\Gamma$ at $A$ intersects $(BC)$ at $P$. We denote $M$ as the midpoint of $[AP]$. The line $(BM)$ intersects $\Gamma$ at $R$ and the line $(PR)$ intersects $\Gamma$ at $S$.
Show that $(AP)$ and $(CS)$ are parallel.

|
By writing the power of $M$ with respect to $\Gamma$ and the fact that $M$ is the midpoint of $[A P]$, we obtain
$$
M R \times M B=M A^{2}=M P^{2}
$$
The triangles $M R P$ and $M P B$ are therefore indirectly similar, so $\widehat{R P M}=\widehat{P B M}$. We thus have
$$
\begin{aligned}
\widehat{C S P} & =\widehat{C S R} \\
& =\widehat{C B R} \\
& =\widehat{P B M} \\
& =\widehat{R P M} \\
& =\widehat{S P A},
\end{aligned}
$$
where $\widehat{C S R}=\widehat{C B R}$ by the inscribed angle theorem. By alternate interior angles, the lines $(C S)$ and $(A P)$ are therefore parallel.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle dont les trois angles sont aigus et $\Gamma$ son cercle circonscrit. La tangente à $\Gamma$ en $A$ recoupe $(B C)$ en $P$. On note $M$ le milieu de $[A P]$. La droite $(B M)$ recoupe $\Gamma$ en $R$ et la droite $(P R)$ recoupe $\Gamma$ en $S$.
Montrer que $(A P)$ et $(C S)$ sont parallèles.

|
En écrivant la puissance de $M$ par rapport à $\Gamma$ puis le fait que $M$ est le milieu de $[A P]$, on obtient
$$
M R \times M B=M A^{2}=M P^{2}
$$
Les triangles $M R P$ et $M P B$ sont donc indirectement semblables, donc $\widehat{R P M}=\widehat{P B M}$. On a donc
$$
\begin{aligned}
\widehat{C S P} & =\widehat{C S R} \\
& =\widehat{C B R} \\
& =\widehat{P B M} \\
& =\widehat{R P M} \\
& =\widehat{S P A},
\end{aligned}
$$
où $\widehat{C S R}=\widehat{C B R}$ par le théorème de l'angle inscrit. Par angles alternes-internes, les droites $(C S)$ et $(A P)$ sont donc parallèles.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 5.",
"solution_match": "\nSolution de l'exercice 5"
}
|
9fcf45cc-1286-5faa-b86c-2fb031bfc1eb
| 607,668
|
Let $ABC$ be a triangle and $(I)$ the center of its inscribed circle. The line $(AI)$ intersects $[BC]$ at $D$. The perpendicular bisector of $[AD]$ intersects $(BI)$ at $M$ and $(CI)$ at $N$.
Show that $A, M, N$ and $I$ are concyclic.

|
We start by recalling the South Pole Theorem:
Lemma 1 (South Pole Theorem). Let $ABC$ be a triangle, $\Gamma$ its circumcircle, and $I$ the center of its incircle. Let $S$ be the second intersection point of the angle bisector of $\widehat{BAC}$ with $\Gamma$. Then $SB = SC$. The point $S$ is called the South Pole of $A$ in the triangle $ABC$.
Proof of the lemma. The inscribed angle theorem in $\Gamma$ gives $\widehat{SBC} = \widehat{SAC}$ and $\widehat{SCB} = \widehat{SAB}$. Since $S$ is on the angle bisector of $\widehat{BAC}$, we have $\widehat{SAC} = \widehat{SAB}$, hence $\widehat{SBC} = \widehat{SCB}$, so $\triangle SCB$ is isosceles at $S$ and $SB = SC$.
Let's return to our exercise. Note that the South Pole of $A$ in a triangle $ABC$ lies on the angle bisector of $\widehat{BAC}$ and on the perpendicular bisector of $[BC]$, so it can be defined as the intersection of these two lines. We start by showing that $A, B, D$, and $M$ are concyclic. The point $M$ is on the perpendicular bisector of $[AD]$ and on the angle bisector of $\widehat{ABD}$. Therefore, it is the South Pole of $B$ in $\triangle ABD$, so it lies on the circumcircle of $\triangle ABD$. Similarly, the points $A, C, D$, and $N$ are concyclic. We can now do some angle chasing:
$$
\widehat{AMI} = \widehat{AMB} = \widehat{ADB} = 180^{\circ} - \widehat{ADC} = 180^{\circ} - \widehat{ANC} = 180^{\circ} - \widehat{ANI}
$$
Therefore, the points $A, I, M$, and $N$ are concyclic.
## Exercises of Group A
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle et $(I)$ le centre de son cercle inscrit. La droite ( $A I)$ recoupe $[B C]$ en $D$. La médiatrice de $[A D]$ recoupe $(B I)$ en $M$ et $(C I)$ en $N$.
Montrer que $A, M, N$ et $I$ sont cocycliques.

|
On commence par rappeler le théorème du Pôle Sud :
Lemme 1 (Théorème du Pôle Sud). Soit $A B C$ un triangle, $\Gamma$ son cercle circonscrit et $I$ le centre de son cercle inscrit. Soit $S$ le second point d'intersection de la bissectrice de $\widehat{B A C}$ avec $\Gamma$. Alors $S B=S C$. Le point $S$ est appelé Pôle Sud de $A$ dans le triangle $A B C$.
Preuve du lemme. Le théorème de l'angle inscrit dans $\Gamma$ donne $\widehat{S B C}=\widehat{S A C}$ et $\widehat{S C B}=\widehat{S A B}$. Or, comme $S$ est sur la bissectrice de $\widehat{B A C}$ on a $\widehat{S A C}=\widehat{S A B}$, d'où $\widehat{S B C}=\widehat{S C B}$, donc $S C B$ est isocèle en $S$ et $S B=S C$.
Revenons à notre exercice. Notons que le pôle Sud de $A$ dans un triangle $A B C$ est sur la bissectrice de $\widehat{B A C}$ et sur la médiatrice de $[B C]$, donc il peut être défini comme l'intersection de ces deux droites. On commence par montrer que $A, B, D$ et $M$ sont cocycliques. Le point $M$ est sur la médiatrice de $[A D]$ et sur la bissectrice de $\widehat{A B D}$. C'est donc le pôle Sud de $B$ dans $A B D$, donc il est sur le cercle circonscrit à $A B D$. De même, les points $A, C, D$ et $N$ sont cocycliques. On peut maintenant faire une chasse aux angles:
$$
\widehat{A M I}=\widehat{A M B}=\widehat{A D B}=180^{\circ}-\widehat{A D C}=180^{\circ}-\widehat{A N C}=180^{\circ}-\widehat{A N I}
$$
Les points $A, I, M$ et $N$ sont donc cocycliques.
## Exercices du groupe A
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 6.",
"solution_match": "\nSolution de l'exercice 6"
}
|
fe5fc261-b149-5260-bf80-2ad258629722
| 607,669
|
Let $A B C$ be a triangle whose orthocenter $H$ is distinct from the vertices as well as from the center of the circumcircle $O$. We denote by $M, N, P$ the centers of the circumcircles of triangles $H B C, H C A$ and $H A B$.
Show that the lines $(A M),(B N),(C P)$ and $(O H)$ are concurrent.

|
Let $H^{\prime}$ be the symmetric point of $H$ with respect to $(B C)$. We know that $H^{\prime}$ is on the circumcircle of $A B C$ (it is easy to verify $\widehat{B H^{\prime} C}=\widehat{B H C}=180^{\circ}-\widehat{B A C}$). The center of the circumcircle of $H^{\prime} B C$ is therefore 0. By symmetry with respect to $(B C)$, the center of the circumcircle of $B H C$ is the symmetric point of 0 with respect to $(B C)$, so $M$ is the symmetric point of $O$ with respect to $(B C)$. We will now show that $A H M O$ is a parallelogram. If this is true, then $[A M]$ and $[O H]$ intersect at their midpoints, so the midpoint of $[O H]$ is on $(A M)$ and, by the same reasoning, it is also on $(B N)$ and $(C P)$. If we denote $D$ as the midpoint of $[B C]$, then $\overrightarrow{O D}=\frac{1}{2}(\overrightarrow{O B}+\overrightarrow{O C})=\frac{1}{2}(\overrightarrow{O H}-\overrightarrow{O A})=\frac{1}{2} \overrightarrow{A H}$, so $\overrightarrow{O M}=\overrightarrow{A H}$. Using the relation $\overrightarrow{O A}+\overrightarrow{O B}+\overrightarrow{O C}=\overrightarrow{O H}$, which is equivalent to $\overrightarrow{O H}=3 \overrightarrow{O G}$ (Euler line).
We also provide another method, less quick but requiring less knowledge, to show that $A H M O$ is a parallelogram. The lines $(A H)$ and $(O M)$ are parallel, so it suffices to show that $A H=O M$. For this, we can use trigonometry. On the one hand, denoting $R$ as the radius of the circumcircle of $A B C$ and $\alpha, \beta, \gamma$ as its angles, we have
$$
O M=2 O D=2 O B \sin \widehat{O B C}=2 R \sin \left(90^{\circ}-\alpha\right)=2 R \cos \alpha
$$
On the other hand, denoting $P$ as the foot of the altitude from $C$, we have
$$
A H=\frac{A P}{\cos \widehat{P A H}}=\frac{A P}{\sin \beta}=\frac{A C \sin \widehat{A C P}}{\sin \beta}=2 R \sin \widehat{A C P}=2 R \sin \left(90^{\circ}-\alpha\right)=2 R \cos \alpha
$$
using the law of sines.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle dont l'orthocentre $H$ est distinct des sommets ainsi que du centre du cercle circonscrit $O$. On désigne par $M, N, P$ les centres des cercles circonscrits aux triangles $H B C, H C A$ et $H A B$.
Montrer que les droites $(A M),(B N),(C P)$ et $(O H)$ sont concourantes.

|
Soit $H^{\prime}$ le symétrique de $H$ par rapport à $(B C)$. On sait que $H^{\prime}$ est sur le cercle circonscrit à $A B C$ (il est facile de vérifier $\widehat{B H^{\prime} C}=\widehat{B H C}=180^{\circ}-\widehat{B A C}$ ). Le centre du cercle circonscrit à $H^{\prime} B C$ est donc 0 . Par symétrie par rapport à $(B C)$, le centre du cercle circonscrit à $B H C$ est donc le symétrique de 0 par rapport à $(B C)$, donc $M$ est le symétrique de $O$ par rapport à $(B C)$. On va maintenant montrer que $A H M O$ est un parallélogramme. Si c'est bien vrai, alors $[A M]$ et $[O H]$ se coupent en leur milieu, donc le milieu de $[O H]$ est sur $(A M)$ et, par le même raisonnement, il est aussi $\operatorname{sur}(B N)$ et $(C P)$. Si on note $D$ le milieu de $[B C]$, alors $\overrightarrow{O D}=\frac{1}{2}(\overrightarrow{O B}+\overrightarrow{O C})=\frac{1}{2}(\overrightarrow{O H}-\overrightarrow{O A})=\frac{1}{2} \overrightarrow{A H}$, donc $\overrightarrow{O M}=\overrightarrow{A H}$. En utilisant la relation $\overrightarrow{O A}+\overrightarrow{O B}+\overrightarrow{O C}=\overrightarrow{O H}$, qui est équivalente à $\overrightarrow{O H}=3 \overrightarrow{O G}$ (droite d'Euler).
On donne également une autre manière, moins rapide mais nécessitant moins de connaissances, de montrer que $A H M O$ est un parallélogramme. Les droites $(A H)$ et $(O M)$ sont parallèles, donc il suffit de montrer que $A H=O M$. Pour cela, on peut utiliser la trigonométrie. D'une part, en notant $R$ le rayon
du cercle circonscrit à $A B C$ et $\alpha, \beta, \gamma$ ses angles, on a
$$
O M=2 O D=2 O B \sin \widehat{O B C}=2 R \sin \left(90^{\circ}-\alpha\right)=2 R \cos \alpha
$$
D'autre part, en notant $P$ le pied de la hauteur issue de $C$, on a
$$
A H=\frac{A P}{\cos \widehat{P A H}}=\frac{A P}{\sin \beta}=\frac{A C \sin \widehat{A C P}}{\sin \beta}=2 R \sin \widehat{A C P}=2 R \sin \left(90^{\circ}-\alpha\right)=2 R \cos \alpha
$$
en utilisant la loi des sinus.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "\nSolution de l'exercice 7"
}
|
8afcbb18-0f2e-5a60-a862-e747e4b7d437
| 607,670
|
Let ABC be a triangle with orthocenter H. Let $\left(d_{1}\right)$ and $\left(d_{2}\right)$ be two perpendicular lines intersecting at $H$. Let $A_{1}$ (respectively $B_{1}, C_{1}$) be the intersection of $\left(d_{1}\right)$ with $(B C)$ (respectively $(C A), (A B)$). Let $A_{2}$ (respectively $B_{2}, C_{2}$) be the intersection of $\left(d_{2}\right)$ with $(B C)$ (respectively $(C A)$, $(A B)$). Let $A_{3}, B_{3}, C_{3}$ be points in the plane such that $A_{1} A_{2} A_{3}, B_{1} B_{2} B_{3}, C_{1} C_{2} C_{3}$ are directly similar triangles.
Show that $A_{3}, B_{3}, C_{3}$ are collinear.

|
We provide a proof with direct similarities. There are other proofs, a bit shorter, which use complex numbers.
First, let us recall the following result:
Lemma 2. Let $ABC$ be a triangle, $\Gamma$ its circumcircle, and $H$ its orthocenter. Then the symmetrics $H_{A}, H_{B}$, and $H_{C}$ of $H$ with respect to $(BC), (CA)$, and $(AB)$ belong to $\Gamma$.
Proof. Let $H_{A}^{\prime}$ be the intersection of $AH$ and $\Gamma$. By the inscribed angle theorem, we have:
$$
\begin{aligned}
\widehat{H_{A}^{\prime} B C} & =\widehat{H_{A}^{\prime} A C} \\
& =90-\widehat{B C A} \\
& =\widehat{H B C}
\end{aligned}
$$
Thus, $(H_{A}^{\prime} B)$ and $(HB)$ are symmetric with respect to $(BC)$. We deduce that $H_{A}^{\prime}=H_{A} \in \Gamma$. Similarly, $H_{B}, H_{C} \in \Gamma$.
Let us resume the notations of the exercise and introduce $H_{A}, H_{B}$, and $H_{C}$ as in the previous lemma.
Lemma 3. Let $S$ be the intersection of $(A_{1} H_{A})$ and $(B_{1} H_{B})$. Then $S \in \Gamma$.
Proof. We denote by $\mathcal{S}_{yz}$ the symmetry with axis $(YZ)$. Then
$$
\begin{aligned}
\mathcal{S}_{AC}\left(\mathcal{S}_{BC}\left(H_{A} A_{1}\right)\right) & =\mathcal{S}_{AC}\left(A_{1} H\right) \text { since } H_{A} \text { and } H \text { are symmetric with respect to }(BC) \\
& =\mathcal{S}_{AC}\left(B_{1} H\right) \\
& =\left(H_{B} B_{1}\right) \text { since } H \text { and } H_{B} \text { are symmetric with respect to }(AC) .
\end{aligned}
$$
Let $(XY, ZW)$ denote the angle formed by the lines $XY$ and $ZW$. From Proposition 1, we deduce that $(H_{A} A_{1})$ and $(H_{B} B_{1})$ are images of each other by the rotation of angle $2 \cdot(CB, CA)$ centered at $C: (S H_{A}, S H_{B})=2 \cdot(CB, CA)$. Thus,
$$
\begin{aligned}
\left(S H_{A}, S H_{B}\right) & \equiv 2 \cdot(CB, CA) \\
& \equiv(CB, CA)+(CB, CH)+(CH, CA) \\
& \equiv(CB, CA)+\left(CH_{A}, CB\right)+\frac{\pi}{2}-(AC, AB) \\
& \equiv\left(CH_{A}, CA\right)+(BA, BH) \\
& \equiv\left(BH_{A}, BA\right)+\left(BA, BH_{B}\right) \\
& \equiv\left(BH_{A}, BH_{B}\right)[\pi]
\end{aligned}
$$
Thus, $S \in \Gamma$.
Lemma 4. The circles with diameters $[A_{1} A_{2}],[B_{1} B_{2}],[C_{1} C_{2}]$ are concurrent at a point $M$ belonging to $\Gamma$.
Proof. Let $M^{\prime}$ be the intersection point of the circles with diameters $[A_{1} A_{2}]$ (which therefore pass through $H$ and $H_{A}$) and $[B_{1} B_{2}]$ (which therefore pass through $H$ and $H_{B}$) different from $H$. We have:
$$
\begin{aligned}
\left(M^{\prime} H_{A}, M^{\prime} H_{B}\right) & \equiv\left(M^{\prime} H_{A}, M^{\prime} H\right)+\left(M^{\prime} H, M^{\prime} H_{B}\right) \\
& \equiv\left(A_{1} H_{A}, A_{1} H\right)+\left(B_{1} H, B_{1} H_{B}\right) \\
& \equiv 2 \cdot\left(A_{1} B, A_{1} H\right)+2 \cdot\left(B_{1} H, B_{1} A\right) \\
& \equiv 2 \cdot\left(\frac{\pi}{2}+\left(H H_{A}, H A_{1}\right)\right)+2 \cdot\left(H B_{2}, H H_{B}\right) \\
& \equiv 2 \cdot\left(H H_{A}, H A_{1}\right)+2 \cdot \frac{\pi}{2}+2 \cdot\left(H B_{2}, H H_{B}\right) \\
& \equiv 2 \cdot\left(H H_{A}, H H_{B}\right) \\
& \equiv 2 \cdot(CB, CA) \\
& \equiv\left(S H_{A}, S H_{B}\right)[\pi] .
\end{aligned}
$$
Thus, $M^{\prime} \in \Gamma$ by the inscribed angle theorem. Similarly, we show that the intersection of the circles with diameters $[B_{1} B_{2}]$ and $[C_{1} C_{2}]$ is a point $M^{\prime \prime} \in \Gamma$. Since the intersection of the circle with diameter $[B_{1} B_{2}]$ and $\Gamma$ is unique, we deduce that $M^{\prime}=M^{\prime \prime}=M$, that is, the four circles are concurrent at $M$.
We can now complete the exercise:
$$
\begin{aligned}
\left(C_{1} M, C_{1} C_{2}\right) & \equiv\left(H M, H C_{2}\right) \text { since } M, C_{1}, H, C_{2} \text { are concyclic } \\
& \equiv\left(H M, H B_{2}\right) \\
& \equiv\left(B_{1} M, B_{1} B_{2}\right)[\pi] \text { since } M, B_{1}, H, B_{2} \text { are concyclic. }
\end{aligned}
$$
Similarly, we prove that $\left(B_{1} M, B_{1} B_{2}\right) \equiv\left(C_{1} M, C_{1} C_{2}\right)$. Therefore, since $\left(M A_{1}, M A_{2}\right) \equiv$ $\left(M B_{1}, M C_{2}\right) \equiv\left(M C_{1}, M C_{2}\right) \equiv \frac{\pi}{2} \quad[\pi]$, we obtain that $M A_{1} A_{2}, M B_{1} B_{2}$, and $M C_{1} C_{2}$ are directly similar, which we will denote as $M A_{1} A_{2} \sim M B_{1} B_{2} \sim M C_{1} C_{2}$. Furthermore, $A_{1} A_{2} A_{3} \sim$ $B_{1} B_{2} B_{3} \sim C_{1} C_{2} C_{3}$ by hypothesis. Therefore, $M A_{1} A_{2} A_{3} \sim M B_{1} B_{2} B_{3} \sim M C_{1} C_{2} C_{3}$.
The use of direct similarities then allows us to conclude directly: a direct similarity $\mathcal{S}$ centered at $M$ sends $A_{1}$ to $A_{3}$, and also $B_{1}$ to $B_{3}$ and $C_{1}$ to $C_{3}$. Since $A_{1}, B_{1}$, and $C_{1}$ are collinear, we deduce that $A_{3}, B_{3}$, and $C_{3}$ are collinear as well.
$\mathcal{F i n}$
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit ABC un triangle d'orthocentre H. Soient $\left(d_{1}\right)$ et $\left(d_{2}\right)$ deux droites perpendiculaires se coupant en $H$. Soit $A_{1}$ (respectivement $B_{1}, C_{1}$ ) l'intersection de $\left(d_{1}\right)$ avec $(B C)$ (respectivement $(C A),(A B)$ ). Soit $A_{2}$ (respectivement $B_{2}, C_{2}$ ) l'intersection de $\left(d_{2}\right)$ avec $(B C)$ (respectivement $(C A)$, $(A B)$ ). Soient $A_{3}, B_{3}, C_{3}$ des points dans le plan tels que $A_{1} A_{2} A_{3}, B_{1} B_{2} B_{3}, C_{1} C_{2} C_{3}$ soient des triangles directement semblables.
Montrer que $A_{3}, B_{3}, C_{3}$ sont alignés.

|
Nous donnons une preuve avec des similitudes directes. Il existe d'autres preuves, un peu plus courtes, qui utilisent des nombres complexes.
Rappelons tout d'abord le résultat suivant :
Lemme 2. Soit $A B C$ un triangle, $\Gamma$ son cercle circonscrit et $H$ son orthocentre. Alors les symétriques $H_{A}, H_{B}$ et $H_{C}$ de H par rapport à $(\mathrm{BC}),(\mathrm{CA})$ et $(\mathrm{AB})$ appartiennent à $\Gamma$.
Proof. Soit $H_{A}^{\prime}$ l'intersection de $A H$ et $\Gamma$. Par le théorème de l'angle inscrit, on a :
$$
\begin{aligned}
\widehat{H_{A}^{\prime} B C} & =\widehat{H_{A}^{\prime} A C} \\
& =90-\widehat{B C A} \\
& =\widehat{H B C}
\end{aligned}
$$
Ainsi, $\left(H_{A}^{\prime} B\right)$ et $(H B)$ sont symétriques par rapport à $(B C)$. On en déduit que $H_{A}^{\prime}=H_{A} \in \Gamma$. De même $H_{B}, H_{C} \in \Gamma$.
Reprenons les notations de l'exercice et introduisons $H_{A}, H_{B}$ et $H_{C}$ comme dans le lemme précédent.
Lemme 3. Soit S l'intersection de $\left(A_{1} H_{A}\right)$ et de $\left(B_{1} H_{B}\right)$. Alors $S \in \Gamma$.
Proof. On note $\mathcal{S}_{y z}$ la symétrie d'axe $(Y Z)$. Alors
$$
\begin{aligned}
\mathcal{S}_{\mathcal{A C}}\left(\mathcal{S}_{\mathcal{B C}}\left(H_{A} A_{1}\right)\right) & =\mathcal{S}_{\mathcal{A C}}\left(A_{1} H\right) \text { car } H_{A} \text { et } H \text { sont symétriques par rapport à }(B C) \\
& =\mathcal{S}_{\mathcal{A C}}\left(B_{1} H\right) \\
& =\left(H_{B} B_{1}\right) \text { car } H \text { et } H_{B} \text { sont symétriques par rapport à }(A C) .
\end{aligned}
$$
Notons ( $\mathrm{XY}, \mathrm{ZW}$ ) l'angle de droite formé par les droites XY et ZW . De la proposition 1, on déduit que $\left(H_{A} A_{1}\right)$ et $\left(H_{B} B_{1}\right)$ sont images l'une de l'autre par la rotation d'angle $2 \cdot(C B, C A)$ de centre $C:\left(S H_{A}, S H_{B}\right)=2 \cdot(C B, C A)$. Ainsi,
$$
\begin{aligned}
\left(S H_{A}, S H_{B}\right) & \equiv 2 \cdot(C B, C A) \\
& \equiv(C B, C A)+(C B, C H)+(C H, C A) \\
& \equiv(C B, C A)+\left(C H_{A}, C B\right)+\frac{\pi}{2}-(A C, A B) \\
& \equiv\left(C H_{A}, C A\right)+(B A, B H) \\
& \equiv\left(B H_{A}, B A\right)+\left(B A, B H_{B}\right) \\
& \equiv\left(B H_{A}, B H_{B}\right)[\pi]
\end{aligned}
$$
Ainsi, $S \in \Gamma$.
Lemme 4. Les cercles de diamètre $\left[A_{1} A_{2}\right],\left[B_{1} B_{2}\right],\left[C_{1} C_{2}\right]$ sont concourants en un point $M$ appartenant à $\Gamma$.
Proof. Soit $M^{\prime}$ le point d'intersection des cercles de diamètre $\left[A_{1} A_{2}\right]$ (passant donc par $H$ et $H_{A}$ ) et $\left[B_{1} B_{2}\right]$ (passant donc par $H$ et $H_{B}$ ) différent de $H$. On a :
$$
\begin{aligned}
\left(M^{\prime} H_{A}, M^{\prime} H_{B}\right) & \equiv\left(M^{\prime} H_{A}, M^{\prime} H\right)+\left(M^{\prime} H, M^{\prime} H_{B}\right) \\
& \equiv\left(A_{1} H_{A}, A_{1} H\right)+\left(B_{1} H, B_{1} H_{B}\right) \\
& \equiv 2 \cdot\left(A_{1} B, A_{1} H\right)+2 \cdot\left(B_{1} H, B_{1} A\right) \\
& \equiv 2 \cdot\left(\frac{\pi}{2}+\left(H H_{A}, H A_{1}\right)\right)+2 \cdot\left(H B_{2}, H H_{B}\right) \\
& \equiv 2 \cdot\left(H H_{A}, H A_{1}\right)+2 \cdot \frac{\pi}{2}+2 \cdot\left(H B_{2}, H H_{B}\right) \\
& \equiv 2 \cdot\left(H H_{A}, H H_{B}\right) \\
& \equiv 2 \cdot(C B, C A) \\
& \equiv\left(S H_{A}, S H_{B}\right)[\pi] .
\end{aligned}
$$
Ainsi, $M^{\prime} \in \Gamma$ par le théorème de l'angle inscrit. De la même façon, on montre que l'intersection des cercles de diamètre $\left[B_{1} B_{2}\right]$ et $\left[C_{1} C_{2}\right]$ est un point $M^{\prime \prime} \in \Gamma$. Comme l'intersection du cercle de diamètre $\left[B_{1} B_{2}\right]$ et de $\Gamma$ est unique, on en déduit que $M^{\prime}=M^{\prime \prime}=M$, c'est-à-dire que les quatre cercles sont concourants en $M$.
Nous pouvouns maintenant terminer l'exercice :
$$
\begin{aligned}
\left(C_{1} M, C_{1} C_{2}\right) & \equiv\left(H M, H C_{2}\right) \text { car } M, C_{1}, H, C_{2} \text { sont cocycliques } \\
& \equiv\left(H M, H B_{2}\right) \\
& \equiv\left(B_{1} M, B_{1} B_{2}\right)[\pi] \text { car } M, B_{1}, H, B_{2} \text { cocycliques. }
\end{aligned}
$$
De la même façon, on prouve que $\left(B_{1} M, B_{1} B_{2}\right) \equiv\left(C_{1} M, C_{1} C_{2}\right)$. Donc, comme $\left(M A_{1}, M A_{2}\right) \equiv$ $\left(M B_{1}, M C_{2}\right) \equiv\left(M C_{1}, M C_{2}\right) \equiv \frac{\pi}{2} \quad[\pi]$, on obtient que $M A_{1} A_{2}, M B_{1} B_{2}$ et $M C_{1} C_{2}$ sont directement semblables, ce que l'on notera désormais $M A_{1} A_{2} \sim M B_{1} B_{2} \sim M C_{1} C_{2}$. En outre, $A_{1} A_{2} A_{3} \sim$ $B_{1} B_{2} B_{3} \sim C_{1} C_{2} C_{3}$ par hypothèse. Donc $M A_{1} A_{2} A_{3} \sim M B_{1} B_{2} B_{3} \sim M C_{1} C_{2} C_{3}$.
L'utilisation de similitudes directes permet alors de conclure directement : une similitude directe $\mathcal{S}$ de centre $M$ envoie $A_{1}$ sur $A_{3}$, et également $B_{1}$ sur $B_{3}$ et $C_{1}$ sur $C_{3}$. Comme $A_{1}, B_{1}$ et $C_{1}$ sont alignés, on en déduit que $A_{3}, B_{3}$ et $C_{3}$ le sont également.
$\mathcal{F i n}$
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-3-solutions.jsonl",
"problem_match": "\nExercice 9.",
"solution_match": "\nSolution de l'exercice 9"
}
|
9decc747-717b-5596-97f0-b77db51f08e5
| 607,672
|
We place four points in the plane, with no three points ever aligned, and connect each pair of points. We color each of the six segments obtained either blue or red. Show that there exist two different triangles that are colored in the same way. For example, in the following example (where red is replaced by thick and blue by dashed), ABD and ACD are colored in the same way.

|
There are four different ways to color a triangle (with zero, one, two, or three red segments) and there are four triangles drawn. Therefore, either two triangles are colored the same way, or all the triangles are different. Let's show that the second case is not possible. Indeed, two different triangles always share two vertices in common, and thus one side in common. However, if all the triangles are different, there is one triangle that is entirely blue, and another that is entirely red. Their common side would then be both red and blue, which is impossible. Ultimately, we do have two triangles colored the same way.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
On place quatre points dans le plan, trois jamais alignés, et on les relie tous deux à deux. On colorie chacun des six segments obtenus soit en bleu soit en rouge. Montrer qu'il existe deux triangles différents coloriés de la même façon. Par exemple, dans l'exemple suivant (où l'on a remplacé rouge par épais et bleu par pointillé), ABD et ACD sont coloriés de la même façon.

|
Il y a quatre façons différentes de colorier un triangle (avec zéro, un, deux ou trois segments rouges) et il y a quatre triangles dessinés. Donc, soit deux triangles sont coloriés de la même façon, soit tous les triangles sont différents. Montrons que le deuxième cas n'est pas possible. En effet, deux triangles différents partagent toujours deux sommets en commun, donc un côté en commun. Or, si tous les triangles sont différents, il y a un triangle entièrement bleu, et un autre entièrement rouge. Leur côté commun serait alors à la fois rouge et bleu, impossible. Finalement, on a bien deux triangles coloriés de la même façon.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 1.",
"solution_match": "## Solution de l'exercice 1"
}
|
0955073c-2c83-59fd-ad38-7fe99754e900
| 607,673
|
Let $A_{1}, A_{2}, \ldots, A_{m}$ be distinct subsets of $\{1,2, \ldots, n\}$ such that for all $1 \leqslant$ $\mathbf{i}, \mathbf{j} \leqslant \mathrm{n}$ we have $A_{i} \cap A_{j} \neq \emptyset$. Show $m \leqslant 2^{n-1}$.
|
Consider all pairs of sets $\left\{A, A^{c}\right\}$ for all $A \subset\{1,2, \ldots, n\}$. Since there are $2^{n-1}$ such pairs, if $m>2^{n-1}$ there would be $1 \leqslant i<j \leqslant m$ such that $A_{i}, A_{j} \in\left\{A, A^{c}\right\}$ for some $A \subset\{1,2, \ldots, n\}$. Therefore, $A_{i} \cap A_{j}=\emptyset$ which contradicts our assumption.
## Common Exercises
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Soient $A_{1}, A_{2}, \ldots, A_{m}$ des sous-ensembles distincts de $\{1,2, \ldots, n\}$ tels que pour tout $1 \leqslant$ $\boldsymbol{i}, \mathbf{j} \leqslant \mathrm{n}$ on a $A_{i} \cap A_{j} \neq \emptyset$. Montrer $m \leqslant 2^{n-1}$.
|
Considérons toutes les paires d'ensembles $\left\{A, A^{c}\right\}$ pour tout $A \subset\{1,2, \ldots, n\}$. Puisqu'il y a $2^{n-1}$ telles paires, si $m>2^{n-1}$ on aurait $1 \leqslant i<j \leqslant m$ tels que $A_{i}, A_{j} \in\left\{A, A^{c}\right\}$ pour un $A \subset\{1,2, \ldots, n\}$. Donc $A_{i} \cap A_{j}=\emptyset$ ce qui contredit notre hypothèse.
## Exercices communs
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-4-solutions.jsonl",
"problem_match": "\nExercice 3.",
"solution_match": "## Solution de l'exercice 3"
}
|
1299cc8b-96ff-5b0d-be82-2e9f4eeb809d
| 607,675
|
A toy manufacturer creates at least one toy per day. They are not capable of creating more than 725 toys per year. For any $\mathrm{n} \in \mathbb{N}$, show that there exist consecutive days during which they created exactly n toys.
|
Let $x_{i} \in \mathbb{N}$ be the number of toys created on the $i-$th day. If
$$
\mathrm{x}_{1}+\mathrm{x}_{2}+\ldots+\mathrm{x}_{\mathrm{n}}<2 \mathrm{n}
$$
consider the following numbers:
$$
1 \leqslant x_{1}<x_{1}+x_{2}<\ldots<x_{1}+x_{2}+\ldots+x_{n}<2 n .
$$
We have two cases. Either they represent all residues modulo $n$, or there exist $1 \leqslant i<j \leqslant n$ such that
$$
x_{1}+x_{2}+\ldots+x_{i} \equiv x_{1}+x_{2}+\ldots+x_{j} \quad(\bmod n)
$$
The latter case gives us
$$
\mathrm{n} \mid \mathrm{x}_{\mathrm{i}+1}+\ldots+\mathrm{x}_{\mathrm{j}}
$$
and thus
$$
x_{i+1}+\ldots+x_{j}=n
$$
In the first case, there exists $1 \leqslant \mathfrak{j} \leqslant n$ such that
$$
\mathrm{n} \mid \mathrm{x}_{1}+\mathrm{x}_{2}+\ldots+\mathrm{x}_{\mathrm{j}}
$$
so
$$
\mathrm{x}_{1}+\mathrm{x}_{2}+\ldots+\mathrm{x}_{\mathrm{j}}=\mathrm{n}
$$
In both cases, the problem is solved. Now consider what happens if, for any $n$ consecutive days, the total number of toys is greater than $2 n$. Then
$$
2 \mathrm{n} \times 365 \leqslant \sum_{i=1}^{365 n} x_{i} \leqslant 725 n
$$
we reach a contradiction.
## Exercises of group $\mathcal{A}$
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Un constructeur de jouets crée au moins un jouet par jour. Il n'est pas capable de créer plus de 725 jouets par an. Pour tout $\mathrm{n} \in \mathbb{N}$, montrer qu'il existe des jours consécutifs pendant lesquels il a créé exactement n jouets.
|
Soit $x_{i} \in \mathbb{N}$ le nombre de jouets qu'il a crée pendant le $i-$ ème jour. Si
$$
\mathrm{x}_{1}+\mathrm{x}_{2}+\ldots+\mathrm{x}_{\mathrm{n}}<2 \mathrm{n}
$$
étudions les nombres suivants :
$$
1 \leqslant x_{1}<x_{1}+x_{2}<\ldots<x_{1}+x_{2}+\ldots+x_{n}<2 n .
$$
On a deux cas. Soit ils représentent tous les résidus modulo $n$, soit il existe $1 \leqslant i<j \leqslant n$ tels que
$$
x_{1}+x_{2}+\ldots+x_{i} \equiv x_{1}+x_{2}+\ldots+x_{j} \quad(\bmod n)
$$
Ce dernier cas nous donne
$$
\mathrm{n} \mid \mathrm{x}_{\mathrm{i}+1}+\ldots+\mathrm{x}_{\mathrm{j}}
$$
puis
$$
x_{i+1}+\ldots+x_{j}=n
$$
Dans le premier cas, il existe $1 \leqslant \mathfrak{j} \leqslant n$ tel que
$$
\mathrm{n} \mid \mathrm{x}_{1}+\mathrm{x}_{2}+\ldots+\mathrm{x}_{\mathrm{j}}
$$
donc
$$
\mathrm{x}_{1}+\mathrm{x}_{2}+\ldots+\mathrm{x}_{\mathrm{j}}=\mathrm{n}
$$
Dans les deux cas, le problème est résolu. Étudions maintenant ce qui se passe si, pour tous n jours consécutifs, le nombre total de jouets est plus grand que 2 n . Alors
$$
2 \mathrm{n} \times 365 \leqslant \sum_{i=1}^{365 n} x_{i} \leqslant 725 n
$$
on aboutit à une contradiction.
## Exercices dugroupe $\mathcal{A}$
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 7.",
"solution_match": "## Solution de l'exercice 7"
}
|
c54aa952-0293-587f-b03a-73afd1464f39
| 607,679
|
Let $n$ be a positive integer. Show that in a set $A$ of $2^{n}$ strictly positive numbers, one can choose a subset $B$ of size $n+1$ such that the sum of any two different numbers in $B$ is never in $A$.
|
Let $n$ and $A$ be as in the statement. We will show, by induction on $m \leqslant n+1$, that the greedy algorithm consisting of always taking the largest number that does not cause a problem works.
Set $A_{0}=A$, and $B_{0}=B$. Suppose that, for $m<n+1$, we have constructed $A_{m}$ and $B_{m}$, subsets of $A$ such that:
1. the sum of two different elements of $B_{m}$ is never in $A$,
2. the sum of an element of $A_{m}$ and an element of $B_{m}$ is never in $A$,
3. $A_{m}$ and $B_{m}$ are disjoint,
4. $\operatorname{card}\left(A_{m}\right) \geqslant 2^{n}-2^{m}+1$ and
5. $\operatorname{card}\left(B_{m}\right)=m$.
In this case, $A_{m}$ is non-empty because $m \leqslant n$ so $2^{n}-2^{m}+1 \geqslant 1$. Let $b_{m+1}$ be the largest element of $A_{m}$. We set $B_{m+1}=B_{m} \cup\left\{b_{m+1}\right\}$. By hypothesis 3 for order $m$, we obtain 5 for order $m+1$. Similarly, hypotheses 1 and 2 give us 1 for the higher order. Now, we set
$$
A_{m+1}=\left\{a \in A_{m} \mid a \neq b_{m+1} \text { and } a+b_{m+1} \notin A\right\} .
$$
By definition, and by hypothesis 2, $A_{m+1}$ satisfies 2 and 3. The only less obvious point is 4. We want to show that $\operatorname{card}\left(A_{m}\right)-\operatorname{card}\left(A_{m+1}\right) \leqslant 2^{m}$. Now,
$$
\begin{aligned}
A_{\mathfrak{m}} \backslash A_{\mathfrak{m}+1} & =\left\{\mathbf{b}_{\mathfrak{m}+1}\right\} \cup\left\{a \in A_{\mathfrak{m}} \mid a+b_{\mathfrak{m}+1} \in A\right\} \\
& \subset\left\{b_{\mathfrak{m}+1}\right\} \cup\left\{a \in A \mid a>b_{\mathfrak{m}+1}\right\} \\
& \subset\left\{\mathbf{b}_{\mathfrak{m}+1}\right\} \cup\left(A \backslash A_{\mathfrak{m}}\right) .
\end{aligned}
$$
The latter set has size at most $1+\left(2^{n}-\left(2^{n}-2^{m}+1\right)\right)=2^{m}$. Therefore, $\operatorname{card}\left(A_{m}\right)-$ $\operatorname{card}\left(A_{m+1}\right) \leqslant 2^{m}$, and we obtain 4 at order $m+1$. This concludes the induction.
Now, we apply the induction up to $m=n+1$ and we obtain a set $B_{n+1}$ of size $n+1$ that satisfies hypothesis 1, and is thus a solution to the exercise.
|
proof
|
Yes
|
Yes
|
proof
|
Combinatorics
|
Soit $n$ un entier positif. Montrer que dans un ensemble $A$ de $2^{n}$ nombres strictement positifs, on peut choisir un sous-ensemble B de taille $n+1$ tel que la somme de deux nombres différents dans $B$ ne soit jamais dans $A$.
|
Soient $n$ et $A$ comme dans l'énoncé. Nous allons montrer, par récurrence sur $m \leqslant n+1$, que l'algorithme glouton consistant à toujours prendre le plus grand nombre qui ne pose pas de problème convient.
Posons $A_{0}=A$, et $B_{0}=B$. Supposons que, pour $m<n+1$, on a construit $A_{m}$ et $B_{m}$ des sous-ensembles de $A$ tels que :
1. la somme de deux éléments différents de $B_{m}$ ne soit jamais dans $A$,
2. la somme d'un élément de $A_{m}$ et d'un élément de $B_{m}$ ne soit jamais dans $A$,
3. $A_{m}$ et $B_{m}$ sont disjoints,
4. $\operatorname{card}\left(A_{m}\right) \geqslant 2^{n}-2^{m}+1$ et
5. $\operatorname{card}\left(B_{m}\right)=m$.
Dans ce cas, $A_{m}$ est non vide car $m \leqslant n$ donc $2^{n}-2^{m}+1 \geqslant 1$. Soit $b_{m+1}$ le plus grand élément de $A_{m}$. On pose $B_{m+1}=B_{m} \cup\left\{b_{m+1}\right\}$. Par l'hypothèse 3 pour l'ordre $m$, on obtient 5 pour l'ordre $m+1$. De même, les hypothèses 1 et 2 nous donne 1 pour l'ordre supérieur. Maintenant, on pose
$$
A_{m+1}=\left\{a \in A_{m} \mid a \neq b_{m+1} \text { et } a+b_{m+1} \notin A\right\} .
$$
Par définition, et par l'hypothèse $2, A_{m+1}$ vérifie 2 et 3 . Le seul point moins évident est 4 . Nous voulons montrer que $\operatorname{card}\left(A_{m}\right)-\operatorname{card}\left(A_{m+1}\right) \leqslant 2^{m}$. Or,
$$
\begin{aligned}
A_{\mathfrak{m}} \backslash A_{\mathfrak{m}+1} & =\left\{\mathbf{b}_{\mathfrak{m}+1}\right\} \cup\left\{a \in A_{\mathfrak{m}} \mid a+b_{\mathfrak{m}+1} \in A\right\} \\
& \subset\left\{b_{\mathfrak{m}+1}\right\} \cup\left\{a \in A \mid a>b_{\mathfrak{m}+1}\right\} \\
& \subset\left\{\mathbf{b}_{\mathfrak{m}+1}\right\} \cup\left(A \backslash A_{\mathfrak{m}}\right) .
\end{aligned}
$$
Or ce dernier ensemble est de taille au plus $1+\left(2^{n}-\left(2^{n}-2^{m}+1\right)\right)=2^{m}$. Donc, $\operatorname{card}\left(A_{m}\right)-$ $\operatorname{card}\left(A_{m+1}\right) \leqslant 2^{m}$, puis on obtient 4 à l'ordre $m+1$. Ce qui conclut la récurrence.
Maintenant, on applique la récurrence jusqu'à $m=n+1$ et on obtient un ensemble $B_{n+1}$ de taille $n+1$ qui vérifie l'hypothèse 1 , donc qui est bien solution de l'exercice.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 9.",
"solution_match": "## Solution de l'exercice 9"
}
|
b219c537-2aa3-5820-8da3-fd4dfe1ad9b4
| 607,681
|
We have an infinite list of cells, the cells being numbered by $1, 2, \ldots$. Initially, all cells contain the number 1. At each step, we choose a number $a \in \mathbb{N}^{*}$ such that:
- either all the cells numbered by a multiple of $a$ contain 1, in which case we replace these 1s with 0s,
- or all the cells numbered by a multiple of $a$ contain 0, in which case we replace these 0s with 1s.
Show that, for all $n \geqslant 2$, we can ensure that all the cells numbered at most $n$ contain a 0 except the first cell which contains a 1.
|
We will first rephrase the problem. We are working in $\mathbb{N}^{*}$. If $A$, $B$ are two sets (in $\mathbb{N}^{*}$), we denote
- $A \oplus B:=A \cup B$ if $A \cap B=\emptyset$, otherwise the operation is forbidden, and
- $A \ominus B:=A \backslash B$ if $B \subset A$, otherwise the operation is forbidden.
We add the convention that $\oplus$ and $\ominus$ are left-associative, meaning operations are performed from left to right. For example, $\{1\} \oplus\{2\} \ominus\{1,2\}=(\{1\} \oplus \{2\}) \ominus\{1,2\}=\emptyset$, whereas $\{1\} \oplus\{1,2\} \ominus\{1\}$ is forbidden.
The problem can thus be restated as: for $n \in \mathbb{N}^{*}$, there exists a formula starting with $\mathbb{N}^{*}$, containing only sets of multiples of integers and using the operations $\oplus$ and $\ominus$ that results in a set $E$ such that $E \cap\{1, \ldots, \mathbf{n}\}=\{1\}$. To prove this, we will use a lemma, which we will prove later, and which is nothing more than an improved variant of the principle of inclusion-exclusion.
Lemma: If $m \in \mathbb{N}^{*}$ and $A_{1}, \ldots, A_{m}$ are sets, then there exists a formula using the operations $\oplus$ and $\ominus$ and consisting only of arbitrary intersections of the sets $A_{1}, \ldots, A_{m}$ whose value is $A_{1} \cup \cdots \cup A_{m}$.
For example, in the case $m=2, A_{1} \cup A_{2}=A_{1} \ominus\left(A_{1} \cap A_{2}\right) \oplus A_{2}$.
Now, let $\mathrm{p}_{1}, \mathrm{p}_{2}, \ldots$ be the prime numbers in order. Let $A_{i}$ be the set of multiples (strictly positive) of $p_{i}$, for all $i \in \mathbb{N}^{*}$. Take $n \geqslant 2$ and let $m$ be the number of prime numbers less than or equal to $n$. According to the lemma, there exists a formula whose value is $A_{1} \cup \cdots \cup A_{m}$. This union is the set of numbers that are multiples of at least one number among $p_{1}, p_{2}, \ldots$ and $p_{m}$. It therefore contains all numbers less than or equal to $n$ except 1. By replacing the $\oplus$ with $\ominus$ and vice versa in the formula and adding $\mathbb{N}^{*} \ominus$ in front, we obtain an authorized formula whose value satisfies what we want. It remains to add that, if $1 \leqslant \mathrm{l} \leqslant \mathrm{m}$ and if $1 \leqslant \mathfrak{i}_{1}<\mathfrak{i}_{2}<\cdots<\mathfrak{i}_{l} \leqslant \mathfrak{m}$, then $A_{i_{1}} \cap A_{i_{2}} \cap \cdots \cap A_{i_{l}}$ is nothing other than the set of multiples of $p_{i_{1}} p_{i_{2}} \ldots p_{i_{l}}$. Therefore, the formula we have obtained consists only of sets of multiples of integers and thus is suitable.
Now let's prove the lemma by induction on $m$. The case $m=1$ is trivial. Moreover, we have treated the case $m=2$ above as an example. Let $m \geqslant 2$ and suppose the theorem is true for $m$ sets. Let $A_{1}, \ldots, A_{m+1}$ be $m+1$ sets. We have
\[
\begin{aligned}
& A_{1} \cup \cdots \cup A_{m+1}=A_{1} \cup \cdots \cup A_{m} \ominus\left(\left(A_{1} \cup \cdots \cup A_{m}\right) \cap A_{m+1}\right) \oplus A_{m+1} \\
& A_{1} \cup \cdots \cup A_{m+1}=A_{1} \cup \cdots \cup A_{m} \ominus\left(\left(A_{1} \cap A_{m+1}\right) \cup \cdots \cup\left(A_{m} \cap A_{m+1}\right)\right) \oplus A_{m+1}
\end{aligned}
\]
By the induction hypothesis, there exists a formula for the second term consisting only of arbitrary intersections of $A_{1} \cap A_{m+1}, \ldots, A_{m} \cap A_{m+1}$; thus, only of arbitrary intersections of $A_{1}, \ldots, A_{m+1}$. Now, we can insert the formula for the second term into the large formula by replacing, in the formula for the second term, the $\oplus$ with $\ominus$ and vice versa. By directly replacing the first term with the formula obtained by the induction hypothesis, we get the desired formula.
We conclude the proof of the lemma by induction.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
On possède une liste infinie de cases, les cases étant numérotées par $1,2, \ldots$. Au départ, toutes les cases contiennent le nombre 1 . À chaque étape, on choisit un nombre $a \in \mathbb{N}^{*}$ tel que:
- soit toutes les cases numérotées par un multiple de a contiennent 1 auquel cas on remplace ces 1 par des 0 ,
- soit toutes les cases numérotées par un multiple de a contiennent 0 auquel cas on remplace ces 0 par des 1 .
Montrer que, pour tout $n \geqslant 2$, on peut faire en sorte que toutes les cases de numéro au plus n contiennent un 0 sauf la première case qui contient un 1.
|
Nous allons d'abord reformuler le problème. On se place dans $\mathbb{N}^{*}$. Si $A$, B sont deux ensembles (dans $\mathbb{N}^{*}$ ), on note
- $A \oplus B:=A \cup B$ si $A \cap B=\emptyset$, sinon l'opération est interdite, et
- $A \ominus B:=A \backslash B$ si $B \subset A$, sinon l'opération est interdite.
On ajoute la convention que $\oplus$ et $\ominus$ sont associatives à gauche, c'est-à-dire que les opérations sont effectuées de la gauche vers la droite. Par exemple, $\{1\} \oplus\{2\} \ominus\{1,2\}=(\{1\} \oplus$ $\{2\}) \ominus\{1,2\}=\emptyset$, par contre $\{1\} \oplus\{1,2\} \ominus\{1\}$ est interdit.
Le problème se reformule donc par : montrer que, pour $n \in \mathbb{N}^{*}$, il existe une formule commençant par $\mathbb{N}^{*}$, contenant que des ensembles de multiples d'entiers et utilisant les opérations $\oplus$ et $\ominus$ aboutissant à un ensemble $E$ tel que $E \cap\{1, \ldots, \mathbf{n}\}=\{1\}$. Pour montrer cela, nous allons utiliser un lemme, que nous démontrerons plus tard, et qui n'est rien d'autre qu'une variante améliorée du principe d'inclusion-exclusion.
Lemme: Si $m \in \mathbb{N}^{*}$ et $A_{1}, \ldots, A_{m}$ sont des ensembles, alors il existe une formule utilisant les opérations $\oplus$ et $\ominus$ et constituée uniquement d'intersections quelconques des ensembles $A_{1}, \ldots, A_{m}$ dont la valeur est $A_{1} \cup \cdots \cup A_{m}$.
Par exemple, dans le cas $m=2, A_{1} \cup A_{2}=A_{1} \ominus\left(A_{1} \cap A_{2}\right) \oplus A_{2}$.
Maintenant, notons $\mathrm{p}_{1}, \mathrm{p}_{2}, \ldots$ les nombres premiers dans l'ordre. Notons $A_{i}$ l'ensemble des multiples (strictement positifs) de $p_{i}$, pour tout $i \in \mathbb{N}^{*}$. Prenons $n \geqslant 2$ et soit $m$ le nombre de nombres premiers inférieurs ou égaux à $n$. D'après le lemme, il existe une formule dont la valeur est $A_{1} \cup \cdots \cup A_{m}$. Or cette union est l'ensemble des nombres qui sont multiples d'au moins un nombre parmi $p_{1}, p_{2}, \ldots$ et $p_{m}$. Il contient donc tous les nombres inférieurs ou égaux à $n$ sauf 1 . En remplaçant les $\oplus$ par des $\ominus$ et vice-versa dans la formule et en ajoutant $\mathbb{N}^{*} \ominus$ devant, nous obtenons donc une formule autorisée dont la valeur vérifie ce que nous voulons. Il reste à ajouter pour conclure que, si $1 \leqslant \mathrm{l} \leqslant \mathrm{m}$ et si $1 \leqslant \mathfrak{i}_{1}<\mathfrak{i}_{2}<\cdots<\mathfrak{i}_{l} \leqslant \mathfrak{m}$, alors $A_{i_{1}} \cap A_{i_{2}} \cap \cdots \cap A_{i_{l}} n^{\prime}$ est rien d'autre que l'ensemble des multiples de $p_{i_{1}} p_{i_{2}} \ldots p_{i_{l}}$. Donc la formule que l'on a obtenue n'est constituée que d'ensembles de multiples d'entier et donc convient.
Montrons maintenant le lemme par récurrence sur $m$. Le cas $m=1$ est trivial. De plus, nous avons traité le cas $m=2$, pour l'exemple, ci-dessus. Soit $m \geqslant 2$ et supposons le théorème vrai pour $m$ ensembles. Soient $A_{1}, \ldots, A_{m+1} m+1$ ensembles. On a
$$
\begin{aligned}
& A_{1} \cup \cdots \cup A_{m+1}=A_{1} \cup \cdots \cup A_{m} \ominus\left(\left(A_{1} \cup \cdots \cup A_{m}\right) \cap A_{m+1}\right) \oplus A_{m+1} \\
& A_{1} \cup \cdots \cup A_{m+1}=A_{1} \cup \cdots \cup A_{m} \ominus\left(\left(A_{1} \cap A_{m+1}\right) \cup \cdots \cup\left(A_{m} \cap A_{m+1}\right)\right) \oplus A_{m+1}
\end{aligned}
$$
Par hypothèse de récurrence, il existe une formule pour le deuxième terme constituée uniquement d'intersections quelconques de $A_{1} \cap A_{m+1}, \ldots, A_{m} \cap A_{m+1}$; donc uniquement d'intersections quelconques de $A_{1}, \ldots, A_{m+1}$. Maintenant, on peut insérer la formule du deuxième terme dans la grosse formule en remplaçant, dans la formule du deuxième terme, les $\oplus$ par des $\ominus$ et vice-versa. En remplaçant directement le premier terme par la formule obtenue par l'hypothèse de récurrence, on obtient la formule voulue.
On conclut la preuve du lemme par récurrence.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-4-solutions.jsonl",
"problem_match": "## Exercice 10.",
"solution_match": "## Solution de l'exercice 10"
}
|
5aebb581-8b2a-5afb-821f-0b2f444c4cca
| 607,682
|
Let $ABC$ be an acute triangle. We denote $O$ as the center of its circumcircle. Consider the circle $\Gamma_{B}$ passing through $A$ and $B$ and tangent to $(AC)$, as well as the circle $\Gamma_{C}$ passing through $A$ and $C$ and tangent to $(AB)$. A line $\Delta$ passing through $A$ intersects $\Gamma_{B}$ at $X$ and $\Gamma_{C}$ at $Y$. Show that $\mathrm{OX}=\mathrm{OY}$.
|
Let $Z$ be the intersection point of the circumcircle of $A B C$ with $\Delta$. By angle chasing, we find that $\widehat{X B A}=\widehat{Z A C}=\widehat{Z B C}$. We deduce that $\widehat{X B Z}=\widehat{A B C}$. Since $\widehat{B C A}=\widehat{B Z A}$, we deduce that triangles $A B C$ and $X B Z$ are similar. Therefore,
$$
\frac{X Z}{A C}=\frac{B Z}{B C} .
$$
Similarly, we show that triangles $C A Y$ and $C B Z$ are similar, so that
$$
\frac{A Y}{B Z}=\frac{A C}{B C}
$$
We deduce that $A Y=X Z$, and then that $A X=Z Y$. This implies that the perpendicular bisectors of segments $[X Y]$ and $[A Z]$ are the same. Therefore, $O$ lies on the perpendicular bisector of $[X Y]$. Therefore, $O X=O Y$.

|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle acutangle. On note O le centre de son cercle circonscrit. On considère le cercle $\Gamma_{B}$ passant par $A$ et $B$ et qui est tangent à ( $A C$ ), ainsi que le cercle $\Gamma_{C}$ passant par $A$ et $C$ qui est tangent à $(A B)$. Une droite $\Delta$ passant par $A$ recoupe $\Gamma_{B}$ en $X$ et $\Gamma_{C}$ en $Y$. Montrer que $\mathrm{OX}=\mathrm{OY}$.
|
Soit $Z$ le point d'intersection du cercle circonscrit de $A B C$ avec $\Delta$. En faisant une chasse aux angles, on trouve que $\widehat{X B A}=\widehat{Z A C}=\widehat{Z B C}$. On en déduit que $\widehat{X B Z}=\widehat{A B C}$. Or, comme $\widehat{B C A}=$ $\widehat{B Z A}$, on en déduit que les triangles $A B C$ et $X B Z$ sont semblables. Donc
$$
\frac{X Z}{A C}=\frac{B Z}{B C} .
$$
On montre de même que les triangles CAY et CBZ sont semblables, de sorte que
$$
\frac{A Y}{B Z}=\frac{A C}{B C}
$$
On en déduit que $A Y=X Z$, puis que $A X=Z Y$. Ceci implique que les médiatrices des segments $[X Y]$ et $[A Z]$ sont les mêmes. Donc $O$ appartient à la médiatrice de $[X Y]$. Donc $O X=O Y$.

|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 2.",
"solution_match": "## Solution de l'exercice 2"
}
|
7b059c7b-dd86-598e-b88e-06c92f720b28
| 607,684
|
Consider a convex quadrilateral ABCD whose diagonals are perpendicular and intersect at $E$. Let $P \in [AD]$ be a point such that $P \neq A$ and $PE = EC$. Suppose that the circumcircle of triangle $BCD$ intersects $[AD]$ at a point $Q$ different from $A$. Let $R$ be the second intersection point of $[AC]$ with the circle passing through $A$ and tangent to $(EP)$ at $P$. Assume that the points $B, R, Q$ are collinear. Show that $\widehat{BCD} = 90^{\circ}$.
|
Introduce $F$, the intersection point of the circumcircle of triangle ARD and the segment [DE]. The power of E with respect to the circle passing through $A, R, F, D$ is $E R \cdot E A = E F \cdot E D$. Furthermore, the power of $E$ with respect to the circle passing through $A, R, P$ is $E R \cdot E A = E P^2 = E C^2$. We deduce that $E D \cdot E F = E C^2$, which shows that the circle passing through $F, C, D$ is tangent to (CE).
We deduce that $\widehat{E C F} = \widehat{\mathrm{EDC}}$. Furthermore, since $A, R, F, D$ are concyclic, we have $\widehat{A D E} = \widehat{\mathrm{ERF}}$. We deduce that $\widehat{\mathrm{QDB}} + \widehat{\mathrm{BDC}} = \widehat{\mathrm{FRC}} + \widehat{\mathrm{RCF}}$, which implies that $\widehat{\mathrm{RBC}} = \widehat{\mathrm{RFC}}$. Since $(B F)$ and $(C R)$ are perpendicular, this implies that $F$ is the reflection of $B$ with respect to the line $(A C)$. It follows that $\widehat{B C R} = \widehat{R C F} = \widehat{\mathrm{BDC}}$. Since $\widehat{\mathrm{BEC}} = 90^{\circ}$, we have $\widehat{\mathrm{ECD}} = 90^{\circ} - \widehat{\mathrm{BCE}}$ and conclude that $\widehat{B C D} = 90^{\circ}$.

|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
On considère un quadrilatère convexe ABCD dont les diagonales sont perpendiculaires et se coupent en $E$. Soit $P \in[A D]$ un point tel que $P \neq A$ et $P E=E C$. On suppose que le cercle circonscrit du triangle $B C D$ recoupe $[A D]$ en un point $Q$ différent de $A$. On note $R$ le deuxième point d'intersection de $[A C]$ avec le cercle passant par $A$ et tangent à (EP) en $P$. On suppose que les points $B, R, Q$ sont alignés. Montrer que $\widehat{B C D}=90^{\circ}$.
|
Introduisons $F$, le point d'intersection du cercle circonscrit du triangle ARD et du segment [DE]. La puissance de E par rapport au cercle passant par $A, R, F, D$ est $E R \cdot E A=E F \cdot E D$. Par ailleurs, la puissance de $E$ par rapport au cercle passant par $A, R, P$ est
$E R \cdot E A=E P^{2}=E C^{2}$. On en déduit que $E D \cdot E F=E C^{2}$, ce qui montre que le cercle passant par $\mathrm{F}, \mathrm{C}, \mathrm{D}$ est tangent à (CE).
On en déduit que $\widehat{E C F}=\widehat{\mathrm{EDC}}$. Par ailleurs, comme $A, R, F, D$ sont cocycliques, on a $\widehat{A D E}=$ $\widehat{\mathrm{ERF}}$. On en déduit que $\widehat{\mathrm{QDB}}+\widehat{\mathrm{BDC}}=\widehat{\mathrm{FRC}}+\widehat{\mathrm{RCF}}$, ce qui implique que $\widehat{\mathrm{RBC}}=\widehat{\mathrm{RFC}}$. Comme $(B F)$ et $(C R)$ sont perpendiculaires, ceci implique que $F$ est le symétrique de $B$ par rapport à la droite ( $A C$ ). Il en découle que $\widehat{B C R}=\widehat{R C F}=\widehat{\mathrm{BDC}}$. Comme $\widehat{\mathrm{BEC}}=90^{\circ}$, on a $\widehat{\mathrm{ECD}}=90^{\circ}-\widehat{\mathrm{BCE}}$ et conclut que $\widehat{B C D}=90^{\circ}$.

|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 6.",
"solution_match": "\nSolution de l'exercice 6"
}
|
20d88251-4ed9-55d8-8677-5220ba8cfbbe
| 607,688
|
Let $ABCD$ be a quadrilateral inscribed in a circle. We denote $\Delta_{1}$ as the line parallel to $(BC)$ passing through $A$ and $\Delta_{2}$ as the line parallel to $(AD)$ passing through $B$. We denote $E$ as the intersection point of $\Delta_{1}$ with $(CD)$ and $F$ as the intersection point of $\Delta_{2}$ with $(CD)$. The line perpendicular to $\Delta_{1}$ passing through $A$ intersects $(BC)$ at $P$, and the line perpendicular to $\Delta_{2}$ passing through $B$ intersects $(AD)$ at $Q$. We denote $\Gamma_{1}$ as the circumcircle of triangle $ADE$ and $\Gamma_{2}$ as the circumcircle of triangle $BFC$. Show that $\Gamma_{1}$ and $\Gamma_{2}$ are tangent if and only if $(DP)$ and $(CQ)$ are perpendicular.

FIGURE 1 - Proof of the first implication
|
We start with some preliminary remarks. We have $\widehat{\mathrm{EDA}}=180^{\circ}-\widehat{\mathrm{ADC}}=\widehat{\mathrm{ABC}}=180^{\circ}-\widehat{\mathrm{EAB}}$, so $(\mathrm{AB})$ and $\Gamma_{1}$ are tangent. Similarly, $\Gamma_{2}$ and $(AB)$ are tangent. Next, since $(AP) \perp (BC)$ and $(AD) \perp (BQ)$, we have $(PD) \perp (CQ)$ if and only if the triangles $APD$ and $BCQ$ are similar, that is, if and only if $\frac{AP}{AD}=\frac{BC}{CQ}$. Since the triangles $ADE$ and $BFC$ are similar, we have $\frac{AD}{AE}=\frac{BF}{BC}$. We deduce that $\frac{AP}{AD}=\frac{BC}{CQ}$ if and only if $\frac{AP}{AE}=\frac{BF}{BQ}$ if and only if $PAE$ and $FBQ$ are similar (since $\widehat{\mathrm{PAE}}=\widehat{\mathrm{FBQ}}=90^{\circ}$).
Now suppose that $\Gamma_{1}$ and $\Gamma_{2}$ are tangent at $R$. It is easy to see that $\widehat{ARB}=90^{\circ}$, which implies that the points $A, Q, P, B, R$ all lie on the circle with diameter $[AB]$. We deduce that $\widehat{ARP}=180^{\circ}-\widehat{ABP}=180^{\circ}-\widehat{ABC}=180^{\circ}-\widehat{ADE}=180^{\circ}-\widehat{ARE}$. Therefore, $E, R, P$ are collinear. Similarly, we show that $F, R, Q$ are collinear. Thus, $\widehat{PEA}=\widehat{REA}=\widehat{RAB}=\widehat{RQB}=\widehat{FQB}$. We deduce that $PEA$ and $FQB$ are similar.
Now suppose that $PEA$ and $FQB$ are similar. Let $S$ be the intersection of $(PE)$ and $(QF)$. We will show that $\Gamma_{1}$ and $\Gamma_{2}$ are tangent at $S$. We have the equality of angles
$$
\widehat{\mathrm{SQB}}=\widehat{\mathrm{FQB}}=\widehat{\mathrm{PEA}}=\widehat{\mathrm{EPC}}=180^{\circ}-\widehat{\mathrm{SPB}}
$$
We deduce that $S, Q, B, P$ are concyclic. Thus, $A, Q, P, B, S$ are concyclic. It follows that
$$
\widehat{ASE}=180^{\circ}-\widehat{ASP}=\widehat{ABP}=\widehat{ABC}=180^{\circ}-\widehat{ADC}=\widehat{ADE}
$$
Therefore, $S \in \Gamma_{1}$. We show similarly that $S \in \Gamma_{2}$. To conclude, we write
$$
\widehat{BSA}=90^{\circ}=\widehat{SAB}+\widehat{ABS}=\widehat{SDA}+\widehat{BCS}
$$
This easily implies that the tangent to $\Gamma_{1}$ passing through $S$ is tangent to $\Gamma_{2}$.

Figure 2 - Proof of the second implication.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soient $A B C D$ un quadrilatère inscrit dans un cercle. On note $\Delta_{1}$ la droite parallèle à $(B C)$ passant par $A$ et $\Delta_{2}$ la droite parallèle à $(A D)$ passant par $B$. On note $E$ le point d'intersection de $\Delta_{1}$ avec (CD) et $F$ le point d'intersection de $\Delta_{2}$ avec (CD). La droite perpendiculaire à $\Delta_{1}$ passant $A$ coupe $(B C)$ en $P$, et la droite perpendiculaire à $\Delta_{2}$ passant par $B$ coupe ( $\left.A D\right)$ en Q. On note $\Gamma_{1}$ le cercle circonscrit du triangle $A D E$ et $\Gamma_{2}$ le cercle circonscrit du triangle BFC. Montrer que $\Gamma_{1}$ et $\Gamma_{2}$ sont tangents si et seulement si (DP) et (CQ) sont perpendiculaires.

FIGURE 1 - Preuve de la première implication
|
On commence par quelques remarques préliminaires. On a $\widehat{\mathrm{EDA}}=180^{\circ}-\widehat{\mathrm{ADC}}=\widehat{\mathrm{ABC}}=$ $180^{\circ}-\widehat{\mathrm{EAB}}$, donc $(\mathrm{AB})$ et $\Gamma_{1}$ sont tangents. De même, $\Gamma_{2}$ et $(A B)$ sont tangents. Ensuite, comme $(A P) \perp(B C)$ et $(A D) \perp(B Q)$, on a $(P D) \perp(C Q)$ si et seulement si les triangles $A P D$ et $B C Q$ sont semblables, c'est-à-dire si et seulement si $\frac{A P}{A D}=\frac{B C}{C O}$. Or les triangles $A D E$ et $B F C$ sont semblables, donc $\frac{A D}{A E}=\frac{B F}{B C}$. On en déduit que $\frac{A P}{A D}=\frac{B C}{C Q}$ si et seulement si $\frac{A P}{A E}=\frac{B F}{B Q}$ si et seulement si PAE et FBQ sont semblables ( $\operatorname{car} \widehat{\mathrm{PAE}}=\widehat{\mathrm{FBQ}}=90^{\circ}$ ).
Supposons maintenant que $\Gamma_{1}$ et $\Gamma_{2}$ sont tangents en $R$. On vois facilement que $\widehat{A R B}=90^{\circ}$, ce qui implique que les points $A, Q, P, B, R$ appartiennent tous au cercle de diamètre $[A B]$. On en déduit que $\widehat{A R P}=180^{\circ}-\widehat{A B P}=180^{\circ}-\widehat{A B C}=180^{\circ}-\widehat{A D E}=180^{\circ}-\widehat{A R E}$. Donc E, $R, P$ sont alignés. On montre de même que $F, R$, $Q$ sont alignés. Ainsi, $\widehat{P E A}=\widehat{R E A}=\widehat{R A B}=\widehat{R Q B}=\widehat{F Q B}$. On en déduit que $P E A$ et $F Q B$ sont semblables.
Supposons maintenant que PEA et FQB sont semblables. Soit $S$ le point d'intersection de (PE) et (QF). Nous allons montrer que $\Gamma_{1}$ et $\Gamma_{2}$ sont tangents en $S$. On a l'égalité des angles
$$
\widehat{\mathrm{SQB}}=\widehat{\mathrm{FQB}}=\widehat{\mathrm{PEA}}=\widehat{\mathrm{EPC}}=180^{\circ}-\widehat{\mathrm{SPB}}
$$
On en déduit que $S, Q, B, P$ sont cocycliques. Ainsi, $A, Q, P, B, S$ sont cocycliques. Il en découle que
$$
\widehat{A S E}=180^{\circ}-\widehat{A S P}=\widehat{A B P}=\widehat{A B C}=180^{\circ}-\widehat{A D C}=\widehat{A D E}
$$
Donc $S \in \Gamma_{1}$. On montre de même que $S \in \Gamma_{2}$. Pour conclure, on écrit
$$
\widehat{B S A}=90^{\circ}=\widehat{S A B}+\widehat{A B S}=\widehat{S D A}+\widehat{B C S}
$$
$\qquad$

Figure 2 - Preuve de la deuxième implication.
Ceci entraîne aisément que la tangente à $\Gamma_{1}$ passant par $S$ est tangente à $\Gamma_{2}$.
|
{
"resource_path": "French/segmented/envois/fr-ofm-2016-2017-envoi-5-solutions.jsonl",
"problem_match": "\nExercice 9.",
"solution_match": "## Solution de l'exercice 9"
}
|
22754c46-e894-5546-8bf9-448ed03859ba
| 607,690
|
Consider 5 positive integers. By adding them two at a time in all possible ways, 10 integers are generated. Show that these 10 integers cannot be 10 consecutive integers.
|
Suppose the 10 integers are consecutive, and we denote $n$ as the smallest. Their sum is $n+(n+1)+\cdots+(n+9)=10n+45$. But this is also the sum of the 5 initial numbers, each counted 4 times, so it is a multiple of 4. This is impossible because for any integer $n$, $10n+45$ is odd. We arrive at a contradiction, so the 10 integers cannot be consecutive.
## Common Exercises
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
On considère 5 nombres entiers positifs. En les ajoutant deux à deux de toutes les façons possibles, on génère 10 entiers. Montrer que ces 10 entiers ne peuvent pas être 10 entiers consécutifs.
|
On suppose que les 10 entiers sont consécutifs, et on note $n$ le plus petit. Leur somme est $n+(n+1)+\cdots+(n+9)=10 n+45$. Mais c'est aussi la somme des 5 nombres de départ, comptés 4 fois chacun, donc c'est un multiple de 4. C'est impossible car pour tout entier $n, 10 n+45$ est impair. On aboutit à une contradiction, donc les 10 entiers ne peuvent pas être consécutifs.
## Exercices Communs
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi1-corrige.jsonl",
"problem_match": "\nExercice 3",
"solution_match": "\nSolution "
}
|
b7d61536-e18f-5849-bb83-fbc7c1f7cfef
| 607,693
|
Show that $n!=1 \times 2 \times \cdots \times n$ is divisible by $2^{n-1}$ if and only if $n$ is a power of 2.
|
For any prime number $p$, the $p$-adic valuation of an integer $n$ is defined as the largest integer, denoted $v_{p}(n)$, such that $p^{v_{p}(n)}$ divides $n$. The $p$-adic valuation of a product of integers is the sum of their $p$-adic valuations. For a real number $x$, we denote $\lfloor x\rfloor$ as the integer part of $x$, which is the greatest integer less than or equal to $x$.
We observe that $\{1, \ldots, n\}$ contains $\left\lfloor\frac{n}{p}\right\rfloor$ multiples of $p$, $\left\lfloor\frac{n}{p^{2}}\right\rfloor$ multiples of $p^{2}$, etc. From this, we derive Legendre's formula:
$$
v_{p}(n!)=\left\lfloor\frac{n}{p}\right\rfloor+\left\lfloor\frac{n}{p^{2}}\right\rfloor+\ldots
$$
For this exercise, we take $p=2$, and define $k$ as the integer such that $2^{k} \leq n < 2^{k+1}$. Then
$v_{2}(n!)=\left\lfloor\frac{n}{2}\right\rfloor+\left\lfloor\frac{n}{4}\right\rfloor+\cdots+\left\lfloor\frac{n}{2^{k}}\right\rfloor \leq \frac{n}{2}+\frac{n}{4}+\cdots+\frac{n}{2^{k}}=n\left(1-\frac{1}{2^{k}}\right) \leq n-1$.
For $n!$ to be divisible by $2^{n-1}$, i.e., for $v_{2}(n!) \geq n-1$, we must be in the cases of equality. In particular, it must be that $n\left(1-\frac{1}{2^{k}}\right)=n-1$, so $n=2^{k}$.
Conversely, if $n=2^{k}$, then we are in the cases of equality, so $2^{n-1}$ divides $n!$.
## Exercises Group A
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Montrer que $n!=1 \times 2 \times \cdots \times n$ est divisible par $2^{n-1}$ si et seulement si $n$ est une puissance de 2 .
|
On définit, pour tout nombre premier $p$, la valuation $p$-adique d'un entier $n$ comme le plus grand entier, noté $v_{p}(n)$, tel que $p^{v_{p}(n)}$ divise $n$. La valuation $p$-adique d'un produit d'entiers est la somme de leurs valuations $p$ adiques. Pour $x$ un nombre réel, on note $\lfloor x\rfloor$ la partie entière de $x$, c'est-à-dire le plus grand entier inférieur à $x$.
On observe que $\{1, \ldots, n\}$ contient $\left\lfloor\frac{n}{p}\right\rfloor$ multiples de $p,\left\lfloor\frac{n}{p^{2}}\right\rfloor$ multiples de $p^{2}$, etc. On en déduit la formule de Legendre :
$$
v_{p}(n!)=\left\lfloor\frac{n}{p}\right\rfloor+\left\lfloor\frac{n}{p^{2}}\right\rfloor+\ldots
$$
Pour cet exercice, on prend $p=2$, et on définit $k$ l'entier tel que $2^{k} \leq n<2^{k+1}$. Alors
$v_{2}(n!)=\left\lfloor\frac{n}{2}\right\rfloor+\left\lfloor\frac{n}{4}\right\rfloor+\cdots+\left\lfloor\frac{n}{2^{k}}\right\rfloor \leq \frac{n}{2}+\frac{n}{4}+\cdots+\frac{n}{2^{k}}=n\left(1-\frac{1}{2^{k}}\right) \leq n-1$.
Pour que $n$ ! soit divisible par $2^{n-1}$, c'est-à-dire pour que $v_{2}(n!) \geq n-1$, il faut être dans les cas d'égalité. En particulier, il faut que $n\left(1-\frac{1}{2^{k}}\right)=n-1$, donc que $n=2^{k}$.
Réciproquement, si $n=2^{k}$, alors on est dans les cas d'égalité, donc $2^{n-1}$ divise $n$ !.
## Exercices Groupe A
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi1-corrige.jsonl",
"problem_match": "\nExercice 3",
"solution_match": "\nSolution "
}
|
eb66d0cf-48d2-5eb6-9421-1a6d5f11f50c
| 607,696
|
Does there exist an infinite subset $A$ of $\mathbb{N}$ that satisfies the following property: any finite sum of distinct elements of $A$ is never a power of an integer (i.e., an integer of the form $a^{b}$ with $a$ and $b$ integers greater than or equal to 2)?
|
We are looking to construct a set $A=\left\{a_{0}, a_{1}, \ldots\right\}$, where $\left(a_{0}, a_{1}, \ldots\right)$ is an increasing sequence of integers. We choose the first element as $a_{0}=0$.
Let $n \in \mathbb{N}$. Suppose we have already found $a_{0}<\cdots<a_{n}$ such that the set $B$ of sums of distinct elements does not contain any power of an integer. We want to choose $a_{n+1}>a_{n}$ such that the set of sums of distinct elements of $\left\{a_{0}, \ldots a_{n+1}\right\}$ does not contain any power of an integer. It suffices that none of the $a_{n+1}+b$, with $b \in B$, is a power of an integer.
Let $N \in \mathbb{N}$. We bound the proportion $p(N)$ of powers of integers in $\left\{a_{n}+1, \ldots, N\right\}$. There are fewer than $\sqrt{N}$ squares, fewer than $\sqrt[3]{N}$ cubes, and so on up to the $k$-th roots, where $k=\left\lfloor\log _{2}(N)\right\rfloor$. We can stop at $k$ because for all $b>k, 2^{b}>N$ so there are no $b$-th powers in $\left\{a_{n}+1, \ldots, N\right\}$. Therefore,
$$
p(N) \leq \frac{\sqrt{N}+\sqrt[3]{N}+\cdots+\sqrt[k]{N}}{N-a_{n}} \leq \frac{\sqrt{N} \log _{2}(N)}{N-a_{n}} \underset{N \rightarrow+\infty}{\longrightarrow} 0 .
$$
Thus, for sufficiently large $N$, we can find $1+\max B$ consecutive numbers in $\left\{a_{n}+1, \ldots, N\right\}$ that are not powers of integers. We choose for $a_{n+1}$ the smallest of these. Then none of the $a_{n+1}+b$, with $b \in B$, is a power of an integer.
Finally, we have constructed a set $A$ satisfying the required property.
Exercise 3: Let $P(n)$ denote the largest prime divisor of $n$. Show that there are infinitely many integers $n$ such that $P(n-1)<P(n)<P(n+1)$.
|
proof
|
Yes
|
Yes
|
proof
|
Number Theory
|
Existe-t-il un sous-ensemble infini $A$ de $\mathbb{N}$ qui vérifie la propriété suivante : toute somme finie d'éléments distincts de $A$ n'est jamais une puissance d'un entier (c'est-à-dire un entier de la forme $a^{b}$ avec $a$ et $b$ entiers supérieurs ou égaux à 2) ?
|
On cherche à construire un tel ensemble $A=\left\{a_{0}, a_{1}, \ldots\right\}$, avec $\left(a_{0}, a_{1}, \ldots\right)$ une suite croissante d'entiers. On choisit comme premier élément $a_{0}=0$.
Soit $n \in \mathbb{N}$. On suppose qu'on a déjà trouvé $a_{0}<\cdots<a_{n}$ tels que l'ensemble B des somme d'éléments distincts ne contienne pas de puissance d'un entier. On veut choisir $a_{n+1}>a_{n}$ tel que l'ensemble des sommes d'éléments distincts de $\left\{a_{0}, \ldots a_{n+1}\right\}$ ne contienne pas de puissance d'un entier. Il suffit qu'aucun des $a_{n+1}+b$, avec $b \in B$, ne soit une puissance d'un entier.
Soit $N \in \mathbb{N}$. Majorons la proportion $p(N)$ de puissances d'entiers dans $\left\{a_{n}+1, \ldots, N\right\}$. Il y a moins de $\sqrt{N}$ carrés, moins de $\sqrt[3]{N}$ cubes, et ainsi de suites jusqu'aux racines $k$-ièmes, avec $k=\left\lfloor\log _{2}(N)\right\rfloor$. On peut s'arrêter à $k$ car pour tout $b>k, 2^{b}>N$ donc il n'y a pas de puissance $b$-ième dans $\left\{a_{n}+1, \ldots, N\right\}$. Donc
$$
p(N) \leq \frac{\sqrt{N}+\sqrt[3]{N}+\cdots+\sqrt[k]{N}}{N-a_{n}} \leq \frac{\sqrt{N} \log _{2}(N)}{N-a_{n}} \underset{N \rightarrow+\infty}{\longrightarrow} 0 .
$$
Ainsi, pour $N$ assez grand, on peut trouver $1+\max B$ nombres consécutifs dans $\left\{a_{n}+1, \ldots, N\right\}$ qui ne sont pas des puissances d'entiers. On choisit pour $a_{n+1}$ le plus petit d'entre eux. Alors aucun des $a_{n+1}+b$, avec $b \in B$, n'est une puissance d'un entier.
Finalement, on a bien construit un ensemble $A$ satisfaisant la propriété demandée.
Exercices 3 On note $P(n)$ le plus grand diviseur premier de $n$. Montrer qu'il existe une infinité d'entiers $n$ tels que $P(n-1)<P(n)<P(n+1)$.
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi1-corrige.jsonl",
"problem_match": "\nExercice 2",
"solution_match": "\nSolution "
}
|
74d55753-9897-57ff-a710-e746dbea1686
| 607,698
|
Let $\Gamma_{1}$ and $\Gamma_{2}$ be two circles intersecting at distinct points $A$ and $B$. Let $O$ be the center of $\Gamma_{1}$. Let $C$ be a point on $\Gamma_{1}$, and let $D, E$ be the intersections of $(AC)$ and $(BC)$ with $\Gamma_{2}$, respectively.
Show that $(OC)$ and $(DE)$ are perpendicular.
|

We proceed by angle chasing.
Here, we present a solution that is very (too) rigorous; it was not necessary to be so meticulous or to treat all these cases to receive the maximum score on this exercise.
Since we notice that the figure changes significantly depending on whether point $C$ is on the same side of the line (AB) as O or not, we have the choice between distinguishing cases in our angle chasing while being careful about orientation issues or working with directed angles of lines. The second method is often preferable, as long as we don't have to divide angles by two (the problem is that if we look at our directed angles of lines modulo 180 degrees and then divide by 2, we end up looking at directed angles of lines modulo 90 degrees, thus losing information). ${ }^{1}$ Here, we will mix both methods.
We calculate modulo 180 degrees:
$(\mathrm{OC}, \mathrm{DE})=(\mathrm{OC}, \mathrm{CD})+(\mathrm{CD}, \mathrm{DE})=(\mathrm{OC}, \mathrm{CD})+(\mathrm{AB}, \mathrm{BE})=(\mathrm{OC}, \mathrm{CA})+(\mathrm{CB}, \mathrm{AB})$.
Now, $2(O C, C A)+(O A, O C)=0$ and $2(C B, A B)=(O C, O A)$.
Therefore, $2(\mathrm{OC}, \mathrm{DE})=0$ modulo 180 degrees, so $(\mathrm{OC}, \mathrm{DE})$ is a multiple of 90 degrees (thus 0 or 90 degrees modulo 180), meaning that (OC) and (DE) are either parallel or perpendicular.
And here, we are stuck trying to exclude the parallel case. We can get out of this by case disjunction:
- If $A, C$, and the point diametrically opposite to $A$ on $\Gamma_{1}$ are in that order when read in the counterclockwise direction on the circle $\Gamma_{1}$, then $(O C, C A) = \widehat{O C A}$.
- Otherwise, $(OC, CA) = 180^{\circ} - \widehat{O C A}$.
- If $A, B, C$ are read in that order on the circle $\Gamma_{1}$ in the counterclockwise direction, then $(C B, A B) = \widehat{C B A}$.
- Otherwise, $(\mathrm{CB}, \mathrm{AB}) = 180^{\circ} - \widehat{\mathrm{CBA}}$.
- In all cases, $\widehat{C O A} = 180^{\circ} - 2 \widehat{O C A}$.
- But $\widehat{C O A} = 2 \widehat{C B A}$ if and only if $O$ and $B$ are on the same side of the line (AC).
- Conversely, if $O$ and $B$ are not on the same side of the line $(A C)$, then $\widehat{C O A} = 360^{\circ} - 2 \widehat{C B A}$.
The geometric angles have measures between 0 and 180 degrees.
If we treat all the cases presented above, by combining the equalities, we can show that the lines (OC) and (DE) are parallel.
[^0]Exercise 2. Let $A B C D$ be a convex quadrilateral. ${ }^{2}$ We are given two points $E, F$ such that $E, B, C, F$ are collinear in that order. We also assume that $\widehat{B A E} = \widehat{\mathrm{CDF}}$ and $\widehat{\mathrm{EAF}} = \widehat{\mathrm{FDE}}$. Show that $\widehat{\mathrm{FAC}} = \widehat{\mathrm{EDB}}$.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $\Gamma_{1}$ et $\Gamma_{2}$ deux cercles se coupant en $A$ et $B$ distincts. Notons O le centre de $\Gamma_{1}$. Soit $C$ un point de $\Gamma_{1}$, soit $D, E$ les intersections respectives de (AC) et de (BC) avec $\Gamma_{2}$.
Montrer que (OC) et ( DE ) sont perpendiculaires.
|

On procède par chasse aux angles.
On présente ici une solution qui se veut très (trop) rigoureuse, il n'y avait pas besoin d'être aussi pointilleux ni de traiter tous ces cas pour recevoir la note maximale à cet exercice.
Comme on remarque que la figure change beaucoup selon que le point $C$ est du même côté de la droite ( AB ) que O ou non, on a le choix entre distinguer des cas dans notre chasse aux angles en faisant attention aux problèmes d'orientation ou travailler avec des angles orientés de droites. La deuxième méthode est souvent préférable, tant qu'on n'a pas à diviser des angles par deux (le problème est que, si on regarde nos angles orientés de droites modulo 180 degrés et qu'on divise par 2 , on se retrouve à regarder des angles orientés de droite modulo 90 degrés, donc on perd de l'information). ${ }^{1} \mathrm{Ici}$, on va panacher les deux méthodes.
On calcule modulo 180 degrés :
$(\mathrm{OC}, \mathrm{DE})=(\mathrm{OC}, \mathrm{CD})+(\mathrm{CD}, \mathrm{DE})=(\mathrm{OC}, \mathrm{CD})+(\mathrm{AB}, \mathrm{BE})=(\mathrm{OC}, \mathrm{CA})+(\mathrm{CB}, \mathrm{AB})$.
Or $2(O C, C A)+(O A, O C)=0$ et $2(C B, A B)=(O C, O A)$.
Donc 2 (OC, DE$)=0$ modulo 180 degrés, donc (OC, DE) est un multiple de 90 degrés (donc 0 ou 90 degrés modulo 180)donc (OC) et (DE) sont parallèles ou perpendiculaires.
Et là, on est embêtés pour exclure le cas parallèle. On peut s'en sortir par disjonction de cas:
- Si $A, C$ et le point diamétralement opposé à $A$ sur $\Gamma_{1}$ sont dans cet ordre quand on lit dans le sens trigonométrique (anti-horaire) sur le cercle $\Gamma_{1}$, alors $(O C, C A)=$ $\widehat{O C A}$
- Sinon, (OC, CA) $=180^{\circ}-\widehat{O C A}$
- Si $A, B, C$ se lisent dans cet ordre sur le cercle $\Gamma_{1}$ dans les sens trigonométrique, alors $(C B, A B)=\widehat{C B A}$.
- Sinon, $(\mathrm{CB}, \mathrm{AB})=180^{\circ}-\widehat{\mathrm{CBA}}$.
- On a dans tous les cas $\widehat{C O A}=180^{\circ}-2 \widehat{O C A}$.
- Mais $\widehat{C O A}=2 \widehat{C B A}$ si et seulement si $O$ et $B$ sont du même côté de la droite (AC).
- En revanche, si $O$ et $B$ ne sont pas du même côté de la droite $(A C), \widehat{C O A}=$ $360^{\circ}-2 \widehat{C B A}$.
Les angles géométriques ayant des mesures entre 0 et 180 degrés.
Si on traite tous les cas présentés ci-dessus, en combinant les égalités, on arrive à montrer que les droites (OC) et (DE) sont parallèles.
[^0]Exercice 2. Soit un quadrilatère $A B C D$ convexe. ${ }^{2}$ On se donne $E, F$ deux points tels que $E, B, C, F$ soient alignés dans cet ordre. On suppose de plus que $\widehat{B A E}=$ $\widehat{\mathrm{CDF}}$ et $\widehat{\mathrm{EAF}}=\widehat{\mathrm{FDE}}$. Montrer que $\widehat{\mathrm{FAC}}=\widehat{\mathrm{EDB}}$.
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "\nExercice 1.",
"solution_match": "\nSolution de l'exercice 1"
}
|
b4e4a189-dec5-560f-a3b4-97663df9993d
| 607,699
|
Let $\Gamma_{1}$ and $\Gamma_{2}$ be two circles intersecting at distinct points $A$ and $B$. Let $O$ be the center of $\Gamma_{1}$. Let $C$ be a point on $\Gamma_{1}$, and let $D, E$ be the intersections of $(AC)$ and $(BC)$ with $\Gamma_{2}$, respectively.
Show that $(OC)$ and $(DE)$ are perpendicular.
|

This is another angle chase. Since \(\widehat{F A E} = \widehat{FDE}\) and \(A, D\) are on the same side of \((EF)\), the points \(A, D, E, F\) are concyclic.
Furthermore, to show that \(\widehat{F A C} = \widehat{E D B}\), it suffices to show that \(\widehat{C A B} = \widehat{F A B} - \widehat{F A C}\) is equal to \(\widehat{CDB} = \widehat{CDE} - \widehat{EDB}\), in other words, that \(A, B, C, D\) are concyclic. To do this, we need to show that \(\widehat{D A B} + \widehat{D C B} = 180^{\circ}\). We have:
\[
\widehat{D A B} = \widehat{D A F} + \widehat{F A B} = \widehat{D E F} + \widehat{C D E} = 180^{\circ} - \widehat{ECD}
\]
which proves the concyclicity of \(A, B, C, D\) and thus the desired result.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $\Gamma_{1}$ et $\Gamma_{2}$ deux cercles se coupant en $A$ et $B$ distincts. Notons O le centre de $\Gamma_{1}$. Soit $C$ un point de $\Gamma_{1}$, soit $D, E$ les intersections respectives de (AC) et de (BC) avec $\Gamma_{2}$.
Montrer que (OC) et ( DE ) sont perpendiculaires.
|

C'est encore une chasse aux angles. Comme $\widehat{F A E}=\widehat{\mathrm{FDE}}$ et $A, D$ sont du même côté de (EF), les points $A, D, E, F$ sont cocycliques.
De plus, pour montrer que $\widehat{F A C}=\widehat{E D B}$, il suffit de montrer que $\widehat{C A B}=\widehat{F A B}-\widehat{F A C}$ est égal à $\widehat{\mathrm{CDB}}=\widehat{\mathrm{CDE}}-\widehat{\mathrm{EDB}}$, autrement dit que $A, B, C, D$ sont cocycliques. Montrons pour cela que $\widehat{D A B}+\widehat{D C B}=180^{\circ}$. On a :
$$
\widehat{D A B}=\widehat{D A F}+\widehat{F A B}=\widehat{D E F}+\widehat{C D E}=180^{\circ}-\widehat{\mathrm{ECD}}
$$
ce qui prouve la cocyclicité de $A, B, C, D$ et donc le résultat voulu.
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "\nExercice 1.",
"solution_match": "## \nSolution de l'exercice 2"
}
|
b4e4a189-dec5-560f-a3b4-97663df9993d
| 607,699
|
Let $[A B]$ be the diameter of a semicircle on which two points $C$ and $D$ are taken. Let $S$ be the intersection of $(A C)$ and $(B D)$, and $T$ the foot of the perpendicular from $S$ to $[A B]$.
[^1]Show that $(ST)$ is the bisector of the angle $\widehat{\mathrm{CTD}}$.
|

We solve this by angle chasing. The points \(A, D, S, T\) are concyclic (on the circle with diameter \([A S]\)) and similarly the points \(B, C, S, T\). Therefore, \(\widehat{S T D} = \widehat{S A D}\), and \(\widehat{S T C} = \widehat{S B C}\). Since \(\widehat{S A D} = \widehat{C A D} = \widehat{\mathrm{CBD}} = \widehat{\mathrm{SBC}}\) by the concyclicity of the points \(A, B, C, D\), we have \(\widehat{S T C} = \widehat{S T D}\).
We can also solve this problem using projective geometry. Indeed, we notice that \((ST)\) is the angle bisector of \(\widehat{\mathrm{CTD}}\) if and only if \((AB)\), \((ST)\), \((TD)\), \((TC)\) are harmonic (thanks to the 2/4 lemma). Let \(F\) be the intersection of \((BD)\) and \((TC)\). It suffices to show that \(B, S, D, F\) are harmonic, so it suffices to show that \(B, A, (C D) \cap (A B), T\) are harmonic. Now, \((C D) \cap (A B)\) is by construction on the polar of \(S\), so the polar of \((C D) \cap (A B)\) passes through \(S\). Moreover, it is perpendicular to \((A B)\), so \(c'\) is \((S T)\). This is why \((C D) \cap (A B), T, A, B\) are harmonic, which concludes the proof.
## Common Exercises
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $[A B]$ le diamètre d'un demi-cercle sur lequel on prend deux points $C$ et $D$. Soit $S$ l'intersection de ( $A C)$ et $(B D)$ et $T$ le pied de la perpendiculaire à $[A B]$ issue de $S$.
[^1]Montrer que (ST) est la bissectrice de l'angle $\widehat{\mathrm{CTD}}$.
|

On s'en sort par chasse aux angles. Les points $A, D, S, T$ sont cocycliques (sur le cercle de diamètre $[A S])$ et de même les points $B, C, S, T$. Donc $\widehat{S T D}=\widehat{S A D}$, et $\widehat{S T C}=\widehat{S B C}$. Comme $\widehat{S A D}=\widehat{C A D}=\widehat{\mathrm{CBD}}=\widehat{\mathrm{SBC}}$ par cocyclicité des points $A, B, C, D$, on a bien $\widehat{S T C}=\widehat{S T D}$.
On peut aussi résoudre cet exercice avec de la géométrie projective. En effet, on remarque (ST) est la bissectrice de $\widehat{\mathrm{CTD}}$ si et seulement si (AB), (ST), (TD), (TC) sont harmoniques (grâce au lemme 2/4). Soit F l'intersection de (BD) et de (TC). Il suffit de montrer que $B, S, D, F$ sont harmoniques, donc il suffit de montrer que $B, A,(C D) \cap(A B), T$ sont harmoniques. Or $(C D) \cap(A B)$ est par construction sur la polaire de $S$ donc la polaire de $(C D) \cap(A B)$ passe par $S$. De plus, elle est perpendiculaire à $(A B)$, donc $c^{\prime}$ est $(S T)$. C'est pourquoi on a bien $(C D) \cap(A B), T, A$, $B$ harmoniques, ce qui conclut.
## Exercices Communs
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "\nExercice 3.",
"solution_match": "## Solution de l'exercice 3"
}
|
e938902e-fe7a-5543-927b-096494107539
| 607,700
|
Let $ABC$ be a triangle such that $AB < AC$, $H$ its orthocenter, $\Gamma$ its circumcircle, and $d$ the tangent to $\Gamma$ at $A$. Consider the circle centered at $B$ passing through $A$. It intersects $d$ at $D$ and $(AC)$ at $E$.
Show that $D$, $E$, and $H$ are collinear.
|
First, we notice that the height from $B$ in $ABC$ is the perpendicular bisector of [AE]. Let $L$ be its intersection point with ($AC$). By the power of a point, $CE \cdot CA = CB^2 - AB^2 = CL^2 - AL^2 = CA \cdot (CL - AL)$, so $LA = LE$.
Therefore, HAE is isosceles at H. Thus, by angle chasing,
$$
\widehat{\mathrm{HEA}} = \widehat{\mathrm{HAC}} = 90^{\circ} - \widehat{\mathrm{ACB}} = 90^{\circ} - \widehat{\mathrm{DAB}} = \frac{1}{2} \widehat{\mathrm{ABD}} = \widehat{\mathrm{DEA}}.
$$
Therefore, D, E, H are collinear.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle tel que $A B<A C, H$ son orthocentre, $\Gamma$ son cercle circonscrit, d la tangente à $\Gamma$ en $A$. On considère le cercle de centre $B$ passant par $A$. Il coupe d en D et ( $A C$ ) en $E$.
Montrer que D, E, H sont alignés.
|

On remarque tout d'abord que la hauteur issue de $B$ dans $A B C$ est la médiatrice de [AE]. Soit en effet $L$ son point d'intersection avec ( $A C$ ). Par la puissance d'un point, $C E \cdot C A=C B^{2}-A B^{2}=C L^{2}-A L^{2}=C A \cdot(C L-A L)$ donc $L A=L E$.
Donc HAE est isocèle en H. Donc, par chasse aux angles,
$$
\widehat{\mathrm{HEA}}=\widehat{\mathrm{HAC}}=90^{\circ}-\widehat{\mathrm{ACB}}=90^{\circ}-\widehat{\mathrm{DAB}}=\frac{1}{2} \widehat{\mathrm{ABD}}=\widehat{\mathrm{DEA}} .
$$
Donc D, E, H sont alignés.
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "\nExercice 4.",
"solution_match": "## Solution de l'exercice 4"
}
|
f30cc14a-99d0-5adc-a28d-659905f009b8
| 607,701
|
Let $ABC$ be a triangle, $\Gamma$ its circumcircle. Let $\omega_{A}$ be the circle internally tangent to $(AB)$, $(AC)$, and $\Gamma$. Denote $T_{A}$ as the point of tangency of $\Gamma$ with $\omega_{A}$. Similarly, define $T_{B}$ and $T_{C}$.
Show that $\left(A T_{A}\right)$, $\left(B T_{B}\right)$, and $\left(C T_{C}\right)$ are concurrent.
|
When we see many tangent circles, we should think about homotheties that exchange them. In this case, we have three positive homotheties with centers at \( \mathrm{T}_{\mathrm{A}}, \mathrm{T}_{\mathrm{B}}, \mathrm{T}_{\mathrm{C}} \) and which map \( \omega_{\mathrm{A}}, \omega_{\mathrm{B}} \) and \( \omega_{\mathrm{C}} \) to \( \Gamma \), respectively.
Moreover, since \( \omega_{\mathrm{A}} \) is tangent to (AB) and (AC), we also have a positive homothety with center \( A \) that maps \( \omega_{A} \) to the incircle \( \omega \) of \( \triangle ABC \). The same applies for \( B \) and \( C \).
The composition of two positive homotheties with centers \( \mathrm{O}_{1} \) and \( \mathrm{O}_{2} \) is a positive homothety whose center lies on the line \( \left(\mathrm{O}_{1} \mathrm{O}_{2}\right) \). Therefore, we have constructed three positive homotheties that all map \( \Gamma \) to \( \omega \), and their respective centers lie on \( \left(\mathrm{AT}_{\mathrm{A}}\right), \left(B \mathrm{BT}_{\mathrm{B}}\right) \) and \( \left(\mathrm{CT}_{\mathrm{C}}\right) \).
Since there is at most one positive homothety that maps one given circle to another, these three homotheties are actually the same homothety, with center \( Z \). Therefore, \( Z \in \left(A T_{A}\right), Z \in \left(B T_{B}\right) \) and \( Z \in \left(C T_{C}\right) \).
The lines \( \left(A T_{A}\right), \left(B T_{B}\right) \) and \( \left(C T_{C}\right) \) are thus concurrent.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle, $\Gamma$ son cercle circonscrit. Soit $\omega_{A}$ le cercle inscrit intérieurement à $(A B),(A C)$ et à $\Gamma$. On note $T_{A}$ le point de tangence de $\Gamma$ avec $\omega_{A}$. On définit de même $T_{B}$ et $T_{C}$.
Montrer que $\left(A T_{A}\right),\left(B T_{B}\right)$ et $\left(C T_{C}\right)$ sont concourantes.
|

Quand on voit beaucoup de cercles tangents, on doit penser aux homothéties qui les échangent. En l'occurrence, on a trois homothéties positives, de centre respectifs $\mathrm{T}_{\mathrm{A}}, \mathrm{T}_{\mathrm{B}}, \mathrm{T}_{\mathrm{C}}$ et qui envoient respectivement $\omega_{\mathrm{A}}, \omega_{\mathrm{B}}$ et $\omega_{\mathrm{C}}$ sur $\Gamma$.
De plus, $\omega_{\mathrm{A}}$ étant tangent à ( AB ) et ( AC ), on aussi une homothétie positive de centre $A$ qui envoie $\omega_{A}$ sur le cercle $\omega$ inscrit à $A B C$. De même pour $B$ et $C$.
Or la composée de deux homothéties positives de centres $\mathrm{O}_{1}$ et $\mathrm{O}_{2}$ est une homothétie positive dont le centre est sur la droite ( $\left.\mathrm{O}_{1} \mathrm{O}_{2}\right)$. On a donc construit trois homothéties positives qui envoient toutes $\Gamma$ sur $\omega$, et leurs centres respectifs appartiennent à $\left(\mathrm{AT}_{\mathrm{A}}\right),\left(B \mathrm{BT}_{\mathrm{B}}\right)$ et $\left(\mathrm{CT}_{\mathrm{C}}\right)$.
Comme il existe au plus une homothétie positive envoyant un cercle donné sur un autre cercle, ces trois homothéties sont en fait une seule et même homothétie, de centre $Z$. On a donc $Z \in\left(A T_{A}\right), Z \in\left(B T_{B}\right)$ et $Z \in\left(C T_{C}\right)$.
Les droites $\left(A T_{A},\left(B T_{B}\right)\right.$ et ( $C T_{C}$ sont donc concourantes.
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "\nExercice 5.",
"solution_match": "## Solution de l'exercice 5"
}
|
4f8226aa-f950-54ae-b147-b831f62c2323
| 607,702
|
Let $O$ be the center of a regular 18-sided polygon with vertices $A_{1}, \ldots, A_{18}$. Let $B$ be the point on $\left[\mathrm{OA}_{1}\right]$ such that $\widehat{\mathrm{BA} A_{2} \mathrm{O}}=20^{\circ}$ and $C$ the point on $\left[\mathrm{OA}_{2}\right]$ such that $\widehat{\mathrm{CA}_{1} \mathrm{O}}=10^{\circ}$. Show that $\mathrm{BCA}_{2} \mathrm{~A}_{3}$ are concyclic.
|

We already extend the different existing lines: \(A_{1}, O, A_{10}\) are collinear, \(A_{2}, O, A_{11}\) are also collinear.
We then apply the inscribed angle theorem: any central angle that intercepts a segment of length \(A_{1} A_{2}\) is \(20^{\circ}\), and any inscribed angle that intercepts such a segment is \(10^{\circ}\). Therefore, \(A_{1}, C, A_{9}\) are collinear, and \(A_{2}, B, A_{13}\) are collinear.
By axial symmetry with respect to the axis \((OA_{2})\), it follows that \(A_{3}, C, A_{13}\) are collinear.
If we can show that \(A_{3}, B, A_{15}\) are collinear, then \(\widehat{CA_{3}B} = \widehat{A_{13}A_{3}A_{15}} = 20^{\circ} = \widehat{CA_{2}B}\), which establishes the required cocyclicity in this exercise.
Let's now show that \(A_{3}, B, A_{15}\) are indeed collinear. By axial symmetry with respect to the axis \((OA_{1})\), this is equivalent to showing that \(A_{17}, B, A_{5}\) are collinear.
We notice that \((A_{17}A_{5})\) is the perpendicular bisector of the segment \([OA_{2}]\): indeed, the triangle \(OA_{2}A_{5}\) is equilateral (since \(OA_{2} = OA_{5}\) and \(\widehat{A_{2}OA_{5}} = 60^{\circ}\)), so \(A_{5}\) is on the perpendicular bisector of \([OA_{2}]\), and the same applies to \(A_{17}\).
Since \(\triangle BO_{2}\) is isosceles at \(B\), \(B\) is also on the perpendicular bisector of \([OA_{2}]\), which establishes the desired collinearity and completes the solution.
## Exercises of Group A
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $O$ le centre d'un polygone régulier à 18 côtés de sommets $A_{1}, \ldots, A_{18}$. Soit $B$ le point de $\left[\mathrm{OA}_{1}\right]$ tel que $\widehat{\mathrm{BA} A_{2} \mathrm{O}}=20^{\circ}$ et C le point de $\left[\mathrm{OA}_{2}\right]$ tel que $\widehat{\mathrm{CA}_{1} \mathrm{O}}=10^{\circ}$. Montrer que $\mathrm{BCA}_{2} \mathrm{~A}_{3}$ sont cocycliques.
|

On prolonge déjà les différentes droites existantes: $A_{1}, O, A_{10}$ sont alignés, $A_{2}, 0, A_{11}$ aussi.
On applique ensuite le théorème de l'angle inscrit : tout angle au centre qui intercepte un segment de longueur $A_{1} A_{2}$ vaut $20^{\circ}$, tout angle inscrit qui intercepte un tel segment vaut $10^{\circ}$. Donc $A_{1}, C, A_{9}$ alignés, $A_{2}, B, A_{13}$ alignés.
Par symétrie axiale d'axe $\left(\mathrm{OA}_{2}\right)$, il vient $A_{3}, \mathrm{C}, \mathrm{A}_{13}$ alignés.
Si on parvient à montrer que $A_{3}, B, A_{1} 5$ alignés, alors $\widehat{\mathrm{CA}_{3} \mathrm{~B}}=\widehat{A_{13} \mathrm{~A}_{3} \mathcal{A}_{15}}=20^{\circ}=$ $\widehat{C A_{2} B}$, ce qui établit la cocyclicité demandée dans cet exercice.
Montrons maintenant qu'on a effectivement $A_{3}, B, A_{1} 5$ alignés. Par symétrie axiale d'axe $\left(\mathrm{OA}_{1}\right)$, cela équivaut à montrer que $A_{17}, \mathrm{~B}, A_{5}$ sont alignés.
Or, on remarque que ( $A_{17} A_{5}$ ) est la médiatrice du segment $\left[\mathrm{OA}_{2}\right]$ : en effet, le triangle $\mathrm{OA}_{2} A_{5}$ est équilatéral (comme $\mathrm{OA}_{2}=\mathrm{OA}_{5}$ et ${\widehat{A_{2} \mathrm{OA}}}_{5}=60^{\circ}$ ) donc $A_{5}$ est sur la médiatrice de $\left[\mathrm{OA}_{2}\right.$, de même pour $A_{17}$.
Comme $\mathrm{BO}_{2}$ est isocèle en $\mathrm{B}, \mathrm{B}$ est aussi sur la médiatrice de $\left[\mathrm{OA}_{2}\right]$, ce qui établit l'alignement voulu et termine la solution.
## Exercices du groupe A
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "## Exercice 6.",
"solution_match": "## Solution de l'exercice 6"
}
|
36b6fb4f-38da-5629-a419-1ee82d17be18
| 607,703
|
Let $ABC$ be a triangle such that $AB \neq AC$. Let $E$ be such that $AE = BE$ and $(BE)$ is perpendicular to $(BC)$, and let $F$ be such that $AF = CF$ and $(CF)$ is perpendicular to $(BC)$. Let $D$ be the point on $(BC)$ such that $(AD)$ is tangent to the circumcircle of $ABC$ at $A$.
Show that the points $D, E, F$ are collinear.
|
Suppose (without loss of generality) that $AB < AC$.
Let $O$ be the center of the circumcircle of $ABC$ and $G$ the point on the line $(AD)$ such that $(AB)$ is parallel to $(GC)$.
First, let's show that the angles $\widehat{BAD}$ and $\widehat{BCA}$ are of the same measure $\gamma$, and that the angles $\widehat{BOA}$ and $\widehat{CFA}$ are both of measure $2\gamma$. The only point that does not immediately follow from the inscribed angle theorem is the equality $\widehat{BOA} = \widehat{CFA}$.
Triangles $DBA$ and $DAC$ are similar, so there exists a similarity $s$ centered at $D$ that maps $B$ to $A$ and $A$ to $C$. Since $s$ preserves length ratios, it maps the perpendicular bisector of $[AB]$ to the perpendicular bisector of $[BC]$. It also maps the perpendicular to $(DA)$ passing through $A$ (which is $(AO)$, since $(AD)$ is tangent to the circle centered at $O$ passing through $A$) to the perpendicular to $(DC)$ passing through $C$ (which is $(CF)$). Therefore, $O$ is mapped to $F$. Since $s$ preserves the measures of geometric angles (note for those working with oriented angles, this is an indirect similarity!), $\widehat{BOA} = \widehat{AFC}$.
We deduce that $F$ is the center of the circumcircle of $AGC$. In particular, $F$ lies on the perpendicular bisector of $[GC]$.
Now consider the homothety $h$ centered at $D$ that maps $B$ to $C$. Since the image of any line by $h$ is a parallel line, $(AB)$ is mapped to $(GC)$, and $(DA)$ is fixed, so $A$ is mapped to $G$. Since $h$ preserves length ratios, the perpendicular bisector of $[AB]$ is mapped to the perpendicular bisector of $[GC]$. Additionally, $(EB)$ is mapped to $(CF)$ due to the parallelism, so $E$ is mapped to $F$.
Therefore, $D$ (as the center of the homothety), $E$, and $F$ are collinear.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle tel que $A B \neq A C$. Soit $E$ tel que $A E=B E$ et $(B E)$ perpendiculaire à $(B C)$ et soit $F$ tel que $A F=C F$ et ( $C F)$ perpendiculaire à ( $B C$ ). Soit $D$ le point de $(B C)$ tel que $(A D)$ soit tangente au cercle circonscrit à $A B C$ en A.
Montrer que les points $D, E, F$ sont colinéaires.
|

Supposons (sans restreindre la généralité) que $A B<A C$.
Soit $O$ le centre du cercle circonscrit à $A B C$ et $G$ le point de la droite (AD) tel que $(\mathrm{AB})$ soit parallèle à (GC).
Montrons tout d'abord que les angles $\widehat{\mathrm{BAD}}$ et $\widehat{\mathrm{BCA}}$ sont de même mesure $\gamma$, et que les angles $\widehat{B O A}$ et $\widehat{C F A}$ sont tous les deux de mesure $2 \gamma$. Le seul point qui ne découle pas immédiatement du théorème de l'angle inscrit est l'égalité $\widehat{\mathrm{BOA}}=$ $\widehat{C F A}$.
Or DBA et DAC sont semblables, donc il existe une similitude $s$ de centre D qui envoie $B$ sur $A$ et $A$ sur $C$. Comme $s$ conserve les rapports de longueur, elle envoie la médiatrice de $[\mathrm{AB}]$ sur la médiatrice de $[\mathrm{BC}]$. Elle envoie aussi la perpendiculaire à ( $D A$ ) passant par $A$ (c'est-à-dire (AO), puisque ( $A D$ ) est tangente en $A$ au cercle de centre $O$ passant par $A$ ) sur la perpendiculaire à (DC) passant par C (c'est-à-dire (CF)). Donc O est envoyé sur F. Comme s conserve les mesure d'angles géométriques (attention pour ceux qui travaillent en angles orientés, c'est une similitude indirecte!), $\widehat{B O A}=\widehat{A F C}$.
On en déduit que $F$ est le centre du cercle circonscrit à $A G C$. En particulier, $F$ est sur la médiatrice de [GC].
On considère maintenant l'homothétie $h$ de centre $D$ qui envoie $B$ sur $C$. Comme l'image de toute droite par $h$ est une droite parallèle, $(A B)$ est envoyée sur (GC), et ( $D A$ ) est fixée donc $A$ est envoyé sur $G$. Comme $h$ conserve les rapports de longueurs, la médiatrice de $[A B]$ est envoyée sur la médiatrice de [GC]. De plus, (EB) est envoyée sur (CF) grâce au parallélisme, donc E est envoyé sur $F$.
Donc D (en tant que centre de l'homothétie), E et F sont alignés.
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "\nExercice 7.",
"solution_match": "## Solution de l'exercice 7"
}
|
b7cc953e-f4f4-5eef-b8dc-5847dc621148
| 607,704
|
Let $ABC$ be a triangle.
For a given point $P$ on $(BC)$, we denote $E(P)$ and $F(P)$ as the second points of intersection of the lines $(AB)$ and $(AC)$ with the circle of diameter $[AP]$. Let $T(P)$ be the intersection of the tangents to this circle at $E(P)$ and $F(P)$.
Show that as $P$ varies on $(BC)$, the geometric locus of $T(P)$ is a line.
|

## Step 1: An important initial observation.
Let H be the foot of the altitude from A in triangle ABC. Let P and P' be two points on line (BC). We denote E = E(P), F = F(P), T = T(P), E' = E(P'), F' = F(P'), T' = T(P'). We also introduce O (respectively O') as the center of the circle with diameter [AP] (respectively [AP']).
Note that the circumcircles of EAF and E'AF' intersect at A and H. In particular, H is the Miquel point of the quadrilateral with sides (EE'), (E'F'), (F'F), (FE), meaning there exists a unique direct similarity s centered at H that maps E to E' and F to F'.
Furthermore, we have \(\widehat{EOF} = 2 \widehat{EHF} = 360^\circ - 2 \widehat{EAF} = 360^\circ - \widehat{BAC}\), which does not depend on P. Therefore, \(\widehat{EOF} = \widehat{E'O'F'}\), so the direct similarity s maps O to O'.
The point T is entirely defined by the data of E, O, F (via operations such as drawing a circle, taking a tangent, etc., which are preserved by similarities). Therefore, s also maps T to T'.
From this point, the hardest part is done.
Step 2: A technical game with similarities to conclude.
Let \(P_0\) be a point on (BC). We denote \(\sigma\) as the direct similarity centered at H that maps \(E(P_0)\) to \(T(P_0)\). Let P be a point on (BC). We denote \(\sigma_P\) as the direct similarity (centered at H) that maps \(E(P_0)\) to \(E(P)\). According to the previous results, it also maps \(T(P_0)\) to \(T(P)\).
Since the two similarities have the same center, \(\sigma_P \circ \sigma = \sigma \circ \sigma_P\). In particular, \(\sigma(E(P)) = \sigma \circ \sigma_P(E(P_0)) = \sigma_P(T(P_0)) = T(P)\).
Therefore, the locus of \(T(P)\) is the image by \(\sigma\) (which is a direct similarity) of the locus of \(E(P)\) (which is a line). This is therefore a line, as desired.
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle.
Pour un point $P$ de ( $B C$ ) donné, on note $E(P)$ et $F(P)$ les deuxièmes points d'intersection des droites $(A B)$ et ( $A C$ ) avec le cercle de diamètre $[A P]$. Soit $T(P)$ l'intersection des tangentes à ce cercle en $E(P)$ et $F(P)$.
Montrer que quand $P$ varie sur ( $B C$ ), le lieu géométrique de $T(P)$ est une droite.
|

## Étape 1 : une première remarque importante.
Posons tout d'abord H le pied de la hauteur issue de $A$ dans $A B C$. Soient deux points $P$ et $P^{\prime}$ de la droite (BC). On note $E=E(P), F=F(P), T=T(P), E^{\prime}=$ $E\left(P^{\prime}\right), F^{\prime}=F\left(P^{\prime}\right), T^{\prime}=T\left(P^{\prime}\right)$. On introduit également $O$ (respectivement $O^{\prime}$ ) le centre du cercle de diamètre $[A P]$ (respectivement $\left.\left[A P^{\prime}\right]\right)$.
Remarquons que les cercles circonscrits à EAF et à $E^{\prime} A F^{\prime}$ se coupent en $A$ et H . En particulier, H est le point du Miquel du quadrilatère de côtés ( $\left.E E^{\prime}\right),\left(E^{\prime} F^{\prime}\right),\left(F^{\prime} F\right)$, (FE) autrement dit il existe une unique similitude directe $s$ de centre $H$ qui envoie $E$ sur $E^{\prime}$ et $F$ sur $F^{\prime}$.
D'autre part, on a $^{\mathrm{EOF}}=2 \widehat{\mathrm{EHF}}=360^{\circ}-2 \widehat{\mathrm{EAF}}=360^{\circ}-\widehat{\mathrm{BAC}}$, ce qui ne dépend pas de $P$. Donc $\widehat{\mathrm{EOF}}=\widehat{\mathrm{E}^{\prime} \mathrm{O}^{\prime} \mathrm{F}^{\prime}}$, donc la similitude directe $s$ envoie O sur $\mathrm{O}^{\prime}$.
Or, le point $T$ est entièrement défini par la donnée de $E, O, F$ (via des opérations de type tracer un cercle, prendre une tangente..., qui sont conservées par les similitudes). Donc s envoie aussi T sur $\mathrm{T}^{\prime}$.
À partir de là, le plus dur est fait.
Étape 2 : un jeu technique avec les similitudes pour conclure.
Soit $P_{0}$ un point de (BC). On note $\sigma$ la similitude directe de centre $H$ qui envoie $E\left(P_{0}\right)$ sur $T\left(P_{0}\right)$. Soit $P$ un point de (BC). On note $\sigma_{P}$ la similitude directe (de centre $H)$ qui envoie $E\left(P_{0}\right)$ sur $E(P)$. D'après ce qui précède, elle envoie aussi $T\left(P_{0}\right)$ sur T(P).
Comme les deux similitudes on le même centre $\sigma_{P} \circ \sigma=\sigma \circ \sigma_{P}$. En particulier, $\sigma(E(P))=\sigma \circ \sigma_{P}\left(E\left(P_{0}\right)\right)=\sigma_{P}\left(T\left(P_{0}\right)\right)=T(P)$.
Donc le lieu de $T(P)$ est l'image par $\sigma$ (qui est une similitude directe) du lieu de $E(P)$ (qui est une droite). C'est donc une droite, comme voulu.
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "## Exercice 8.",
"solution_match": "## Solution de l'exercice 8"
}
|
ee47f55d-b66b-5445-912c-3835e60ed4f2
| 607,705
|
Let $ABC$ be a triangle, $O$ the center of its circumcircle. Let $P$ be a point on $(AO)$ and $D, E, F$ the orthogonal projections of $P$ on $(AB)$, $(BC)$, and $(CA)$. Let $X$ and $Y$ be the intersections of the circumcircles of $DEF$ and $BCP$.
Show that $\widehat{B A X}=\widehat{Y A C}$
|

## Step 1: Show that (DF) is parallel to (BC).
Let \( \mathrm{P}_{0} \) be the point diametrically opposite to \( A \) on the circumcircle of \( \triangle ABC \). \((P_{0} C)\) is perpendicular to \((A C)\) and thus parallel to \((\mathrm{PF})\), and \((\mathrm{P}_{0} B)\) is similarly parallel to \((\mathrm{PD})\).
Therefore, by the theorem of Thales, \(\frac{A D}{A B} = \frac{A P}{A P_{0}} = \frac{A F}{A C}\), implying that \((D F)\) is parallel to \((B C)\). Step 2: Show that \( H_{A} \), the foot of the altitude from \( A \), lies on (DEF).

Let \( G = (A H_{A} A) \cap (D F) \), \( J \) the orthogonal projection of \( P \) (and also of \( E \)) on \((D F)\), and \( K \) the orthogonal projection of \( P \) on \((A H_{A})\).
\( PKGJ \) is a rectangle, and \( P, K, D, F \) are concyclic on the circle with diameter \([PA]\). Therefore, \( PKFD \) is an isosceles trapezoid, so \((PJ)\) and \((KG)\) are symmetric with respect to the perpendicular bisector of \([DF]\).
Since \( EJGH \) is a rectangle and \((H_{A} G)\) and \((E J)\) are symmetric with respect to the perpendicular bisector of \((EF)\), \( D, H_{A}, E, F \) are concyclic.
Step 3: To conclude.
Step 1 shows that there exists an involution centered at \( A \) that swaps \( B \) and \( F \) on one hand, and \( C \) and \( D \) on the other. To conclude, it suffices to show that this involution swaps \( X \) and \( Y \), i.e., it maps the circumcircle of \( \triangle BCP \) to the circumcircle of \( \triangle DEF \).
The only difficulty is to show that the point to which the involution maps \( P \) lies on the circumcircle of \( \triangle DEF \).
Since \( P \) is a point on the circumcircle of \( \triangle ADF \) such that \((AP)\) and the circumcircle of \( \triangle ADF \) are perpendicular at \( P \), its image \( I \) is a point on the line \((BC)\) such that \((BC)\) and \((AI)\) are perpendicular at \( I \). Therefore, \( I = H_{A} \), and Step 2 allows us to conclude.
[^0]: 1. see the beginner geometry textbook for more details on directed angles of lines
[^1]: 2. i.e., the lines \((A B)\) and \((C D)\) are parallel or intersect outside the segments \([A B]\) and \([C D]\), and the lines \((B C)\) and \((D A)\) are parallel or intersect outside the segments \([BC]\) and \([DA]\)
|
proof
|
Yes
|
Yes
|
proof
|
Geometry
|
Soit $A B C$ un triangle, O le centre de son cercle circonscrit. Soit P un point sur (AO) et $D, E, F$ les projections orthogonales de $P$ sur ( $A B$ ), ( $B C$ ) et (CA). Soit $X$ et $Y$ les intersections des cercles circonscrits à DEF et à BCP.
Montrer que $\widehat{B A X}=\widehat{Y A C}$
|

## Étape 1 : Montrons que (DF) est parallèle à (BC).
Soit $\mathrm{P}_{0}$ le point diamétralement opposé à $A$ sur le cercle circonscrit à $A B C .\left(P_{0} C\right)$ est perpendiculaire à $(A C)$ donc parallèle à $(\mathrm{PF})$ et $\left(\mathrm{P}_{0} B\right)$ est de même parallèle à (PD).
Donc, d'après le théorème de Thalès, $\frac{A D}{A B}=\frac{A P}{A P_{0}}=\frac{A F}{A C}$, $d^{\prime}$ où ( $D F$ ) parallèle à ( $B C$ ). Étape 2 : Montrons que $H_{A}$, le pied de la hauteur issue de $A$ appartient à (DEF).

On pose $G=\left(A H_{A} A\right) \cap(D F), J$ la projection orthogonale de $P$ (celle de $E$ aussi) sur (DF) et $K$ la projection (orthogonale) de $P$ sur $\left(A H_{A}\right)$.
PKGJ est un rectangle, et $P, K, D, F$ sont cocycliques sur le cercle de diamètre [PA]. Donc PKFD est un trapèze isocèle, donc (PJ) et ( KG ) sont symétriques par rapport à la médiatrice de [DF].
Comme $E_{J G H}$ est un rectangle et $\left(H_{A} G\right)$ et $(E J)$ sont symétriques par rapport à la médiatrice de (EF), $D, H_{A}, E, F$ sont cocycliques.
Étape 3 : pour conclure.
L'étape 1 permet de montrer qu'il existe une involution de centre $A$ qui échange $B$ et $F$ d'une part, $C$ et $D$ d'autre part.Pour conclure, il suffit de montrer que cette involution échange $X$ et $Y$, c'est-à-dire qu'elle envoie le cercle circonscrit à BCP sur le cercle circonscrit à DEF.
La seule difficulté est de montrer que le point sur lequel l'involution envoie P appartient au cercle circonscrit à DEF.
Or $P$ est un point du cercle circonscrit à ADF tel que (AP) et le cercle circonscrit à $A D F$ sont perpendiculaires en $P$. Donc son image $I$ est un point de la droite (BC) tels que (BC) et (AI) sont perpendiculaires en I. Donc $I=H_{A}$, et l'étape 2 permet de conclure.
[^0]: 1. voir le poly de géométrie débutant pour plus de détails sur les angles orientés de droites
[^1]: 2. c'est-à-dire que les droites $(A B)$ et $(C D)$ sont parallèles ou se coupent à l'extérieur des segments $[A B]$ et $[C D]$ et les droites $(B C)$ et $(D A)$ sont parallèles ou se coupent à l'extérieur des segments [BC] et [DA]
|
{
"resource_path": "French/segmented/envois/fr-pofm-2017-2018-envoi2-corrige.jsonl",
"problem_match": "\nExercice 9.",
"solution_match": "## Solution de l'exercice 9"
}
|
d7487115-8bc0-5f6c-8a34-dbfa5c0f81ce
| 607,706
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.