Browse Problems

Search and filter the ASI Benchmark problem set. Click any problem to see its Lean statement and recent submissions.

Filters

Showing 50 of 1,494

Results

Prize Problem Status ID
$1,000,000 beal_conjecture
The **Beal Conjecture**: if we are given positive integers $A, B, C, x, y, z$ such that $x, y, z > 2$ and $A^x + B^y = C^z$ then $A, B, C$ …
Open Wikipedia__BealConjecture__beal_conjecture
$1,000,000 generalized_riemann_hypothesis
The **Generalized Riemann Hypothesis** asserts that all the non-trivial zeros of the Dirichlet $L$-function $L(\chi, s)$ of a primitive Dirichlet character $\chi$ have real part $\frac{1}{2}$.
Open Millenium__GeneralizedRiemannHypothesis__generalized_riemann_hypothesis
$1,000,000 NP_ne_coNP
**NP ≠ coNP**: The conjecture that the complexity classes NP and coNP are not equal.
Open Millenium__PvsNP__NP_ne_coNP
$1,000,000 P_ne_NP
**P ≠ NP**: The conjecture that the complexity classes P and NP are not equal.
Open Millenium__PvsNP__P_ne_NP
$770,000 collatz_conjecture
Now form a sequence beginning with any positive integer, where each subsequent term is obtained by applying the operation defined above to the previous term. The **Collatz conjecture** states that for any …
Open Wikipedia__CollatzConjecture__collatz_conjecture
$10,000 erdos_142
Prove an asymptotic formula for $r_k(N)$, the largest possible size of a subset of $\{1, \dots, N\}$ that does not contain any non-trivial $k$-term arithmetic progression.
Open ErdosProblems__142__erdos_142
$10,000 erdos_142.variants.lower
Show that $r_k(N) = o_k(N / \log N)$, where $r_k(N)$ the largest possible size of a subset of $\{1, \dots, N\}$ that does not contain any non-trivial $k$-term arithmetic progression.
Open ErdosProblems__142__erdos_142.variants.lower
$10,000 erdos_142.variants.three
Prove an asymptotic formula for $r_3(N)$, the largest possible size of a subset of $\{1, \dots, N\}$ that does not contain any non-trivial $3$-term arithmetic progression.
Open ErdosProblems__142__erdos_142.variants.three
$10,000 erdos_142.variants.upper
Find functions $f_k$, such that $r_k(N) = O_k(f_k)$, where $r_k(N)$ the largest possible size of a subset of $\{1, \dots, N\}$ that does not contain any non-trivial $k$-term arithmetic progression.
Open ErdosProblems__142__erdos_142.variants.upper
$5,000 erdos_3
If $A \subset \mathbb{N} has $\sum_{n \in A}\frac 1 n = \infty$, then must $A$ contain arbitrarily long arithmetic progressions?
Open ErdosProblems__3__erdos_3
$500 erdos_1
If $A\subseteq\{1, ..., N\}$ with $|A| = n$ is such that the subset sums $\sum_{a\in S}a$ are distinct for all $S\subseteq A$ then $$ N \gg 2 ^ n. $$
Open ErdosProblems__1__erdos_1
$500 erdos_1135 Open ErdosProblems__1135__erdos_1135
$500 erdos_143.parts.i
Does this imply that $$ \liminf \frac{|A \cap [1,x]|}{x} = 0? $$
Open ErdosProblems__143__erdos_143.parts.i
$500 erdos_143.parts.ii
Or $$ \sum_{x \in A} \frac{1}{x \log x} < \infty, $$
Open ErdosProblems__143__erdos_143.parts.ii
$500 erdos_1.variants.lb
Erdős and Moser [Er56] proved $$ N \geq (\tfrac{1}{4} - o(1)) \frac{2^n}{\sqrt{n}}. $$ [Er56] Erdős, P., _Problems and results in additive number theory_. Colloque sur la Th\'{E}orie des Nombres, Bruxelles, 1955 (1956), …
Solved ErdosProblems__1__erdos_1.variants.lb
$500 erdos_1.variants.lb_strong
A number of improvements of the constant $\frac{1}{4}$ have been given, with the current record $\sqrt{2 / \pi}$ first provied in unpublished work of Elkies and Gleason.
Solved ErdosProblems__1__erdos_1.variants.lb_strong
$500 erdos_1.variants.least_N_5
The minimal value of $N$ such that there exists a sum-distinct set with five elements is $13$. https://oeis.org/A276661
Solved ErdosProblems__1__erdos_1.variants.least_N_5
$500 erdos_1.variants.least_N_9
The minimal value of $N$ such that there exists a sum-distinct set with nine elements is $161$. https://oeis.org/A276661
Solved ErdosProblems__1__erdos_1.variants.least_N_9
$500 erdos_1.variants.real
A generalisation of the problem to sets $A \subseteq (0, N]$ of real numbers, such that the subset sums all differ by at least $1$ is proposed in [Er73] and [ErGr80]. [Er73] …
Open ErdosProblems__1__erdos_1.variants.real
$500 erdos_28
If $A ⊆ \mathbb{N}$ is such that $A + A$ contains all but finitely many integers then $\limsup 1_A ∗ 1_A(n) = \infty$.
Open ErdosProblems__28__erdos_28
$500 erdos_41
Let `A ⊆ ℕ` be an infinite set such that the triple sums `a + b + c` are all distinct for `a, b, c` in `A` (aside from the trivial coincidences). …
Open ErdosProblems__41__erdos_41
$500 erdos_41_i
Erdős proved the following pairwise version. Let `A ⊆ ℕ` be an infinite set such that the pairwise sums `a + b` are all distinct for `a, b` in `A` (aside from …
Solved ErdosProblems__41__erdos_41_i
$500 erdos_89
Does every set of $n$ distinct points in $\mathbb{R}^2$ determine $\gg \frac{n}{\sqrt{\log n}}$ many distinct distances?
Open ErdosProblems__89__erdos_89
$500 erdos_89.variants.n_dvd_log_n
Guth and Katz [GuKa15] proved that there are always $\gg \frac{n}{\log n}$ many distinct distances. [GuKa15] Guth, Larry and Katz, Nets Hawk, On the Erdős distinct distances problem in the plane. Ann. …
Solved ErdosProblems__89__erdos_89.variants.n_dvd_log_n
$250 erdos_126
Let $f(n)$ be maximal such that if $A\subseteq\mathbb{N}$ has $|A| = n$ then $\prod_{a\neq b\in A}(a + b)$ has at least $f(n)$ distinct prime factors. Is it true that $\frac{f(n)}{\log n} \to\infty$?
Open ErdosProblems__126__erdos_126
$250 erdos_126.variants.IsBigO
Erdős and Turán proved [ErTu34] in their first joint paper that $$ \log n \ll f(n) \ll \frac{n}{\log n} $$ [ErTu34] Erdős, Paul and Turan, Paul, _On a Problem in the Elementary …
Solved ErdosProblems__126__erdos_126.variants.IsBigO
$250 erdos_126.variants.isLittleO
Erdős says that $f(n) = o(\frac{n}{\log n})$ has never been proved.
Open ErdosProblems__126__erdos_126.variants.isLittleO
- _02062_le_density_rank_zero
Theorem 5 of [BS2013]: when elliptic curves over ℚ are ordered by height, a density of at least 20.62% have rank 0.
Solved Wikipedia__EllipticCurveRank___02062_le_density_rank_zero
- _08375_le_density_rank_zero_one
Theorem 4 of [BS2013]: when elliptic curves over ℚ are ordered by height, a density of at least 83.75% have rank 0 or 1.
Solved Wikipedia__EllipticCurveRank___08375_le_density_rank_zero_one
- abc
For every positive real number `ε`, there exist only finitely many triples `(a, b, c)` of coprime positive integers, with `a + b = c`, such that `c > rad(abc)^(1+ε)`
Open Wikipedia__ABC__abc
- abc.variants.lt_constant_mul
For every positive real number ε, there exists a constant `K_ε` such that for all triples (a, b, c) of coprime positive integers, with a + b = c we have `c …
Open Wikipedia__ABC__abc.variants.lt_constant_mul
- abc.variants.quality
For every positive real number ε, there exist only finitely many triples `(a, b, c)` of coprime positive integers with `a + b = c` such that `q(a, b, c) > 1 …
Open Wikipedia__ABC__abc.variants.quality
- abelian_is_leinster_iff_cyclic_perfect
An abelian group is a Leinster group if and only if it is cyclic with order equal to a perfect number. Reference: Leinster, Tom (2001). "Perfect numbers and groups". Theorem 2.1.
Solved Wikipedia__LeinsterGroup__abelian_is_leinster_iff_cyclic_perfect
- a_formula
Conjecture: a(n) = 3^n + 3 * 2^n + 6 for n ≥ 1.
Solved OEIS__87719__a_formula
- agoh_giuga
The **Agoh-Giuga Conjecture**, Agoh's formulation
Open Wikipedia__AgohGiuga__agoh_giuga
- agoh_giuga.variants._1000_le_digits_length_of_isStrongGiuga
Giuga showed that a counterexample Giuga number has at least 1000 digits. Ref: G. Giuga, _Su una presumibile proprieta caratteristica dei numeri primi_
Solved Wikipedia__AgohGiuga__agoh_giuga.variants._1000_le_digits_length_of_isStrongGiuga
- agoh_giuga.variants._13000_le_digits_length_of_isStrongGiuga
Borwein, Borwein, Borwein and Girgensohn showed that any strong Giuga number has at least 13000 digits. Ref: D. Borwein, J. M. Borwein, P. B. Borwein, and R. Girgensohn, _Giuga’s conjecture on primality_
Solved Wikipedia__AgohGiuga__agoh_giuga.variants._13000_le_digits_length_of_isStrongGiuga
- agoh_giuga.variants._1700_le_digits_length_of_isStrongGiuga
Bedocchi showed that any Giuga number has at least 1700 digits. Ref: E. Bedocchi, _Note on a conjecture about prime numbers_
Solved Wikipedia__AgohGiuga__agoh_giuga.variants._1700_le_digits_length_of_isStrongGiuga
- agoh_giuga.variants.equivalence
The two statements of the conjecture are equivalent.
Solved Wikipedia__AgohGiuga__agoh_giuga.variants.equivalence
- agoh_giuga.variants.giuga
The **Agoh-Giuga Conjecture**, Giuga's formulation
Open Wikipedia__AgohGiuga__agoh_giuga.variants.giuga
- agoh_giuga.variants.isStrongGiuga_growth
Let `G(X)` denote the number of exceptions `n ≤ X` to Giuga’s conjecture. Then for `X` larger than an absolute constant which can be made explicit, `G(X) ≪ X^{1/2} log X`. Ref: …
Solved Wikipedia__AgohGiuga__agoh_giuga.variants.isStrongGiuga_growth
- agoh_giuga.variants.isStrongGiuga_implies_isCarmichael
Every strong Giuga number is a Carmichael number.
Solved Wikipedia__AgohGiuga__agoh_giuga.variants.isStrongGiuga_implies_isCarmichael
- agoh_giuga.variants.le_primeFactors_card_of_isStrongGiuga
Giuga showed that a Giuga number has at least 9 prime factors. Ref: G. Giuga, _Su una presumibile proprieta caratteristica dei numeri primi_
Solved Wikipedia__AgohGiuga__agoh_giuga.variants.le_primeFactors_card_of_isStrongGiuga
- a.infinite
Conjecture: the sequence A228828 is infinite.
Open OEIS__228828__a.infinite
- a_isBigO
Conjecture: $a(n) = O(\log(n)\log(\log(n)))$.
Open OEIS__34693__a_isBigO
- algebraicIndependent_e_pi
Are $e$ and $\pi$ algebraically independent?
Open Wikipedia__Irrational__algebraicIndependent_e_pi
- all_fermat_squarefree
Are all Fermat numbers are square-free?
Open Wikipedia__Fermat__all_fermat_squarefree
- amitsur_conjecture
The **Amitsur Conjecture**: If `J` is a nil ideal in `R`, then `J[x]` is a nil ideal of the polynomial ring `R[x]`. This is known to be false, see Agata Smoktunowicz, _Polynomial …
Solved Wikipedia__Koethe__amitsur_conjecture
- andrica_conjecture
**Andrica's conjecture** The inequality $\sqrt{p_{n+1}}-\sqrt{p_n} < 1$ holds for all $n$, where $p_n$ is the $n$-th prime number.
Open Wikipedia__Andrica__andrica_conjecture
- andrica_conjecture.ferreira_large_n
Ferreira proved that Andrica's conjecture is true for sufficiently large n.
Solved Wikipedia__Andrica__andrica_conjecture.ferreira_large_n