AI × SCIENCE · 未解決問題トラッカー

未知、証明終わり。

Where AI turns unknowns into Q.E.D.

AI が解いた科学の問題をひとつ残らず追跡します。各記録には結果の格付け、検証の方法、元の出典を明記し、誰でも注釈や異議を書き込めます。

格付け基準

完全解AI が単独で、または主導して、完全かつ新しい解を与えた。
部分的結果評価の改良、新しい構成、特殊な場合の解決。元の問題は未解決のまま。
既知文献AI が示した「新しい解」は既存の文献にすでにあった。
未検証公に主張されているが、まだ独立に検証されていない。

問題一覧

新しい順 · 全 262 件
  1. 2025-12-30数学 · Number theory
    Erdős Problem #1095Partial progress by Aristotle (30 Dec 2025): new proof of (slightly weaker) partial result (Lean). 2 AI contributions are recorded in all.Aristotle✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    部分的結果
  2. 2025-12-27数学 · Distances
    Erdős Problem #958Aristotle found a new proof of a problem that was already solved (27 Dec 2025).Aristotle✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    既知文献
  3. 2025-12-26数学 · Number theory
    Erdős Problem #897Archivara and Aristotle produced a solution (26 Dec 2025), but a comparable result was already in the literature: Wirsing (1981).Archivara and Aristotle✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    既知文献
  4. 2025-12-25数学 · Number theory
    Erdős Problem #333Claude Opus 4.5 and GPT-5.2 Pro produced a solution (25 Dec 2025), but a comparable result was already in the literature: Erdős and Newman (1977). 2 AI contributions are recorded in all.Claude Opus 4.5 and GPT-5.2 Pro✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    既知文献
  5. 2025-12-21数学 · Number theory
    Erdős Problem #379Seed Prover 1.5 found a new proof of a problem that was already solved (21 Dec 2025).Seed Prover 1.5✓ Listed in Tao's wiki注釈 0 件
    既知文献
  6. 2025-12-18数学 · Irrationality
    Erdős Problem #264Partial progress by Aristotle (18 Dec 2025): new proof of partial result (Lean).Aristotle✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    部分的結果
  7. 2025-12-16数学 · Analysis
    Erdős Problem #1038Partial progress by catsflowers5544, jspier, Junnosuke Koizumi, Kenneth Mendoza, Nat Sothanaphan, Terence Tao and Hua Xu with AlphaEvolve, Claude Fable 5, Codex, GPT-5.2 Thinking, GPT-5.4 Thinking and GPT-5.5 (16 Dec 2025): partial result.catsflowers5544, jspier, Junnosuke Koizumi, Kenneth Mendoza, Nat Sothanaphan, Terence Tao and Hua Xu with AlphaEvolve, Claude Fable 5, Codex, GPT-5.2 Thinking, GPT-5.4 Thinking and GPT-5.5✓ Listed in Tao's wiki注釈 0 件
    部分的結果
  8. 2025-12-08数学 · Combinatorics
    Erdős Problem #1026Full solution by Boris Alexeev, Stijn Cambie, Terence Tao and Lawrence Wu with AlphaEvolve, Aristotle, Gemini and GPT, formalized in Lean (8 Dec 2025). 2 AI contributions are recorded in all.Boris Alexeev, Stijn Cambie, Terence Tao and Lawrence Wu with AlphaEvolve, Aristotle, Gemini and GPT✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    完全解
  9. 2025-12-04数学 · Number theory
    Erdős Problem #43Partial progress by Aristotle (4 Dec 2025): new proof of partial result (Lean).Aristotle✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    部分的結果
  10. 2025-12-03数学 · Number theory
    Erdős Problem #481GPT found that the problem had already been solved in the literature (3 Dec 2025).GPT✓ Listed in Tao's wiki注釈 0 件
    既知文献
  11. 2025-11-29数学 · Number theory
    Erdős Problem #124Partial progress by Aristotle (29 Nov 2025): partial result (Lean).Aristotle✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    部分的結果
  12. 2025-11-27数学 · Number theory
    Erdős Problem #488Partial progress by Aristotle (27 Nov 2025): new solution to variant problem (Lean). 2 AI contributions are recorded in all.Aristotle✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    部分的結果
  13. 2025-11-23数学 · Number theory
    Erdős Problem #942Partial progress by Gemini (23 Nov 2025): new proof found. 2 AI contributions are recorded in all.Gemini✓ Lean formalization · Listed in Tao's wiki注釈 0 件
    部分的結果
  14. 2025-11-20数学 · Number theory
    Erdős Problem #367Partial progress by Boris Alexeev, Wouter van Doorn and Terence Tao with Aristotle and Gemini Deep Think (20 Nov 2025): partial result.Boris Alexeev, Wouter van Doorn and Terence Tao with Aristotle and Gemini Deep Think✓ Listed in Tao's wiki注釈 0 件
    部分的結果
  15. 2025-11-20数学 · Number theory
    Erdős Problem #848Full solution by Mehtaab Sawhney and Mark Sellke with GPT-5 (20 Nov 2025). 2 AI contributions are recorded in all.Mehtaab Sawhney and Mark Sellke with GPT-5✓ Listed in Tao's wiki注釈 0 件
    完全解
  16. 2025-11-03数学 · Mathematical discovery
    Kakeya and Nikodym sets in finite fieldsAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  17. 2025-11-03数学 · Mathematical discovery
    3D Kakeya problemAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  18. 2025-11-03数学 · Mathematical discovery
    An autocorrelation problem related to Sidon setsAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  19. 2025-11-03数学 · Mathematical discovery
    How much can an autocorrelation of a non-negative function resemble an indicator function?AlphaEvolve improved the best known bound; the record has since been surpassed. The problem remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  20. 2025-11-03数学 · Mathematical discovery
    The Arithmetic Kakeya ConjectureAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  21. 2025-11-03数学 · Mathematical discovery
    Spherical DesignsAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  22. 2025-11-03数学 · Mathematical discovery
    Packing in a dilateAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  23. 2025-11-03数学 · Mathematical discovery
    Circle packing in a square / rectangleAlphaEvolve improved the best known bound; the record has since been surpassed. The problem remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  24. 2025-11-03数学 · Mathematical discovery
    Factoring N! into N numbersAlphaEvolve improved the best known bound; the record has since been surpassed. The problem remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  25. 2025-11-03数学 · Mathematical discovery
    An autocorrelation problem with functions that can take negative valuesAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  26. 2025-11-03数学 · Mathematical discovery
    Sum-difference problem IAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  27. 2025-11-03数学 · Mathematical discovery
    Sum-difference problem IIIAlphaEvolve improved the best known bound; the record has since been surpassed. The problem remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  28. 2025-11-03数学 · Mathematical discovery
    Heilbronn problem in a fixed bounding boxAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  29. 2025-11-03数学 · Mathematical discovery
    Heilbronn problem in an arbitrary convex bounding boxAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  30. 2025-11-03数学 · Mathematical discovery
    Erdős minimum overlap problemAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  31. 2025-11-03数学 · Mathematical discovery
    Max to min ratiosAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  32. 2025-11-03数学 · Mathematical discovery
    Subsets of the grid with no isosceles trianglesAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  33. 2025-11-03数学 · Mathematical discovery
    The no 5 on a sphere problemAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  34. 2025-11-03数学 · Mathematical discovery
    The Ring Loading ProblemAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  35. 2025-11-03数学 · Mathematical discovery
    The three-dimensional moving sofa problem with two perpendicular turnsAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  36. 2025-11-03数学 · Mathematical discovery
    Difference BasesAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  37. 2025-11-03数学 · Mathematical discovery
    Kissing numbersAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  38. 2025-11-03数学 · Mathematical discovery
    Kakeya needle problemAlphaEvolve found a construction that improved on the best bound known at the time; the problem itself remains open.AlphaEvolve (Google DeepMind)✓ Construction can be checked directly · Preprint (arXiv, 2025)注釈 0 件
    部分的結果
  39. 2025-11-03数学 · Number theory
    Erdős Problem #1097Partial progress by AlphaEvolve (3 Nov 2025): slight improvement to past construction.AlphaEvolve✓ Listed in Tao's wiki注釈 0 件
    部分的結果
  40. 2025-11-03数学 · Number theory
    Erdős Problem #36Partial progress by AlphaEvolve (3 Nov 2025): slight improvement to past construction. 2 AI contributions are recorded in all.AlphaEvolve✓ Listed in Tao's wiki注釈 0 件
    部分的結果