--- id: "2026-11-07-ai-assisted-results-november-7-listing" url: "https://postcutoff.com/e/2026-11-07-ai-assisted-results-november-7-listing/" as_of: "2026-11-09T21:13:00+01:00" date: "2026-11-07" date_precision: day category: science importance: 2 confidence: medium status: [Awaiting review] verification: Lean-verified sources: 65 editor: human editor human_review: null version: "2026-11-07" --- As of: 2026-11-09 21:13 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-11-07-ai-assisted-results-november-7-listing/ # AI-assisted results, 7 Nov: Hexagon of 6 Nov and arXiv Full title: AI-assisted results in the 7 Nov sweep: Whiteley's vertex-splitting conjecture by ChatGPT 6.1 Sol, single-exponential Minimum Bisection, isometric embedding in n(n+1)/2+28 dimensions, Armstrong–Vicol's Obukhov–Corrsin regularization, plus 35 Hexagon works Catalogue of AI-disclosing works from the Hexagon deposits of 6 Nov 2026 and the arXiv announcement read on 7 Nov, beyond the items with own entries. AI statements are quoted from Hexagon provenance records or PDFs (Hexagon does not judge correctness); none is refereed. Also: eight lines of the October Hexagon backlog and the launch of the Futures of Maths survey. ## Key facts - Own entries: [2026-11-06-axiom-weil-conjectures-lean-formalization](https://postcutoff.com/e/2026-11-06-axiom-weil-conjectures-lean-formalization/index.md) (AxiomMath/Weil), [2026-11-04-axiom-stacks-project-lean-formalization](https://postcutoff.com/e/2026-11-04-axiom-stacks-project-lean-formalization/index.md) (AxiomMath/Stacks), [2026-11-06-navier-stokes-unforced-leray-hopf-nonuniqueness-buckmaster-coiculescu-li](https://postcutoff.com/e/2026-11-06-navier-stokes-unforced-leray-hopf-nonuniqueness-buckmaster-coiculescu-li/index.md) (Hexagon 2611.00143) - Rigidity: James Cruickshank (Galway) with a co-author, Whiteley's conjecture that every nontrivial vertex split of a generically globally rigid graph preserves generic global rigidity in R^d for all d; 'All the proofs of the main results presented in this paper were created by ChatGPT 6.1 Sol', all parts human-checked (Hexagon 2611.00140) - Geometry and analysis: Yi Wang and Wenchang Yang, every closed Riemannian n-manifold embeds isometrically in R^{n(n+1)/2+28} (was surplus max{n+5, 2n}); 'the detailed technical arguments have not yet been fully verified or understood by humans' (2611.00153). Scott Armstrong and Vlad Vicol, anomalous regularization of passive scalars up to the Obukhov–Corrsin exponent: their 2022 outline 'was fed to LLMs (Claude Opus 5.5 and GPT 6 Astra)' who produced 'a complete but very long (612 page) natural language (slop) proof', then autoformalized and simplified (2611.00165). Dave Goel, Sheil-Small's 1974 covering problem (Hayman–Lingham 4.24) answered yes, 'done overwhelmingly by AI models' (2611.00154) - Combinatorics: Matthew Kwan and Huy Tuan Pham, the constant Steiner kernel is not optimal at large girth, found 'Using ChatGPT 6 Pro', primarily AI-written, all human-checked (2611.00166); Alexander Kramer disproves the Cambie–Jooken–Wagner edge-contraction conjecture on mean subtree order (2611.00151); Max Glass, R_2(n) for binary rich words is not O(n^{C√n}), disproving a conjectured bound, GPT-6 Astra, Lean end to end, no human checking (2611.00167); Teo Banica, regular complex Hadamard matrices of order 7, 8, 'Written by Chat GPT' (2611.00079) - Qiyue Tang (Tsinghua) with GPT-6-Pro sessions of 2–24 hours, audited by Codex, 'some' human understanding: equivalence of the four-variable Hessian and planar Jacobian conjectures (2611.00156); deterministic polynomial-time factorization over finite fields using 'a Dedekind zeta zero-free theorem' (2611.00135; would settle a long-open derandomization question; it relies on that cited input and has no expert check); undecidability of quiver mutation equivalence (2611.00158), decidability of mutation-acyclicity (2611.00163), Schmeisser's conjecture in large degree (2611.00162), no minimum adapted CAD in dimension ≥ 4 (2611.00131) - Hessian conjecture HC_4: David Niedbala Giraudin with Claude, degree ≤ 5 potentials (2611.00161, 2611.00134), 'None of this contribution has been checked and understood by any human' - Complexity after the ETH refutations: Xiaoyu Li (UNSW) with Claude Opus 5.5 in Claude Code, exact exponent of fast attention after SETH (2611.00132) and the price of Bayes-optimal in-context learning, where 'Claude chose the question, proved the results and wrote the text' (2611.00133); Vaibhav Tulsyan with Claude, barriers for the OpenAI and Anthropic counting engines, 45 Lean theorems (2611.00149) - Number theory and Lean: twinheterodox with Codex Astra-6-Max, irrational even Dirichlet beta values (at least one of β(m+1)…β(67m−1); counts for s ≥ 160) (2611.00160, 2611.00139); Steve Hubbard, Lean proofs of Dudek's RH prime gap and Saouter's criterion toward odd Goldbach to 10^20, 'No human expert has reviewed the mathematics' (2611.00157, 2611.00159); Antonio Mennillo, prime sums and Riemann zeros in Lean (2611.00130); Yi-kun Li, Gauss law for eras of Bianchi IX, Lean (2611.00150); Lean formalizations of SPR synthesis (2611.00146) and COBOL-to-Rust/Java translations (2611.00152) - Other Hexagon 6 Nov: quartic Fekete points on every simplex (2611.00155, no human check); Haagerup center at c = 8 (2611.00164); N-body symplectic integration across collisions with Gemini and Antigravity (2611.00136); and human-written works with minor AI use (2611.00138, 2611.00142, 2611.00145, 2611.00147) - arXiv, AI credited with content: Anand–Kipouridis–Węgrzycki, Minimum Bisection in 2^{O(k)} n^{O(1)} (was 2^{O(k log k)}, Cygan et al.), 'Claude Opus-5.5 and GPT-6 Astra obtained the main improvement to the dynamic program' (2611.08202); streaming CSPs under deletions, a GPT-6 Astra proof of an Ω(n²) 3-XOR lower bound 'served as a key inspiration' (2611.07309); star-shaped polygon packing, 'ChatGPT was used to obtain some of the crucial ideas' (2611.07100); Fei, ChatGPT provided 'most of the arguments in Section 8' (2611.07549); random reshuffling, GPT-5.6 Sol for 'a key intermediate result' (2611.07406); higher theta lifts, technical steps 'developed in close cooperation with ChatGPT' (2611.07090) - arXiv, smaller AI steps: simpler argument found with Claude Opus (2611.07185); monotone quantity 'discovered with the help of ChatGPT Plus' (2611.06978); LLM proved Proposition 2.11 (2611.07556); duality found with ChatGPT 5.6 Sol (2611.08073); Gemini completed Lemma 5.4 (2611.08002); ChatGPT 6.1 Sol produced a Lean certificate (2611.07043); Astra and Claude Opus worked out lower-bound details (2611.08351); proofs 'the product of useful conversations with ChatGPT6' (2611.08464); 'produced in collaboration with ChatGPT' (2611.08480); Aristotle-generated Lean (2611.07303); ChatGPT for a quartic computation in AdS₃ (2611.07019); examples generated with Claude Sonnet 5.5 (2611.08071); a reference found with LLMs (2611.07202). The rest of the 200 mention AI for editing, literature, code or figures only - Conjecture papers without AI disclosure (79): no famous problem with an AI angle; a few notable human results (Yang–Koolen conjecture 2611.00591, Erdős–Gyárfás for odd-order Cayley graphs 2611.05060, Cameron–Praeger for Steiner 6-designs 2611.06081) - Repos: google-deepmind/formal-conjectures commits of 5–6 Nov add statements only (98 OEIS files; Green's and Erdős problems listed on 6 Nov); AxiomMath/Weil has its own entry - Hexagon backlog (8 lines): Deep Bhattacharjee with Claude, counterexamples to Graffiti.pc conjectures 66, 319, 352, 358, 359, 427 (2610.00501, 2610.00500), to the Adaricheva–Mata–Silberger–Zamojska-Dzienio conjecture on maximal sublattices (2610.00497, 2610.00495), Sahbi's β_k = SF_k question (2610.00498), regular Morley tetrahedra (2610.00499); Codex-assisted fault detection (2610.00503); human-written inequality note (2610.00496) - Community: Futures of Maths, an anonymous survey of research mathematicians on maths and AI, launched 5 Nov (guest post on Terence Tao's blog by Fournier-Facio, Kyrychenko, Roozenbeek and Wykowski; respondents need a zbMATH-indexed paper in the last 5 years) ## What happened The 7 Nov sweep listed 35 Hexagon works deposited on 6 Nov and 200 arXiv papers from the latest announcement that mention AI (most only for editing, literature search or code). The items above are those where the authors credit AI with mathematical content. Quotes come from Hexagon provenance statements or PDFs. Hexagon does not judge correctness, and none of these works is refereed. ## What is disputed or not yet verified - Verification: Unrefereed preprints and Hexagon deposits ## Your AI and this story - GPT-6 Astra (training cutoff April 2026): 191 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 130 days after its cutoff - Gemini 4 Argon (training cutoff March 2026): 221 days after its cutoff - Grok 4.7 (training cutoff May 2026): 160 days after its cutoff ## Sources 1. [Hexagon 2611.00079](https://hexagonmath.org/abs/2611.00079) (hexagonmath.org, paper) 2. [Hexagon 2611.00130](https://hexagonmath.org/abs/2611.00130) (hexagonmath.org, paper) 3. [Hexagon 2611.00131](https://hexagonmath.org/abs/2611.00131) (hexagonmath.org, paper) 4. [Hexagon 2611.00132](https://hexagonmath.org/abs/2611.00132) (hexagonmath.org, paper) 5. [Hexagon 2611.00133](https://hexagonmath.org/abs/2611.00133) (hexagonmath.org, paper) 6. [Hexagon 2611.00134](https://hexagonmath.org/abs/2611.00134) (hexagonmath.org, paper) 7. [Hexagon 2611.00135](https://hexagonmath.org/abs/2611.00135) (hexagonmath.org, paper) 8. [Hexagon 2611.00136](https://hexagonmath.org/abs/2611.00136) (hexagonmath.org, paper) 9. [Hexagon 2611.00138](https://hexagonmath.org/abs/2611.00138) (hexagonmath.org, paper) 10. [Hexagon 2611.00139](https://hexagonmath.org/abs/2611.00139) (hexagonmath.org, paper) 11. [Hexagon 2611.00140](https://hexagonmath.org/abs/2611.00140) (hexagonmath.org, paper) 12. [Hexagon 2611.00142](https://hexagonmath.org/abs/2611.00142) (hexagonmath.org, paper) 13. [Hexagon 2611.00145](https://hexagonmath.org/abs/2611.00145) (hexagonmath.org, paper) 14. [Hexagon 2611.00146](https://hexagonmath.org/abs/2611.00146) (hexagonmath.org, paper) 15. [Hexagon 2611.00147](https://hexagonmath.org/abs/2611.00147) (hexagonmath.org, paper) 16. [Hexagon 2611.00149](https://hexagonmath.org/abs/2611.00149) (hexagonmath.org, paper) 17. [Hexagon 2611.00150](https://hexagonmath.org/abs/2611.00150) (hexagonmath.org, paper) 18. [Hexagon 2611.00151](https://hexagonmath.org/abs/2611.00151) (hexagonmath.org, paper) 19. [Hexagon 2611.00152](https://hexagonmath.org/abs/2611.00152) (hexagonmath.org, paper) 20. [Hexagon 2611.00153](https://hexagonmath.org/abs/2611.00153) (hexagonmath.org, paper) 21. [Hexagon 2611.00154](https://hexagonmath.org/abs/2611.00154) (hexagonmath.org, paper) 22. [Hexagon 2611.00155](https://hexagonmath.org/abs/2611.00155) (hexagonmath.org, paper) 23. [Hexagon 2611.00156](https://hexagonmath.org/abs/2611.00156) (hexagonmath.org, paper) 24. [Hexagon 2611.00157](https://hexagonmath.org/abs/2611.00157) (hexagonmath.org, paper) 25. [Hexagon 2611.00158](https://hexagonmath.org/abs/2611.00158) (hexagonmath.org, paper) 26. [Hexagon 2611.00159](https://hexagonmath.org/abs/2611.00159) (hexagonmath.org, paper) 27. [Hexagon 2611.00160](https://hexagonmath.org/abs/2611.00160) (hexagonmath.org, paper) 28. [Hexagon 2611.00161](https://hexagonmath.org/abs/2611.00161) (hexagonmath.org, paper) 29. [Hexagon 2611.00162](https://hexagonmath.org/abs/2611.00162) (hexagonmath.org, paper) 30. [Hexagon 2611.00163](https://hexagonmath.org/abs/2611.00163) (hexagonmath.org, paper) 31. [Hexagon 2611.00164](https://hexagonmath.org/abs/2611.00164) (hexagonmath.org, paper) 32. [Hexagon 2611.00165](https://hexagonmath.org/abs/2611.00165) (hexagonmath.org, paper) 33. [Hexagon 2611.00166](https://hexagonmath.org/abs/2611.00166) (hexagonmath.org, paper) 34. [Hexagon 2611.00167](https://hexagonmath.org/abs/2611.00167) (hexagonmath.org, paper) 35. [Hexagon 2610.00503](https://hexagonmath.org/abs/2610.00503) (hexagonmath.org, paper) 36. [Hexagon 2610.00501](https://hexagonmath.org/abs/2610.00501) (hexagonmath.org, paper) 37. [Hexagon 2610.00500](https://hexagonmath.org/abs/2610.00500) (hexagonmath.org, paper) 38. [Hexagon 2610.00499](https://hexagonmath.org/abs/2610.00499) (hexagonmath.org, paper) 39. [Hexagon 2610.00498](https://hexagonmath.org/abs/2610.00498) (hexagonmath.org, paper) 40. [Hexagon 2610.00497](https://hexagonmath.org/abs/2610.00497) (hexagonmath.org, paper) 41. [Hexagon 2610.00496](https://hexagonmath.org/abs/2610.00496) (hexagonmath.org, paper) 42. [Hexagon 2610.00495](https://hexagonmath.org/abs/2610.00495) (hexagonmath.org, paper) 43. [arXiv 2611.08202](https://arxiv.org/abs/2611.08202) (arxiv.org, paper) 44. [arXiv 2611.07309](https://arxiv.org/abs/2611.07309) (arxiv.org, paper) 45. [arXiv 2611.07100](https://arxiv.org/abs/2611.07100) (arxiv.org, paper) 46. [arXiv 2611.07549](https://arxiv.org/abs/2611.07549) (arxiv.org, paper) 47. [arXiv 2611.07406](https://arxiv.org/abs/2611.07406) (arxiv.org, paper) 48. [arXiv 2611.07090](https://arxiv.org/abs/2611.07090) (arxiv.org, paper) 49. [arXiv 2611.07185](https://arxiv.org/abs/2611.07185) (arxiv.org, paper) 50. [arXiv 2611.06978](https://arxiv.org/abs/2611.06978) (arxiv.org, paper) 51. [arXiv 2611.07556](https://arxiv.org/abs/2611.07556) (arxiv.org, paper) 52. [arXiv 2611.08073](https://arxiv.org/abs/2611.08073) (arxiv.org, paper) 53. [arXiv 2611.08002](https://arxiv.org/abs/2611.08002) (arxiv.org, paper) 54. [arXiv 2611.07043](https://arxiv.org/abs/2611.07043) (arxiv.org, paper) 55. [arXiv 2611.08351](https://arxiv.org/abs/2611.08351) (arxiv.org, paper) 56. [arXiv 2611.08464](https://arxiv.org/abs/2611.08464) (arxiv.org, paper) 57. [arXiv 2611.08480](https://arxiv.org/abs/2611.08480) (arxiv.org, paper) 58. [arXiv 2611.07303](https://arxiv.org/abs/2611.07303) (arxiv.org, paper) 59. [arXiv 2611.07019](https://arxiv.org/abs/2611.07019) (arxiv.org, paper) 60. [arXiv 2611.08071](https://arxiv.org/abs/2611.08071) (arxiv.org, paper) 61. [arXiv 2611.07202](https://arxiv.org/abs/2611.07202) (arxiv.org, paper) 62. [arXiv 2611.00591](https://arxiv.org/abs/2611.00591) (arxiv.org, paper) 63. [arXiv 2611.05060](https://arxiv.org/abs/2611.05060) (arxiv.org, paper) 64. [arXiv 2611.06081](https://arxiv.org/abs/2611.06081) (arxiv.org, paper) 65. [Futures of Maths launch (Terence Tao's blog, 5 Nov)](https://terrytao.wordpress.com/2026/11/05/futures-of-maths-launch/) (terrytao.wordpress.com, discussion) ## Changes - 2026-11-07 (filed): Created ## Related - 2026-11-06: [Axiom: the Weil conjectures proved in Lean](https://postcutoff.com/e/2026-11-06-axiom-weil-conjectures-lean-formalization/index.md) - 2026-11-06: [Navier–Stokes: unforced Leray–Hopf non-uniqueness, AI-written](https://postcutoff.com/e/2026-11-06-navier-stokes-unforced-leray-hopf-nonuniqueness-buckmaster-coiculescu-li/index.md) - 2026-11-06: [AI-assisted results, 6 Nov: arXiv of 6 Nov and Hexagon of 5 Nov](https://postcutoff.com/e/2026-11-06-ai-assisted-results-november-6-listing/index.md) - 2026-11-04: [Axiom: the Stacks Project formalized in Lean](https://postcutoff.com/e/2026-11-04-axiom-stacks-project-lean-formalization/index.md) - 2026-10-27: [Anthropic's Claude also refutes ETH](https://postcutoff.com/e/2026-10-27-anthropic-claude-eth-refutation-3sat-subexponential/index.md) - 2026-07-24: [Hessian conjecture refuted in five variables, derived from Claude-found Jacobian counterexample](https://postcutoff.com/e/2026-07-24-hessian-conjecture-counterexample/index.md) - People: [Terence Tao](https://postcutoff.com/person/terence-tao/)