--- id: "2026-11-08-ai-assisted-results-november-8-listing" url: "https://postcutoff.com/e/2026-11-08-ai-assisted-results-november-8-listing/" as_of: "2026-11-09T21:13:00+01:00" date: "2026-11-08" date_precision: day category: science importance: 2 confidence: medium status: [Awaiting review] verification: Lean-verified sources: 61 editor: human editor human_review: null version: "2026-11-08" --- 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/2026-11-08-ai-assisted-results-november-8-listing/ # AI-assisted results, 8 Nov: Hexagon of 7 Nov and arXiv Full title: AI-assisted results in the 8 Nov sweep: GPT-6-Pro claims on Lusztig positivity (multiplication) and Foregger's permanent conjecture, Claude's Lean proof of Gasull's periodicity problem at every order, a second MUB-6 proof, a fourth Courtade–Kumar proof, plus 20 Hexagon works Catalogue of AI-disclosing works from the Hexagon deposits of 7 Nov 2026 and the arXiv papers read on 8 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. ## Key facts - Own entries: [2026-11-04-matrix-mortality-2x2-undecidable-codex-claude-lean](https://postcutoff.com/e/2026-11-04-matrix-mortality-2x2-undecidable-codex-claude-lean/index.md) (arXiv 2611.06562), [2026-11-05-quasiplanar-graphs-linear-edges-chatgpt-6-pach-tardos-zeng](https://postcutoff.com/e/2026-11-05-quasiplanar-graphs-linear-edges-chatgpt-6-pach-tardos-zeng/index.md) (2611.07314), [2026-11-03-d-equivalence-generalized-kummer-chatgpt-6](https://postcutoff.com/e/2026-11-03-d-equivalence-generalized-kummer-chatgpt-6/index.md) (2611.04118), [2026-11-07-anthropic-claude-hawking-page-modular-bootstrap-hexagon](https://postcutoff.com/e/2026-11-07-anthropic-claude-hawking-page-modular-bootstrap-hexagon/index.md) (Hexagon 2611.00175, 2611.00174) - Qiyue Tang (Tsinghua), GPT-6-Pro sessions of 2–10 hours reviewed by Codex, 'some' human understanding, Rethlas-OSV review 'planned': the multiplication part of Lusztig's positivity conjecture for symmetric Cartan data (2611.00190, a 5 h 46 min session; would be a major result, no expert check); the Lu–Wenzel conjecture (2611.00179); disproof of Xi's conjecture on representation dimension of idempotent corners (2611.00137, 'passed the Rethlas-OSV review'); Conjecture 5.5 of Armstrong-Williams–Hirst–Jackson–Lee (2611.00181); counterexamples to Reading–Stella source–sink recursions (2611.00186); NP/RE-completeness of mutation equivalence (2611.00180); singleton dominance regions (2611.00185) - Gasull's problem on globally periodic rational difference equations answered yes at every order (was known for k ∈ {1,2,3,4,5,7,9,11}); John Rudge (Cambridge Earth Sciences) with Claude Opus 5.5 and Fable 5.1, Lean-formalized: 'almost entirely AI-generated … Human input was mostly limited to encouragement ("keep going" etc)'; 'I understand the statement … but not the details' (2611.00183) - Foregger's conjecture (per A ≥ 2^{1−n} for nearly decomposable doubly stochastic matrices) claimed by Yair Lavi with GPT Sol, GPT Astra and Claude Fable; mixed text, all parts human-checked (2611.00169) - L'vov–Kaplansky conjecture, partial cases: standard polynomials in every degree, Y. T. Miah with GPT-6 Pro, which 'contributed substantially to developing the odd- and even-degree mathematical arguments' (2611.00184); multilinear polynomials of degrees 4–6, Shengyong Pan (Beijing Jiaotong), declared human-written (2611.00173) - Other Hexagon 7 Nov: Černý-type reset threshold cubic coefficient 8242/49923 (Shitov's was 8257/49923), 'primarily AI-generated' by Codex, no human understanding (2611.00172, Sungbin Hong, U Tokyo); Subset Sum exponent 0.48758, Jennifer Voitle with Claude Opus 5.5, conditional on OpenAI's and Kapila's written proofs (2611.00178); four exponentials conjecture at CM and Beta periods and a Lean formalization of Waldschmidt's subgroup theorem, Shawn Krisman, 'done by Claude Opus 5.5', no human check (2611.00171, 2611.00170); 'orphan theorem' for perpendicular billiard orbits in rational right triangles, Joshua Boorstein with Claude (2611.00191); two Grothendieck Montpellier-notes results in Lean, Michel Hua with Claude Opus 5/5.5 (2611.00189, 2611.00188); four-cycle supersaturation at q²+q vertices, Codex-revised (2611.00176); positive holomorphic sectional curvature of flag manifolds, alternative proof with ChatGPT, all human-checked (2611.00168) - arXiv, AI credited with content: a second proof that dimension 6 has no four MUBs, by topology of complex Hadamard matrices; 'ChatGPT 6 Astra and Claude Opus 5.5 assisted significantly in developing the proof' (Wuttig, Tindall; 2611.06917; follows OpenAI's family-266 claim); a fourth AI-assisted proof of the Courtade–Kumar conjecture, 'obtained with interactive collaboration with GPT-6 Astra and DeepSeekV4.1-Flash' (Kramer, Saglam; 2611.05430; see [2026-09-21-courtade-kumar-conjecture-proved](https://postcutoff.com/e/2026-09-21-courtade-kumar-conjecture-proved/index.md)); Behnezhad and Azarmehr break the 2-approximation barrier for sublinear metric TSP (sublinear.info problem 71), ChatGPT-6 Astra 'played a substantial role in developing parts of the final algorithm' (2611.04283); Kaplansky's four group-ring conjectures fail for torsion-free hyperbolic groups in every positive characteristic, extending OpenAI's constructions (Mghirbi, Douglas; 2611.04599); Fujita's advanced generalised Mukai conjecture, single author, after reading OpenAI's generalised Mukai proof with ChatGPT 6 (Duo Li; 2611.05452); Tarun Grover extends OpenAI's Haldane gap proof to higher dimensions with ChatGPT Astra and Codex (2611.07400) - arXiv, AI found key steps: 'Theorem 1.2 was resolved using GPT-6 Astra with Xean in 13 hours' (all minimum cuts of symmetric submodular functions, 2611.08253); quickest transshipment result 'obtained by using GPT-6 Astra' (2611.07369); robust streaming clustering developed with GPT Astra (2611.07678); Runge–Kutta order barrier and SSP bound, 'AI-assisted proofs' (Gottlieb et al., IBM; 2611.07981); 29-point counterexample to the happy edge conjecture found with ChatGPT-Sol 6.1 (2611.05300); Douglas' conjecture for m-Kronecker quivers with Astra and Fable in Lean (2611.04862); VOA library in Lean with Claude and Codex (2611.06616); Monodromy computation model, AI 'contributed substantially to the conception' (2611.04377); Claude Code pipeline refuting 162,964 and proving 117,390 spectral-graph conjectures, 79,505 Lean-verified (2611.03879); Bergeron's two diagonal-harmonics conjectures with ChatGPT (2611.00629); hypercube noise stability of order 7/8 with GPT-6 Astra (2611.00868); log-concavity criterion with Claude, Codex and GPT-6 Pro (2611.01561); Katok periodic-point counterexamples, GPT-6 for construction details (2611.01980); weighted convolution counterexample, ChatGPT strategies for Theorem 1.2 (2611.03334); parity decision trees with GPT Astra (2611.03452); non-pseudo-arithmetic hyperbolic 4-manifolds with Codex (2611.05795) - arXiv, smaller AI steps: proofs written up by GPT-6 Astra from sketches (2611.07661); ChatGPT 6.1 Sol first draft of §3.2.2 (2611.08429); Claude for drafting and checking proofs (2611.08404); GPT-6 contributed Remark 1.25 (2611.07365); ChatGPT for some proof development (2611.07460); ChatGPT Pro suggested a key connection (2611.07336); proof strategy debugged with GPT-6 Sol, Astra and Claude (2611.08356); ideas developed with ChatGPT for relativistic Vlasov–Poisson (2611.01004); Gyárfás–Sumner polylogarithmic bound is the authors' own, Astra Pro only simplified (2611.06699). The rest of the 352 mention AI only for editing, literature, code or figures, or are about AI - Conjecture papers without AI disclosure (65 listed; ~60 uncited): no famous problem with an AI angle - Repos: google-deepmind/formal-conjectures commits of 6 Nov add statements only (98 OEIS files; Green's Open Problems 68, 70, 75, 87, 93, 97; Erdős 651, 1164, 1166) - Hexagon backlog (8 lines): Deep Bhattacharjee with Claude Code, refutes Brešar et al.'s Conjecture 22 on Grundy domination (2610.00494) and finds his own Geometric Selection Conjecture 'cannot be closed as stated' (2610.00493); Patrick Lopatto, largest gaps of the GOE, 'Proof discovery, verification, and writing were done with GPT 6 Astra, GPT 6.1 Sol, and Claude Opus 5.5' (2610.00491); twisted Haagerup–Izumi VOAs, not fully human-verified (2610.00490); Parthasarathy rank bound tightness, Kimi K3 and Gemini for structuring (2610.00489); Möbius circles of eta terms (2610.00487); heat-evolved Weyl polynomials, no human check (2610.00486); Turán power-sum constant C_42 ≤ 0.6888863712 by AI agents (2610.00485) ## What happened Daily catalogue; see key facts. The Lusztig positivity claim (2611.00190) would be notable if it holds, but it comes from a contributor who posts many fast GPT-6-Pro results with "some" human understanding and no expert review. It stays here until someone checks it. ## 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): 192 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 131 days after its cutoff - Gemini 4 Argon (training cutoff March 2026): 222 days after its cutoff - Grok 4.7 (training cutoff May 2026): 161 days after its cutoff ## Sources 1. [Hexagon 2611.00191](https://hexagonmath.org/abs/2611.00191) (hexagonmath.org, paper) 2. [Hexagon 2611.00190](https://hexagonmath.org/abs/2611.00190) (hexagonmath.org, paper) 3. [Hexagon 2611.00189](https://hexagonmath.org/abs/2611.00189) (hexagonmath.org, paper) 4. [Hexagon 2611.00188](https://hexagonmath.org/abs/2611.00188) (hexagonmath.org, paper) 5. [Hexagon 2611.00186](https://hexagonmath.org/abs/2611.00186) (hexagonmath.org, paper) 6. [Hexagon 2611.00185](https://hexagonmath.org/abs/2611.00185) (hexagonmath.org, paper) 7. [Hexagon 2611.00184](https://hexagonmath.org/abs/2611.00184) (hexagonmath.org, paper) 8. [Hexagon 2611.00183](https://hexagonmath.org/abs/2611.00183) (hexagonmath.org, paper) 9. [Hexagon 2611.00181](https://hexagonmath.org/abs/2611.00181) (hexagonmath.org, paper) 10. [Hexagon 2611.00180](https://hexagonmath.org/abs/2611.00180) (hexagonmath.org, paper) 11. [Hexagon 2611.00179](https://hexagonmath.org/abs/2611.00179) (hexagonmath.org, paper) 12. [Hexagon 2611.00178](https://hexagonmath.org/abs/2611.00178) (hexagonmath.org, paper) 13. [Hexagon 2611.00176](https://hexagonmath.org/abs/2611.00176) (hexagonmath.org, paper) 14. [Hexagon 2611.00137](https://hexagonmath.org/abs/2611.00137) (hexagonmath.org, paper) 15. [Hexagon 2611.00173](https://hexagonmath.org/abs/2611.00173) (hexagonmath.org, paper) 16. [Hexagon 2611.00172](https://hexagonmath.org/abs/2611.00172) (hexagonmath.org, paper) 17. [Hexagon 2611.00171](https://hexagonmath.org/abs/2611.00171) (hexagonmath.org, paper) 18. [Hexagon 2611.00170](https://hexagonmath.org/abs/2611.00170) (hexagonmath.org, paper) 19. [Hexagon 2611.00169](https://hexagonmath.org/abs/2611.00169) (hexagonmath.org, paper) 20. [Hexagon 2611.00168](https://hexagonmath.org/abs/2611.00168) (hexagonmath.org, paper) 21. [Hexagon 2610.00494](https://hexagonmath.org/abs/2610.00494) (hexagonmath.org, paper) 22. [Hexagon 2610.00493](https://hexagonmath.org/abs/2610.00493) (hexagonmath.org, paper) 23. [Hexagon 2610.00491](https://hexagonmath.org/abs/2610.00491) (hexagonmath.org, paper) 24. [Hexagon 2610.00490](https://hexagonmath.org/abs/2610.00490) (hexagonmath.org, paper) 25. [Hexagon 2610.00489](https://hexagonmath.org/abs/2610.00489) (hexagonmath.org, paper) 26. [Hexagon 2610.00487](https://hexagonmath.org/abs/2610.00487) (hexagonmath.org, paper) 27. [Hexagon 2610.00486](https://hexagonmath.org/abs/2610.00486) (hexagonmath.org, paper) 28. [Hexagon 2610.00485](https://hexagonmath.org/abs/2610.00485) (hexagonmath.org, paper) 29. [arXiv 2611.06917](https://arxiv.org/abs/2611.06917) (arxiv.org, paper) 30. [arXiv 2611.05430](https://arxiv.org/abs/2611.05430) (arxiv.org, paper) 31. [arXiv 2611.05452](https://arxiv.org/abs/2611.05452) (arxiv.org, paper) 32. [arXiv 2611.04283](https://arxiv.org/abs/2611.04283) (arxiv.org, paper) 33. [arXiv 2611.04599](https://arxiv.org/abs/2611.04599) (arxiv.org, paper) 34. [arXiv 2611.07400](https://arxiv.org/abs/2611.07400) (arxiv.org, paper) 35. [arXiv 2611.07369](https://arxiv.org/abs/2611.07369) (arxiv.org, paper) 36. [arXiv 2611.07678](https://arxiv.org/abs/2611.07678) (arxiv.org, paper) 37. [arXiv 2611.08253](https://arxiv.org/abs/2611.08253) (arxiv.org, paper) 38. [arXiv 2611.07981](https://arxiv.org/abs/2611.07981) (arxiv.org, paper) 39. [arXiv 2611.05300](https://arxiv.org/abs/2611.05300) (arxiv.org, paper) 40. [arXiv 2611.04862](https://arxiv.org/abs/2611.04862) (arxiv.org, paper) 41. [arXiv 2611.06616](https://arxiv.org/abs/2611.06616) (arxiv.org, paper) 42. [arXiv 2611.04377](https://arxiv.org/abs/2611.04377) (arxiv.org, paper) 43. [arXiv 2611.03879](https://arxiv.org/abs/2611.03879) (arxiv.org, paper) 44. [arXiv 2611.06699](https://arxiv.org/abs/2611.06699) (arxiv.org, paper) 45. [arXiv 2611.07567](https://arxiv.org/abs/2611.07567) (arxiv.org, paper) 46. [arXiv 2611.08429](https://arxiv.org/abs/2611.08429) (arxiv.org, paper) 47. [arXiv 2611.08404](https://arxiv.org/abs/2611.08404) (arxiv.org, paper) 48. [arXiv 2611.00629](https://arxiv.org/abs/2611.00629) (arxiv.org, paper) 49. [arXiv 2611.00868](https://arxiv.org/abs/2611.00868) (arxiv.org, paper) 50. [arXiv 2611.01561](https://arxiv.org/abs/2611.01561) (arxiv.org, paper) 51. [arXiv 2611.01980](https://arxiv.org/abs/2611.01980) (arxiv.org, paper) 52. [arXiv 2611.03334](https://arxiv.org/abs/2611.03334) (arxiv.org, paper) 53. [arXiv 2611.03452](https://arxiv.org/abs/2611.03452) (arxiv.org, paper) 54. [arXiv 2611.05795](https://arxiv.org/abs/2611.05795) (arxiv.org, paper) 55. [arXiv 2611.07661](https://arxiv.org/abs/2611.07661) (arxiv.org, paper) 56. [arXiv 2611.08356](https://arxiv.org/abs/2611.08356) (arxiv.org, paper) 57. [arXiv 2611.07365](https://arxiv.org/abs/2611.07365) (arxiv.org, paper) 58. [arXiv 2611.07460](https://arxiv.org/abs/2611.07460) (arxiv.org, paper) 59. [arXiv 2611.07336](https://arxiv.org/abs/2611.07336) (arxiv.org, paper) 60. [arXiv 2611.01004](https://arxiv.org/abs/2611.01004) (arxiv.org, paper) 61. [google-deepmind/formal-conjectures commit (6 Nov, Erdős 1164)](https://github.com/google-deepmind/formal-conjectures/commit/20a5a5aa8310a6c0be1ee5fb26ffaee747901edf) (github.com, code) ## Changes - 2026-11-08 (filed): Created (science agent; arXiv; Hexagon backlog lines 2610.00485–00494) ## Related - 2026-11-07: [AI-assisted results, 7 Nov: Hexagon of 6 Nov and arXiv](https://postcutoff.com/e/2026-11-07-ai-assisted-results-november-7-listing/index.md) - 2026-09-21: [Courtade–Kumar 'most informative Boolean function' conjecture (2013) proved three times in two days, all with AI: Ky & Tran (ChatGPT), Google + CUHK (Gemini, Lean-verified end-to-end), Mahdavifar & Beirami](https://postcutoff.com/e/2026-09-21-courtade-kumar-conjecture-proved/index.md)