--- id: "2026-11-10-ai-assisted-results-november-10-listing" url: "https://postcutoff.com/e/2026-11-10-ai-assisted-results-november-10-listing/" as_of: "2026-11-13T13:49:00+01:00" date: "2026-11-10" date_precision: day category: science importance: 2 confidence: medium status: [Awaiting review] verification: Lean-verified sources: 82 editor: human editor human_review: null version: "2026-11-10" --- As of: 2026-11-13 13:49 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/2026-11-10-ai-assisted-results-november-10-listing/ # AI-assisted results, 10 Nov: arXiv and Hexagon Full title: AI-assisted results in the 10 Nov sweep: Etingof–Gelaki finiteness question answered by ChatGPT, Mendel's GPT-6 Astra metric cotype bound, Milne's report on OpenAI's Hodge preprints, R(12,12) ≥ 1661 with Claude, plus 65 Hexagon deposits and 200 new arXiv disclosures Catalogue of AI-disclosing works from the Hexagon deposits of 9–10 Nov 2026 (65 new), the arXiv listing of 10 Nov (200 new papers mentioning AI; the strongest disclosures quoted), commits to google-deepmind/formal-conjectures and eight lines of the October Hexagon backlog. Statements are quoted from Hexagon provenance records (Hexagon does not judge correctness) or PDFs. ## Key facts - Own entries: [2026-11-09-non-split-cartan-121-two-ai-proofs](https://postcutoff.com/e/2026-11-09-non-split-cartan-121-two-ai-proofs/index.md) (2611.00231, 2611.00255, 2611.00234), [2026-09-24-benjamini-schramm-pc-pu-nonamenable-openai-lean](https://postcutoff.com/e/2026-09-24-benjamini-schramm-pc-pu-nonamenable-openai-lean/index.md) (2611.00251); Smale constant deposits 2611.00258 and 2611.00187 added to [2026-09-03-smale-mean-value-conjecture-disproved-gpt-6-astra](https://postcutoff.com/e/2026-09-03-smale-mean-value-conjecture-disproved-gpt-6-astra/index.md); Euler Part II (arXiv 2611.10211) to [2026-10-17-2d-euler-unforced-nonuniqueness-lp-vorticity-ai](https://postcutoff.com/e/2026-10-17-2d-euler-unforced-nonuniqueness-lp-vorticity-ai/index.md); Dixmier Lean commit to [2026-07-20-jacobian-conjecture-counterexample](https://postcutoff.com/e/2026-07-20-jacobian-conjecture-counterexample/index.md) - Pavel Etingof (MIT), Hexagon 2611.00226: a one-parameter family of 1024-dimensional complex Hopf algebras with fixed coalgebra and varying algebra structure, answering 'negatively the finiteness question of Etingof and Gelaki'; 'This text has been produced by ChatGPT at a request by Pavel Etingof. It was repeatedly checked by AI agents'; human understanding 'some' - Manor Mendel, Hexagon 2611.00209: metric cotype q inequality with scaling m = O(n^(1/2+1/q)) for Banach spaces of Rademacher cotype q; 'The proofs in this paper were obtained by GPT~6 Astra … verifying the correctness of the proofs' by the author; human understanding 'all' - James Milne, Hexagon 2611.00244 (human-written): 'a report on two preprints of OpenAI, "Milne's rationality conjecture for abelian varieties" and "The rational Hodge conjecture for CM abelian varieties", placing them in context' - Nicholas Nash, 2611.00196: deterministic adversary forcing (1−o(1)) n log₂ n comparisons on any sorting algorithm (previous 37/64); 'Except for the abstract, the text is AI-generated using GPT 6 Astra' - Yue Ma, 2611.00248: R(12,12) ≥ 1661 by extending the Mathon–Shearer colouring; Claude Opus 5.5 in Claude Code 'designed and ran the searches' (SAT with CaDiCaL), Lean 4 listed - Claude-agent deposits with little or no human checking: holographic entropy inequalities lacking unscaled contraction proofs (2611.00252, 'checked only by other instances of the same models'); Boshernitzan 1992 complete-periodicity conjecture for rational right triangles, two papers (2611.00250, 2611.00213); ten DSRG parameter sets excluded (2611.00230, Lean listed); interpolation lemma of OpenAI's Landau–Siegel paper formalized (2611.00200) - Other Hexagon 9–10 Nov: Cereceda's 2007 conjecture for bipartite 2-degenerate graphs (Dave Goel, 2611.00260, 'overwhelmingly by AI models'); Cazenave's eigenvalue conjecture μ₂² ≥ 4λ₂+1 (2611.00232, Codex); Yair Lavi with GPT and Claude Fable: cubic-lattice dimer constant ℓ₃ ≥ 0.44477 (2611.00227), counterexamples to a Drury-conjecture inequality (2611.00198) and three more (2611.00197, 2611.00201, 2611.00225); Palcoux et al. fusion categories (2611.00233); Banica (2611.00221, 'Written by Chat GPT, with help from Teo Banica'); Enomoto pretorsion theories ('Sol proved almost all materials', 2611.00207); Kominers, Fibonacci polynomials (2611.00212); Yampolsky, non-computable derivatives (2611.00243); Qiyue Tang, ten deposits on L'vov–Kaplansky, Lusztig, Laurent positivity and Markov numbers (2611.00195, 00205, 00206, 00210, 00216, 00218, 00219, 00238, 00239, 00194, 00192) - arXiv 10 Nov, AI found main results: 'The proofs of all the new results in this paper were discovered by ChatGPT 6.1 Sol' (vertex splitting and global rigidity, 2611.10919); 'All mathematical statements and proofs were found by ChatGPT 6 Pro' (Kronecker coefficients, 2611.11593); 'The mathematical content of this paper was generated using ChatGPT 6 Astra' (Hodge–Witt torsion, 2611.11269); 'The main results of this paper were initially obtained by Claude Opus 5.5' (magnetic Ginzburg–Landau vortices, 2611.11360); proof of main theorem 'discovered using ChatGPT-6 Astra Max' (permutation complexes, 2611.11362); counterexample 'generated through discussions with ChatGPT 6 Astra' (divisorial domain, 2611.11357); maximal curves 'discovered through extensive searches' with GPT-6 Astra (2611.11298); R∞ for Higman–Thompson groups, idea 'suggested by ChatGPT 6 Astra' (2611.11294); Glauber dynamics on G(n,d/n), main ideas with GPT-5.6/6.1 Sol (2611.12444); unipotent Specht modules with Claude (2611.10813); Weak λ-sets, first proof drafts by GPT-6 Astra (2611.11025) - Repos: formal-conjectures commits of 9 Nov add formal proofs for Erdős 423, 1098, 1193, 427 solved statements and a formal proof link for the AME(7,d) classification (exists iff d ≥ 3); no new openai/math commits; mathcommunity/oai-math-revised reverted a BFSS SU(2) Lean package (#77) - Hexagon backlog (8 lines): Masaki Oshikawa, RP² model correlations decay faster than any power, 'The proof was entirely generated by ChatGPT 6 Astra', then formalized (2610.00453); Aronow and Lopatto, superfluid stiffness of the dilute hard-sphere Bose gas, 'Proof discovery and verification were done with GPT 6 Astra, GPT 6.1 Sol, and Claude Opus 5.5' (2610.00450); Brian Nugent, point separation for K_X + mL, m ≥ n+2, conditional on inputs stated in the paper, 'Produced by GPT-6.1 Sol' (2610.00447); Jungang Chen with ChatGPT, counterexamples to Csikvári's Conjecture 7.3 (2610.00433) and three conjectures of Ok (2610.00431); Qiyue Tang, weakly Gorenstein symmetry counterexamples (2610.00436); Kominers (2610.00451); Bhattacharjee, Kreuzer–Skarke descent (2610.00456) - Provenance read for all Hexagon works listed here. Qiyue Tang's deposits come from long GPT-6-Pro runs audited by Codex, e.g. L'vov–Kaplansky for large matrices from 'ten GPT-6-Pro research runs with a combined scheduled duration of 62.5 hours' (2611.00206); a Rethlas-OSV review is 'planned' for some. Steve Hubbard's ternary Goldbach note: 'main results are checked in Lean 4 with Mathlib' (2611.00211). Primarily human-written: 2611.00228, 2611.00229; Anwesh Ray (2611.00202) used ChatGPT 6.1 Sol only to explore and correct - formal-conjectures, other 9 Nov commits: new Lean statements (no proofs) of Pittel's stable-matching conjectures (#7812, #7852), the Irving–Leather conjectures (#7818, drafted with Codex), a Fanelli–Moscardelli roommates threshold (#7853), Erdős 1132 and 1042; proofs of the Erdős 963 greedy bound and links to existing formal proofs for Erdős 835, 654 and AME(7,2); Erdős 143 part (i) marked solved from Koukoulopoulos–Lamzouri–Lichtman (arXiv 2502.09539, not AI). None is a new open-problem resolution - Other conjecture papers of 10 Nov (23): PDFs scanned, none discloses AI use and none concerns a famous problem ## What happened The Hexagon flow kept rising: 65 new deposits on 9–10 Nov, most declared "Primarily AI-generated". Well-known contributors now include Etingof, Mendel, Najman, Zureick-Brown and Milne (whose own deposit is a human-written report on OpenAI's Hodge preprints). Many deposits state that results were checked only by other model instances; read each as a claim. ## What is disputed or not yet verified - Verification: Unrefereed preprints and Hexagon deposits; some Lean ## Your AI and this story - GPT-6 Astra (training cutoff April 2026): 194 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 133 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 224 days after its cutoff - Grok 4.7 (training cutoff May 2026): 163 days after its cutoff ## Sources 1. [Hexagon 2611.00244](https://hexagonmath.org/abs/2611.00244) (hexagonmath.org, paper) 2. [Hexagon 2611.00226](https://hexagonmath.org/abs/2611.00226) (hexagonmath.org, paper) 3. [Hexagon 2611.00209](https://hexagonmath.org/abs/2611.00209) (hexagonmath.org, paper) 4. [Hexagon 2611.00196](https://hexagonmath.org/abs/2611.00196) (hexagonmath.org, paper) 5. [Hexagon 2611.00248](https://hexagonmath.org/abs/2611.00248) (hexagonmath.org, paper) 6. [Hexagon 2611.00250](https://hexagonmath.org/abs/2611.00250) (hexagonmath.org, paper) 7. [Hexagon 2611.00213](https://hexagonmath.org/abs/2611.00213) (hexagonmath.org, paper) 8. [Hexagon 2611.00252](https://hexagonmath.org/abs/2611.00252) (hexagonmath.org, paper) 9. [Hexagon 2611.00260](https://hexagonmath.org/abs/2611.00260) (hexagonmath.org, paper) 10. [Hexagon 2611.00232](https://hexagonmath.org/abs/2611.00232) (hexagonmath.org, paper) 11. [Hexagon 2611.00230](https://hexagonmath.org/abs/2611.00230) (hexagonmath.org, paper) 12. [Hexagon 2611.00200](https://hexagonmath.org/abs/2611.00200) (hexagonmath.org, paper) 13. [Hexagon 2611.00207](https://hexagonmath.org/abs/2611.00207) (hexagonmath.org, paper) 14. [Hexagon 2611.00233](https://hexagonmath.org/abs/2611.00233) (hexagonmath.org, paper) 15. [Hexagon 2611.00221](https://hexagonmath.org/abs/2611.00221) (hexagonmath.org, paper) 16. [Hexagon 2611.00227](https://hexagonmath.org/abs/2611.00227) (hexagonmath.org, paper) 17. [Hexagon 2611.00198](https://hexagonmath.org/abs/2611.00198) (hexagonmath.org, paper) 18. [Hexagon 2611.00243](https://hexagonmath.org/abs/2611.00243) (hexagonmath.org, paper) 19. [Hexagon 2611.00212](https://hexagonmath.org/abs/2611.00212) (hexagonmath.org, paper) 20. [Hexagon 2611.00215](https://hexagonmath.org/abs/2611.00215) (hexagonmath.org, paper) 21. [Hexagon 2611.00254](https://hexagonmath.org/abs/2611.00254) (hexagonmath.org, paper) 22. [Hexagon 2611.00206](https://hexagonmath.org/abs/2611.00206) (hexagonmath.org, paper) 23. [Hexagon 2611.00195](https://hexagonmath.org/abs/2611.00195) (hexagonmath.org, paper) 24. [Hexagon 2611.00210](https://hexagonmath.org/abs/2611.00210) (hexagonmath.org, paper) 25. [Hexagon 2611.00216](https://hexagonmath.org/abs/2611.00216) (hexagonmath.org, paper) 26. [Hexagon 2611.00245](https://hexagonmath.org/abs/2611.00245) (hexagonmath.org, paper) 27. [Hexagon 2611.00208](https://hexagonmath.org/abs/2611.00208) (hexagonmath.org, paper) 28. [Hexagon 2611.00259](https://hexagonmath.org/abs/2611.00259) (hexagonmath.org, paper) 29. [Hexagon 2611.00237](https://hexagonmath.org/abs/2611.00237) (hexagonmath.org, paper) 30. [Hexagon 2611.00228](https://hexagonmath.org/abs/2611.00228) (hexagonmath.org, paper) 31. [Hexagon 2611.00236](https://hexagonmath.org/abs/2611.00236) (hexagonmath.org, paper) 32. [Hexagon 2611.00253](https://hexagonmath.org/abs/2611.00253) (hexagonmath.org, paper) 33. [Hexagon 2611.00256](https://hexagonmath.org/abs/2611.00256) (hexagonmath.org, paper) 34. [Hexagon 2611.00257](https://hexagonmath.org/abs/2611.00257) (hexagonmath.org, paper) 35. [Hexagon 2611.00246](https://hexagonmath.org/abs/2611.00246) (hexagonmath.org, paper) 36. [Hexagon 2611.00220](https://hexagonmath.org/abs/2611.00220) (hexagonmath.org, paper) 37. [Hexagon 2611.00217](https://hexagonmath.org/abs/2611.00217) (hexagonmath.org, paper) 38. [Hexagon 2611.00211](https://hexagonmath.org/abs/2611.00211) (hexagonmath.org, paper) 39. [Hexagon 2611.00214](https://hexagonmath.org/abs/2611.00214) (hexagonmath.org, paper) 40. [Hexagon 2611.00202](https://hexagonmath.org/abs/2611.00202) (hexagonmath.org, paper) 41. [Hexagon 2611.00229](https://hexagonmath.org/abs/2611.00229) (hexagonmath.org, paper) 42. [Hexagon 2611.00241](https://hexagonmath.org/abs/2611.00241) (hexagonmath.org, paper) 43. [Hexagon 2611.00240](https://hexagonmath.org/abs/2611.00240) (hexagonmath.org, paper) 44. [Hexagon 2611.00239](https://hexagonmath.org/abs/2611.00239) (hexagonmath.org, paper) 45. [Hexagon 2611.00238](https://hexagonmath.org/abs/2611.00238) (hexagonmath.org, paper) 46. [Hexagon 2611.00249](https://hexagonmath.org/abs/2611.00249) (hexagonmath.org, paper) 47. [Hexagon 2611.00235](https://hexagonmath.org/abs/2611.00235) (hexagonmath.org, paper) 48. [Hexagon 2611.00199](https://hexagonmath.org/abs/2611.00199) (hexagonmath.org, paper) 49. [Hexagon 2611.00201](https://hexagonmath.org/abs/2611.00201) (hexagonmath.org, paper) 50. [Hexagon 2611.00197](https://hexagonmath.org/abs/2611.00197) (hexagonmath.org, paper) 51. [Hexagon 2611.00203](https://hexagonmath.org/abs/2611.00203) (hexagonmath.org, paper) 52. [Hexagon 2611.00205](https://hexagonmath.org/abs/2611.00205) (hexagonmath.org, paper) 53. [Hexagon 2611.00194](https://hexagonmath.org/abs/2611.00194) (hexagonmath.org, paper) 54. [Hexagon 2611.00192](https://hexagonmath.org/abs/2611.00192) (hexagonmath.org, paper) 55. [Hexagon 2611.00219](https://hexagonmath.org/abs/2611.00219) (hexagonmath.org, paper) 56. [Hexagon 2611.00218](https://hexagonmath.org/abs/2611.00218) (hexagonmath.org, paper) 57. [Hexagon 2611.00224](https://hexagonmath.org/abs/2611.00224) (hexagonmath.org, paper) 58. [Hexagon 2611.00223](https://hexagonmath.org/abs/2611.00223) (hexagonmath.org, paper) 59. [Hexagon 2611.00225](https://hexagonmath.org/abs/2611.00225) (hexagonmath.org, paper) 60. [Hexagon 2610.00456](https://hexagonmath.org/abs/2610.00456) (hexagonmath.org, paper) 61. [Hexagon 2610.00453](https://hexagonmath.org/abs/2610.00453) (hexagonmath.org, paper) 62. [Hexagon 2610.00451](https://hexagonmath.org/abs/2610.00451) (hexagonmath.org, paper) 63. [Hexagon 2610.00450](https://hexagonmath.org/abs/2610.00450) (hexagonmath.org, paper) 64. [Hexagon 2610.00447](https://hexagonmath.org/abs/2610.00447) (hexagonmath.org, paper) 65. [Hexagon 2610.00436](https://hexagonmath.org/abs/2610.00436) (hexagonmath.org, paper) 66. [Hexagon 2610.00433](https://hexagonmath.org/abs/2610.00433) (hexagonmath.org, paper) 67. [Hexagon 2610.00431](https://hexagonmath.org/abs/2610.00431) (hexagonmath.org, paper) 68. [arXiv 2611.10919](https://arxiv.org/abs/2611.10919) (arxiv.org, paper) 69. [arXiv 2611.11593](https://arxiv.org/abs/2611.11593) (arxiv.org, paper) 70. [arXiv 2611.11025](https://arxiv.org/abs/2611.11025) (arxiv.org, paper) 71. [arXiv 2611.11269](https://arxiv.org/abs/2611.11269) (arxiv.org, paper) 72. [arXiv 2611.11360](https://arxiv.org/abs/2611.11360) (arxiv.org, paper) 73. [arXiv 2611.11362](https://arxiv.org/abs/2611.11362) (arxiv.org, paper) 74. [arXiv 2611.11357](https://arxiv.org/abs/2611.11357) (arxiv.org, paper) 75. [arXiv 2611.11298](https://arxiv.org/abs/2611.11298) (arxiv.org, paper) 76. [arXiv 2611.11294](https://arxiv.org/abs/2611.11294) (arxiv.org, paper) 77. [arXiv 2611.12444](https://arxiv.org/abs/2611.12444) (arxiv.org, paper) 78. [arXiv 2611.10813](https://arxiv.org/abs/2611.10813) (arxiv.org, paper) 79. [arXiv 2611.09978](https://arxiv.org/abs/2611.09978) (arxiv.org, paper) 80. [arXiv 2611.10283](https://arxiv.org/abs/2611.10283) (arxiv.org, paper) 81. [formal-conjectures #7611: AME(7,d) classification formal proof link](https://github.com/google-deepmind/formal-conjectures/commit/03b0ded8b3d8adb665ef0a863df434754467c117) (github.com, code) 82. [formal-conjectures #7668: Erdős 423, 1098, 1193, 427 solved statements proved](https://github.com/google-deepmind/formal-conjectures/commit/2f91d251c07fbbaf9435166d47c11e884a08a6cf) (github.com, code) ## Changes - 2026-11-10 (filed): Created (science agent; Hexagon API records and provenance, GitHub commit pages) ## Related - 2026-11-09: [X_ns+(121): two AI-generated proofs in two days](https://postcutoff.com/e/2026-11-09-non-split-cartan-121-two-ai-proofs/index.md) - 2026-11-09: [AI-assisted results, 9 Nov: arXiv and Hexagon](https://postcutoff.com/e/2026-11-09-ai-assisted-results-november-9-listing/index.md) - 2026-10-06: [Hexagon launches: a new arXiv-style repository for LLM-assisted mathematics papers](https://postcutoff.com/e/2026-10-06-hexagon-repository-llm-assisted-math/index.md) - 2026-09-24: [Benjamini–Schramm p_c < p_u: OpenAI bond proof in Lean, Claude site form](https://postcutoff.com/e/2026-09-24-benjamini-schramm-pc-pu-nonamenable-openai-lean/index.md)