--- id: "2026-11-06-ai-assisted-results-november-6-listing" url: "https://postcutoff.com/e/2026-11-06-ai-assisted-results-november-6-listing/" as_of: "2026-11-09T21:13:00+01:00" date: "2026-11-06" date_precision: day category: science importance: 2 confidence: medium status: [Awaiting review] verification: Lean-verified sources: 48 editor: human editor human_review: null version: "2026-11-06" --- 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/2026-11-06-ai-assisted-results-november-6-listing/ # AI-assisted results, 6 Nov: arXiv of 6 Nov and Hexagon of 5 Nov Full title: AI-assisted results in the 6 Nov 2026 sweep: generalized Lax conjecture for mixed determinants, L'vov–Kaplansky in degree four, unrecognizability of #²(S²×S²) by ChatGPT's agent, second Hamilton cycles from r ≥ 17, plus 26 Hexagon works Catalogue of AI-disclosing papers from the arXiv announcement of 6 Nov 2026 and the Hexagon works of 5 Nov beyond the items with own entries. AI statements are quoted from PDFs or Hexagon provenance records (Hexagon does not judge correctness); none is refereed. ## Key facts - Own entries: [2026-11-06-tusnady-problem-settled-two-ai-assisted-preprints](https://postcutoff.com/e/2026-11-06-tusnady-problem-settled-two-ai-assisted-preprints/index.md) (2611.06998, 2611.08455), [2026-11-05-singmaster-bound-claude-opus-5-5-whitmore](https://postcutoff.com/e/2026-11-05-singmaster-bound-claude-opus-5-5-whitmore/index.md) (Hexagon 2611.00106), [2026-11-05-hopfield-critical-capacity-claude-opus-5-5](https://postcutoff.com/e/2026-11-05-hopfield-critical-capacity-claude-opus-5-5/index.md) (Hexagon 2611.00105); Najman's degrees 9–22 (Hexagon 2611.00120) added to [2026-11-04-elliptic-curve-torsion-degrees-6-9-gpt-6-1-sol-najman](https://postcutoff.com/e/2026-11-04-elliptic-curve-torsion-degrees-6-9-gpt-6-1-sol-najman/index.md) - Real algebraic geometry: Suvrit Sra proves the generalized Lax conjecture for the Borcea–Brändén mixed determinant (spectrahedral hyperbolicity cone) and answers four Borcea–Brändén problems negatively (Hexagon 2611.00117, mixed, understanding 'some'): 'GPT Astra (Pro) found the construction of Theorem 1.1' after a failed counterexample search; also a new proof of van der Waerden's permanent inequality by monotone averaging, 'GPT-6 Astra Pro … carried out the derivations' (2611.00118) - Algebra and topology: L'vov–Kaplansky conjecture for multilinear polynomials of degree four, 'developed through two research conversations with GPT-6-Pro … seven hours' (Qiyue Tang, 2611.00119); Qiuyu Ren, a 2-generator 3-relator universal group and #ⁿ(S²×S²) unrecognizable for every n ≥ 2, 'The main theorems were produced by ChatGPT's agent "dot." … less than half a day' (2611.00112); terminal symplectic singularities for parabolic base affine spaces, Tom Gannon, 'this pdf is entirely AI generated' with ChatGPT Astra (2611.00107) - Number theory and complexity (Hexagon): Vaibhav Tulsyan with Claude Code, parity of π(x) in time x^o(1) and class numbers / quadratic non-residues in 2^O(n/√log n), both conditional on Anthropic's #SAT algorithms of 27 Oct and Lean-checked on that development (2611.00116, 2611.00115); Hadamard difference sets in C₂×C₂ᵤ² and 2-automatic Baum–Sweet Hankel determinants, Claude, 'No professional mathematician has reviewed the note yet' (2611.00102, 2611.00101); Fuchs' extremal problem for 0 < λ ≤ 3 (2611.00126) - Other Hexagon 5 Nov: Grothendieck Montpellier notes, seventy-five folders of restated statements proved in Lean with Claude Opus/Sonnet 5.5, readings not verified against the facsimile (2611.00125); twistor correspondence for analytic Einstein germs (2611.00123); sup-norm ∂̄ estimates on convex domains in C², 'primarily AI-generated', fully human-checked (2611.00121); Hurwitz interval family without degree-5 WSPR numerator, Lean (2611.00127); transcendence of the 3x+1 conjugacy map on Sturmian words (2611.00108); Voblint, Isabelle/HOL soundness (2611.00109); human-written or editing-only: 2611.00124, 00122, 00114, 00093 (Claude found Example 2.7), 00085, 2610.00681, 00059 - Graph theory and combinatorics (arXiv 6 Nov): Liu–Liu–Ning, every Hamiltonian r-regular graph with r ≥ 17 has a second Hamilton cycle (was r ≥ 23, Haxell–Seamone–Verstraëte), 'The proofs in this paper were developed with substantial contributions from ChatGPT (5.5 and 6 Astra)' (2611.06985); perfect q-hash codes beat the probabilistic bound for every q ≥ 3, settling part of a Xing–Yuan conjecture, 'Claude (Anthropic) suggested the directions that led to Theorems 1.5 and 1.7' (2611.08230); maximal partial Room squares, construction 'produced by ChatGPT Plus' (2611.07117); double-factorial consecutive-pattern packings, Lean (2611.06937); simpler proof for a noncommutative harmonic oscillator determinant offered unprompted by Claude Opus 5.5 (2611.07626) - Geometry, analysis, TCS: Arman–Bondarenko–Prymak–Radchenko, a diameter-one set in R⁵ not covered by six diameter-one balls, 'The example presented in this paper was found using generative AI tools' (2611.08198); Medwed proves the Chang–Lyons–Ni length conjecture for path signatures, 'central arguments … generated with the assistance of AI (ChatGPT 5.6 Sol)' (2611.08030); Alrabiah–Goyal–Guruswami refute a conjecture on list-decoding Reed–Solomon codes, 'Initial versions of our key statements were established by GPT-6 Astra Pro' (2611.07607); Riis, linear degree lower bounds for Nullstellensatz and Polynomial Calculus with 'Astra and Claude for sustained proof search' (2611.07280) - Smaller AI-credited steps: CM counterexamples found with ChatGPT 5.6 Pro (Kim–Yu, 2611.07259); Fermat quotients with CM Jacobians, GPT-6 Astra Pro extended the proof (2611.08176); void percolation, tree-embedding idea by GPT 5.6 (2611.07196); stochastic heat equation weak uniqueness via GPT-6.1 (2611.07310); free Tₙ-Heyting algebras, implication 'found by Claude Sonnet 4.6' (2611.07915); 2×4 LEGO counts with Claude (2611.06986); worldsheet skein sequence 'found by GPT-5.6 Sol' (2611.07455) - Repos: google-deepmind/formal-conjectures added statements of Green's Open Problems 68, 70, 75, 87, 93, 97 and Erdős 651, 1164, 1166 (statements, no solutions); 3f44904 (Erdős 354(i)) was covered on 5 Nov; 2befc3a links a Turing-machine formalization (docs) - Hexagon backlog (6 lines): Basok, perfect t-embeddings exist, answering Chelkak–Laslier–Russkikh (2021), 'The proof and the main part of the writing were produced by GPT-6 Astra' (2610.00520); Enomoto, Astra re-proves the Bautista–Gabriel–Roiter–Salmerón multiplicative-basis theorem (2610.00505); Riesen, VOA realizations of untwisted Haagerup–Izumi centers, AI 'assisted in developing proof arguments' (2610.00508); Pinho, reverse Brunn–Minkowski constant C_70 ≥ exp(1/(2e)) and a degree-3 local-weight cap, AI agents, 'reviewed the results at summary level' (2610.00515, 2610.00514); Lin, de Bruijn–Newman coefficients, human-written (2610.00521) ## What happened The 6 Nov sweep listed 183 arXiv papers from that day's announcement with an AI mention (most only for editing or literature search) and 26 Hexagon works of 5 Nov. The items above are those where the authors credit AI with mathematical content. Quotes come from PDFs or Hexagon provenance statements; Hexagon does not judge correctness and none of these 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): 190 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 129 days after its cutoff - Gemini 4 Argon (training cutoff March 2026): 220 days after its cutoff - Grok 4.7 (training cutoff May 2026): 159 days after its cutoff ## Sources 1. [Hexagon 2611.00127](https://hexagonmath.org/abs/2611.00127) (hexagonmath.org, paper) 2. [Hexagon 2611.00126](https://hexagonmath.org/abs/2611.00126) (hexagonmath.org, paper) 3. [Hexagon 2611.00125](https://hexagonmath.org/abs/2611.00125) (hexagonmath.org, paper) 4. [Hexagon 2611.00124](https://hexagonmath.org/abs/2611.00124) (hexagonmath.org, paper) 5. [Hexagon 2611.00123](https://hexagonmath.org/abs/2611.00123) (hexagonmath.org, paper) 6. [Hexagon 2611.00122](https://hexagonmath.org/abs/2611.00122) (hexagonmath.org, paper) 7. [Hexagon 2611.00121](https://hexagonmath.org/abs/2611.00121) (hexagonmath.org, paper) 8. [Hexagon 2611.00120](https://hexagonmath.org/abs/2611.00120) (hexagonmath.org, paper) 9. [Hexagon 2611.00119](https://hexagonmath.org/abs/2611.00119) (hexagonmath.org, paper) 10. [Hexagon 2611.00118](https://hexagonmath.org/abs/2611.00118) (hexagonmath.org, paper) 11. [Hexagon 2611.00117](https://hexagonmath.org/abs/2611.00117) (hexagonmath.org, paper) 12. [Hexagon 2611.00116](https://hexagonmath.org/abs/2611.00116) (hexagonmath.org, paper) 13. [Hexagon 2611.00115](https://hexagonmath.org/abs/2611.00115) (hexagonmath.org, paper) 14. [Hexagon 2611.00114](https://hexagonmath.org/abs/2611.00114) (hexagonmath.org, paper) 15. [Hexagon 2611.00112](https://hexagonmath.org/abs/2611.00112) (hexagonmath.org, paper) 16. [Hexagon 2611.00109](https://hexagonmath.org/abs/2611.00109) (hexagonmath.org, paper) 17. [Hexagon 2611.00108](https://hexagonmath.org/abs/2611.00108) (hexagonmath.org, paper) 18. [Hexagon 2611.00107](https://hexagonmath.org/abs/2611.00107) (hexagonmath.org, paper) 19. [Hexagon 2611.00102](https://hexagonmath.org/abs/2611.00102) (hexagonmath.org, paper) 20. [Hexagon 2611.00101](https://hexagonmath.org/abs/2611.00101) (hexagonmath.org, paper) 21. [Hexagon 2610.00681](https://hexagonmath.org/abs/2610.00681) (hexagonmath.org, paper) 22. [Hexagon 2611.00093](https://hexagonmath.org/abs/2611.00093) (hexagonmath.org, paper) 23. [Hexagon 2611.00085](https://hexagonmath.org/abs/2611.00085) (hexagonmath.org, paper) 24. [Hexagon 2611.00059](https://hexagonmath.org/abs/2611.00059) (hexagonmath.org, paper) 25. [arXiv 2611.06985](https://arxiv.org/abs/2611.06985) (arxiv.org, paper) 26. [arXiv 2611.08030](https://arxiv.org/abs/2611.08030) (arxiv.org, paper) 27. [arXiv 2611.08198](https://arxiv.org/abs/2611.08198) (arxiv.org, paper) 28. [arXiv 2611.07607](https://arxiv.org/abs/2611.07607) (arxiv.org, paper) 29. [arXiv 2611.08230](https://arxiv.org/abs/2611.08230) (arxiv.org, paper) 30. [arXiv 2611.07117](https://arxiv.org/abs/2611.07117) (arxiv.org, paper) 31. [arXiv 2611.07280](https://arxiv.org/abs/2611.07280) (arxiv.org, paper) 32. [arXiv 2611.06937](https://arxiv.org/abs/2611.06937) (arxiv.org, paper) 33. [arXiv 2611.07259](https://arxiv.org/abs/2611.07259) (arxiv.org, paper) 34. [arXiv 2611.08176](https://arxiv.org/abs/2611.08176) (arxiv.org, paper) 35. [arXiv 2611.07196](https://arxiv.org/abs/2611.07196) (arxiv.org, paper) 36. [arXiv 2611.07310](https://arxiv.org/abs/2611.07310) (arxiv.org, paper) 37. [arXiv 2611.07626](https://arxiv.org/abs/2611.07626) (arxiv.org, paper) 38. [arXiv 2611.07915](https://arxiv.org/abs/2611.07915) (arxiv.org, paper) 39. [arXiv 2611.06986](https://arxiv.org/abs/2611.06986) (arxiv.org, paper) 40. [arXiv 2611.07455](https://arxiv.org/abs/2611.07455) (arxiv.org, paper) 41. [arXiv 2611.08455](https://arxiv.org/abs/2611.08455) (arxiv.org, paper) 42. [arXiv 2611.06998](https://arxiv.org/abs/2611.06998) (arxiv.org, paper) 43. [Hexagon 2610.00520](https://hexagonmath.org/abs/2610.00520) (hexagonmath.org, paper) 44. [Hexagon 2610.00505](https://hexagonmath.org/abs/2610.00505) (hexagonmath.org, paper) 45. [Hexagon 2610.00508](https://hexagonmath.org/abs/2610.00508) (hexagonmath.org, paper) 46. [Hexagon 2610.00515](https://hexagonmath.org/abs/2610.00515) (hexagonmath.org, paper) 47. [Hexagon 2610.00514](https://hexagonmath.org/abs/2610.00514) (hexagonmath.org, paper) 48. [Hexagon 2610.00521](https://hexagonmath.org/abs/2610.00521) (hexagonmath.org, paper) ## Changes - 2026-11-06 (filed): Created ## Related - 2026-11-06: [Tusnády's problem claimed settled twice, with AI help](https://postcutoff.com/e/2026-11-06-tusnady-problem-settled-two-ai-assisted-preprints/index.md) - 2026-11-05: [Singmaster's problem: new bound by Claude Opus 5.5](https://postcutoff.com/e/2026-11-05-singmaster-bound-claude-opus-5-5-whitmore/index.md) - 2026-11-05: [Hopfield critical capacity bracketed, by Claude Opus 5.5](https://postcutoff.com/e/2026-11-05-hopfield-critical-capacity-claude-opus-5-5/index.md) - 2026-11-05: [AI-assisted results, 5 Nov: arXiv of 5 Nov and Hexagon of 4 Nov](https://postcutoff.com/e/2026-11-05-ai-assisted-results-november-5-listing/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) - 2026-10-06: [Generalized Lax conjecture: OpenAI counterexample claim; AI-found generic case (Kummer–Netzer)](https://postcutoff.com/e/2026-10-06-generalized-lax-conjecture-openai-counterexample-kummer-netzer-generic-case/index.md)