{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-09-25-zeta2-irrationality-measure-claude-lean/","md":"https://postcutoff.com/e/2026-09-25-zeta2-irrationality-measure-claude-lean/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-09-25-zeta2-irrationality-measure-claude-lean","date":"2026-09-25","date_precision":"day","short_title":"New record bound on the irrationality measure of ζ(2), μ ≤ 5.0495243, released as a 92k-line Lean proof written by Claude; beaten a week later by a Claude-assisted paper","deck":null,"takeaway":"On Sept 25, 2026 Jonathan Kleid published a machine-checked Lean 4 proof that the irrationality measure of ζ(2) = π²/6 is at most 5.0495243, improving Zudilin's 2014 record of 5.095412.","category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Result confirmed"]},"sources":[{"n":1,"title":"GitHub qedbook/zeta2-irrationality-measure: μ(ζ(2)) ≤ 5.0495243, machine-checked in Lean 4","url":"https://github.com/qedbook/zeta2-irrationality-measure","type":"code","group":"primary","domain":"github.com"},{"n":2,"title":"qedbook","url":"https://qedbook.com","type":"official","group":"primary","domain":"qedbook.com"},{"n":3,"title":"arXiv 2610.02912: A new upper bound for the irrationality exponent of ζ(2) (Niedbala Giraudin)","url":"https://arxiv.org/abs/2610.02912","type":"paper","group":"primary","domain":"arxiv.org"},{"n":4,"title":"arXiv 2609.26980: A new upper bound for the irrationality exponent of ζ(3) (Niedbala Giraudin)","url":"https://arxiv.org/abs/2609.26980","type":"paper","group":"primary","domain":"arxiv.org"},{"n":5,"title":"Zudilin (2014): Two hypergeometric tales and a new irrationality measure of ζ(2)","url":"https://arxiv.org/abs/1310.1526","type":"paper","group":"primary","domain":"arxiv.org"}],"official":5,"filed":"2026-10-05","updated":"2026-10-11","orgs":["Anthropic"],"title":"New record bound on the irrationality measure of ζ(2), μ ≤ 5.0495243, released as a 92k-line Lean proof written by Claude; beaten a week later by a Claude-assisted paper","summary":"On Sept 25, 2026 Jonathan Kleid published a machine-checked Lean 4 proof that the irrationality measure of ζ(2) = π²/6 is at most 5.0495243, improving Zudilin's 2014 record of 5.095412. Kleid found the parameters, (13, 11, 9, 15; 26) in Zudilin's construction, with his own computer-algebra system qedbook. Per the repository, \"the Lean text was written by Claude (Anthropic) sessions directed by Jonathan Kleid\". The development has 166 hand-structured modules (91,672 lines) plus 559 generated certificate modules, with no sorry and only Lean's three standard axioms. On Oct 2 David Niedbala Giraudin posted a 6-page paper (arXiv 2610.02912; \"Technical assistance: Claude (Anthropic)\") lowering the bound to 5.0193784; it cites Kleid's bound as the previous record.","key_facts":["Theorem (Lean): ¬ LiouvilleWith 5.0495243 ζ(2), plus the explicit rational-approximation form C/n^5.0495243 ≤ |ζ(2) − m/n| for large n; certified value of the construction 5.04952429053…","Previous records: 5.441243 (Rhin–Viola, 1996), 5.095412 (Zudilin, Ann. Math. Québec 2014)","Provenance (README): 'The Lean text was written by Claude (Anthropic) sessions directed by Jonathan Kleid, who also designed the search program and the verification discipline (every gate proven able to go red before its green was accepted)'","Size: 166 modules / 91,672 lines, plus 559 generated modules holding a creative-telescoping certificate as exact integer data; full build ~12.6 CPU-hours, ~13 GB disk, assembly modules peak near 18 GB RAM","Fills Mathlib gaps: explicit complex Binet bound for log Γ, a linear-forms criterion for ¬LiouvilleWith, Poincaré-type growth bounds for three-term recurrences, p-adic analysis of the common factor; the PNT comes from the vendored PrimeNumberTheoremAnd project (Kontorovich, Tao et al.)","Repository qedbook/zeta2-irrationality-measure created 2026-09-25 (Apache-2.0); no accompanying paper","Superseded Oct 2, 2026: Niedbala Giraudin, arXiv 2610.02912, μ(ζ(2)) < 5.0193784, using Zudilin's two hypergeometric constructions at new parameters without creative telescoping, constants checked by ball arithmetic; acknowledgements: 'Technical assistance: Claude (Anthropic)'. The same author's arXiv 2609.26980 (Sept 22) improved the 25-year-old ζ(3) record to μ(ζ(3)) < 5.5138800 (from 5.513891), 'carried out with the assistance of an AI system (Claude, Anthropic)'; both follow Bai's GPT-assisted π bound (2026-09-10-pi-irrationality-measure-bai-gpt)"],"key_numbers":[],"tags":["math","number-theory","zeta-values","irrationality-measure","lean","formal-verification","claude"],"science":{"field":"mathematics","subfield":"number theory / Diophantine approximation","problem":"Irrationality measure (exponent) of ζ(2) = π²/6","result":"μ(ζ(2)) ≤ 5.0495243 (from 5.095412), fully formalized in Lean 4; later improved to < 5.0193784 (Niedbala Giraudin, Claude as technical assistant)","open_since":"2014","ai_system":["Claude"],"human_role":"Human-led: Kleid ran the parameter search in his own CAS and directed the work; Claude wrote the Lean formalization","verification":{"key":"lean","label":"Lean-verified","text":"Formal proof in Lean 4 (no sorry, standard axioms only); not peer-reviewed"},"status":"confirmed","shock":"A record in classical Diophantine approximation was published as a ~92k-line AI-written Lean proof with no paper at all."},"body_md":"## What happened\n\nKleid searched the parameter space of Zudilin's Mellin–Barnes construction with qedbook, his own computer-algebra system, using Marcovecchio's pairing theorem to make each candidate tractable. He found a member whose growth rates give the exponent 1 + (42.034 + 15.019)/(29.108 − 15.019) ≈ 5.0495. He then had Claude write a complete Lean 4 proof. Every value computed in qedbook enters the proof as data that Lean's kernel re-checks. The repository says what is and is not proved: the sharper figure 5.04952429 printed by the search is *not* claimed.\n\nA week later a preprint by David Niedbala Giraudin (Claude credited for technical assistance) beat the bound, citing Kleid's \"machine-verified bound … published in September 2026\" as the intermediate record.\n\n## Why it matters\n\nIt is a new way to publish: a record in analytic number theory released as a fully kernel-checked, AI-written formal proof rather than a paper. It also shows the pace of autumn 2026, when an AI-formalized record stood for only a week before a short paper, itself written with Claude as technical assistant, improved it. The open question is whether qedbook-style search plus AI formalization can now reach the new bound.","disputed":[],"related":[{"id":"2026-09-30-ai-assisted-conjecture-wave-summer-2026","url":"https://postcutoff.com/e/2026-09-30-ai-assisted-conjecture-wave-summer-2026/","date":"2026-09-30","date_precision":"day","short_title":"Summer 2026 flood: dozens of named conjectures settled on arXiv with disclosed AI help","deck":null,"takeaway":"This entry catalogues about 50 of them, with the AI role as the authors state it.","category":"science","category_label":"Science & math","importance":4,"confidence":"medium","status":{"key":"pending","labels":["Awaiting review"]},"sources":11,"official":5,"filed":"2026-09-30","updated":"2026-10-19","orgs":["OpenAI","Anthropic","Google DeepMind","various mathematicians"]},{"id":"2026-09-10-pi-irrationality-measure-bai-gpt","url":"https://postcutoff.com/e/2026-09-10-pi-irrationality-measure-bai-gpt/","date":"2026-09-10","date_precision":"day","short_title":"Irrationality measure of π lowered to 7.101862832357, the first improvement on Zeilberger–Zudilin (2019), with GPT-5.6 Sol and GPT-6 Astra; four weeks later OpenAI claimed the exact value 2","deck":null,"takeaway":"The best known bound on how well π can be approximated by fractions moved for the first time since 2019, in a preprint whose author says OpenAI models helped with parameter search, proofs and computation. Claude-assisted papers then moved the ζ(3) and ζ(2) records the same way. OpenAI's 6 Oct release goes much further, claiming the conjectured exact value μ(π) = 2 with a Lean proof, which would make all these upper bounds obsolete.","category":"science","category_label":"Science & math","importance":3,"confidence":"high","status":{"key":"pending","labels":["Event confirmed","Awaiting review"]},"sources":8,"official":7,"filed":"2026-10-11","updated":"2026-10-12","orgs":["OpenAI","Anthropic"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-11","type":"edit","text":"Corrected: the Niedbala Giraudin ζ(2) and ζ(3) papers do credit Claude (acknowledgements); earlier text said \"no AI disclosure\". Linked the new π entry"},{"date":"2026-10-05","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-05","run":null,"sources_read":null,"updated":"2026-10-11","human_review":null,"version":{"date":"2026-10-11"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":117,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":87,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":178,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":117,"in_training_data":false}],"short_url":null}