tags. Use Persian for terms like "formal verification" -> اثبات صوری or تأیید صوری? "crypto verification" -> تأیید رمزنگاری. "smart-contract auditing" -> حسابرسی قراردادهای هوشمند. "zero-knowledge proofs" -> اثباتهای دانش صفر. "consensus algorithms" -> الگوریتمهای اجماع. "Erdős problems" -> مسائل اردوش (keep Erdős in original but add Persian pronunciation? Usually in Persian it's written as اردوش but name is Erdős, so I'll keep "Erdős" as is in English since it's a proper noun? Requirement says keep proper nouns in original form. So "Erdős" stays as is. But in Persian text, we can write "Erdős" with Latin script or use Persian script? The requirement: "Keep proper nouns (names, company names) in original form" means keep them as they are in English, e.g., Google DeepMind, AlphaProof Nexus, Paul Erdős, OEIS. So I'll keep them in English within Persian text. That's acceptable.
Meta description: Translate similarly.
Now write JSON. Ensure valid JSON: double quotes, escape any inner quotes. The content has double quotes in original, need to escape them. For example: "could revolutionize fields like cryptography" -> در Persian: "میتواند زمینههایی مانند رمزنگاری را متحول کند". But the original has quotes around that phrase? Actually original: "could revolutionize fields like cryptography and software auditing by making proof validation more efficient and cost-effective." - DeepMind's announcement says that. So in translation, we need to put that in quotes? The original has quotes around the statement? Let's check: DeepMind's announcement says AI-driven formal verification 'could revolutionize fields like cryptography...' - it uses single quotes. In translation, we can use Persian quotation marks or keep as is. But to preserve HTML, we can keep the quotes as they are. However, in JSON we need to escape double quotes if we use them. Better to use Persian quotation marks (« ») or just single quotes. I'll use double quotes but escape them. Alternatively, use single quotes inside. I'll use double quotes and escape with backslash.
Let's write each translation carefully.
Title translation: "هوش مصنوعی DeepMind ۴۴ حدس دنبالهای را اثبات کرد، امیدها برای تأیید رمزنگاری را افزایش میدهد"
But to be more natural: "هوش مصنوعی DeepMind ۴۴ حدس دنبالهای را اثبات کرد و امیدها را برای تأیید رمزنگاری افزایش داد" (past tense). Original title is present tense "proves" and "boosts" -> present. In Persian, present tense can be used. I'll use present: "اثبات میکند" and "افزایش میدهد". But the article describes past event (announced this week). However title is present. I'll keep present: "هوش مصنوعی DeepMind ۴۴ حدس دنبالهای را اثبات میکند، امیدها برای تأیید رمزنگاری را افزایش میدهد". That's fine.
Meta description: "Google DeepMind's AlphaProof Nexus solved nine Erdős problems and 44 sequence conjectures, advancing AI-driven formal verification for cryptography and auditing." -> "AlphaProof Nexus گوگل دیپمایند نه مسئله اردوش و ۴۴ حدس دنبالهای را حل کرد و تأیید صوری مبتنی بر هوش مصنوعی را برای رمزنگاری و حسابرسی پیش برد." But keep proper nouns: "Google DeepMind's AlphaProof Nexus" -> "AlphaProof Nexus گوگل دیپمایند" (DeepMind is a name, keep as is but in Persian we often write گوگل دیپمایند). I'll keep "Google DeepMind" as is? Requirement: "keep proper nouns (names, company names) in original form" - so "Google DeepMind" should be in English. But in Persian text, it's common to write them in English. I'll write them in English: "AlphaProof Nexus گوگل DeepMind" or "Google DeepMind's AlphaProof Nexus" -> "AlphaProof Nexus از Google DeepMind". I think it's fine to write Google DeepMind in English. For consistency, I'll keep all proper nouns in English as in original.
Now translate content paragraph by paragraph.
First paragraph: "Google DeepMind's AlphaProof Nexus has cracked nine Erdős problems and proved 44 sequence conjectures, a milestone in AI-driven formal verification that could eventually make cryptographic proof validation faster and cheaper. The results, announced this week, show an AI system tackling famously hard math problems, with direct implications for fields that rely on airtight proofs — including cryptography and smart-contract auditing."
Translation: "AlphaProof Nexus از Google DeepMind نه مسئله اردوش را شکافته و ۴۴ حدس دنبالهای را اثبات کرده است، نقطه عطفی در تأیید صوری مبتنی بر هوش مصنوعی که در نهایت میتواند اعتبارسنجی اثبات رمزنگاری را سریعتر و ارزانتر کند. نتایج که این هفته اعلام شد، نشاندهنده یک سیستم هوش مصنوعی است که به مسائل ریاضی مشهوراً دشوار میپردازد، با پیامدهای مستقیم برای حوزههایی که به اثباتهای بدون نقص متکی هستند — از جمله رمزنگاری و حسابرسی قراردادهای هوشمند."
Second paragraph: "The system tackled a set of problems named after mathematician Paul Erdős, known for their difficulty. Of those, AlphaProof Nexus solved nine — a feat that previously required years of human effort. It also independently proved 44 open conjectures in integer sequences, pulling them from the OEIS database. Each proof was generated without human guidance beyond the initial problem statement."
Translation: "این سیستم مجموعهای از مسائل به نام ریاضیدان Paul Erdős را که به دشواری شهرت دارند، مورد بررسی قرار داد. از میان آنها، AlphaProof Nexus نه مسئله را حل کرد — شاهکاری که پیشتر سالها تلاش انسانی نیاز داشت. همچنین به طور مستقل ۴۴ حدس باز در دنبالههای اعداد صحیح را اثبات کرد و آنها را از پایگاه داده OEIS استخراج کرد. هر اثبات بدون راهنمایی انسانی فراتر از بیان اولیه مسئله تولید شد."
Third paragraph: "Formal verification is the process of mathematically proving that software or hardware behaves exactly as intended. It's used in cryptography to check that encryption algorithms have no hidden flaws, but it's slow and expensive. DeepMind's announcement says AI-driven formal verification 'could revolutionize fields like cryptography and software auditing by making proof validation more efficient and cost-effective.'"
Translation: "تأیید صوری فرآیند اثبات ریاضی این است که نرمافزار یا سختافزار دقیقاً همانطور که انتظار میرود رفتار میکند. در رمزنگاری برای بررسی اینکه الگوریتمهای رمزگذاری هیچ نقص پنهانی ندارند استفاده میشود، اما کند و گران است. اعلامیه DeepMind میگوید تأیید صوری مبتنی بر هوش مصنوعی «میتواند زمینههایی مانند رمزنگاری و حسابرسی نرم
